Authors: Robert M. Kent, Wendson A. S. Barbosa, Daniel J. Gauthier
Abstract: Machine learning provides a data-driven approach for creating a digital twin of a system - a digital model used to predict the system behavior. Having an accurate digital twin can drive many applications, such as controlling autonomous systems. Often the size, weight, and power consumption of the digital twin or related controller must be minimized, ideally realized on embedded computing hardware that can operate without a cloud-computing connection. Here, we show that a nonlinear controller based on next-generation reservoir computing can tackle a difficult control problem: controlling a chaotic system to an arbitrary time-dependent state. The model is accurate, yet it is small enough to be evaluated on a field-programmable gate array typically found in embedded devices. Furthermore, the model only requires 25.0 $\pm$ 7.0 nJ per evaluation, well below other algorithms, even without systematic power optimization. Our work represents the first step in deploying efficient machine learning algorithms to the computing "edge."
Authors: Faseela Abdullakutty, Younes Akbari, Somaya Al-Maadeed, Ahmed Bouridane, Rifat Hamoudi
Abstract: It is imperative that breast cancer is detected precisely and timely to improve patient outcomes. Diagnostic methodologies have traditionally relied on unimodal approaches; however, medical data analytics is integrating diverse data sources beyond conventional imaging. Using multi-modal techniques, integrating both image and non-image data, marks a transformative advancement in breast cancer diagnosis. The purpose of this review is to explore the burgeoning field of multimodal techniques, particularly the fusion of histopathology images with non-image data. Further, Explainable AI (XAI) will be used to elucidate the decision-making processes of complex algorithms, emphasizing the necessity of explainability in diagnostic processes. This review utilizes multi-modal data and emphasizes explainability to enhance diagnostic accuracy, clinician confidence, and patient engagement, ultimately fostering more personalized treatment strategies for breast cancer, while also identifying research gaps in multi-modality and explainability, guiding future studies, and contributing to the strategic direction of the field.
Authors: Jialun Cao, Zhiyong Chen, Jiarong Wu, Shing-chi Cheung, Chang Xu
Abstract: Code generation benchmarks such as HumanEval are widely adopted to evaluate LLMs' capabilities. However, after consolidating the latest 24 benchmarks, we noticed three significant imbalances. First, imbalanced programming language. 95.8% of benchmarks involve Python, while only 5 benchmarks involve Java. Second, imbalanced code granularity. Function-/statement-level benchmarks account for over 83.3% of benchmarks. Only a mere handful extends to class-/project-levels, and all are limited to Python. Third, lacking advanced features. Existing benchmarks primarily assess basic coding skills, while overlooking advanced Object-Oriented Programming (OOP) features (i.e., encapsulation, inheritance, and polymorphism). To fill these gaps, we propose JavaBench, a project-level Java benchmark that exercises OOP features. It comprises four Java projects with 389 methods in 106 Java classes. The test coverage is up to 92%, and JavaBench is attested by 282 undergraduate students, reaching a 90.93/100 average score (i.e., pass rate against the test suite), ensuring the quality of documentation, code skeleton, and tests. To better evaluate LLM's capability against JavaBench, we introduce a systematic evaluation design covering three context settings and five synthesis strategies at two granularities using three hierarchical metrics. Our extensive experiment yields several interesting findings. First, we noticed that regarding project-level Java programming, LLMs are far behind undergraduate students (no project can be correctly completed by any studied LLMs, and at most 41.17% Pass@5 in a more relaxed evaluation). Second, using method signature as prompt context may strike an ideal balance for project-level code generation. JavaBench is publicly available at https://github.com/java-bench/JavaBench.
Authors: Yongha Kim, Anthony W. Jung, Sanmun Kim, Kevin Octavian, Doyoung Heo, Chaejin Park, Jeongmin Shin, Sunghyun Nam, Chanhyung Park, Juho Park, Sangjun Han, Jinmyoung Lee, Seolho Kim, Min Seok Jang, Chan Y. Park
Abstract: Electromagnetic (EM) simulation plays a crucial role in analyzing and designing devices with sub-wavelength scale structures such as solar cells, semiconductor devices, image sensors, future displays and integrated photonic devices. Specifically, optics problems such as estimating semiconductor device structures and designing nanophotonic devices provide intriguing research topics with far-reaching real world impact. Traditional algorithms for such tasks require iteratively refining parameters through simulations, which often yield sub-optimal results due to the high computational cost of both the algorithms and EM simulations. Machine learning (ML) emerged as a promising candidate to mitigate these challenges, and optics research community has increasingly adopted ML algorithms to obtain results surpassing classical methods across various tasks. To foster a synergistic collaboration between the optics and ML communities, it is essential to have an EM simulation software that is user-friendly for both research communities. To this end, we present Meent, an EM simulation software that employs rigorous coupled-wave analysis (RCWA). Developed in Python and equipped with automatic differentiation (AD) capabilities, Meent serves as a versatile platform for integrating ML into optics research and vice versa. To demonstrate its utility as a research platform, we present three applications of Meent: 1) generating a dataset for training neural operator, 2) serving as an environment for the reinforcement learning of nanophotonic device optimization, and 3) providing a solution for inverse problems with gradient-based optimizers. These applications highlight Meent's potential to advance both EM simulation and ML methodologies. The code is available at https://github.com/kc-ml2/meent with the MIT license to promote the cross-polinations of ideas among academic researchers and industry practitioners.
Authors: Joseph Suarez
Abstract: You have an environment, a model, and a reinforcement learning library that are designed to work together but don't. PufferLib makes them play nice. The library provides one-line environment wrappers that eliminate common compatibility problems and fast vectorization to accelerate training. With PufferLib, you can use familiar libraries like CleanRL and SB3 to scale from classic benchmarks like Atari and Procgen to complex simulators like NetHack and Neural MMO. We release pip packages and prebuilt images with dependencies for dozens of environments. All of our code is free and open-source software under the MIT license, complete with baselines, documentation, and support at pufferai.github.io.
Authors: Tim Pearce, Jinyeop Song
Abstract: Kaplan et al. [2020] (`Kaplan') and Hoffmann et al. [2022] (`Chinchilla') studied the scaling behavior of transformers trained on next-token language prediction. These studies produced different estimates for how the number of parameters ($N$) and training tokens ($D$) should be set to achieve the lowest possible loss for a given compute budget ($C$). Kaplan: $N_\text{optimal} \propto C^{0.73}$, Chinchilla: $N_\text{optimal} \propto C^{0.50}$. This note finds that much of this discrepancy can be attributed to Kaplan counting non-embedding rather than total parameters, combined with their analysis being performed at small scale. Simulating the Chinchilla study under these conditions produces biased scaling coefficients close to Kaplan's. Hence, this note reaffirms Chinchilla's scaling coefficients, by explaining the cause of Kaplan's original overestimation.
Authors: Kausik Lakkaraju, Rachneet Kaur, Zhen Zeng, Parisa Zehtabi, Sunandita Patra, Biplav Srivastava, Marco Valtorta
Abstract: AI systems are notorious for their fragility; minor input changes can potentially cause major output swings. When such systems are deployed in critical areas like finance, the consequences of their uncertain behavior could be severe. In this paper, we focus on multi-modal time-series forecasting, where imprecision due to noisy or incorrect data can lead to erroneous predictions, impacting stakeholders such as analysts, investors, and traders. Recently, it has been shown that beyond numeric data, graphical transformations can be used with advanced visual models to achieve better performance. In this context, we introduce a rating methodology to assess the robustness of Multi-Modal Time-Series Forecasting Models (MM-TSFM) through causal analysis, which helps us understand and quantify the isolated impact of various attributes on the forecasting accuracy of MM-TSFM. We apply our novel rating method on a variety of numeric and multi-modal forecasting models in a large experimental setup (six input settings of control and perturbations, ten data distributions, time series from six leading stocks in three industries over a year of data, and five time-series forecasters) to draw insights on robust forecasting models and the context of their strengths. Within the scope of our study, our main result is that multi-modal (numeric + visual) forecasting, which was found to be more accurate than numeric forecasting in previous studies, can also be more robust in diverse settings. Our work will help different stakeholders of time-series forecasting understand the models` behaviors along trust (robustness) and accuracy dimensions to select an appropriate model for forecasting using our rating method, leading to improved decision-making.
Authors: Massimiliano Lupo Pasini, Jong Youl Choi, Kshitij Mehta, Pei Zhang, David Rogers, Jonghyun Bae, Khaled Z. Ibrahim, Ashwin M. Aji, Karl W. Schulz, Jorda Polo, Prasanna Balaprakash
Abstract: We present our work on developing and training scalable graph foundation models (GFM) using HydraGNN, a multi-headed graph convolutional neural network architecture. HydraGNN expands the boundaries of graph neural network (GNN) in both training scale and data diversity. It abstracts over message passing algorithms, allowing both reproduction of and comparison across algorithmic innovations that define convolution in GNNs. This work discusses a series of optimizations that have allowed scaling up the GFM training to tens of thousands of GPUs on datasets that consist of hundreds of millions of graphs. Our GFMs use multi-task learning (MTL) to simultaneously learn graph-level and node-level properties of atomistic structures, such as the total energy and atomic forces. Using over 150 million atomistic structures for training, we illustrate the performance of our approach along with the lessons learned on two United States Department of Energy (US-DOE) supercomputers, namely the Perlmutter petascale system at the National Energy Research Scientific Computing Center and the Frontier exascale system at Oak Ridge National Laboratory. The HydraGNN architecture enables the GFM to achieve near-linear strong scaling performance using more than 2,000 GPUs on Perlmutter and 16,000 GPUs on Frontier. Hyperparameter optimization (HPO) was performed on over 64,000 GPUs on Frontier to select GFM architectures with high accuracy. Early stopping was applied on each GFM architecture for energy awareness in performing such an extreme-scale task. The training of an ensemble of highest-ranked GFM architectures continued until convergence to establish uncertainty quantification (UQ) capabilities with ensemble learning. Our contribution opens the door for rapidly developing, training, and deploying GFMs using large-scale computational resources to enable AI-accelerated materials discovery and design.
Authors: Jiebin Fang (Hainan Institute of Zhejiang University, Institute of Marine Biology and Pharmacology, Ocean College, Zhejiang University), Churu Mao (Institute of Marine Biology and Pharmacology, Ocean College, Zhejiang University), Yuchen Zhu (College of Pharmaceutical Sciences and Cancer Center, Zhejiang University), Xiaoming Chen (Institute of Marine Biology and Pharmacology, Ocean College, Zhejiang University), Chang-Yu Hsieh (College of Pharmaceutical Sciences and Cancer Center, Zhejiang University), Zhongjun Ma (Hainan Institute of Zhejiang University, Institute of Marine Biology and Pharmacology, Ocean College, Zhejiang University)
Abstract: De novo molecule generation allows the search for more drug-like hits across a vast chemical space. However, lead optimization is still required, and the process of optimizing molecular structures faces the challenge of balancing structural novelty with pharmacological properties. This study introduces the Deep Genetic Molecular Modification Algorithm (DGMM), which brings structure modification to the level of medicinal chemists. A discrete variational autoencoder (D-VAE) is used in DGMM to encode molecules as quantization code, mol-gene, which incorporates deep learning into genetic algorithms for flexible structural optimization. The mol-gene allows for the discovery of pharmacologically similar but structurally distinct compounds, and reveals the trade-offs of structural optimization in drug discovery. We demonstrate the effectiveness of the DGMM in several applications.
Authors: Aditya Datar, Pramit Saha
Abstract: Much of the present-day Artificial Intelligence (AI) utilizes artificial neural networks, which are sophisticated computational models designed to recognize patterns and solve complex problems by learning from data. However, a major bottleneck occurs during a device's calculation of weighted sums for forward propagation and optimization procedure for backpropagation, especially for deep neural networks, or networks with numerous layers. Exploration into different methods of implementing neural networks is necessary for further advancement of the area. While a great deal of research into AI hardware in both directions, analog and digital implementation widely exists, much of the existing survey works lacks discussion on the progress of analog deep learning. To this end, we attempt to evaluate and specify the advantages and disadvantages, along with the current progress with regards to deep learning, for analog implementations. In this paper, our focus lies on the comprehensive examination of eight distinct analog deep learning methodologies across multiple key parameters. These parameters include attained accuracy levels, application domains, algorithmic advancements, computational speed, and considerations of energy efficiency and power consumption. We also identify the neural network-based experiments implemented using these hardware devices and discuss comparative performance achieved by the different analog deep learning methods along with an analysis of their current limitations. Overall, we find that Analog Deep Learning has great potential for future consumer-level applications, but there is still a long road ahead in terms of scalability. Most of the current implementations are more proof of concept and are not yet practically deployable for large-scale models.
Authors: Lihuan Li, Hao Xue, Yang Song, Flora Salim
Abstract: Trajectory similarity computation is an essential technique for analyzing moving patterns of spatial data across various applications such as traffic management, wildlife tracking, and location-based services. Modern methods often apply deep learning techniques to approximate heuristic metrics but struggle to learn more robust and generalized representations from the vast amounts of unlabeled trajectory data. Recent approaches focus on self-supervised learning methods such as contrastive learning, which have made significant advancements in trajectory representation learning. However, contrastive learning-based methods heavily depend on manually pre-defined data augmentation schemes, limiting the diversity of generated trajectories and resulting in learning from such variations in 2D Euclidean space, which prevents capturing high-level semantic variations. To address these limitations, we propose T-JEPA, a self-supervised trajectory similarity computation method employing Joint-Embedding Predictive Architecture (JEPA) to enhance trajectory representation learning. T-JEPA samples and predicts trajectory information in representation space, enabling the model to infer the missing components of trajectories at high-level semantics without relying on domain knowledge or manual effort. Extensive experiments conducted on three urban trajectory datasets and two Foursquare datasets demonstrate the effectiveness of T-JEPA in trajectory similarity computation.
Authors: Miguel Fernandes, Catarina Silva, Alberto Cardoso, Bernardete Ribeiro
Abstract: Condition-Based Maintenance is pivotal in enabling the early detection of potential failures in engineering systems, where precise prediction of the Remaining Useful Life is essential for effective maintenance and operation. However, a predominant focus in the field centers on predicting the Remaining Useful Life using unprocessed or minimally processed data, frequently neglecting the intricate dynamics inherent in the dataset. In this work we introduce a novel methodology grounded in the analysis of statistical similarity within latent data from system components. Leveraging a specifically designed architecture based on a Vector Quantized Variational Autoencoder, we create a sequence of discrete vectors which is used to estimate system-specific priors. We infer the similarity between systems by evaluating the divergence of these priors, offering a nuanced understanding of individual system behaviors. The efficacy of our approach is demonstrated through experiments on the NASA commercial modular aero-propulsion system simulation (C-MAPSS) dataset. Our validation not only underscores the potential of our method in advancing the study of latent statistical divergence but also demonstrates its superiority over existing techniques.
Authors: Yijin Zhou, Yuguang Wang
Abstract: Transformer networks excel in natural language processing (NLP) and computer vision (CV) tasks. However, they face challenges in generalizing to Out-of-Distribution (OOD) datasets, that is, data whose distribution differs from that seen during training. The OOD detection aims to distinguish data that deviates from the expected distribution, while maintaining optimal performance on in-distribution (ID) data. This paper introduces a novel approach based on OOD detection, termed the Generate Rounded OOD Data (GROD) algorithm, which significantly bolsters the generalization performance of transformer networks across various tasks. GROD is motivated by our new OOD detection Probably Approximately Correct (PAC) Theory for transformer. The transformer has learnability in terms of OOD detection that is, when the data is sufficient the outlier can be well represented. By penalizing the misclassification of OOD data within the loss function and generating synthetic outliers, GROD guarantees learnability and refines the decision boundaries between inlier and outlier. This strategy demonstrates robust adaptability and general applicability across different data types. Evaluated across diverse OOD detection tasks in NLP and CV, GROD achieves SOTA regardless of data format. On average, it reduces the SOTA FPR@95 from 21.97% to 0.12%, and improves AUROC from 93.62% to 99.98% on image classification tasks, and the SOTA FPR@95 by 12.89% and AUROC by 2.27% in detecting semantic text outliers. The code is available at https://anonymous.4open.science/r/GROD-OOD-Detection-with-transformers-B70F.
URLs: https://anonymous.4open.science/r/GROD-OOD-Detection-with-transformers-B70F.
Authors: Yanick Thurn, Ro Jefferson, Johanna Erdmenger
Abstract: An important challenge in machine learning is to predict the initial conditions under which a given neural network will be trainable. We present a method for predicting the trainable regime in parameter space for deep feedforward neural networks, based on reconstructing the input from subsequent activation layers via a cascade of single-layer auxiliary networks. For both MNIST and CIFAR10, we show that a single epoch of training of the shallow cascade networks is sufficient to predict the trainability of the deep feedforward network, thereby providing a significant reduction in overall training time. We achieve this by computing the relative entropy between reconstructed images and the original inputs, and show that this probe of information loss is sensitive to the phase behaviour of the network. Our results provide a concrete link between the flow of information and the trainability of deep neural networks, further elucidating the role of criticality in these systems.
Authors: Mo-Ran Liu, Tao Sun, Xi-Ming Sun
Abstract: Aero-engine fault prediction aims to accurately predict the development trend of the future state of aero-engines, so as to diagnose faults in advance. Traditional aero-engine parameter prediction methods mainly use the nonlinear mapping relationship of time series data but generally ignore the adequate spatiotemporal features contained in aero-engine data. To this end, we propose a brain-inspired spike echo state network (Spike-ESN) model for aero-engine intelligent fault prediction, which is used to effectively capture the evolution process of aero-engine time series data in the framework of spatiotemporal dynamics. In the proposed approach, we design a spike input layer based on Poisson distribution inspired by the spike neural encoding mechanism of biological neurons, which can extract the useful temporal characteristics in aero-engine sequence data. Then, the temporal characteristics are input into a spike reservoir through the current calculation method of spike accumulation in neurons, which projects the data into a high-dimensional sparse space. In addition, we use the ridge regression method to read out the internal state of the spike reservoir. Finally, the experimental results of aero-engine states prediction demonstrate the superiority and potential of the proposed method.
Authors: Jeonghyeon Kim, Juno Nam, Seongok Ryu
Abstract: With the advancing capabilities of computational methodologies and resources, ultra-large-scale virtual screening via molecular docking has emerged as a prominent strategy for in silico hit discovery. Given the exhaustive nature of ultra-large-scale virtual screening, active learning methodologies have garnered attention as a means to mitigate computational cost through iterative small-scale docking and machine learning model training. While the efficacy of active learning methodologies has been empirically validated in extant literature, a critical investigation remains in how surrogate models can predict docking score without considering three-dimensional structural features, such as receptor conformation and binding poses. In this paper, we thus investigate how active learning methodologies effectively predict docking scores using only 2D structures and under what circumstances they may work particularly well through benchmark studies encompassing six receptor targets. Our findings suggest that surrogate models tend to memorize structural patterns prevalent in high docking scored compounds obtained during acquisition steps. Despite this tendency, surrogate models demonstrate utility in virtual screening, as exemplified in the identification of actives from DUD-E dataset and high docking-scored compounds from EnamineReal library, a significantly larger set than the initial screening pool. Our comprehensive analysis underscores the reliability and potential applicability of active learning methodologies in virtual screening campaigns.
Authors: Quangao Liu, Ruiqi Li, Maowei Jiang, Wei Yang, Chen Liang, LongLong Pang, Zhuozhang Zou
Abstract: Time series forecasting (TSF) is crucial in fields like economic forecasting, weather prediction, traffic flow analysis, and public health surveillance. Real-world time series data often include noise, outliers, and missing values, making accurate forecasting challenging. Traditional methods model point-to-point relationships, which limits their ability to capture complex temporal patterns and increases their susceptibility to noise.To address these issues, we introduce the WindowMixer model, built on an all-MLP framework. WindowMixer leverages the continuous nature of time series by examining temporal variations from a window-based perspective. It decomposes time series into trend and seasonal components, handling them individually. For trends, a fully connected (FC) layer makes predictions. For seasonal components, time windows are projected to produce window tokens, processed by Intra-Window-Mixer and Inter-Window-Mixer modules. The Intra-Window-Mixer models relationships within each window, while the Inter-Window-Mixer models relationships between windows. This approach captures intricate patterns and long-range dependencies in the data.Experiments show WindowMixer consistently outperforms existing methods in both long-term and short-term forecasting tasks.
Authors: Wenzhao Jiang, Jindong Han, Hao Liu, Tao Tao, Naiqiang Tan, Hui Xiong
Abstract: Rapid urbanization has significantly escalated traffic congestion, underscoring the need for advanced congestion prediction services to bolster intelligent transportation systems. As one of the world's largest ride-hailing platforms, DiDi places great emphasis on the accuracy of congestion prediction to enhance the effectiveness and reliability of their real-time services, such as travel time estimation and route planning. Despite numerous efforts have been made on congestion prediction, most of them fall short in handling heterogeneous and dynamic spatio-temporal dependencies (e.g., periodic and non-periodic congestions), particularly in the presence of noisy and incomplete traffic data. In this paper, we introduce a Congestion Prediction Mixture-of-Experts, CP-MoE, to address the above challenges. We first propose a sparsely-gated Mixture of Adaptive Graph Learners (MAGLs) with congestion-aware inductive biases to improve the model capacity for efficiently capturing complex spatio-temporal dependencies in varying traffic scenarios. Then, we devise two specialized experts to help identify stable trends and periodic patterns within the traffic data, respectively. By cascading these experts with MAGLs, CP-MoE delivers congestion predictions in a more robust and interpretable manner. Furthermore, an ordinal regression strategy is adopted to facilitate effective collaboration among diverse experts. Extensive experiments on real-world datasets demonstrate the superiority of our proposed method compared with state-of-the-art spatio-temporal prediction models. More importantly, CP-MoE has been deployed in DiDi to improve the accuracy and reliability of the travel time estimation system.
Authors: Ihor Stepanov, Mykhailo Shtopko
Abstract: Information extraction tasks require both accurate, efficient, and generalisable models. Classical supervised deep learning approaches can achieve the required performance, but they need large datasets and are limited in their ability to adapt to different tasks. On the other hand, large language models (LLMs) demonstrate good generalization, meaning that they can adapt to many different tasks based on user requests. However, LLMs are computationally expensive and tend to fail to generate structured outputs. In this article, we will introduce a new kind of GLiNER model that can be used for various information extraction tasks while being a small encoder model. Our model achieved SoTA performance on zero-shot NER benchmarks and leading performance on question-answering, summarization and relation extraction tasks. Additionally, in this article, we will cover experimental results on self-learning approaches for named entity recognition using GLiNER models.
Authors: Yijun Liu, Yuan Meng, Fang Wu, Shenhao Peng, Hang Yao, Chaoyu Guan, Chen Tang, Xinzhu Ma, Zhi Wang, Wenwu Zhu
Abstract: Large language models (LLMs) have exhibited exciting progress in multiple scenarios, while the huge computational demands hinder their deployments in lots of real-world applications. As an effective means to reduce memory footprint and inference cost, quantization also faces challenges in performance degradation at low bit-widths. Understanding the impact of quantization on LLM capabilities, especially the generalization ability, is crucial. However, the community's main focus remains on the algorithms and models of quantization, with insufficient attention given to whether the quantized models can retain the strong generalization abilities of LLMs. In this work, we fill this gap by providing a comprehensive benchmark suite for this research topic, including an evaluation system, detailed analyses, and a general toolbox. Specifically, based on the dominant pipeline in LLM quantization, we primarily explore the impact of calibration data distribution on the generalization of quantized LLMs and conduct the benchmark using more than 40 datasets within two main scenarios. Based on this benchmark, we conduct extensive experiments with two well-known LLMs (English and Chinese) and four quantization algorithms to investigate this topic in-depth, yielding several counter-intuitive and valuable findings, e.g., models quantized using a calibration set with the same distribution as the test data are not necessarily optimal. Besides, to facilitate future research, we also release a modular-designed toolbox, which decouples the overall pipeline into several separate components, e.g., base LLM module, dataset module, quantizer module, etc. and allows subsequent researchers to easily assemble their methods through a simple configuration. Our benchmark suite is publicly available at https://github.com/TsingmaoAI/MI-optimize
Authors: Jungi Lee, Wonbeom Lee, Jaewoong Sim
Abstract: Large language models (LLMs) demonstrate outstanding performance in various tasks in machine learning and have thus become one of the most important workloads in today's computing landscape. However, deploying LLM inference poses challenges due to the high compute and memory requirements stemming from the enormous model size and the difficulty of running it in the integer pipelines. In this paper, we present Tender, an algorithm-hardware co-design solution that enables efficient deployment of LLM inference at low precision. Based on our analysis of outlier values in LLMs, we propose a decomposed quantization technique in which the scale factors of decomposed matrices are powers of two apart. The proposed scheme allows us to avoid explicit requantization (i.e., dequantization/quantization) when accumulating the partial sums from the decomposed matrices, with a minimal extension to the commodity tensor compute hardware. Our evaluation shows that Tender achieves higher accuracy and inference performance compared to the state-of-the-art methods while also being significantly less intrusive to the existing accelerators.
Authors: G. Charbel N. Kindji (IRISA, LACODAM), Lina Maria Rojas-Barahona (IRISA, LACODAM), Elisa Fromont (IRISA, LACODAM), Tanguy Urvoy
Abstract: We investigate the impact of dataset-specific hyperparameter, feature encoding, and architecture tuning on five recent model families for tabular data generation through an extensive benchmark on 16 datasets. This study addresses the practical need for a unified evaluation of models that fully considers hyperparameter optimization. Additionally, we propose a reduced search space for each model that allows for quick optimization, achieving nearly equivalent performance at a significantly lower cost.Our benchmark demonstrates that, for most models, large-scale dataset-specific tuning substantially improves performance compared to the original configurations. Furthermore, we confirm that diffusion-based models generally outperform other models on tabular data. However, this advantage is not significant when the entire tuning and training process is restricted to the same GPU budget for all models.
Authors: Mark Potanin, Kirill Vayser, Vadim Strijov
Abstract: Neural network structures have a critical impact on the accuracy and stability of forecasting. Neural architecture search procedures help design an optimal neural network according to some loss function, which represents a set of quality criteria. This paper investigates the problem of neural network structure optimization. It proposes a way to construct a loss function, which contains a set of additive elements. Each element is called the regularizer. It corresponds to some part of the neural network structure and represents a criterion to optimize. The optimization procedure changes the structure in iterations. To optimize various parts of the structure, the procedure changes the set of regularizers according to some schedule. The authors propose a way to construct the additive regularization schedule. By comparing regularized models with non-regularized ones for a collection of datasets the computational experiments show that the proposed method finds efficient neural network structure and delivers accurate networks of low complexity.
Authors: Joshua Ward, Chi-Hua Wang, Guang Cheng
Abstract: The promise of tabular generative models is to produce realistic synthetic data that can be shared and safely used without dangerous leakage of information from the training set. In evaluating these models, a variety of methods have been proposed to measure the tendency to copy data from the training dataset when generating a sample. However, these methods suffer from either not considering data-copying from a privacy threat perspective, not being motivated by recent results in the data-copying literature or being difficult to make compatible with the high dimensional, mixed type nature of tabular data. This paper proposes a new similarity metric and Membership Inference Attack called Data Plagiarism Index (DPI) for tabular data. We show that DPI evaluates a new intuitive definition of data-copying and characterizes the corresponding privacy risk. We show that the data-copying identified by DPI poses both privacy and fairness threats to common, high performing architectures; underscoring the necessity for more sophisticated generative modeling techniques to mitigate this issue.
Authors: Wei Xiao, Tsun-Hsuan Wang, Daniela Rus
Abstract: Safe learning is central to AI-enabled robots where a single failure may lead to catastrophic results. Barrier-based method is one of the dominant approaches for safe robot learning. However, this method is not scalable, hard to train, and tends to generate unstable signals under noisy inputs that are challenging to be deployed for robots. To address these challenges, we propose a novel Attention BarrierNet (ABNet) that is scalable to build larger foundational safe models in an incremental manner. Each head of BarrierNet in the ABNet could learn safe robot control policies from different features and focus on specific part of the observation. In this way, we do not need to one-shotly construct a large model for complex tasks, which significantly facilitates the training of the model while ensuring its stable output. Most importantly, we can still formally prove the safety guarantees of the ABNet. We demonstrate the strength of ABNet in 2D robot obstacle avoidance, safe robot manipulation, and vision-based end-to-end autonomous driving, with results showing much better robustness and guarantees over existing models.
Authors: Haoyuan Cai, Sulaiman A. Alghunaim, Ali H. Sayed
Abstract: Lower-bound analyses for nonconvex strongly-concave minimax optimization problems have shown that stochastic first-order algorithms require at least $\mathcal{O}(\varepsilon^{-4})$ oracle complexity to find an $\varepsilon$-stationary point. Some works indicate that this complexity can be improved to $\mathcal{O}(\varepsilon^{-3})$ when the loss gradient is Lipschitz continuous. The question of achieving enhanced convergence rates under distinct conditions, remains unresolved. In this work, we address this question for optimization problems that are nonconvex in the minimization variable and strongly concave or Polyak-Lojasiewicz (PL) in the maximization variable. We introduce novel bias-corrected momentum algorithms utilizing efficient Hessian-vector products. We establish convergence conditions and demonstrate a lower iteration complexity of $\mathcal{O}(\varepsilon^{-3})$ for the proposed algorithms. The effectiveness of the method is validated through applications to robust logistic regression using real-world datasets.
Authors: Zilin Bian, Jingqin Gao, Kaan Ozbay, Fan Zuo, Dachuan Zuo, Zhenning Li
Abstract: While deep learning has shown success in predicting traffic states, most methods treat it as a general prediction task without considering transportation aspects. Recently, graph neural networks have proven effective for this task, but few incorporate external factors that impact roadway capacity and traffic flow. This study introduces the Roadway Capacity Driven Graph Convolution Network (RCDGCN) model, which incorporates static and dynamic roadway capacity attributes in spatio-temporal settings to predict network-wide traffic states. The model was evaluated on two real-world datasets with different transportation factors: the ICM-495 highway network and an urban network in Manhattan, New York City. Results show RCDGCN outperformed baseline methods in forecasting accuracy. Analyses, including ablation experiments, weight analysis, and case studies, investigated the effect of capacity-related factors. The study demonstrates the potential of using RCDGCN for transportation system management.
Authors: Zhang Wan, Shuo Wang, Xudong Zhang
Abstract: Internal solitary waves (ISWs) are gravity waves that are often observed in the interior ocean rather than the surface. They hold significant importance due to their capacity to carry substantial energy, thus influence pollutant transport, oil platform operations, submarine navigation, etc. Researchers have studied ISWs through optical images, synthetic aperture radar (SAR) images, and altimeter data from remote sensing instruments. However, cloud cover in optical remote sensing images variably obscures ground information, leading to blurred or missing surface observations. As such, this paper aims at altimeter-based machine learning solutions to automatically locate ISWs. The challenges, however, lie in the following two aspects: 1) the altimeter data has low resolution, which requires a strong machine learner; 2) labeling data is extremely labor-intensive, leading to very limited data for training. In recent years, the grand progress of deep learning demonstrates strong learning capacity given abundant data. Besides, more recent studies on efficient learning and self-supervised learning laid solid foundations to tackle the aforementioned challenges. In this paper, we propose to inject prior knowledge to achieve a strong and efficient learner. Specifically, intrinsic patterns in altimetry data are efficiently captured using a scale-translation equivariant convolutional neural network (ST-ECNN). By considering inherent symmetries in neural network design, ST-ECNN achieves higher efficiency and better performance than baseline models. Furthermore, we also introduce prior knowledge from massive unsupervised data to enhance our solution using the SimCLR framework for pre-training. Our final solution achieves an overall better performance than baselines on our handcrafted altimetry dataset. Data and codes are available at https://github.com/ZhangWan-byte/Internal_Solitary_Wave_Localization .
URLs: https://github.com/ZhangWan-byte/Internal_Solitary_Wave_Localization
Authors: Harrison Gietz, Jugal Kalita
Abstract: The improvement of language model robustness, including successful defense against adversarial attacks, remains an open problem. In computer vision settings, the stochastic noising and de-noising process provided by diffusion models has proven useful for purifying input images, thus improving model robustness against adversarial attacks. Similarly, some initial work has explored the use of random noising and de-noising to mitigate adversarial attacks in an NLP setting, but improving the quality and efficiency of these methods is necessary for them to remain competitive. We extend upon methods of input text purification that are inspired by diffusion processes, which randomly mask and refill portions of the input text before classification. Our novel method, MaskPure, exceeds or matches robustness compared to other contemporary defenses, while also requiring no adversarial classifier training and without assuming knowledge of the attack type. In addition, we show that MaskPure is provably certifiably robust. To our knowledge, MaskPure is the first stochastic-purification method with demonstrated success against both character-level and word-level attacks, indicating the generalizable and promising nature of stochastic denoising defenses. In summary: the MaskPure algorithm bridges literature on the current strongest certifiable and empirical adversarial defense methods, showing that both theoretical and practical robustness can be obtained together. Code is available on GitHub at https://github.com/hubarruby/MaskPure.
Authors: Md Hasan Shahriar, Ning Wang, Y. Thomas Hou, Wenjing Lou
Abstract: The exponential adoption of machine learning (ML) is propelling the world into a future of intelligent automation and data-driven solutions. However, the proliferation of malicious data manipulation attacks against ML, namely adversarial and backdoor attacks, jeopardizes its reliability in safety-critical applications. The existing detection methods against such attacks are built upon assumptions, limiting them in diverse practical scenarios. Thus, motivated by the need for a more robust and unified defense mechanism, we investigate the shared traits of adversarial and backdoor attacks and propose NoiSec that leverages solely the noise, the foundational root cause of such attacks, to detect any malicious data alterations. NoiSec is a reconstruction-based detector that disentangles the noise from the test input, extracts the underlying features from the noise, and leverages them to recognize systematic malicious manipulation. Experimental evaluations conducted on the CIFAR10 dataset demonstrate the efficacy of NoiSec, achieving AUROC scores exceeding 0.954 and 0.852 under white-box and black-box adversarial attacks, respectively, and 0.992 against backdoor attacks. Notably, NoiSec maintains a high detection performance, keeping the false positive rate within only 1\%. Comparative analyses against MagNet-based baselines reveal NoiSec's superior performance across various attack scenarios.
Authors: Daniel Floryan
Abstract: When neural networks are trained from data to simulate the dynamics of physical systems, they encounter a persistent challenge: the long-time dynamics they produce are often unphysical or unstable. We analyze the origin of such instabilities when learning linear dynamical systems, focusing on the training dynamics. We make several analytical findings which empirical observations suggest extend to nonlinear dynamical systems. First, the rate of convergence of the training dynamics is uneven and depends on the distribution of energy in the data. As a special case, the dynamics in directions where the data have no energy cannot be learned. Second, in the unlearnable directions, the dynamics produced by the neural network depend on the weight initialization, and common weight initialization schemes can produce unstable dynamics. Third, injecting synthetic noise into the data during training adds damping to the training dynamics and can stabilize the learned simulator, though doing so undesirably biases the learned dynamics. For each contributor to instability, we suggest mitigative strategies. We also highlight important differences between learning discrete-time and continuous-time dynamics, and discuss extensions to nonlinear systems.
Authors: Yu Xia, Chi-Hua Wang, Joshua Mabry, Guang Cheng
Abstract: The evaluation of synthetic data generation is crucial, especially in the retail sector where data accuracy is paramount. This paper introduces a comprehensive framework for assessing synthetic retail data, focusing on fidelity, utility, and privacy. Our approach differentiates between continuous and discrete data attributes, providing precise evaluation criteria. Fidelity is measured through stability and generalizability. Stability ensures synthetic data accurately replicates known data distributions, while generalizability confirms its robustness in novel scenarios. Utility is demonstrated through the synthetic data's effectiveness in critical retail tasks such as demand forecasting and dynamic pricing, proving its value in predictive analytics and strategic planning. Privacy is safeguarded using Differential Privacy, ensuring synthetic data maintains a perfect balance between resembling training and holdout datasets without compromising security. Our findings validate that this framework provides reliable and scalable evaluation for synthetic retail data. It ensures high fidelity, utility, and privacy, making it an essential tool for advancing retail data science. This framework meets the evolving needs of the retail industry with precision and confidence, paving the way for future advancements in synthetic data methodologies.
Authors: Yili Wang, Kaixiong Zhou, Ninghao Liu, Ying Wang, Xin Wang
Abstract: Sharpness-aware minimization (SAM) has received increasing attention in computer vision since it can effectively eliminate the sharp local minima from the training trajectory and mitigate generalization degradation. However, SAM requires two sequential gradient computations during the optimization of each step: one to obtain the perturbation gradient and the other to obtain the updating gradient. Compared with the base optimizer (e.g., Adam), SAM doubles the time overhead due to the additional perturbation gradient. By dissecting the theory of SAM and observing the training gradient of the molecular graph transformer, we propose a new algorithm named GraphSAM, which reduces the training cost of SAM and improves the generalization performance of graph transformer models. There are two key factors that contribute to this result: (i) \textit{gradient approximation}: we use the updating gradient of the previous step to approximate the perturbation gradient at the intermediate steps smoothly (\textbf{increases efficiency}); (ii) \textit{loss landscape approximation}: we theoretically prove that the loss landscape of GraphSAM is limited to a small range centered on the expected loss of SAM (\textbf{guarantees generalization performance}). The extensive experiments on six datasets with different tasks demonstrate the superiority of GraphSAM, especially in optimizing the model update process. The code is in:https://github.com/YL-wang/GraphSAM/tree/graphsam
Authors: Bohao Xu, Yanbo Wang, Wenyu Chen, Shimin Shan
Abstract: Therapeutic antibodies have been extensively studied in drug discovery and development in the past decades. Antibodies are specialized protective proteins that bind to antigens in a lock-to-key manner. The binding strength/affinity between an antibody and a specific antigen is heavily determined by the complementarity-determining regions (CDRs) on the antibodies. Existing machine learning methods cast in silico development of CDRs as either sequence or 3D graph (with a single chain) generation tasks and have achieved initial success. However, with CDR loops having specific geometry shapes, learning the 3D geometric structures of CDRs remains a challenge. To address this issue, we propose AntibodyFlow, a 3D flow model to design antibody CDR loops. Specifically, AntibodyFlow first constructs the distance matrix, then predicts amino acids conditioned on the distance matrix. Also, AntibodyFlow conducts constraint learning and constrained generation to ensure valid 3D structures. Experimental results indicate that AntibodyFlow outperforms the best baseline consistently with up to 16.0% relative improvement in validity rate and 24.3% relative reduction in geometric graph level error (root mean square deviation, RMSD).
Authors: Haibo Wang, Lutfu S. Sua, Bahram Alidaee
Abstract: This study tackles the complexities of global supply chains, which are increasingly vulnerable to disruptions caused by port congestion, material shortages, and inflation. To address these challenges, we explore the application of machine learning methods, which excel in predicting and optimizing solutions based on large datasets. Our focus is on enhancing supply chain security through fraud detection, maintenance prediction, and material backorder forecasting. We introduce an automated machine learning framework that streamlines data analysis, model construction, and hyperparameter optimization for these tasks. By automating these processes, our framework improves the efficiency and effectiveness of supply chain security measures. Our research identifies key factors that influence machine learning performance, including sampling methods, categorical encoding, feature selection, and hyperparameter optimization. We demonstrate the importance of considering these factors when applying machine learning to supply chain challenges. Traditional mathematical programming models often struggle to cope with the complexity of large-scale supply chain problems. Our study shows that machine learning methods can provide a viable alternative, particularly when dealing with extensive datasets and complex patterns. The automated machine learning framework presented in this study offers a novel approach to supply chain security, contributing to the existing body of knowledge in the field. Its comprehensive automation of machine learning processes makes it a valuable contribution to the domain of supply chain management.
Authors: Kartikeya Bhardwaj, Nilesh Prasad Pandey, Sweta Priyadarshi, Viswanath Ganapathy, Rafael Esteves, Shreya Kadambi, Shubhankar Borse, Paul Whatmough, Risheek Garrepalli, Mart Van Baalen, Harris Teague, Markus Nagel
Abstract: Low Rank Adaptation (LoRA) has gained massive attention in the recent generative AI research. One of the main advantages of LoRA is its ability to be fused with pretrained models adding no overhead during inference. However, from a mobile deployment standpoint, we can either avoid inference overhead in the fused mode but lose the ability to switch adapters rapidly, or suffer significant (up to 30% higher) inference latency while enabling rapid switching in the unfused mode. LoRA also exhibits concept-loss when multiple adapters are used concurrently. In this paper, we propose Sparse High Rank Adapters (SHiRA), a new paradigm which incurs no inference overhead, enables rapid switching, and significantly reduces concept-loss. Specifically, SHiRA can be trained by directly tuning only 1-2% of the base model weights while leaving others unchanged. This results in a highly sparse adapter which can be switched directly in the fused mode. We further provide theoretical and empirical insights on how high sparsity in SHiRA can aid multi-adapter fusion by reducing concept loss. Our extensive experiments on LVMs and LLMs demonstrate that finetuning only a small fraction of the parameters in the base model is sufficient for many tasks while enabling both rapid switching and multi-adapter fusion. Finally, we provide a latency- and memory-efficient SHiRA implementation based on Parameter-Efficient Finetuning (PEFT) Library. This implementation trains at nearly the same speed as LoRA while consuming lower peak GPU memory, thus making SHiRA easy to adopt for practical use cases.
Authors: Hansi Yang, James T. Kwok
Abstract: Distributed learning, which does not require gathering training data in a central location, has become increasingly important in the big-data era. In particular, random-walk-based decentralized algorithms are flexible in that they do not need a central server trusted by all clients and do not require all clients to be active in all iterations. However, existing distributed learning algorithms assume that all learning clients share the same task. In this paper, we consider the more difficult meta-learning setting, in which different clients perform different (but related) tasks with limited training data. To reduce communication cost and allow better privacy protection, we propose LoDMeta (Local Decentralized Meta-learning) with the use of local auxiliary optimization parameters and random perturbations on the model parameter. Theoretical results are provided on both convergence and privacy analysis. Empirical results on a number of few-shot learning data sets demonstrate that LoDMeta has similar meta-learning accuracy as centralized meta-learning algorithms, but does not require gathering data from each client and is able to better protect data privacy for each client.
Authors: Kai Gan, Tong Wei, Min-Ling Zhang
Abstract: While long-tailed semi-supervised learning (LTSSL) has received tremendous attention in many real-world classification problems, existing LTSSL algorithms typically assume that the class distributions of labeled and unlabeled data are almost identical. Those LTSSL algorithms built upon the assumption can severely suffer when the class distributions of labeled and unlabeled data are mismatched since they utilize biased pseudo-labels from the model. To alleviate this problem, we propose a new simple method that can effectively utilize unlabeled data from unknown class distributions through Boosting cOnsistency in duAl Training (BOAT). Specifically, we construct the standard and balanced branch to ensure the performance of the head and tail classes, respectively. Throughout the training process, the two branches incrementally converge and interact with each other, eventually resulting in commendable performance across all classes. Despite its simplicity, we show that BOAT achieves state-of-the-art performance on a variety of standard LTSSL benchmarks, e.g., an averaged 2.7% absolute increase in test accuracy against existing algorithms when the class distributions of labeled and unlabeled data are mismatched. Even when the class distributions are identical, BOAT consistently outperforms many sophisticated LTSSL algorithms. We carry out extensive ablation studies to tease apart the factors that are the most important to the success of BOAT. The source code is available at https://github.com/Gank0078/BOAT.
Authors: He Cao, Yanjun Shao, Zhiyuan Liu, Zijing Liu, Xiangru Tang, Yuan Yao, Yu Li
Abstract: Multimodal Large Language Models (MLLMs) have seen growing adoption across various scientific disciplines. These advancements encourage the investigation of molecule-text modeling within synthetic chemistry, a field dedicated to designing and conducting chemical reactions to synthesize new compounds with desired properties and applications. Current approaches, however, often neglect the critical role of multiple molecule graph interaction in understanding chemical reactions, leading to suboptimal performance in synthetic chemistry tasks. This study introduces PRESTO(Progressive Pretraining Enhances Synthetic Chemistry Outcomes), a new framework that bridges the molecule-text modality gap by integrating a comprehensive benchmark of pretraining strategies and dataset configurations. It progressively improves multimodal LLMs through cross-modal alignment and multi-graph understanding. Our extensive experiments demonstrate that PRESTO offers competitive results in downstream synthetic chemistry tasks. The code can be found at https://github.com/IDEA-XL/PRESTO.
Authors: Xinyi Gao, Hongzhi Yin, Tong Chen, Guanhua Ye, Wentao Zhang, Bin Cui
Abstract: Graph neural networks (GNNs) have attracted widespread attention for their impressive capability of graph representation learning. However, the increasing prevalence of large-scale graphs presents a significant challenge for GNN training due to their computational demands, limiting the applicability of GNNs in various scenarios. In response to this challenge, graph condensation (GC) is proposed as a promising acceleration solution, focusing on generating an informative compact graph that enables efficient training of GNNs while retaining performance. Despite the potential to accelerate GNN training, existing GC methods overlook the quality of large training graphs during both the training and inference stages. They indiscriminately emulate the training graph distributions, making the condensed graphs susceptible to noises within the training graph and significantly impeding the application of GC in intricate real-world scenarios. To address this issue, we propose robust graph condensation (RobGC), a plug-and-play approach for GC to extend the robustness and applicability of condensed graphs in noisy graph structure environments. Specifically, RobGC leverages the condensed graph as a feedback signal to guide the denoising process on the original training graph. A label propagation-based alternating optimization strategy is in place for the condensation and denoising processes, contributing to the mutual purification of the condensed graph and training graph. Additionally, as a GC method designed for inductive graph inference, RobGC facilitates test-time graph denoising by leveraging the noise-free condensed graph to calibrate the structure of the test graph. Extensive experiments show that RobGC is compatible with various GC methods, significantly boosting their robustness under different types and levels of graph structural noises.
Authors: Yicong Li, Yu Yang, Jiannong Cao, Shuaiqi Liu, Haoran Tang, Guandong Xu
Abstract: Recent studies successfully learned static graph embeddings that are structurally fair by preventing the effectiveness disparity of high- and low-degree vertex groups in downstream graph mining tasks. However, achieving structure fairness in dynamic graph embedding remains an open problem. Neglecting degree changes in dynamic graphs will significantly impair embedding effectiveness without notably improving structure fairness. This is because the embedding performance of high-degree and low-to-high-degree vertices will significantly drop close to the generally poorer embedding performance of most slightly changed vertices in the long-tail part of the power-law distribution. We first identify biased structural evolutions in a dynamic graph based on the evolving trend of vertex degree and then propose FairDGE, the first structurally Fair Dynamic Graph Embedding algorithm. FairDGE learns biased structural evolutions by jointly embedding the connection changes among vertices and the long-short-term evolutionary trend of vertex degrees. Furthermore, a novel dual debiasing approach is devised to encode fair embeddings contrastively, customizing debiasing strategies for different biased structural evolutions. This innovative debiasing strategy breaks the effectiveness bottleneck of embeddings without notable fairness loss. Extensive experiments demonstrate that FairDGE achieves simultaneous improvement in the effectiveness and fairness of embeddings.
Authors: Sangwoo Seo, Sungwon Kim, Jihyeong Jung, Yoonho Lee, Chanyoung Park
Abstract: Temporal Graph Neural Networks (TGNN) have the ability to capture both the graph topology and dynamic dependencies of interactions within a graph over time. There has been a growing need to explain the predictions of TGNN models due to the difficulty in identifying how past events influence their predictions. Since the explanation model for a static graph cannot be readily applied to temporal graphs due to its inability to capture temporal dependencies, recent studies proposed explanation models for temporal graphs. However, existing explanation models for temporal graphs rely on post-hoc explanations, requiring separate models for prediction and explanation, which is limited in two aspects: efficiency and accuracy of explanation. In this work, we propose a novel built-in explanation framework for temporal graphs, called Self-Explainable Temporal Graph Networks based on Graph Information Bottleneck (TGIB). TGIB provides explanations for event occurrences by introducing stochasticity in each temporal event based on the Information Bottleneck theory. Experimental results demonstrate the superiority of TGIB in terms of both the link prediction performance and explainability compared to state-of-the-art methods. This is the first work that simultaneously performs prediction and explanation for temporal graphs in an end-to-end manner.
Authors: Songyang Chen, Yu Liu, Lei Zou, Zexuan Wang, Youfang Lin, Yuxing Chen, Anqun Pan
Abstract: Unsupervised graph alignment finds the one-to-one node correspondence between a pair of attributed graphs by only exploiting graph structure and node features. One category of existing works first computes the node representation and then matches nodes with close embeddings, which is intuitive but lacks a clear objective tailored for graph alignment in the unsupervised setting. The other category reduces the problem to optimal transport (OT) via Gromov-Wasserstein (GW) learning with a well-defined objective but leaves a large room for exploring the design of transport cost. We propose a principled approach to combine their advantages motivated by theoretical analysis of model expressiveness. By noticing the limitation of discriminative power in separating matched and unmatched node pairs, we improve the cost design of GW learning with feature transformation, which enables feature interaction across dimensions. Besides, we propose a simple yet effective embedding-based heuristic inspired by the Weisfeiler-Lehman test and add its prior knowledge to OT for more expressiveness when handling non-Euclidean data. Moreover, we are the first to guarantee the one-to-one matching constraint by reducing the problem to maximum weight matching. The algorithm design effectively combines our OT and embedding-based predictions via stacking, an ensemble learning strategy. We propose a model framework named \texttt{CombAlign} integrating all the above modules to refine node alignment progressively. Through extensive experiments, we demonstrate significant improvements in alignment accuracy compared to state-of-the-art approaches and validate the effectiveness of the proposed modules.
Authors: Xiaoxiong Zhang, Zhiwei Zeng, Xin Zhou, Dusit Niyato, Zhiqi Shen
Abstract: Federated Knowledge Graphs Embedding learning (FKGE) encounters challenges in communication efficiency stemming from the considerable size of parameters and extensive communication rounds. However, existing FKGE methods only focus on reducing communication rounds by conducting multiple rounds of local training in each communication round, and ignore reducing the size of parameters transmitted within each communication round. To tackle the problem, we first find that universal reduction in embedding precision across all entities during compression can significantly impede convergence speed, underscoring the importance of maintaining embedding precision. We then propose bidirectional communication-efficient FedS based on Entity-Wise Top-K Sparsification strategy. During upload, clients dynamically identify and upload only the Top-K entity embeddings with the greater changes to the server. During download, the server first performs personalized embedding aggregation for each client. It then identifies and transmits the Top-K aggregated embeddings to each client. Besides, an Intermittent Synchronization Mechanism is used by FedS to mitigate negative effect of embedding inconsistency among shared entities of clients caused by heterogeneity of Federated Knowledge Graph. Extensive experiments across three datasets showcase that FedS significantly enhances communication efficiency with negligible (even no) performance degradation.
Authors: Yang Chen, Bin Zhou
Abstract: Graph Neural Networks(GNNs) are vulnerable to adversarial attack that cause performance degradation by adding small perturbations to the graph. Gradient-based attacks are one of the most commonly used methods and have achieved good performance in many attack scenarios. However, current gradient attacks face the problems of easy to fall into local optima and poor attack invisibility. Specifically, most gradient attacks use greedy strategies to generate perturbations, which tend to fall into local optima leading to underperformance of the attack. In addition, many attacks only consider the effectiveness of the attack and ignore the invisibility of the attack, making the attacks easily exposed leading to failure. To address the above problems, this paper proposes an attack on GNNs, called AGSOA, which consists of an average gradient calculation and a structre optimization module. In the average gradient calculation module, we compute the average of the gradient information over all moments to guide the attack to generate perturbed edges, which stabilizes the direction of the attack update and gets rid of undesirable local maxima. In the structure optimization module, we calculate the similarity and homogeneity of the target node's with other nodes to adjust the graph structure so as to improve the invisibility and transferability of the attack. Extensive experiments on three commonly used datasets show that AGSOA improves the misclassification rate by 2$\%$-8$\%$ compared to other state-of-the-art models.
Authors: Thien Nguyen, Tuomo Sipola, Jari Hautam\"aki
Abstract: At the intersection of quantum computing and machine learning, this review paper explores the transformative impact these technologies are having on the capabilities of data processing and analysis, far surpassing the bounds of traditional computational methods. Drawing upon an in-depth analysis of 32 seminal papers, this review delves into the interplay between quantum computing and machine learning, focusing on transcending the limitations of classical computing in advanced data processing and applications. This review emphasizes the potential of quantum-enhanced methods in enhancing cybersecurity, a critical sector that stands to benefit significantly from these advancements. The literature review, primarily leveraging Science Direct as an academic database, delves into the transformative effects of quantum technologies on machine learning, drawing insights from a diverse collection of studies and scholarly articles. While the focus is primarily on the growing significance of quantum computing in cybersecurity, the review also acknowledges the promising implications for other sectors as the field matures. Our systematic approach categorizes sources based on quantum machine learning algorithms, applications, challenges, and potential future developments, uncovering that quantum computing is increasingly being implemented in practical machine learning scenarios. The review highlights advancements in quantum-enhanced machine learning algorithms and their potential applications in sectors such as cybersecurity, emphasizing the need for industry-specific solutions while considering ethical and security concerns. By presenting an overview of the current state and projecting future directions, the paper sets a foundation for ongoing research and strategic advancement in quantum machine learning.
Authors: Zetian Mao, Jiawen Li, Chen Liang, Diptesh Das, Masato Sumita, Koji Tsuda
Abstract: Message passing neural networks have demonstrated significant efficacy in predicting molecular interactions. Introducing equivariant vectorial representations augments expressivity by capturing geometric data symmetries, thereby improving model accuracy. However, two-body bond vectors in opposition may cancel each other out during message passing, leading to the loss of directional information on their shared node. In this study, we develop Equivariant N-body Interaction Networks (ENINet) that explicitly integrates equivariant many-body interactions to preserve directional information in the message passing scheme. Experiments indicate that integrating many-body equivariant representations enhances prediction accuracy across diverse scalar and tensorial quantum chemical properties. Ablation studies show an average performance improvement of 7.9% across 11 out of 12 properties in QM9, 27.9% in forces in MD17, and 11.3% in polarizabilities (CCSD) in QM7b.
Authors: Bj\"orn Nieth, Thomas Altstidl, Leo Schwinn, Bj\"orn Eskofier
Abstract: Their vulnerability to small, imperceptible attacks limits the adoption of deep learning models to real-world systems. Adversarial training has proven to be one of the most promising strategies against these attacks, at the expense of a substantial increase in training time. With the ongoing trend of integrating large-scale synthetic data this is only expected to increase even further. Thus, the need for data-centric approaches that reduce the number of training samples while maintaining accuracy and robustness arises. While data pruning and active learning are prominent research topics in deep learning, they are as of now largely unexplored in the adversarial training literature. We address this gap and propose a new data pruning strategy based on extrapolating data importance scores from a small set of data to a larger set. In an empirical evaluation, we demonstrate that extrapolation-based pruning can efficiently reduce dataset size while maintaining robustness.
Authors: Han Yang, Guangjun Qin, Ziyuan Liu, Yongqing Hu, Qinglong Dai
Abstract: To enhance the robustness of the Light Gradient Boosting Machine (LightGBM) algorithm for image classification, a topological data analysis (TDA)-based robustness optimization algorithm for LightGBM, TDA-LightGBM, is proposed to address the interference of noise on image classification. Initially, the method partitions the feature engineering process into two streams: pixel feature stream and topological feature stream for feature extraction respectively. Subsequently, these pixel and topological features are amalgamated into a comprehensive feature vector, serving as the input for LightGBM in image classification tasks. This fusion of features not only encompasses traditional feature engineering methodologies but also harnesses topological structure information to more accurately encapsulate the intrinsic features of the image. The objective is to surmount challenges related to unstable feature extraction and diminished classification accuracy induced by data noise in conventional image processing. Experimental findings substantiate that TDA-LightGBM achieves a 3% accuracy improvement over LightGBM on the SOCOFing dataset across five classification tasks under noisy conditions. In noise-free scenarios, TDA-LightGBM exhibits a 0.5% accuracy enhancement over LightGBM on two classification tasks, achieving a remarkable accuracy of 99.8%. Furthermore, the method elevates the classification accuracy of the Ultrasound Breast Images for Breast Cancer dataset and the Masked CASIA WebFace dataset by 6% and 15%, respectively, surpassing LightGBM in the presence of noise. These empirical results underscore the efficacy of the TDA-LightGBM approach in fortifying the robustness of LightGBM by integrating topological features, thereby augmenting the performance of image classification tasks amidst data perturbations.
Authors: Lech T. Polkowski
Abstract: Given a raw knowledge in the form of a data table/a decision system, one is facing two possible venues. One, to treat the system as closed, i.e., its universe does not admit new objects, or, to the contrary, its universe is open on admittance of new objects. In particular, one may obtain new objects whose sets of values of features are new to the system. In this case the problem is to assign a decision value to any such new object. This problem is somehow resolved in the rough set theory, e.g., on the basis of similarity of the value set of a new object to value sets of objects already assigned a decision value. It is crucial for online learning when each new object must have a predicted decision value.\ There is a vast literature on various methods for decision prediction for new yet unseen object. The approach we propose is founded in the theory of rough mereology and it requires a theory of sets/concepts, and, we root our theory in classical set theory of Syllogistic within which we recall the theory of parts known as Mereology. Then, we recall our theory of Rough Mereology along with the theory of weight assignment to the Tarski algebra of Mereology.\ This allows us to introduce the notion of a part to a degree. Once we have defined basics of Mereology and rough Mereology, we recall our theory of weight assignment to elements of the Boolean algebra within Mereology and this allows us to define the relation of parts to the degree and we apply this notion in a procedure to select a decision for new yet unseen objects.\ In selecting a plausible candidate which would pass its decision value to the new object, we employ the notion of Vapnik - Chervonenkis dimension in order to select at the first stage the candidate with the largest VC-dimension of the family of its $\varepsilon$-components for some choice of $\varepsilon$.
Authors: Ruirui Zhang, Xingze Wu, Yifei Zou, Zhenzhen Xie, Peng Li, Xiuzhen Cheng, Dongxiao Yu
Abstract: The paper studies a fundamental federated learning (FL) problem involving multiple clients with heterogeneous constrained resources. Compared with the numerous training parameters, the computing and communication resources of clients are insufficient for fast local training and real-time knowledge sharing. Besides, training on clients with heterogeneous resources may result in the straggler problem. To address these issues, we propose Fed-RAA: a Resource-Adaptive Asynchronous Federated learning algorithm. Different from vanilla FL methods, where all parameters are trained by each participating client regardless of resource diversity, Fed-RAA adaptively allocates fragments of the global model to clients based on their computing and communication capabilities. Each client then individually trains its assigned model fragment and asynchronously uploads the updated result. Theoretical analysis confirms the convergence of our approach. Additionally, we design an online greedy-based algorithm for fragment allocation in Fed-RAA, achieving fairness comparable to an offline strategy. We present numerical results on MNIST, CIFAR-10, and CIFAR-100, along with necessary comparisons and ablation studies, demonstrating the advantages of our work. To the best of our knowledge, this paper represents the first resource-adaptive asynchronous method for fragment-based FL with guaranteed theoretical convergence.
Authors: Shengyuan Hu, Yiwei Fu, Zhiwei Steven Wu, Virginia Smith
Abstract: Machine unlearning is a promising approach to mitigate undesirable memorization of training data in ML models. However, in this work we show that existing approaches for unlearning in LLMs are surprisingly susceptible to a simple set of targeted relearning attacks. With access to only a small and potentially loosely related set of data, we find that we can 'jog' the memory of unlearned models to reverse the effects of unlearning. We formalize this unlearning-relearning pipeline, explore the attack across three popular unlearning benchmarks, and discuss future directions and guidelines that result from our study.
Authors: Louis Van Langendonck, Ismael Castell-Uroz, Pere Barlet-Ros
Abstract: Recent works have demonstrated the potential of Graph Neural Networks (GNN) for network intrusion detection. Despite their advantages, a significant gap persists between real-world scenarios, where detection speed is critical, and existing proposals, which operate on large graphs representing several hours of traffic. This gap results in unrealistic operational conditions and impractical detection delays. Moreover, existing models do not generalize well across different networks, hampering their deployment in production environments. To address these issues, we introduce PPTGNN, a practical spatio-temporal GNN for intrusion detection. PPTGNN enables near real-time predictions, while better capturing the spatio-temporal dynamics of network attacks. PPTGNN employs self-supervised pre-training for improved performance and reduced dependency on labeled data. We evaluate PPTGNN on three public datasets and show that it significantly outperforms state-of-the-art models, such as E-ResGAT and E-GraphSAGE, with an average accuracy improvement of 10.38%. Finally, we show that a pre-trained PPTGNN can easily be fine-tuned to unseen networks with minimal labeled examples. This highlights the potential of PPTGNN as a general, large-scale pre-trained model that can effectively operate in diverse network environments.
Authors: Hewen Wang, Renchi Yang, Xiaokui Xiao
Abstract: Graph representation learning (GRL) is to encode graph elements into informative vector representations, which can be used in downstream tasks for analyzing graph-structured data and has seen extensive applications in various domains. However, the majority of extant studies on GRL are geared towards generating node representations, which cannot be readily employed to perform edge-based analytics tasks in edge-attributed bipartite graphs (EABGs) that pervade the real world, e.g., spam review detection in customer-product reviews and identifying fraudulent transactions in user-merchant networks. Compared to node-wise GRL, learning edge representations (ERL) on such graphs is challenging due to the need to incorporate the structure and attribute semantics from the perspective of edges while considering the separate influence of two heterogeneous node sets U and V in bipartite graphs. To our knowledge, despite its importance, limited research has been devoted to this frontier, and existing workarounds all suffer from sub-par results. Motivated by this, this paper designs EAGLE, an effective ERL method for EABGs. Building on an in-depth and rigorous theoretical analysis, we propose the factorized feature propagation (FFP) scheme for edge representations with adequate incorporation of long-range dependencies of edges/features without incurring tremendous computation overheads. We further ameliorate FFP as a dual-view FFP by taking into account the influences from nodes in U and V severally in ERL. Extensive experiments on 5 real datasets showcase the effectiveness of the proposed EAGLE models in semi-supervised edge classification tasks. In particular, EAGLE can attain a considerable gain of at most 38.11% in AP and 1.86% in AUC when compared to the best baselines.
Authors: Julius von K\"ugelgen
Abstract: Causal models provide rich descriptions of complex systems as sets of mechanisms by which each variable is influenced by its direct causes. They support reasoning about manipulating parts of the system and thus hold promise for addressing some of the open challenges of artificial intelligence (AI), such as planning, transferring knowledge in changing environments, or robustness to distribution shifts. However, a key obstacle to more widespread use of causal models in AI is the requirement that the relevant variables be specified a priori, which is typically not the case for the high-dimensional, unstructured data processed by modern AI systems. At the same time, machine learning (ML) has proven quite successful at automatically extracting useful and compact representations of such complex data. Causal representation learning (CRL) aims to combine the core strengths of ML and causality by learning representations in the form of latent variables endowed with causal model semantics. In this thesis, we study and present new results for different CRL settings. A central theme is the question of identifiability: Given infinite data, when are representations satisfying the same learning objective guaranteed to be equivalent? This is an important prerequisite for CRL, as it formally characterises if and when a learning task is, at least in principle, feasible. Since learning causal models, even without a representation learning component, is notoriously difficult, we require additional assumptions on the model class or rich data beyond the classical i.i.d. setting. By partially characterising identifiability for different settings, this thesis investigates what is possible for CRL without direct supervision, and thus contributes to its theoretical foundations. Ideally, the developed insights can help inform data collection practices or inspire the design of new practical estimation methods.
Authors: Adam Jelley, Trevor McInroe, Sam Devlin, Amos Storkey
Abstract: Recent work has demonstrated both benefits and limitations from using supervised approaches (without temporal-difference learning) for offline reinforcement learning. While off-policy reinforcement learning provides a promising approach for improving performance beyond supervised approaches, we observe that training is often inefficient and unstable due to temporal difference bootstrapping. In this paper we propose a best-of-both approach by first learning the behavior policy and critic with supervised learning, before improving with off-policy reinforcement learning. Specifically, we demonstrate improved efficiency by pre-training with a supervised Monte-Carlo value-error, making use of commonly neglected downstream information from the provided offline trajectories. We find that we are able to more than halve the training time of the considered offline algorithms on standard benchmarks, and surprisingly also achieve greater stability. We further build on the importance of having consistent policy and value functions to propose novel hybrid algorithms, TD3+BC+CQL and EDAC+BC, that regularize both the actor and the critic towards the behavior policy. This helps to more reliably improve on the behavior policy when learning from limited human demonstrations. Code is available at https://github.com/AdamJelley/EfficientOfflineRL
Authors: Danial Dervovic, Freddy L\'ecu\'e, Nicol\'as Marchesotti, Daniele Magazzeni
Abstract: The demand for open and trustworthy AI models points towards widespread publishing of model weights. Consumers of these model weights must be able to act accordingly with the information provided. That said, one of the simplest AI classification models, Logistic Regression (LR), has an unwieldy interpretation of its model weights, with greater difficulties when extending LR to generalised additive models. In this work, we show via a User Study that skilled participants are unable to reliably reproduce the action of small LR models given the trained parameters. As an antidote to this, we define Linearised Additive Models (LAMs), an optimal piecewise linear approximation that augments any trained additive model equipped with a sigmoid link function, requiring no retraining. We argue that LAMs are more interpretable than logistic models -- survey participants are shown to solve model reasoning tasks with LAMs much more accurately than with LR given the same information. Furthermore, we show that LAMs do not suffer from large performance penalties in terms of ROC-AUC and calibration with respect to their logistic counterparts on a broad suite of public financial modelling data.
Authors: Matthew Wicker, Philip Sosnin, Adrianna Janik, Mark N. M\"uller, Adrian Weller, Calvin Tsay
Abstract: Proper data stewardship requires that model owners protect the privacy of individuals' data used during training. Whether through anonymization with differential privacy or the use of unlearning in non-anonymized settings, the gold-standard techniques for providing privacy guarantees can come with significant performance penalties or be too weak to provide practical assurances. In part, this is due to the fact that the guarantee provided by differential privacy represents the worst-case privacy leakage for any individual, while the true privacy leakage of releasing the prediction for a given individual might be substantially smaller or even, as we show, non-existent. This work provides a novel framework based on convex relaxations and bounds propagation that can compute formal guarantees (certificates) that releasing specific predictions satisfies $\epsilon=0$ privacy guarantees or do not depend on data that is subject to an unlearning request. Our framework offers a new verification-centric approach to privacy and unlearning guarantees, that can be used to further engender user trust with tighter privacy guarantees, provide formal proofs of robustness to certain membership inference attacks, identify potentially vulnerable records, and enhance current unlearning approaches. We validate the effectiveness of our approach on tasks from financial services, medical imaging, and natural language processing.
Authors: Junhan Kim, Ho-young Kim, Eulrang Cho, Chungman Lee, Joonyoung Kim, Yongkweon Jeon
Abstract: Quantization is a promising solution for deploying large-scale language models (LLMs) on resource-constrained devices. Existing quantization approaches, however, rely on gradient-based optimization, regardless of it being post-training quantization (PTQ) or quantization-aware training (QAT), which becomes problematic for hyper-scale LLMs with billions of parameters. This overhead can be alleviated via recently proposed backpropagation-free PTQ methods; however, their performance is somewhat limited by their lack of consideration of inter-layer dependencies. In this paper, we thus propose a novel PTQ algorithm that considers inter-layer dependencies without relying on backpropagation. The fundamental concept involved is the development of attention-aware Hessian matrices, which facilitates the consideration of inter-layer dependencies within the attention module. Extensive experiments demonstrate that the proposed algorithm significantly outperforms conventional PTQ methods, particularly for low bit-widths.
Authors: Ling Huang, Yucheng Xing, Thierry Denoeux, Mengling Feng
Abstract: We introduce an evidential model for time-to-event prediction with censored data. In this model, uncertainty on event time is quantified by Gaussian random fuzzy numbers, a newly introduced family of random fuzzy subsets of the real line with associated belief functions, generalizing both Gaussian random variables and Gaussian possibility distributions. Our approach makes minimal assumptions about the underlying time-to-event distribution. The model is fit by minimizing a generalized negative log-likelihood function that accounts for both normal and censored data. Comparative experiments on two real-world datasets demonstrate the very good performance of our model as compared to the state-of-the-art.
Authors: Yuqing Kong, Shu Wang, Ying Wang
Abstract: Robust aggregation integrates predictions from multiple experts without knowledge of the experts' information structures. Prior work assumes experts are Bayesian, providing predictions as perfect posteriors based on their signals. However, real-world experts often deviate systematically from Bayesian reasoning. Our work considers experts who tend to ignore the base rate. We find that a certain degree of base rate neglect helps with robust forecast aggregation. Specifically, we consider a forecast aggregation problem with two experts who each predict a binary world state after observing private signals. Unlike previous work, we model experts exhibiting base rate neglect, where they incorporate the base rate information to degree $\lambda\in[0,1]$, with $\lambda=0$ indicating complete ignorance and $\lambda=1$ perfect Bayesian updating. To evaluate aggregators' performance, we adopt Arieli et al. (2018)'s worst-case regret model, which measures the maximum regret across the set of considered information structures compared to an omniscient benchmark. Our results reveal the surprising V-shape of regret as a function of $\lambda$. That is, predictions with an intermediate incorporating degree of base rate $\lambda<1$ can counter-intuitively lead to lower regret than perfect Bayesian posteriors with $\lambda=1$. We additionally propose a new aggregator with low regret robust to unknown $\lambda$. Finally, we conduct an empirical study to test the base rate neglect model and evaluate the performance of various aggregators.
Authors: Matthew Ashman, Cristiana Diaconu, Adrian Weller, Richard E. Turner
Abstract: Neural processes (NPs) are a powerful family of meta-learning models that seek to approximate the posterior predictive map of the ground-truth stochastic process from which each dataset in a meta-dataset is sampled. There are many cases in which practitioners, besides having access to the dataset of interest, may also have access to other datasets that share similarities with it. In this case, integrating these datasets into the NP can improve predictions. We equip NPs with this functionality and describe this paradigm as in-context in-context learning. Standard NP architectures, such as the convolutional conditional NP (ConvCNP) or the family of transformer neural processes (TNPs), are not capable of in-context in-context learning, as they are only able to condition on a single dataset. We address this shortcoming by developing the in-context in-context learning pseudo-token TNP (ICICL-TNP). The ICICL-TNP builds on the family of PT-TNPs, which utilise pseudo-token-based transformer architectures to sidestep the quadratic computational complexity associated with regular transformer architectures. Importantly, the ICICL-TNP is capable of conditioning on both sets of datapoints and sets of datasets, enabling it to perform in-context in-context learning. We demonstrate the importance of in-context in-context learning and the effectiveness of the ICICL-TNP in a number of experiments.
Authors: Sanketh Vedula, Valentino Maiorca, Lorenzo Basile, Francesco Locatello, Alex Bronstein
Abstract: Aligning data from different domains is a fundamental problem in machine learning with broad applications across very different areas, most notably aligning experimental readouts in single-cell multiomics. Mathematically, this problem can be formulated as the minimization of disagreement of pair-wise quantities such as distances and is related to the Gromov-Hausdorff and Gromov-Wasserstein distances. Computationally, it is a quadratic assignment problem (QAP) that is known to be NP-hard. Prior works attempted to solve the QAP directly with entropic or low-rank regularization on the permutation, which is computationally tractable only for modestly-sized inputs, and encode only limited inductive bias related to the domains being aligned. We consider the alignment of metric structures formulated as a discrete Gromov-Wasserstein problem and instead of solving the QAP directly, we propose to learn a related well-scalable linear assignment problem (LAP) whose solution is also a minimizer of the QAP. We also show a flexible extension of the proposed framework to general non-metric dissimilarities through differentiable ranks. We extensively evaluate our approach on synthetic and real datasets from single-cell multiomics and neural latent spaces, achieving state-of-the-art performance while being conceptually and computationally simple.
Authors: Eunjeong Jeong, Marios Kountouris
Abstract: Recent developments and emerging use cases, such as smart Internet of Things (IoT) and Edge AI, have sparked considerable interest in the training of neural networks over fully decentralized (serverless) networks. One of the major challenges of decentralized learning is to ensure stable convergence without resorting to strong assumptions applied for each agent regarding data distributions or updating policies. To address these issues, we propose DRACO, a novel method for decentralized asynchronous Stochastic Gradient Descent (SGD) over row-stochastic gossip wireless networks by leveraging continuous communication. Our approach enables edge devices within decentralized networks to perform local training and model exchanging along a continuous timeline, thereby eliminating the necessity for synchronized timing. The algorithm also features a specific technique of decoupling communication and computation schedules, which empowers complete autonomy for all users and manageable instructions for stragglers. Through a comprehensive convergence analysis, we highlight the advantages of asynchronous and autonomous participation in decentralized optimization. Our numerical experiments corroborate the efficacy of the proposed technique.
Authors: Yuchang Zhu, Jintang Li, Yatao Bian, Zibin Zheng, Liang Chen
Abstract: Recent studies have highlighted fairness issues in Graph Neural Networks (GNNs), where they produce discriminatory predictions against specific protected groups categorized by sensitive attributes such as race and age. While various efforts to enhance GNN fairness have made significant progress, these approaches are often tailored to specific sensitive attributes. Consequently, they necessitate retraining the model from scratch to accommodate changes in the sensitive attribute requirement, resulting in high computational costs. To gain deeper insights into this issue, we approach the graph fairness problem from a causal modeling perspective, where we identify the confounding effect induced by the sensitive attribute as the underlying reason. Motivated by this observation, we formulate the fairness problem in graphs from an invariant learning perspective, which aims to learn invariant representations across environments. Accordingly, we propose a graph fairness framework based on invariant learning, namely FairINV, which enables the training of fair GNNs to accommodate various sensitive attributes within a single training session. Specifically, FairINV incorporates sensitive attribute partition and trains fair GNNs by eliminating spurious correlations between the label and various sensitive attributes. Experimental results on several real-world datasets demonstrate that FairINV significantly outperforms state-of-the-art fairness approaches, underscoring its effectiveness. Our code is available via: https://github.com/ZzoomD/FairINV/.
Authors: Christian Scano, Giuseppe Floris, Biagio Montaruli, Luca Demetrio, Andrea Valenza, Luca Compagna, Davide Ariu, Luca Piras, Davide Balzarotti, Battista Biggio
Abstract: ModSecurity is widely recognized as the standard open-source Web Application Firewall (WAF), maintained by the OWASP Foundation. It detects malicious requests by matching them against the Core Rule Set (CRS), identifying well-known attack patterns. Each rule is manually assigned a weight based on the severity of the corresponding attack, and a request is blocked if the sum of the weights of matched rules exceeds a given threshold. However, we argue that this strategy is largely ineffective against web attacks, as detection is only based on heuristics and not customized on the application to protect. In this work, we overcome this issue by proposing a machine-learning model that uses the CRS rules as input features. Through training, ModSec-Learn is able to tune the contribution of each CRS rule to predictions, thus adapting the severity level to the web applications to protect. Our experiments show that ModSec-Learn achieves a significantly better trade-off between detection and false positive rates. Finally, we analyze how sparse regularization can reduce the number of rules that are relevant at inference time, by discarding more than 30% of the CRS rules. We release our open-source code and the dataset at https://github.com/pralab/modsec-learn and https://github.com/pralab/http-traffic-dataset, respectively.
URLs: https://github.com/pralab/modsec-learn, https://github.com/pralab/http-traffic-dataset,
Authors: Tim Cech, Ole Wegen, Daniel Atzberger, Rico Richter, Willy Scheibel, J\"urgen D\"ollner
Abstract: Standard datasets are frequently used to train and evaluate Machine Learning models. However, the assumed standardness of these datasets leads to a lack of in-depth discussion on how their labels match the derived categories for the respective use case. In other words, the standardness of the datasets seems to fog coherency and applicability, thus impeding the trust in Machine Learning models. We propose to adopt Grounded Theory and Hypotheses Testing through Visualization as methods to evaluate the match between use case, derived categories, and labels of standard datasets. To showcase the approach, we apply it to the 20 Newsgroups dataset and the MNIST dataset. For the 20 Newsgroups dataset, we demonstrate that the labels are imprecise. Therefore, we argue that neither a Machine Learning model can learn a meaningful abstraction of derived categories nor one can draw conclusions from achieving high accuracy. For the MNIST dataset, we demonstrate how the labels can be confirmed to be defined well. We conclude that a concept of standardness of a dataset implies that there is a match between use case, derived categories, and class labels, as in the case of the MNIST dataset. We argue that this is necessary to learn a meaningful abstraction and, thus, improve trust in the Machine Learning model.
Authors: Cale Colony, Razan Andigani
Abstract: This project presents an extension to the GraphCast model, a state-of-the-art graph neural network (GNN) for global weather forecasting, by integrating solar energy production forecasting capabilities. The proposed approach leverages the weather forecasts generated by GraphCast and trains a neural network model to predict the ratio of actual solar output to potential solar output based on various weather conditions. The model architecture consists of an input layer corresponding to weather features (temperature, humidity, dew point, wind speed, rain, barometric pressure, and altitude), two hidden layers with ReLU activations, and an output layer predicting solar radiation. The model is trained using a mean absolute error loss function and Adam optimizer. The results demonstrate the model's effectiveness in accurately predicting solar radiation, with its convergence behavior, decreasing training loss, and accurate prediction of solar radiation patterns suggesting successful learning of the underlying relationships between weather conditions and solar radiation. The integration of solar energy production forecasting with GraphCast offers valuable insights for the renewable energy sector, enabling better planning and decision-making based on expected solar energy production. Future work could explore further model refinements, incorporation of additional weather variables, and extension to other renewable energy sources.
Authors: Sayan Biswas, Mark Dras, Pedro Faustini, Natasha Fernandes, Annabelle McIver, Catuscia Palamidessi, Parastoo Sadeghi
Abstract: Within the machine learning community, reconstruction attacks are a principal attack of concern and have been identified even in federated learning, which was designed with privacy preservation in mind. In federated learning, it has been shown that an adversary with knowledge of the machine learning architecture is able to infer the exact value of a training element given an observation of the weight updates performed during stochastic gradient descent. In response to these threats, the privacy community recommends the use of differential privacy in the stochastic gradient descent algorithm, termed DP-SGD. However, DP has not yet been formally established as an effective countermeasure against reconstruction attacks. In this paper, we formalise the reconstruction threat model using the information-theoretic framework of quantitative information flow. We show that the Bayes' capacity, related to the Sibson mutual information of order infinity, represents a tight upper bound on the leakage of the DP-SGD algorithm to an adversary interested in performing a reconstruction attack. We provide empirical results demonstrating the effectiveness of this measure for comparing mechanisms against reconstruction threats.
Authors: Thea Br\"usch, Kristoffer K. Wickstr{\o}m, Mikkel N. Schmidt, Tommy S. Alstr{\o}m, Robert Jenssen
Abstract: Time series data is fundamentally important for describing many critical domains such as healthcare, finance, and climate, where explainable models are necessary for safe automated decision-making. To develop eXplainable AI (XAI) in these domains therefore implies explaining salient information in the time series. Current methods for obtaining saliency maps assumes localized information in the raw input space. In this paper, we argue that the salient information of a number of time series is more likely to be localized in the frequency domain. We propose FreqRISE, which uses masking based methods to produce explanations in the frequency and time-frequency domain, which shows the best performance across a number of tasks.
Authors: Fan Zhang, Xin Zhang
Abstract: Massive number of applications involve data with underlying relationships embedded in non-Euclidean space. Graph neural networks (GNNs) are utilized to extract features by capturing the dependencies within graphs. Despite groundbreaking performances, we argue that Multi-layer perceptrons (MLPs) and fixed activation functions impede the feature extraction due to information loss. Inspired by Kolmogorov Arnold Networks (KANs), we make the first attempt to GNNs with KANs. We discard MLPs and activation functions, and instead used KANs for feature extraction. Experiments demonstrate the effectiveness of GraphKAN, emphasizing the potential of KANs as a powerful tool. Code is available at https://github.com/Ryanfzhang/GraphKan.
Authors: Elena Tomasi, Gabriele Franch, Marco Cristoforetti
Abstract: Downscaling techniques are one of the most prominent applications of Deep Learning (DL) in Earth System Modeling. A robust DL downscaling model can generate high-resolution fields from coarse-scale numerical model simulations, saving the timely and resourceful applications of regional/local models. Additionally, generative DL models have the potential to provide uncertainty information, by generating ensemble-like scenario pools, a task that is computationally prohibitive for traditional numerical simulations. In this study, we apply a Latent Diffusion Model (LDM) to downscale ERA5 data over Italy up to a resolution of 2 km. The high-resolution target data consists of results from a high-resolution dynamical downscaling performed with COSMO-CLM. Our goal is to demonstrate that recent advancements in generative modeling enable DL-based models to deliver results comparable to those of numerical dynamical downscaling models, given the same input data (i.e., ERA5 data), preserving the realism of fine-scale features and flow characteristics. The training and testing database consists of hourly data from 2000 to 2020. The target variables of this study are 2-m temperature and 10-m horizontal wind components. A selection of predictors from ERA5 is used as input to the LDM, and a residual approach against a reference UNET is leveraged in applying the LDM. The performance of the generative LDM is compared with reference baselines of increasing complexity: quadratic interpolation of ERA5, a UNET, and a Generative Adversarial Network (GAN) built on the same reference UNET. Results highlight the improvements introduced by the LDM architecture and the residual approach over these baselines. The models are evaluated on a yearly test dataset, assessing the models' performance through deterministic metrics, spatial distribution of errors, and reconstruction of frequency and power spectra distributions.
Authors: Jaehyun Park, Dabeen Lee
Abstract: We study model-based reinforcement learning with non-linear function approximation where the transition function of the underlying Markov decision process (MDP) is given by a multinomial logistic (MNL) model. In this paper, we develop two algorithms for the infinite-horizon average reward setting. Our first algorithm \texttt{UCRL2-MNL} applies to the class of communicating MDPs and achieves an $\tilde{\mathcal{O}}(dD\sqrt{T})$ regret, where $d$ is the dimension of feature mapping, $D$ is the diameter of the underlying MDP, and $T$ is the horizon. The second algorithm \texttt{OVIFH-MNL} is computationally more efficient and applies to the more general class of weakly communicating MDPs, for which we show a regret guarantee of $\tilde{\mathcal{O}}(d^{2/5} \mathrm{sp}(v^*)T^{4/5})$ where $\mathrm{sp}(v^*)$ is the span of the associated optimal bias function. We also prove a lower bound of $\Omega(d\sqrt{DT})$ for learning communicating MDPs with MNL transitions of diameter at most $D$. Furthermore, we show a regret lower bound of $\Omega(dH^{3/2}\sqrt{K})$ for learning $H$-horizon episodic MDPs with MNL function approximation where $K$ is the number of episodes, which improves upon the best-known lower bound for the finite-horizon setting.
Authors: Vaibhav Singh, Rahaf Aljundi, Eugene Belilovsky
Abstract: Foundational vision-language models have shown impressive performance on various downstream tasks. Yet, there is still a pressing need to update these models later as new tasks or domains become available. Ongoing Continual Learning (CL) research provides techniques to overcome catastrophic forgetting of previous information when new knowledge is acquired. To date, CL techniques focus only on the supervised training sessions. This results in significant forgetting yielding inferior performance to even the prior model zero shot performance. In this work, we argue that test-time data hold great information that can be leveraged in a self supervised manner to refresh the model's memory of previous learned tasks and hence greatly reduce forgetting at no extra labelling cost. We study how unsupervised data can be employed online to improve models' performance on prior tasks upon encountering representative samples. We propose a simple yet effective student-teacher model with gradient based sparse parameters updates and show significant performance improvements and reduction in forgetting, which could alleviate the role of an offline episodic memory/experience replay buffer.
Authors: Nikita Morozov, Daniil Tiapkin, Sergey Samsonov, Alexey Naumov, Dmitry Vetrov
Abstract: Generative Flow Networks (GFlowNets) treat sampling from distributions over compositional discrete spaces as a sequential decision-making problem, training a stochastic policy to construct objects step by step. Recent studies have revealed strong connections between GFlowNets and entropy-regularized reinforcement learning. Building on these insights, we propose to enhance planning capabilities of GFlowNets by applying Monte Carlo Tree Search (MCTS). Specifically, we show how the MENTS algorithm (Xiao et al., 2019) can be adapted for GFlowNets and used during both training and inference. Our experiments demonstrate that this approach improves the sample efficiency of GFlowNet training and the generation fidelity of pre-trained GFlowNet models.
Authors: Davide Carbone (Dipartimento di Scienze Matematiche, Politecnico di Torino, Torino, Italy, INFN, Sezione di Torino, Torino, Italy)
Abstract: Energy-Based Models (EBMs) have emerged as a powerful framework in the realm of generative modeling, offering a unique perspective that aligns closely with principles of statistical mechanics. This review aims to provide physicists with a comprehensive understanding of EBMs, delineating their connection to other generative models such as Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and Normalizing Flows. We explore the sampling techniques crucial for EBMs, including Markov Chain Monte Carlo (MCMC) methods, and draw parallels between EBM concepts and statistical mechanics, highlighting the significance of energy functions and partition functions. Furthermore, we delve into state-of-the-art training methodologies for EBMs, covering recent advancements and their implications for enhanced model performance and efficiency. This review is designed to clarify the often complex interconnections between these models, which can be challenging due to the diverse communities working on the topic.
Authors: Pengbo Yang, Jian Yu
Abstract: Binary Classification plays an important role in machine learning. For linear classification, SVM is the optimal binary classification method. For nonlinear classification, the SVM algorithm needs to complete the classification task by using the kernel function. Although the SVM algorithm with kernel function is very effective, the selection of kernel function is empirical, which means that the kernel function may not be optimal. Therefore, it is worth studying how to obtain an optimal binary classifier. In this paper, the problem of finding the optimal binary classifier is considered as a variational problem. We design the objective function of this variational problem through the max-min problem of the (Euclidean) distance between two classes. For linear classification, it can be deduced that SVM is a special case of this variational problem framework. For Euclidean distance, it is proved that the proposed variational problem has some limitations for nonlinear classification. Therefore, how to design a more appropriate objective function to find the optimal binary classifier is still an open problem. Further, it's discussed some challenges and problems in finding the optimal classifier.
Authors: Yuval Dagan, Constantinos Daskalakis, Maxwell Fishelson, Noah Golowich, Robert Kleinberg, Princewill Okoroafor
Abstract: A set of probabilistic forecasts is calibrated if each prediction of the forecaster closely approximates the empirical distribution of outcomes on the subset of timesteps where that prediction was made. We study the fundamental problem of online calibrated forecasting of binary sequences, which was initially studied by Foster & Vohra (1998). They derived an algorithm with $O(T^{2/3})$ calibration error after $T$ time steps, and showed a lower bound of $\Omega(T^{1/2})$. These bounds remained stagnant for two decades, until Qiao & Valiant (2021) improved the lower bound to $\Omega(T^{0.528})$ by introducing a combinatorial game called sign preservation and showing that lower bounds for this game imply lower bounds for calibration. We introduce a strengthening of Qiao & Valiant's game that we call sign preservation with reuse (SPR). We prove that the relationship between SPR and calibrated forecasting is bidirectional: not only do lower bounds for SPR translate into lower bounds for calibration, but algorithms for SPR also translate into new algorithms for calibrated forecasting. In particular, any strategy that improves the trivial upper bound for the value of the SPR game would imply a forecasting algorithm with calibration error exponent less than 2/3, improving Foster & Vohra's upper bound for the first time. Using similar ideas, we then prove a slightly stronger lower bound than that of Qiao & Valiant, namely $\Omega(T^{0.54389})$. Our lower bound is obtained by an oblivious adversary, marking the first $\omega(T^{1/2})$ calibration lower bound for oblivious adversaries.
Authors: Abdalwahab Almajed, Maryam Tabar, Peyman Najafirad
Abstract: With growing applications of Machine Learning (ML) techniques in the real world, it is highly important to ensure that these models work in an equitable manner. One main step in ensuring fairness is to effectively measure fairness, and to this end, various metrics have been proposed in the past literature. While the computation of those metrics are straightforward in the classification set-up, it is computationally intractable in the regression domain. To address the challenge of computational intractability, past literature proposed various methods to approximate such metrics. However, they did not verify the extent to which the output of such approximation algorithms are consistent with each other. To fill this gap, this paper comprehensively studies the consistency of the output of various fairness measurement methods through conducting an extensive set of experiments on various regression tasks. As a result, it finds that while some fairness measurement approaches show strong consistency across various regression tasks, certain methods show a relatively poor consistency in certain regression tasks. This, in turn, calls for a more principled approach for measuring fairness in the regression domain.
Authors: Viet-Hoang Tran, Trang Pham, Tho Tran, Tam Le, Tan M. Nguyen
Abstract: Sliced Wasserstein (SW) distance in Optimal Transport (OT) is widely used in various applications thanks to its statistical effectiveness and computational efficiency. On the other hand, Tree Wassenstein (TW) and Tree-sliced Wassenstein (TSW) are instances of OT for probability measures where its ground cost is a tree metric. TSW also has a low computational complexity, i.e. linear to the number of edges in the tree. Especially, TSW is identical to SW when the tree is a chain. While SW is prone to loss of topological information of input measures due to relying on one-dimensional projection, TSW is more flexible and has a higher degree of freedom by choosing a tree rather than a line to alleviate the curse of dimensionality in SW. However, for practical applications, popular tree metric sampling methods are heavily built upon given supports, which limits their capacity to adapt to new supports. In this paper, we propose the Tree-Sliced Wasserstein distance on a System of Lines (TSW-SL), which brings a connection between SW and TSW. Compared to SW and TSW, our TSW-SL benefits from the higher degree of freedom of TSW while being suitable to dynamic settings as SW. In TSW-SL, we use a variant of the Radon Transform to project measures onto a system of lines, resulting in measures on a space with a tree metric, then leverage TW to efficiently compute distances between them. We empirically verify the advantages of TSW-SL over the traditional SW by conducting a variety of experiments on gradient flows, image style transfer, and generative models.
Authors: Nabeel Seedat, Nicolas Huynh, Fergus Imrie, Mihaela van der Schaar
Abstract: Pseudo-labeling is a popular semi-supervised learning technique to leverage unlabeled data when labeled samples are scarce. The generation and selection of pseudo-labels heavily rely on labeled data. Existing approaches implicitly assume that the labeled data is gold standard and 'perfect'. However, this can be violated in reality with issues such as mislabeling or ambiguity. We address this overlooked aspect and show the importance of investigating labeled data quality to improve any pseudo-labeling method. Specifically, we introduce a novel data characterization and selection framework called DIPS to extend pseudo-labeling. We select useful labeled and pseudo-labeled samples via analysis of learning dynamics. We demonstrate the applicability and impact of DIPS for various pseudo-labeling methods across an extensive range of real-world tabular and image datasets. Additionally, DIPS improves data efficiency and reduces the performance distinctions between different pseudo-labelers. Overall, we highlight the significant benefits of a data-centric rethinking of pseudo-labeling in real-world settings.
Authors: Honorius Galmeanu, Razvan Andonie
Abstract: In machine learning, concept drift is an evolution of information that invalidates the current data model. It happens when the statistical properties of the input data change over time in unforeseen ways. Concept drift detection is crucial when dealing with dynamically changing data. Its visualization can bring valuable insight into the data dynamics, especially for multidimensional data, and is related to visual knowledge discovery. We propose a novel visualization model based on parallel coordinates, denoted as parallel histograms through time. Our model represents histograms of feature distributions for successive time-shifted windows. The drift is shown as variations of these histograms, obtained by connecting the means of the distribution for successive time windows. We show how these diagrams can be used to explain the decision made by the machine learning model in choosing the drift point. By isolating the drift at the edges of successive time windows, there will be none (or reduced) drift within the adjacent windows. We illustrate this concept on both synthetic and real datasets. In our experiments, we use an incremental/decremental SVM with shifting window, introduced by us in previous work. With our proposed technique, in addition to detect the presence of concept drift, we can also depict it. This information can be further used to explain the change. mental results, opening the possibility for further investigations.
Authors: Rachel S. Y. Teo, Tan M. Nguyen
Abstract: The remarkable success of transformers in sequence modeling tasks, spanning various applications in natural language processing and computer vision, is attributed to the critical role of self-attention. Similar to the development of most deep learning models, the construction of these attention mechanisms rely on heuristics and experience. In our work, we derive self-attention from kernel principal component analysis (kernel PCA) and show that self-attention projects its query vectors onto the principal component axes of its key matrix in a feature space. We then formulate the exact formula for the value matrix in self-attention, theoretically and empirically demonstrating that this value matrix captures the eigenvectors of the Gram matrix of the key vectors in self-attention. Leveraging our kernel PCA framework, we propose Attention with Robust Principal Components (RPC-Attention), a novel class of robust attention that is resilient to data contamination. We empirically demonstrate the advantages of RPC-Attention over softmax attention on the ImageNet-1K object classification, WikiText-103 language modeling, and ADE20K image segmentation task.
Authors: Stefan K. Nielsen, Laziz U. Abdullaev, Rachel Teo, Tan M. Nguyen
Abstract: Pairwise dot-product self-attention is key to the success of transformers that achieve state-of-the-art performance across a variety of applications in language and vision. This dot-product self-attention computes attention weights among the input tokens using Euclidean distance, which makes the model prone to representation collapse and vulnerable to contaminated samples. In this paper, we propose using a Mahalanobis distance metric for computing the attention weights to stretch the underlying feature space in directions of high contextual relevance. In particular, we define a hyper-ellipsoidal neighborhood around each query to increase the attention weights of the tokens lying in the contextually important directions. We term this novel class of attention Elliptical Attention. Our Elliptical Attention provides two benefits: 1) reducing representation collapse and 2) enhancing the model's robustness as the Elliptical Attention pays more attention to contextually relevant information rather than focusing on some small subset of informative features. We empirically demonstrate the advantages of Elliptical Attention over the baseline dot-product attention and state-of-the-art attention methods on various practical tasks, including object classification, image segmentation, and language modeling across different data modalities.
Authors: Shruthi K. Hiremath, Thomas Ploetz
Abstract: Human Activity Recognition is a time-series analysis problem. A popular analysis procedure used by the community assumes an optimal window length to design recognition pipelines. However, in the scenario of smart homes, where activities are of varying duration and frequency, the assumption of a constant sized window does not hold. Additionally, previous works have shown these activities to be made up of building blocks. We focus on identifying these underlying building blocks--structural constructs, with the use of large language models. Identifying these constructs can be beneficial especially in recognizing short-duration and infrequent activities. We also propose the development of an activity recognition procedure that uses these building blocks to model activities, thus helping the downstream task of activity monitoring in smart homes.
Authors: Tan M. Nguyen, Tam Nguyen, Nhat Ho, Andrea L. Bertozzi, Richard G. Baraniuk, Stanley J. Osher
Abstract: Self-attention is key to the remarkable success of transformers in sequence modeling tasks including many applications in natural language processing and computer vision. Like neural network layers, these attention mechanisms are often developed by heuristics and experience. To provide a principled framework for constructing attention layers in transformers, we show that the self-attention corresponds to the support vector expansion derived from a support vector regression problem, whose primal formulation has the form of a neural network layer. Using our framework, we derive popular attention layers used in practice and propose two new attentions: 1) the Batch Normalized Attention (Attention-BN) derived from the batch normalization layer and 2) the Attention with Scaled Head (Attention-SH) derived from using less training data to fit the SVR model. We empirically demonstrate the advantages of the Attention-BN and Attention-SH in reducing head redundancy, increasing the model's accuracy, and improving the model's efficiency in a variety of practical applications including image and time-series classification.
Authors: Nirjhor Rouf, Fin Amin, Paul D. Franzon
Abstract: In this work, we present empirical results regarding the feasibility of using offline large language models (LLMs) in the context of electronic design automation (EDA). The goal is to investigate and evaluate a contemporary language model's (Llama-2-7B) ability to function as a microelectronic Q & A expert as well as its reasoning, and generation capabilities in solving microelectronic-related problems. Llama-2-7B was tested across a variety of adaptation methods, including introducing a novel low-rank knowledge distillation (LoRA-KD) scheme. Our experiments produce both qualitative and quantitative results.
Authors: Ciaran O'Connor, Joseph Collins, Steven Prestwich, Andrea Visentin
Abstract: Efficiently integrating renewable resources into electricity markets is vital for addressing the challenges of matching real-time supply and demand while reducing the significant energy wastage resulting from curtailments. To address this challenge effectively, the incorporation of storage devices can enhance the reliability and efficiency of the grid, improving market liquidity and reducing price volatility. In short-term electricity markets, participants navigate numerous options, each presenting unique challenges and opportunities, underscoring the critical role of the trading strategy in maximizing profits. This study delves into the optimization of day-ahead and balancing market trading, leveraging quantile-based forecasts. Employing three trading approaches with practical constraints, our research enhances forecast assessment, increases trading frequency, and employs flexible timestamp orders. Our findings underscore the profit potential of simultaneous participation in both day-ahead and balancing markets, especially with larger battery storage systems; despite increased costs and narrower profit margins associated with higher-volume trading, the implementation of high-frequency strategies plays a significant role in maximizing profits and addressing market challenges. Finally, we modelled four commercial battery storage systems and evaluated their economic viability through a scenario analysis, with larger batteries showing a shorter return on investment.
Authors: Arian R. Jamasb, Alex Morehead, Chaitanya K. Joshi, Zuobai Zhang, Kieran Didi, Simon V. Mathis, Charles Harris, Jian Tang, Jianlin Cheng, Pietro Lio, Tom L. Blundell
Abstract: We introduce ProteinWorkshop, a comprehensive benchmark suite for representation learning on protein structures with Geometric Graph Neural Networks. We consider large-scale pre-training and downstream tasks on both experimental and predicted structures to enable the systematic evaluation of the quality of the learned structural representation and their usefulness in capturing functional relationships for downstream tasks. We find that: (1) large-scale pretraining on AlphaFold structures and auxiliary tasks consistently improve the performance of both rotation-invariant and equivariant GNNs, and (2) more expressive equivariant GNNs benefit from pretraining to a greater extent compared to invariant models. We aim to establish a common ground for the machine learning and computational biology communities to rigorously compare and advance protein structure representation learning. Our open-source codebase reduces the barrier to entry for working with large protein structure datasets by providing: (1) storage-efficient dataloaders for large-scale structural databases including AlphaFoldDB and ESM Atlas, as well as (2) utilities for constructing new tasks from the entire PDB. ProteinWorkshop is available at: github.com/a-r-j/ProteinWorkshop.
Authors: Geonhwa Jeong, Po-An Tsai, Stephen W. Keckler, Tushar Krishna
Abstract: Recently, large language models (LLMs) have shown surprising performance in task-specific workloads as well as general tasks with the given prompts. However, to achieve unprecedented performance, recent LLMs use billions to trillions of parameters, which hinder the wide adaptation of those models due to their extremely large compute and memory requirements. To resolve the issue, various model compression methods are being actively investigated. In this work, we propose SDQ (Sparse Decomposed Quantization) to exploit both structured sparsity and quantization to achieve both high compute and memory efficiency. From our evaluations, we observe that SDQ can achieve 4x effective compute throughput with <1% quality drop.
Authors: Danqing Wang, Antonis Antoniades, Kha-Dinh Luong, Edwin Zhang, Mert Kosan, Jiachen Li, Ambuj Singh, William Yang Wang, Lei Li
Abstract: Counterfactual explanations of Graph Neural Networks (GNNs) offer a powerful way to understand data that can naturally be represented by a graph structure. Furthermore, in many domains, it is highly desirable to derive data-driven global explanations or rules that can better explain the high-level properties of the models and data in question. However, evaluating global counterfactual explanations is hard in real-world datasets due to a lack of human-annotated ground truth, which limits their use in areas like molecular sciences. Additionally, the increasing scale of these datasets provides a challenge for random search-based methods. In this paper, we develop a novel global explanation model RLHEX for molecular property prediction. It aligns the counterfactual explanations with human-defined principles, making the explanations more interpretable and easy for experts to evaluate. RLHEX includes a VAE-based graph generator to generate global explanations and an adapter to adjust the latent representation space to human-defined principles. Optimized by Proximal Policy Optimization (PPO), the global explanations produced by RLHEX cover 4.12% more input graphs and reduce the distance between the counterfactual explanation set and the input set by 0.47% on average across three molecular datasets. RLHEX provides a flexible framework to incorporate different human-designed principles into the counterfactual explanation generation process, aligning these explanations with domain expertise. The code and data are released at https://github.com/dqwang122/RLHEX.
Authors: Jiang You, Arben Cela, Ren\'e Natowicz, Jacob Ouanounou, Patrick Siarry
Abstract: Forecasting multivariate time series is a computationally intensive task challenged by extreme or redundant samples. Recent resampling methods aim to increase training efficiency by reweighting samples based on their running losses. However, these methods do not solve the problems caused by heavy-tailed distribution losses, such as overfitting to outliers. To tackle these issues, we introduce a novel approach: a Gaussian loss-weighted sampler that multiplies their running losses with a Gaussian distribution weight. It reduces the probability of selecting samples with very low or very high losses while favoring those close to average losses. As it creates a weighted loss distribution that is not heavy-tailed theoretically, there are several advantages to highlight compared to existing methods: 1) it relieves the inefficiency in learning redundant easy samples and overfitting to outliers, 2) It improves training efficiency by preferentially learning samples close to the average loss. Application on real-world time series forecasting datasets demonstrate improvements in prediction quality for 1%-4% using mean square error measurements in channel-independent settings. The code will be available online after 1 the review.
Authors: Ali Shirali, Rediet Abebe, Moritz Hardt
Abstract: Algorithmic predictions are emerging as a promising solution concept for efficiently allocating societal resources. Fueling their use is an underlying assumption that such systems are necessary to identify individuals for interventions. We propose a principled framework for assessing this assumption: Using a simple mathematical model, we evaluate the efficacy of prediction-based allocations in settings where individuals belong to larger units such as hospitals, neighborhoods, or schools. We find that prediction-based allocations outperform baseline methods using aggregate unit-level statistics only when between-unit inequality is low and the intervention budget is high. Our results hold for a wide range of settings for the price of prediction, treatment effect heterogeneity, and unit-level statistics' learnability. Combined, we highlight the potential limits to improving the efficacy of interventions through prediction.
Authors: Simone Parisi, Alireza Kazemipour, Michael Bowling
Abstract: Exploration in reinforcement learning (RL) remains an open challenge. RL algorithms rely on observing rewards to train the agent, and if informative rewards are sparse the agent learns slowly or may not learn at all. To improve exploration and reward discovery, popular algorithms rely on optimism. But what if sometimes rewards are unobservable, e.g., situations of partial monitoring in bandits and the recent formalism of monitored Markov decision process? In this case, optimism can lead to suboptimal behavior that does not explore further to collapse uncertainty. With this paper, we present a novel exploration strategy that overcomes the limitations of existing methods and guarantees convergence to an optimal policy even when rewards are not always observable. We further propose a collection of tabular environments for benchmarking exploration in RL (with and without unobservable rewards) and show that our method outperforms existing ones.
Authors: Tao Wu, Canyixing Cui, Xingping Xian, Shaojie Qiao, Chao Wang, Lin Yuan, Shui Yu
Abstract: Graph neural networks (GNNs) have achieved tremendous success, but recent studies have shown that GNNs are vulnerable to adversarial attacks, which significantly hinders their use in safety-critical scenarios. Therefore, the design of robust GNNs has attracted increasing attention. However, existing research has mainly been conducted via experimental trial and error, and thus far, there remains a lack of a comprehensive understanding of the vulnerability of GNNs. To address this limitation, we systematically investigate the adversarial robustness of GNNs by considering graph data patterns, model-specific factors, and the transferability of adversarial examples. Through extensive experiments, a set of principled guidelines is obtained for improving the adversarial robustness of GNNs, for example: (i) rather than highly regular graphs, the training graph data with diverse structural patterns is crucial for model robustness, which is consistent with the concept of adversarial training; (ii) the large model capacity of GNNs with sufficient training data has a positive effect on model robustness, and only a small percentage of neurons in GNNs are affected by adversarial attacks; (iii) adversarial transfer is not symmetric and the adversarial examples produced by the small-capacity model have stronger adversarial transferability. This work illuminates the vulnerabilities of GNNs and opens many promising avenues for designing robust GNNs.
Authors: Ben Adcock, Nick Dexter, Sebastian Moraga
Abstract: Operator learning problems arise in many key areas of scientific computing where Partial Differential Equations (PDEs) are used to model physical systems. In such scenarios, the operators map between Banach or Hilbert spaces. In this work, we tackle the problem of learning operators between Banach spaces, in contrast to the vast majority of past works considering only Hilbert spaces. We focus on learning holomorphic operators - an important class of problems with many applications. We combine arbitrary approximate encoders and decoders with standard feedforward Deep Neural Network (DNN) architectures - specifically, those with constant width exceeding the depth - under standard $\ell^2$-loss minimization. We first identify a family of DNNs such that the resulting Deep Learning (DL) procedure achieves optimal generalization bounds for such operators. For standard fully-connected architectures, we then show that there are uncountably many minimizers of the training problem that yield equivalent optimal performance. The DNN architectures we consider are `problem agnostic', with width and depth only depending on the amount of training data $m$ and not on regularity assumptions of the target operator. Next, we show that DL is optimal for this problem: no recovery procedure can surpass these generalization bounds up to log terms. Finally, we present numerical results demonstrating the practical performance on challenging problems including the parametric diffusion, Navier-Stokes-Brinkman and Boussinesq PDEs.
Authors: Wentse Chen, Shiyu Huang, Jeff Schneider
Abstract: Multi-agent reinforcement learning (MARL) tasks often utilize a centralized training with decentralized execution (CTDE) framework. QMIX is a successful CTDE method that learns a credit assignment function to derive local value functions from a global value function, defining a deterministic local policy. However, QMIX is hindered by its poor exploration strategy. While maximum entropy reinforcement learning (RL) promotes better exploration through stochastic policies, QMIX's process of credit assignment conflicts with the maximum entropy objective and the decentralized execution requirement, making it unsuitable for maximum entropy RL. In this paper, we propose an enhancement to QMIX by incorporating an additional local Q-value learning method within the maximum entropy RL framework. Our approach constrains the local Q-value estimates to maintain the correct ordering of all actions. Due to the monotonicity of the QMIX value function, these updates ensure that locally optimal actions align with globally optimal actions. We theoretically prove the monotonic improvement and convergence of our method to an optimal solution. Experimentally, we validate our algorithm in matrix games, Multi-Agent Particle Environment and demonstrate state-of-the-art performance in SMAC-v2.
Authors: Yuan Zhong, Xiaochen Wang, Jiaqi Wang, Xiaokun Zhang, Yaqing Wang, Mengdi Huai, Cao Xiao, Fenglong Ma
Abstract: Synthesizing electronic health records (EHR) data has become a preferred strategy to address data scarcity, improve data quality, and model fairness in healthcare. However, existing approaches for EHR data generation predominantly rely on state-of-the-art generative techniques like generative adversarial networks, variational autoencoders, and language models. These methods typically replicate input visits, resulting in inadequate modeling of temporal dependencies between visits and overlooking the generation of time information, a crucial element in EHR data. Moreover, their ability to learn visit representations is limited due to simple linear mapping functions, thus compromising generation quality. To address these limitations, we propose a novel EHR data generation model called EHRPD. It is a diffusion-based model designed to predict the next visit based on the current one while also incorporating time interval estimation. To enhance generation quality and diversity, we introduce a novel time-aware visit embedding module and a pioneering predictive denoising diffusion probabilistic model (PDDPM). Additionally, we devise a predictive U-Net (PU-Net) to optimize P-DDPM.We conduct experiments on two public datasets and evaluate EHRPD from fidelity, privacy, and utility perspectives. The experimental results demonstrate the efficacy and utility of the proposed EHRPD in addressing the aforementioned limitations and advancing EHR data generation.
Authors: Arsh Tangri, Ondrej Biza, Dian Wang, David Klee, Owen Howell, Robert Platt
Abstract: Sample efficiency is critical when applying learning-based methods to robotic manipulation due to the high cost of collecting expert demonstrations and the challenges of on-robot policy learning through online Reinforcement Learning (RL). Offline RL addresses this issue by enabling policy learning from an offline dataset collected using any behavioral policy, regardless of its quality. However, recent advancements in offline RL have predominantly focused on learning from large datasets. Given that many robotic manipulation tasks can be formulated as rotation-symmetric problems, we investigate the use of $SO(2)$-equivariant neural networks for offline RL with a limited number of demonstrations. Our experimental results show that equivariant versions of Conservative Q-Learning (CQL) and Implicit Q-Learning (IQL) outperform their non-equivariant counterparts. We provide empirical evidence demonstrating how equivariance improves offline learning algorithms in the low-data regime.
Authors: Yaochen Zhu, Yinhan He, Jing Ma, Mengxuan Hu, Sheng Li, Jundong Li
Abstract: Causality lays the foundation for the trajectory of our world. Causal inference (CI), which aims to infer intrinsic causal relations among variables of interest, has emerged as a crucial research topic. Nevertheless, the lack of observation of important variables (e.g., confounders, mediators, exogenous variables, etc.) severely compromises the reliability of CI methods. The issue may arise from the inherent difficulty in measuring the variables. Additionally, in observational studies where variables are passively recorded, certain covariates might be inadvertently omitted by the experimenter. Depending on the type of unobserved variables and the specific CI task, various consequences can be incurred if these latent variables are carelessly handled, such as biased estimation of causal effects, incomplete understanding of causal mechanisms, lack of individual-level causal consideration, etc. In this survey, we provide a comprehensive review of recent developments in CI with latent variables. We start by discussing traditional CI techniques when variables of interest are assumed to be fully observed. Afterward, under the taxonomy of circumvention and inference-based methods, we provide an in-depth discussion of various CI strategies to handle latent variables, covering the tasks of causal effect estimation, mediation analysis, counterfactual reasoning, and causal discovery. Furthermore, we generalize the discussion to graph data where interference among units may exist. Finally, we offer fresh aspects for further advancement of CI with latent variables, especially new opportunities in the era of large language models (LLMs).
Authors: Noushin Behboudi, Sobhan Moosavi, Rajiv Ramnath
Abstract: Traffic accidents pose a severe global public health issue, leading to 1.19 million fatalities annually, with the greatest impact on individuals aged 5 to 29 years old. This paper addresses the critical need for advanced predictive methods in road safety by conducting a comprehensive review of recent advancements in applying machine learning (ML) techniques to traffic accident analysis and prediction. It examines 191 studies from the last five years, focusing on predicting accident risk, frequency, severity, duration, as well as general statistical analysis of accident data. To our knowledge, this study is the first to provide such a comprehensive review, covering the state-of-the-art across a wide range of domains related to accident analysis and prediction. The review highlights the effectiveness of integrating diverse data sources and advanced ML techniques to improve prediction accuracy and handle the complexities of traffic data. By mapping the current landscape and identifying gaps in the literature, this study aims to guide future research towards significantly reducing traffic-related deaths and injuries by 2030, aligning with the World Health Organization (WHO) targets.
Authors: Yizhou Liu
Abstract: Training neural networks involves optimizing parameters to minimize a loss function, where the nature of the loss function and the optimization strategy are crucial for effective training. Hyperparameter choices, such as the learning rate in gradient descent (GD), significantly affect the success and speed of convergence. Recent studies indicate that the boundary between bounded and divergent hyperparameters can be fractal, complicating reliable hyperparameter selection. However, the nature of this fractal boundary and methods to avoid it remain unclear. In this study, we focus on GD to investigate the loss landscape properties that might lead to fractal trainability boundaries. We discovered that fractal boundaries can emerge from simple non-convex perturbations, i.e., adding or multiplying cosine type perturbations to quadratic functions. The observed fractal dimensions are influenced by factors like parameter dimension, type of non-convexity, perturbation wavelength, and perturbation amplitude. Our analysis identifies "roughness of perturbation", which measures the gradient's sensitivity to parameter changes, as the factor controlling fractal dimensions of trainability boundaries. We observed a clear transition from non-fractal to fractal trainability boundaries as roughness increases, with the critical roughness causing the perturbed loss function non-convex. Thus, we conclude that fractal trainability boundaries can arise from very simple non-convexity. We anticipate that our findings will enhance the understanding of complex behaviors during neural network training, leading to more consistent and predictable training strategies.
Authors: Georgi Ganev, Meenatchi Sundaram Muthu Selva Annamalai, Emiliano De Cristofaro
Abstract: Synthetic data created by differentially private (DP) generative models is increasingly used in real-world settings. In this context, PATE-GAN has emerged as a popular algorithm, combining Generative Adversarial Networks (GANs) with the private training approach of PATE (Private Aggregation of Teacher Ensembles). In this paper, we analyze and benchmark six open-source PATE-GAN implementations, including three by (a subset of) the original authors. First, we shed light on architecture deviations and empirically demonstrate that none replicate the utility performance reported in the original paper. Then, we present an in-depth privacy evaluation, including DP auditing, showing that all implementations leak more privacy than intended and uncovering 17 privacy violations and 5 other bugs. Our codebase is available from https://github.com/spalabucr/pategan-audit.
Authors: Noah Topper, Alvaro Velasquez, George Atia
Abstract: Inverse reinforcement learning (IRL) is the problem of inferring a reward function from expert behavior. There are several approaches to IRL, but most are designed to learn a Markovian reward. However, a reward function might be non-Markovian, depending on more than just the current state, such as a reward machine (RM). Although there has been recent work on inferring RMs, it assumes access to the reward signal, absent in IRL. We propose a Bayesian IRL (BIRL) framework for inferring RMs directly from expert behavior, requiring significant changes to the standard framework. We define a new reward space, adapt the expert demonstration to include history, show how to compute the reward posterior, and propose a novel modification to simulated annealing to maximize this posterior. We demonstrate that our method performs well when optimizing according to its inferred reward and compares favorably to an existing method that learns exclusively binary non-Markovian rewards.
Authors: Yimin Zhao, Jin Gu
Abstract: An objective and accurate emotion diagnostic reference is vital to psychologists, especially when dealing with patients who are difficult to communicate with for pathological reasons. Nevertheless, current systems based on Electroencephalography (EEG) data utilized for sentiment discrimination have some problems, including excessive model complexity, mediocre accuracy, and limited interpretability. Consequently, we propose a novel and effective feature fusion mechanism named Mutual-Cross-Attention (MCA). Combining with a specially customized 3D Convolutional Neural Network (3D-CNN), this purely mathematical mechanism adeptly discovers the complementary relationship between time-domain and frequency-domain features in EEG data. Furthermore, the new designed Channel-PSD-DE 3D feature also contributes to the high performance. The proposed method eventually achieves 99.49% (valence) and 99.30% (arousal) accuracy on DEAP dataset.
Authors: Qingpeng Cai, Kaiping Zheng, H. V. Jagadish, Beng Chin Ooi, James Yip
Abstract: Cohort studies are of significant importance in the field of healthcare analysis. However, existing methods typically involve manual, labor-intensive, and expert-driven pattern definitions or rely on simplistic clustering techniques that lack medical relevance. Automating cohort studies with interpretable patterns has great potential to facilitate healthcare analysis but remains an unmet need in prior research efforts. In this paper, we propose a cohort auto-discovery model, CohortNet, for interpretable healthcare analysis, focusing on the effective identification, representation, and exploitation of cohorts characterized by medically meaningful patterns. CohortNet initially learns fine-grained patient representations by separately processing each feature, considering both individual feature trends and feature interactions at each time step. Subsequently, it classifies each feature into distinct states and employs a heuristic cohort exploration strategy to effectively discover substantial cohorts with concrete patterns. For each identified cohort, it learns comprehensive cohort representations with credible evidence through associated patient retrieval. Ultimately, given a new patient, CohortNet can leverage relevant cohorts with distinguished importance, which can provide a more holistic understanding of the patient's conditions. Extensive experiments on three real-world datasets demonstrate that it consistently outperforms state-of-the-art approaches and offers interpretable insights from diverse perspectives in a top-down fashion.
Authors: Xiaolei Wang, Xinyu Tang, Wayne Xin Zhao, Ji-Rong Wen
Abstract: The emergence of in-context learning (ICL) is potentially attributed to two major abilities: task recognition (TR) for recognizing the task from demonstrations and utilizing pre-trained priors, and task learning (TL) for learning from demonstrations. However, relationships between the two abilities and how such relationships affect the emergence of ICL is unclear. In this paper, we take the first step by examining the pre-training dynamics of the emergence of ICL. With carefully designed metrics, we find that these two abilities are, in fact, competitive during pre-training. Moreover, we observe a strong negative correlation between the competition and ICL performance. Further analysis of common pre-training factors (i.e., model size, dataset size, and data curriculum) demonstrates possible ways to manage the competition. Based on these insights, we propose a simple yet effective method to better integrate these two abilities for ICL at inference time. Through adaptive ensemble learning, the performance of ICL can be significantly boosted, enabling two small models to outperform a larger one with more than twice the parameters. The code is available at https://github.com/RUCAIBox/Competitive-ICL.
Authors: Xisen Jin, Xiang Ren
Abstract: Language models (LMs) are known to suffer from forgetting of previously learned examples when fine-tuned, breaking stability of deployed LM systems. Despite efforts on mitigating forgetting, few have investigated whether, and how forgotten upstream examples are associated with newly learned tasks. Insights on such associations enable efficient and targeted mitigation of forgetting. In this paper, we empirically analyze forgetting that occurs in $N$ upstream examples while the model learns $M$ new tasks and visualize their associations with a $M \times N$ matrix. We empirically demonstrate that the degree of forgetting can often be approximated by simple multiplicative contributions of the upstream examples and newly learned tasks. We also reveal more complicated patterns where specific subsets of examples are forgotten with statistics and visualization. Following our analysis, we predict forgetting that happens on upstream examples when learning a new task with matrix completion over the empirical associations, outperforming prior approaches that rely on trainable LMs. Project website: https://inklab.usc.edu/lm-forgetting-prediction/
Authors: Jiuxiang Gu, Yingyu Liang, Zhenmei Shi, Zhao Song, Chiwun Yang
Abstract: Prompting and contextual-based fine-tuning methods, which we call Prefix Learning, have been proposed to enhance the performance of language models on various downstream tasks that can match full parameter fine-tuning. There remains a limited theoretical understanding of how these methods work. In this paper, we aim to relieve this limitation by studying the learning ability of Prefix Learning from the perspective of prefix length. In particular, we approximate the infinite-long Prefix Learning optimization process by the Neural Tangent Kernel (NTK) technique. We formulate and solve it as a learning problem of the infinite-long prefix in a one-layer attention network. Our results confirm the over-parameterization property and arbitrary small loss convergence guarantee of the infinite-long Prefix Learning in attention. To the implementation end, we propose our NTK-Attention method, which is "equivalent" to attention computation with arbitrary prefix length efficiently. Its time complexity mainly depends on the sub-quadratic of input length (without prefix), and our method only requires $d^2 + d$ extra parameters for representation, where $d$ is the feature dimension. In addition, we conducted experiments that compare our NTK-Attention with full parameters fine-tuning, LoRA, and P-Tuning V2 methods across vision or natural language datasets. The results indicate our approach may be a promising parameter-efficient-fine-tuning method since it has demonstrated superior performance in numerous scenarios. Our code can be found at \url{https://github.com/ChristianYang37/chiwun/tree/main/src/NTK-Attention}.
URLs: https://github.com/ChristianYang37/chiwun/tree/main/src/NTK-Attention
Authors: Yu-Neng Chuang, Songchen Li, Jiayi Yuan, Guanchu Wang, Kwei-Herng Lai, Leisheng Yu, Sirui Ding, Chia-Yuan Chang, Qiaoyu Tan, Daochen Zha, Xia Hu
Abstract: Inspired by Large Language Models (LLMs), Time Series Forecasting (TSF), a long-standing task in time series analysis, is undergoing a transition towards Large Time Series Models (LTSMs), aiming to train universal transformer-based models for TSF. However, training LTSMs on heterogeneous time series data poses unique challenges, including diverse frequencies, dimensions, and patterns across datasets. Recent endeavors have studied and evaluated various design choices aimed at enhancing LTSM training and generalization capabilities, spanning pre-processing techniques, model configurations, and dataset configurations. In this work, we comprehensively analyze these design choices and aim to identify the best practices for training LTSM. Moreover, we propose \emph{time series prompt}, a novel statistical prompting strategy tailored to time series data. Furthermore, based on the observations in our analysis, we introduce \texttt{LTSM-bundle}, which bundles the best design choices we have identified. Empirical results demonstrate that \texttt{LTSM-bundle} achieves superior zero-shot and few-shot performances compared to state-of-the-art LSTMs and traditional TSF methods on benchmark datasets.
Authors: Karam Daaboul, Florian Kuhm, Tim Joseph, J. Marius Zoellner
Abstract: Meta-Reinforcement Learning (Meta-RL) aims to acquire meta-knowledge for quick adaptation to diverse tasks. However, applying these policies in real-world environments presents a significant challenge in balancing rapid adaptability with adherence to environmental constraints. Our novel approach, Constraint Model Agnostic Meta Learning (C-MAML), merges meta learning with constrained optimization to address this challenge. C-MAML enables rapid and efficient task adaptation by incorporating task-specific constraints directly into its meta-algorithm framework during the training phase. This fusion results in safer initial parameters for learning new tasks. We demonstrate the effectiveness of C-MAML in simulated locomotion with wheeled robot tasks of varying complexity, highlighting its practicality and robustness in dynamic environments.
Authors: Xinbo Zhao, Yingxue Zhang, Xin Zhang, Yu Yang, Yiqun Xie, Yanhua Li, Jun Luo
Abstract: Enhancing diverse human decision-making processes in an urban environment is a critical issue across various applications, including ride-sharing vehicle dispatching, public transportation management, and autonomous driving. Offline reinforcement learning (RL) is a promising approach to learn and optimize human urban strategies (or policies) from pre-collected human-generated spatial-temporal urban data. However, standard offline RL faces two significant challenges: (1) data scarcity and data heterogeneity, and (2) distributional shift. In this paper, we introduce MODA -- a Multi-Task Offline Reinforcement Learning with Contrastive Data Sharing approach. MODA addresses the challenges of data scarcity and heterogeneity in a multi-task urban setting through Contrastive Data Sharing among tasks. This technique involves extracting latent representations of human behaviors by contrasting positive and negative data pairs. It then shares data presenting similar representations with the target task, facilitating data augmentation for each task. Moreover, MODA develops a novel model-based multi-task offline RL algorithm. This algorithm constructs a robust Markov Decision Process (MDP) by integrating a dynamics model with a Generative Adversarial Network (GAN). Once the robust MDP is established, any online RL or planning algorithm can be applied. Extensive experiments conducted in a real-world multi-task urban setting validate the effectiveness of MODA. The results demonstrate that MODA exhibits significant improvements compared to state-of-the-art baselines, showcasing its capability in advancing urban decision-making processes. We also made our code available to the research community.
Authors: In\^es Valentim, Nuno Antunes, Nuno Louren\c{c}o
Abstract: Adversarial examples, designed to trick Artificial Neural Networks (ANNs) into producing wrong outputs, highlight vulnerabilities in these models. Exploring these weaknesses is crucial for developing defenses, and so, we propose a method to assess the adversarial robustness of image-classifying ANNs. The t-distributed Stochastic Neighbor Embedding (t-SNE) technique is used for visual inspection, and a metric, which compares the clean and perturbed embeddings, helps pinpoint weak spots in the layers. Analyzing two ANNs on CIFAR-10, one designed by humans and another via NeuroEvolution, we found that differences between clean and perturbed representations emerge early on, in the feature extraction layers, affecting subsequent classification. The findings with our metric are supported by the visual analysis of the t-SNE maps.
Authors: Lucas Grativol Ribeiro (IMT Atlantique - MEE, Lab\_STICC\_BRAIn, Lab-STICC\_2AI, LHC), Mathieu Leonardon (IMT Atlantique - MEE, Lab\_STICC\_BRAIn), Guillaume Muller (Mines Saint-\'Etienne MSE, FAYOL-ENSMSE, FAYOL-ENSMSE), Virginie Fresse (LHC, TSE), Matthieu Arzel (IMT Atlantique - MEE, Lab-STICC\_2AI)
Abstract: Low-Rank Adaptation (LoRA) methods have gained popularity in efficient parameter fine-tuning of models containing hundreds of billions of parameters. In this work, instead, we demonstrate the application of LoRA methods to train small-vision models in Federated Learning (FL) from scratch. We first propose an aggregation-agnostic method to integrate LoRA within FL, named FLoCoRA, showing that the method is capable of reducing communication costs by 4.8 times, while having less than 1% accuracy degradation, for a CIFAR-10 classification task with a ResNet-8. Next, we show that the same method can be extended with an affine quantization scheme, dividing the communication cost by 18.6 times, while comparing it with the standard method, with still less than 1% of accuracy loss, tested with on a ResNet-18 model. Our formulation represents a strong baseline for message size reduction, even when compared to conventional model compression works, while also reducing the training memory requirements due to the low-rank adaptation.
Authors: Qianli Shen, Yezhen Wang, Zhouhao Yang, Xiang Li, Haonan Wang, Yang Zhang, Jonathan Scarlett, Zhanxing Zhu, Kenji Kawaguchi
Abstract: Bi-level optimization (BO) has become a fundamental mathematical framework for addressing hierarchical machine learning problems. As deep learning models continue to grow in size, the demand for scalable bi-level optimization solutions has become increasingly critical. Traditional gradient-based bi-level optimization algorithms, due to their inherent characteristics, are ill-suited to meet the demands of large-scale applications. In this paper, we introduce $\textbf{F}$orward $\textbf{G}$radient $\textbf{U}$nrolling with $\textbf{F}$orward $\textbf{F}$radient, abbreviated as $(\textbf{FG})^2\textbf{U}$, which achieves an unbiased stochastic approximation of the meta gradient for bi-level optimization. $(\text{FG})^2\text{U}$ circumvents the memory and approximation issues associated with classical bi-level optimization approaches, and delivers significantly more accurate gradient estimates than existing large-scale bi-level optimization approaches. Additionally, $(\text{FG})^2\text{U}$ is inherently designed to support parallel computing, enabling it to effectively leverage large-scale distributed computing systems to achieve significant computational efficiency. In practice, $(\text{FG})^2\text{U}$ and other methods can be strategically placed at different stages of the training process to achieve a more cost-effective two-phase paradigm. Further, $(\text{FG})^2\text{U}$ is easy to implement within popular deep learning frameworks, and can be conveniently adapted to address more challenging zeroth-order bi-level optimization scenarios. We provide a thorough convergence analysis and a comprehensive practical discussion for $(\text{FG})^2\text{U}$, complemented by extensive empirical evaluations, showcasing its superior performance in diverse large-scale bi-level optimization tasks.
Authors: Juan Jose Garau-Luis, Patrick Bordes, Liam Gonzalez, Masa Roller, Bernardo P. de Almeida, Lorenz Hexemer, Christopher Blum, Stefan Laurent, Jan Grzegorzewski, Maren Lang, Thomas Pierrot, Guillaume Richard
Abstract: Biological sequences encode fundamental instructions for the building blocks of life, in the form of DNA, RNA, and proteins. Modeling these sequences is key to understand disease mechanisms and is an active research area in computational biology. Recently, Large Language Models have shown great promise in solving certain biological tasks but current approaches are limited to a single sequence modality (DNA, RNA, or protein). Key problems in genomics intrinsically involve multiple modalities, but it remains unclear how to adapt general-purpose sequence models to those cases. In this work we propose a multi-modal model that connects DNA, RNA, and proteins by leveraging information from different pre-trained modality-specific encoders. We demonstrate its capabilities by applying it to the largely unsolved problem of predicting how multiple RNA transcript isoforms originate from the same gene (i.e. same DNA sequence) and map to different transcription expression levels across various human tissues. We show that our model, dubbed IsoFormer, is able to accurately predict differential transcript expression, outperforming existing methods and leveraging the use of multiple modalities. Our framework also achieves efficient transfer knowledge from the encoders pre-training as well as in between modalities. We open-source our model, paving the way for new multi-modal gene expression approaches.
Authors: Niklas Freymuth, Philipp Dahlinger, Tobias W\"urth, Philipp Becker, Aleksandar Taranovic, Onno Gr\"onheim, Luise K\"arger, Gerhard Neumann
Abstract: Many engineering systems require accurate simulations of complex physical systems. Yet, analytical solutions are only available for simple problems, necessitating numerical approximations such as the Finite Element Method (FEM). The cost and accuracy of the FEM scale with the resolution of the underlying computational mesh. To balance computational speed and accuracy meshes with adaptive resolution are used, allocating more resources to critical parts of the geometry. Currently, practitioners often resort to hand-crafted meshes, which require extensive expert knowledge and are thus costly to obtain. Our approach, Adaptive Meshing By Expert Reconstruction (AMBER), views mesh generation as an imitation learning problem. AMBER combines a graph neural network with an online data acquisition scheme to predict the projected sizing field of an expert mesh on a given intermediate mesh, creating a more accurate subsequent mesh. This iterative process ensures efficient and accurate imitation of expert mesh resolutions on arbitrary new geometries during inference. We experimentally validate AMBER on heuristic 2D meshes and 3D meshes provided by a human expert, closely matching the provided demonstrations and outperforming a single-step CNN baseline.
Authors: Marco Fumero, Marco Pegoraro, Valentino Maiorca, Francesco Locatello, Emanuele Rodol\`a
Abstract: Neural models learn data representations that lie on low-dimensional manifolds, yet modeling the relation between these representational spaces is an ongoing challenge. By integrating spectral geometry principles into neural modeling, we show that this problem can be better addressed in the functional domain, mitigating complexity, while enhancing interpretability and performances on downstream tasks. To this end, we introduce a multi-purpose framework to the representation learning community, which allows to: (i) compare different spaces in an interpretable way and measure their intrinsic similarity; (ii) find correspondences between them, both in unsupervised and weakly supervised settings, and (iii) to effectively transfer representations between distinct spaces. We validate our framework on various applications, ranging from stitching to retrieval tasks, demonstrating that latent functional maps can serve as a swiss-army knife for representation alignment.
Authors: Chaoqi Liang, Guanglei Yang, Lifeng Qiao, Zitong Huang, Hongliang Yan, Yunchao Wei, Wangmeng Zuo
Abstract: Deep neural networks have achieved remarkable performance across various tasks when supplied with large-scale labeled data. However, the collection of labeled data can be time-consuming and labor-intensive. Semi-supervised learning (SSL), particularly through pseudo-labeling algorithms that iteratively assign pseudo-labels for self-training, offers a promising solution to mitigate the dependency of labeled data. Previous research generally applies a uniform pseudo-labeling strategy across all model layers, assuming that pseudo-labels exert uniform influence throughout. Contrasting this, our theoretical analysis and empirical experiment demonstrate feature extraction layer and linear classification layer have distinct learning behaviors in response to pseudo-labels. Based on these insights, we develop two layer-specific pseudo-label strategies, termed Grad-ReLU and Avg-Clustering. Grad-ReLU mitigates the impact of noisy pseudo-labels by removing the gradient detrimental effects of pseudo-labels in the linear classification layer. Avg-Clustering accelerates the convergence of feature extraction layer towards stable clustering centers by integrating consistent outputs. Our approach, LayerMatch, which integrates these two strategies, can avoid the severe interference of noisy pseudo-labels in the linear classification layer while accelerating the clustering capability of the feature extraction layer. Through extensive experimentation, our approach consistently demonstrates exceptional performance on standard semi-supervised learning benchmarks, achieving a significant improvement of 10.38% over baseline method and a 2.44% increase compared to state-of-the-art methods.
Authors: Yujing Wang, Hainan Zhang, Sijia Wen, Wangjie Qiu, Binghui Guo
Abstract: Federated learning is highly susceptible to model poisoning attacks, especially those meticulously crafted for servers. Traditional defense methods mainly focus on updating assessments or robust aggregation against manually crafted myopic attacks. When facing advanced attacks, their defense stability is notably insufficient. Therefore, it is imperative to develop adaptive defenses against such advanced poisoning attacks. We find that benign clients exhibit significantly higher data distribution stability than malicious clients in federated learning in both CV and NLP tasks. Therefore, the malicious clients can be recognized by observing the stability of their data distribution. In this paper, we propose AdaAggRL, an RL-based Adaptive Aggregation method, to defend against sophisticated poisoning attacks. Specifically, we first utilize distribution learning to simulate the clients' data distributions. Then, we use the maximum mean discrepancy (MMD) to calculate the pairwise similarity of the current local model data distribution, its historical data distribution, and global model data distribution. Finally, we use policy learning to adaptively determine the aggregation weights based on the above similarities. Experiments on four real-world datasets demonstrate that the proposed defense model significantly outperforms widely adopted defense models for sophisticated attacks.
Authors: Matthew Middlehurst, Ali Ismail-Fawaz, Antoine Guillaume, Christopher Holder, David Guijo Rubio, Guzal Bulatova, Leonidas Tsaprounis, Lukasz Mentel, Martin Walter, Patrick Sch\"afer, Anthony Bagnall
Abstract: aeon is a unified Python 3 library for all machine learning tasks involving time series. The package contains modules for time series forecasting, classification, extrinsic regression and clustering, as well as a variety of utilities, transformations and distance measures designed for time series data. aeon also has a number of experimental modules for tasks such as anomaly detection, similarity search and segmentation. aeon follows the scikit-learn API as much as possible to help new users and enable easy integration of aeon estimators with useful tools such as model selection and pipelines. It provides a broad library of time series algorithms, including efficient implementations of the very latest advances in research. Using a system of optional dependencies, aeon integrates a wide variety of packages into a single interface while keeping the core framework with minimal dependencies. The package is distributed under the 3-Clause BSD license and is available at https://github.com/ aeon-toolkit/aeon. This version was submitted to the JMLR journal on 02 Nov 2023 for v0.5.0 of aeon. At the time of this preprint aeon has released v0.9.0, and has had substantial changes.
URLs: https://github.com/
Authors: Xiangli Yang, Xijie Deng, Hanwei Zhang, Yang Zou, Jianxi Yang
Abstract: Structural health monitoring (SHM) is critical to safeguarding the safety and reliability of aerospace, civil, and mechanical infrastructure. Machine learning-based data-driven approaches have gained popularity in SHM due to advancements in sensors and computational power. However, machine learning models used in SHM are vulnerable to adversarial examples -- even small changes in input can lead to different model outputs. This paper aims to address this problem by discussing adversarial defenses in SHM. In this paper, we propose an adversarial training method for defense, which uses circle loss to optimize the distance between features in training to keep examples away from the decision boundary. Through this simple yet effective constraint, our method demonstrates substantial improvements in model robustness, surpassing existing defense mechanisms.
Authors: Zhaozhe Hu, Jia-Li Yin, Bin Chen, Luojun Lin, Bo-Hao Chen, Ximeng Liu
Abstract: Self-ensemble adversarial training methods improve model robustness by ensembling models at different training epochs, such as model weight averaging (WA). However, previous research has shown that self-ensemble defense methods in adversarial training (AT) still suffer from robust overfitting, which severely affects the generalization performance. Empirically, in the late phases of training, the AT becomes more overfitting to the extent that the individuals for weight averaging also suffer from overfitting and produce anomalous weight values, which causes the self-ensemble model to continue to undergo robust overfitting due to the failure in removing the weight anomalies. To solve this problem, we aim to tackle the influence of outliers in the weight space in this work and propose an easy-to-operate and effective Median-Ensemble Adversarial Training (MEAT) method to solve the robust overfitting phenomenon existing in self-ensemble defense from the source by searching for the median of the historical model weights. Experimental results show that MEAT achieves the best robustness against the powerful AutoAttack and can effectively allievate the robust overfitting. We further demonstrate that most defense methods can improve robust generalization and robustness by combining with MEAT.
Authors: Faried Abu Zaid, Daniel Neider, Mustafa Yal\c{c}{\i}ner
Abstract: Formal verification has emerged as a promising method to ensure the safety and reliability of neural networks. Naively verifying a safety property amounts to ensuring the safety of a neural network for the whole input space irrespective of any training or test set. However, this also implies that the safety of the neural network is checked even for inputs that do not occur in the real-world and have no meaning at all, often resulting in spurious errors. To tackle this shortcoming, we propose the VeriFlow architecture as a flow based density model tailored to allow any verification approach to restrict its search to the some data distribution of interest. We argue that our architecture is particularly well suited for this purpose because of two major properties. First, we show that the transformation and log-density function that are defined by our model are piece-wise affine. Therefore, the model allows the usage of verifiers based on SMT with linear arithmetic. Second, upper density level sets (UDL) of the data distribution take the shape of an $L^p$-ball in the latent space. As a consequence, representations of UDLs specified by a given probability are effectively computable in latent space. This allows for SMT and abstract interpretation approaches with fine-grained, probabilistically interpretable, control regarding on how (a)typical the inputs subject to verification are.
Authors: Md Fahim Sikder, Resmi Ramachandranpillai, Daniel de Leng, Fredrik Heintz
Abstract: We present FairX, an open-source Python-based benchmarking tool designed for the comprehensive analysis of models under the umbrella of fairness, utility, and eXplainability (XAI). FairX enables users to train benchmarking bias-removal models and evaluate their fairness using a wide array of fairness metrics, data utility metrics, and generate explanations for model predictions, all within a unified framework. Existing benchmarking tools do not have the way to evaluate synthetic data generated from fair generative models, also they do not have the support for training fair generative models either. In FairX, we add fair generative models in the collection of our fair-model library (pre-processing, in-processing, post-processing) and evaluation metrics for evaluating the quality of synthetic fair data. This version of FairX supports both tabular and image datasets. It also allows users to provide their own custom datasets. The open-source FairX benchmarking package is publicly available at https://github.com/fahim-sikder/FairX.
Authors: Yunfei Liu, Jintang Li, Yuehe Chen, Ruofan Wu, Ericbk Wang, Jing Zhou, Sheng Tian, Shuheng Shen, Xing Fu, Changhua Meng, Weiqiang Wang, Liang Chen
Abstract: Graph clustering, a fundamental and challenging task in graph mining, aims to classify nodes in a graph into several disjoint clusters. In recent years, graph contrastive learning (GCL) has emerged as a dominant line of research in graph clustering and advances the new state-of-the-art. However, GCL-based methods heavily rely on graph augmentations and contrastive schemes, which may potentially introduce challenges such as semantic drift and scalability issues. Another promising line of research involves the adoption of modularity maximization, a popular and effective measure for community detection, as the guiding principle for clustering tasks. Despite the recent progress, the underlying mechanism of modularity maximization is still not well understood. In this work, we dig into the hidden success of modularity maximization for graph clustering. Our analysis reveals the strong connections between modularity maximization and graph contrastive learning, where positive and negative examples are naturally defined by modularity. In light of our results, we propose a community-aware graph clustering framework, coined MAGI, which leverages modularity maximization as a contrastive pretext task to effectively uncover the underlying information of communities in graphs, while avoiding the problem of semantic drift. Extensive experiments on multiple graph datasets verify the effectiveness of MAGI in terms of scalability and clustering performance compared to state-of-the-art graph clustering methods. Notably, MAGI easily scales a sufficiently large graph with 100M nodes while outperforming strong baselines.
Authors: Charlotte Beylier, Simon M. Hofmann, Nico Scherf
Abstract: The learning process of a reinforcement learning (RL) agent remains poorly understood beyond the mathematical formulation of its learning algorithm. To address this gap, we introduce attention-oriented metrics (ATOMs) to investigate the development of an RL agent's attention during training. We tested ATOMs on three variations of a Pong game, each designed to teach the agent distinct behaviours, complemented by a behavioural assessment. Our findings reveal that ATOMs successfully delineate the attention patterns of an agent trained on each game variation, and that these differences in attention patterns translate into differences in the agent's behaviour. Through continuous monitoring of ATOMs during training, we observed that the agent's attention developed in phases, and that these phases were consistent across games. Finally, we noted that the agent's attention to its paddle emerged relatively late in the training and coincided with a marked increase in its performance score. Overall, we believe that ATOMs could significantly enhance our understanding of RL agents' learning processes, which is essential for improving their reliability and efficiency.
Authors: Ioannis Mavromatis, Kostas Katsaros, Aftab Khan
Abstract: Machine learning (ML) has seen tremendous advancements, but its environmental footprint remains a concern. Acknowledging the growing environmental impact of ML this paper investigates Green ML, examining various model architectures and hyperparameters in both training and inference phases to identify energy-efficient practices. Our study leverages software-based power measurements for ease of replication across diverse configurations, models and datasets. In this paper, we examine multiple models and hardware configurations to identify correlations across the various measurements and metrics and key contributors to energy reduction. Our analysis offers practical guidelines for constructing sustainable ML operations, emphasising energy consumption and carbon footprint reductions while maintaining performance. As identified, short-lived profiling can quantify the long-term expected energy consumption. Moreover, model parameters can also be used to accurately estimate the expected total energy without the need for extensive experimentation.
Authors: Tanapat Ratchatorn, Masayuki Tanaka
Abstract: Recent advancements in learning algorithms have demonstrated that the sharpness of the loss surface is an effective measure for improving the generalization gap. Building upon this concept, Sharpness-Aware Minimization (SAM) was proposed to enhance model generalization and achieved state-of-the-art performance. SAM consists of two main steps, the weight perturbation step and the weight updating step. However, the perturbation in SAM is determined by only the gradient of the training loss, or cross-entropy loss. As the model approaches a stationary point, this gradient becomes small and oscillates, leading to inconsistent perturbation directions and also has a chance of diminishing the gradient. Our research introduces an innovative approach to further enhancing model generalization. We propose the Adaptive Adversarial Cross-Entropy (AACE) loss function to replace standard cross-entropy loss for SAM's perturbation. AACE loss and its gradient uniquely increase as the model nears convergence, ensuring consistent perturbation direction and addressing the gradient diminishing issue. Additionally, a novel perturbation-generating function utilizing AACE loss without normalization is proposed, enhancing the model's exploratory capabilities in near-optimum stages. Empirical testing confirms the effectiveness of AACE, with experiments demonstrating improved performance in image classification tasks using Wide ResNet and PyramidNet across various datasets. The reproduction code is available online
Authors: Ivan Karpukhin, Foma Shipilov, Andrey Savchenko
Abstract: In sequential event prediction, which finds applications in finance, retail, social networks, and healthcare, a crucial task is forecasting multiple future events within a specified time horizon. Traditionally, this has been addressed through autoregressive generation using next-event prediction models, such as Marked Temporal Point Processes. However, autoregressive methods use their own output for future predictions, potentially reducing quality as the prediction horizon extends. In this paper, we challenge traditional approaches by introducing a novel benchmark, HoTPP, specifically designed to evaluate a model's ability to predict event sequences over a horizon. This benchmark features a new metric inspired by object detection in computer vision, addressing the limitations of existing metrics in assessing models with imprecise time-step predictions. Our evaluations on established datasets employing various models demonstrate that high accuracy in next-event prediction does not necessarily translate to superior horizon prediction, and vice versa. HoTPP aims to serve as a valuable tool for developing more robust event sequence prediction methods, ultimately paving the way for further advancements in the field.
Authors: Ilaria Vascotto, Alex Rodriguez, Alessandro Bonaita, Luca Bortolussi
Abstract: The increase of legislative concerns towards the usage of Artificial Intelligence (AI) has recently led to a series of regulations striving for a more transparent, trustworthy and accountable AI. Along with these proposals, the field of Explainable AI (XAI) has seen a rapid growth but the usage of its techniques has at times led to unexpected results. The robustness of the approaches is, in fact, a key property often overlooked: it is necessary to evaluate the stability of an explanation (to random and adversarial perturbations) to ensure that the results are trustable. To this end, we propose a test to evaluate the robustness to non-adversarial perturbations and an ensemble approach to analyse more in depth the robustness of XAI methods applied to neural networks and tabular datasets. We will show how leveraging manifold hypothesis and ensemble approaches can be beneficial to an in-depth analysis of the robustness.
Authors: Afonso de S\'a Delgado Neto, Maximilian Egger, Mayank Bakshi, Rawad Bitar
Abstract: We introduce CYBER-0, the first zero-order optimization algorithm for memory-and-communication efficient Federated Learning, resilient to Byzantine faults. We show through extensive numerical experiments on the MNIST dataset and finetuning RoBERTa-Large that CYBER-0 outperforms state-of-the-art algorithms in terms of communication and memory efficiency while reaching similar accuracy. We provide theoretical guarantees on its convergence for convex loss functions.
Authors: Rushuang Zhou, Zijun Liu, Lei Clifton, David A. Clifton, Kannie W. Y. Chan, Yuan-Ting Zhang, Yining Dong
Abstract: Label scarcity problem is the main challenge that hinders the wide application of deep learning systems in automatic cardiovascular diseases (CVDs) detection using electrocardiography (ECG). Tuning pre-trained models alleviates this problem by transferring knowledge learned from large datasets to downstream small datasets. However, bottlenecks in computational efficiency and CVDs detection performance limit its clinical applications. It is difficult to improve the detection performance without significantly sacrificing model computational efficiency. Here, we propose a computation-efficient semi-supervised learning paradigm (FastECG) for robust and computation-efficient CVDs detection using ECG. It enables a robust adaptation of pre-trained models on downstream datasets with limited supervision and high computational efficiency. First, a random-deactivation technique is developed to achieve robust and fast low-rank adaptation of pre-trained weights. Subsequently, we propose a one-shot rank allocation module to determine the optimal ranks for the update matrices of the pre-trained weights. Finally, a lightweight semi-supervised learning pipeline is introduced to enhance model performance by leveraging labeled and unlabeled data with high computational efficiency. Extensive experiments on four downstream ECG datasets demonstrate that FastECG not only outperforms the state-of-the-art methods in multi-label CVDs detection but also consumes fewer GPU footprints, training time, and parameter storage space. As such, this paradigm provides an effective solution for achieving high computational efficiency and robust detection performance in the clinical applications of pre-trained models under limited supervision.
Authors: Oisin Nolan, Tristan S. W. Stevens, Wessel L. van Nierop, Ruud J. G. van Sloun
Abstract: Subsampling is commonly used to mitigate costs associated with data acquisition, such as time or energy requirements, motivating the development of algorithms for estimating the fully-sampled signal of interest $x$ from partially observed measurements $y$. In maximum-entropy sampling, one selects measurement locations that are expected to have the highest entropy, so as to minimize uncertainty about $x$. This approach relies on an accurate model of the posterior distribution over future measurements, given the measurements observed so far. Recently, diffusion models have been shown to produce high-quality posterior samples of high-dimensional signals using guided diffusion. In this work, we propose Active Diffusion Subsampling (ADS), a method for performing active subsampling using guided diffusion in which the model tracks a distribution of beliefs over the true state of $x$ throughout the reverse diffusion process, progressively decreasing its uncertainty by choosing to acquire measurements with maximum expected entropy, and ultimately generating the posterior distribution $p(x | y)$. ADS can be applied using pre-trained diffusion models for any subsampling rate, and does not require task-specific retraining - just the specification of a measurement model. Furthermore, the maximum entropy sampling policy employed by ADS is interpretable, enhancing transparency relative to existing methods using black-box policies. Experimentally, we show that ADS outperforms fixed sampling strategies, and study an application of ADS in Magnetic Resonance Imaging acceleration using the fastMRI dataset, finding that ADS performs competitively with supervised methods. Code available at https://active-diffusion-subsampling.github.io/.
Authors: Zhihui Xie, Jiahui Gao, Lei Li, Zhenguo Li, Qi Liu, Lingpeng Kong
Abstract: The widespread adoption of large language models (LLMs) has raised concerns about their safety and reliability, particularly regarding their vulnerability to adversarial attacks. In this paper, we propose a novel perspective that attributes this vulnerability to reward misspecification during the alignment process. We introduce a metric ReGap to quantify the extent of reward misspecification and demonstrate its effectiveness and robustness in detecting harmful backdoor prompts. Building upon these insights, we present ReMiss, a system for automated red teaming that generates adversarial prompts against various target aligned LLMs. ReMiss achieves state-of-the-art attack success rates on the AdvBench benchmark while preserving the human readability of the generated prompts. Detailed analysis highlights the unique advantages brought by the proposed reward misspecification objective compared to previous methods.
Authors: Tao Han, Song Guo, Zhenghao Chen, Wanghan Xu, Lei Bai
Abstract: Global Station Weather Forecasting (GSWF) is crucial for various sectors, including aviation, agriculture, energy, and disaster preparedness. Recent advancements in deep learning have significantly improved the accuracy of weather predictions by optimizing models based on public meteorological data. However, existing public datasets for GSWF optimization and benchmarking still suffer from significant limitations, such as small sizes, limited temporal coverage, and a lack of comprehensive variables. These shortcomings prevent them from effectively reflecting the benchmarks of current forecasting methods and fail to support the real needs of operational weather forecasting. To address these challenges, we present the WEATHER-5K dataset. This dataset comprises a comprehensive collection of data from 5,672 weather stations worldwide, spanning a 10-year period with one-hour intervals. It includes multiple crucial weather elements, providing a more reliable and interpretable resource for forecasting. Furthermore, our WEATHER-5K dataset can serve as a benchmark for comprehensively evaluating existing well-known forecasting models, extending beyond GSWF methods to support future time-series research challenges and opportunities. The dataset and benchmark implementation are publicly available at: https://github.com/taohan10200/WEATHER-5K.
Authors: Zhangling Duan, Tianci Li, Xingyu Wu, Zhaolong Ling, Jingye Yang, Zhaohong Jia
Abstract: Streaming feature selection techniques have become essential in processing real-time data streams, as they facilitate the identification of the most relevant attributes from continuously updating information. Despite their performance, current algorithms to streaming feature selection frequently fall short in managing biases and avoiding discrimination that could be perpetuated by sensitive attributes, potentially leading to unfair outcomes in the resulting models. To address this issue, we propose FairSFS, a novel algorithm for Fair Streaming Feature Selection, to uphold fairness in the feature selection process without compromising the ability to handle data in an online manner. FairSFS adapts to incoming feature vectors by dynamically adjusting the feature set and discerns the correlations between classification attributes and sensitive attributes from this revised set, thereby forestalling the propagation of sensitive data. Empirical evaluations show that FairSFS not only maintains accuracy that is on par with leading streaming feature selection methods and existing fair feature techniques but also significantly improves fairness metrics.
Authors: Florence Regol, Joud Chataoui, Bertrand Charpentier, Mark Coates, Pablo Piantanida, Stephan Gunnemann
Abstract: Machine learning models can solve complex tasks but often require significant computational resources during inference. This has led to the development of various post-training computation reduction methods that tackle this issue in different ways, such as quantization which reduces the precision of weights and arithmetic operations, and dynamic networks which adapt computation to the sample at hand. In this work, we propose a more general dynamic network that can combine both quantization and early exit dynamic network: QuEE. Our algorithm can be seen as a form of soft early exiting or input-dependent compression. Rather than a binary decision between exiting or continuing, we introduce the possibility of continuing with reduced computation. This complicates the traditionally considered early exiting problem, which we solve through a principled formulation. The crucial factor of our approach is accurate prediction of the potential accuracy improvement achievable through further computation. We demonstrate the effectiveness of our method through empirical evaluation, as well as exploring the conditions for its success on 4 classification datasets.
Authors: Pedro Valdeira, Jo\~ao Xavier, Cl\'audia Soares, Yuejie Chi
Abstract: Communication overhead is a known bottleneck in federated learning (FL). To address this, lossy compression is commonly used on the information communicated between the server and clients during training. In horizontal FL, where each client holds a subset of the samples, such communication-compressed training methods have recently seen significant progress. However, in their vertical FL counterparts, where each client holds a subset of the features, our understanding remains limited. To address this, we propose an error feedback compressed vertical federated learning (EFVFL) method to train split neural networks. In contrast with previous communication-compressed methods for vertical FL, EFVFL does not require a vanishing compression error for the gradient norm to converge to zero for smooth nonconvex problems. By leveraging error feedback, our method can achieve a $\mathcal{O}(1/T)$ convergence rate in the full-batch case, improving over the state-of-the-art $\mathcal{O}(1/\sqrt{T})$ rate under $\mathcal{O}(1/\sqrt{T})$ compression error, and matching the rate of uncompressed methods. Further, when the objective function satisfies the Polyak-{\L}ojasiewicz inequality, our method converges linearly. In addition to improving convergence rates, our method also supports the use of private labels. Numerical experiments show that EFVFL significantly improves over the prior art, confirming our theoretical results.
Authors: Simeon Allmendinger, Domenique Zipperling, Lukas Struppek, Niklas K\"uhl
Abstract: In the landscape of generative artificial intelligence, diffusion-based models have emerged as a promising method for generating synthetic images. However, the application of diffusion models poses numerous challenges, particularly concerning data availability, computational requirements, and privacy. Traditional approaches to address these shortcomings, like federated learning, often impose significant computational burdens on individual clients, especially those with constrained resources. In response to these challenges, we introduce a novel approach for distributed collaborative diffusion models inspired by split learning. Our approach facilitates collaborative training of diffusion models while alleviating client computational burdens during image synthesis. This reduced computational burden is achieved by retaining data and computationally inexpensive processes locally at each client while outsourcing the computationally expensive processes to shared, more efficient server resources. Through experiments on the common CelebA dataset, our approach demonstrates enhanced privacy by reducing the necessity for sharing raw data. These capabilities hold significant potential across various application areas, including the design of edge computing solutions. Thus, our work advances distributed machine learning by contributing to the evolution of collaborative diffusion models.
Authors: Elisa G\'omez de Lope (University of Luxembourg), Saurabh Deshpande (University of Luxembourg), Ram\'on Vi\~nas Torn\'e (\'Ecole polytechnique f\'ed\'erale de Lausanne), Pietro Li\`o (University of Cambridge), Enrico Glaab (University of Luxembourg, On behalf of the NCER-PD Consortium), St\'ephane P. A. Bordas (University of Luxembourg)
Abstract: Omics data analysis is crucial for studying complex diseases, but its high dimensionality and heterogeneity challenge classical statistical and machine learning methods. Graph neural networks have emerged as promising alternatives, yet the optimal strategies for their design and optimization in real-world biomedical challenges remain unclear. This study evaluates various graph representation learning models for case-control classification using high-throughput biological data from Parkinson's disease and control samples. We compare topologies derived from sample similarity networks and molecular interaction networks, including protein-protein and metabolite-metabolite interactions (PPI, MMI). Graph Convolutional Network (GCNs), Chebyshev spectral graph convolution (ChebyNet), and Graph Attention Network (GAT), are evaluated alongside advanced architectures like graph transformers, the graph U-net, and simpler models like multilayer perceptron (MLP). These models are systematically applied to transcriptomics and metabolomics data independently. Our comparative analysis highlights the benefits and limitations of various architectures in extracting patterns from omics data, paving the way for more accurate and interpretable models in biomedical research.
Authors: Shruthi K. Hiremath, Thomas Ploetz
Abstract: Developing human activity recognition (HAR) systems for smart homes is not straightforward due to varied layouts of the homes and their personalized settings, as well as idiosyncratic behaviors of residents. As such, off-the-shelf HAR systems are effective in limited capacity for an individual home, and HAR systems often need to be derived "from scratch", which comes with substantial efforts and often is burdensome to the resident. Previous work has successfully targeted the initial phase. At the end of this initial phase, we identify seed points. We build on bootstrapped HAR systems and introduce an effective updating and extension procedure for continuous improvement of HAR systems with the aim of keeping up with ever changing life circumstances. Our method makes use of the seed points identified at the end of the initial bootstrapping phase. A contrastive learning framework is trained using these seed points and labels obtained for the same. This model is then used to improve the segmentation accuracy of the identified prominent activities. Improvements in the activity recognition system through this procedure help model the majority of the routine activities in the smart home. We demonstrate the effectiveness of our procedure through experiments on the CASAS datasets that show the practical value of our approach.
Authors: Venkata Ragavendra Vavilthota, Ranjith Ramanathan, Sathyanarayanan N. Aakur
Abstract: Analyzing sequential data is crucial in many domains, particularly due to the abundance of data collected from the Internet of Things paradigm. Time series classification, the task of categorizing sequential data, has gained prominence, with machine learning approaches demonstrating remarkable performance on public benchmark datasets. However, progress has primarily been in designing architectures for learning representations from raw data at fixed (or ideal) time scales, which can fail to generalize to longer sequences. This work introduces a \textit{compositional representation learning} approach trained on statistically coherent components extracted from sequential data. Based on a multi-scale change space, an unsupervised approach is proposed to segment the sequential data into chunks with similar statistical properties. A sequence-based encoder model is trained in a multi-task setting to learn compositional representations from these temporal components for time series classification. We demonstrate its effectiveness through extensive experiments on publicly available time series classification benchmarks. Evaluating the coherence of segmented components shows its competitive performance on the unsupervised segmentation task.
Authors: Sai Prasanth Kotturi, Radha Krishna Ganti
Abstract: This research looks at using AI/ML to achieve centimeter-level user positioning in 6G applications such as the Industrial Internet of Things (IIoT). Initial results show that our AI/ML-based method can estimate user positions with an accuracy of 17 cm in an indoor factory environment. In this proposal, we highlight our approaches and future directions.
Authors: Xinyi Xu, Zhaoxuan Wu, Rui Qiao, Arun Verma, Yao Shu, Jingtan Wang, Xinyuan Niu, Zhenfeng He, Jiangwei Chen, Zijian Zhou, Gregory Kang Ruey Lau, Hieu Dao, Lucas Agussurja, Rachael Hwee Ling Sim, Xiaoqiang Lin, Wenyang Hu, Zhongxiang Dai, Pang Wei Koh, Bryan Kian Hsiang Low
Abstract: This position paper proposes a data-centric viewpoint of AI research, focusing on large language models (LLMs). We start by making the key observation that data is instrumental in the developmental (e.g., pretraining and fine-tuning) and inferential stages (e.g., in-context learning) of LLMs, and yet it receives disproportionally low attention from the research community. We identify four specific scenarios centered around data, covering data-centric benchmarks and data curation, data attribution, knowledge transfer, and inference contextualization. In each scenario, we underscore the importance of data, highlight promising research directions, and articulate the potential impacts on the research community and, where applicable, the society as a whole. For instance, we advocate for a suite of data-centric benchmarks tailored to the scale and complexity of data for LLMs. These benchmarks can be used to develop new data curation methods and document research efforts and results, which can help promote openness and transparency in AI and LLM research.
Authors: F\'atima Garc\'ia-Mart\'inez, Diego Carou, Francisco de Arriba-P\'erez, Silvia Garc\'ia-M\'endez
Abstract: Material extrusion is one of the most commonly used approaches within the additive manufacturing processes available. Despite its popularity and related technical advancements, process reliability and quality assurance remain only partially solved. In particular, the surface roughness caused by this process is a key concern. To solve this constraint, experimental plans have been exploited to optimize surface roughness in recent years. However, the latter empirical trial and error process is extremely time- and resource-consuming. Thus, this study aims to avoid using large experimental programs to optimize surface roughness in material extrusion. Methodology. This research provides an in-depth analysis of the effect of several printing parameters: layer height, printing temperature, printing speed and wall thickness. The proposed data-driven predictive modeling approach takes advantage of Machine Learning models to automatically predict surface roughness based on the data gathered from the literature and the experimental data generated for testing. Findings. Using 10-fold cross-validation of data gathered from the literature, the proposed Machine Learning solution attains a 0.93 correlation with a mean absolute percentage error of 13 %. When testing with our own data, the correlation diminishes to 0.79 and the mean absolute percentage error reduces to 8 %. Thus, the solution for predicting surface roughness in extrusion-based printing offers competitive results regarding the variability of the analyzed factors. Originality. As available manufacturing data continue to increase on a daily basis, the ability to learn from these large volumes of data is critical in future manufacturing and science. Specifically, the power of Machine Learning helps model surface roughness with limited experimental tests.
Authors: Vighnesh Subramaniam, Colin Conwell, Christopher Wang, Gabriel Kreiman, Boris Katz, Ignacio Cases, Andrei Barbu
Abstract: We use (multi)modal deep neural networks (DNNs) to probe for sites of multimodal integration in the human brain by predicting stereoencephalography (SEEG) recordings taken while human subjects watched movies. We operationalize sites of multimodal integration as regions where a multimodal vision-language model predicts recordings better than unimodal language, unimodal vision, or linearly-integrated language-vision models. Our target DNN models span different architectures (e.g., convolutional networks and transformers) and multimodal training techniques (e.g., cross-attention and contrastive learning). As a key enabling step, we first demonstrate that trained vision and language models systematically outperform their randomly initialized counterparts in their ability to predict SEEG signals. We then compare unimodal and multimodal models against one another. Because our target DNN models often have different architectures, number of parameters, and training sets (possibly obscuring those differences attributable to integration), we carry out a controlled comparison of two models (SLIP and SimCLR), which keep all of these attributes the same aside from input modality. Using this approach, we identify a sizable number of neural sites (on average 141 out of 1090 total sites or 12.94%) and brain regions where multimodal integration seems to occur. Additionally, we find that among the variants of multimodal training techniques we assess, CLIP-style training is the best suited for downstream prediction of the neural activity in these sites.
Authors: Vignesh Gopakumar, Joel Oskarrson, Ander Gray, Lorenzo Zanisi, Stanislas Pamela, Daniel Giles, Matt Kusner, Marc Deisenroth
Abstract: Neural weather models have shown immense potential as inexpensive and accurate alternatives to physics-based models. However, most models trained to perform weather forecasting do not quantify the uncertainty associated with their forecasts. This limits the trust in the model and the usefulness of the forecasts. In this work we construct and formalise a conformal prediction framework as a post-processing method for estimating this uncertainty. The method is model-agnostic and gives calibrated error bounds for all variables, lead times and spatial locations. No modifications are required to the model and the computational cost is negligible compared to model training. We demonstrate the usefulness of the conformal prediction framework on a limited area neural weather model for the Nordic region. We further explore the advantages of the framework for deterministic and probabilistic models.
Authors: Alireza Afzal Aghaei
Abstract: The development of Kolmogorov-Arnold networks (KANs) marks a significant shift from traditional multi-layer perceptrons in deep learning. Initially, KANs employed B-spline curves as their primary basis function, but their inherent complexity posed implementation challenges. Consequently, researchers have explored alternative basis functions such as Wavelets, Polynomials, and Fractional functions. In this research, we explore the use of rational functions as a novel basis function for KANs. We propose two different approaches based on Pade approximation and rational Jacobi functions as trainable basis functions, establishing the rational KAN (rKAN). We then evaluate rKAN's performance in various deep learning and physics-informed tasks to demonstrate its practicality and effectiveness in function approximation.
Authors: Nhung Bui, Xinyang Lu, See-Kiong Ng, Bryan Kian Hsian Low
Abstract: Machine unlearning facilitates personal data ownership, including the ``right to be forgotten''. The proliferation of applications of \emph{neural networks} (NNs) trained on users' personal data calls for the need to develop algorithms to unlearn an NN. Since retraining is costly, efficiency is often achieved through approximate unlearning which aims to unlearn a trained NN to be close to the retrained one (in distribution). Though the Newton's method has been used by previous works to approximately unlearn linear models, adapting it for unlearning an NN often encounters degenerate Hessians that make computing the Newton's update impossible. In this paper, we will first show that when coupled with naive yet often effective solutions to mitigate the degeneracy issue for unlearning, the Newton's method surprisingly suffers from catastrophic forgetting. To overcome this difficulty, we revise the Newton's method to include a theoretically justified regularizer and propose a cubic-regularized Newton's method for unlearning an NN. The cubic regularizer comes with the benefits of not requiring manual finetuning and affording a natural interpretation. Empirical evaluation on several models and real-world datasets shows that our method is more resilient to catastrophic forgetting and performs better than the baselines, especially in sequential unlearning.
Authors: Yapei Chang, Kalpesh Krishna, Amir Houmansadr, John Wieting, Mohit Iyyer
Abstract: The most effective techniques to detect LLM-generated text rely on inserting a detectable signature -- or watermark -- during the model's decoding process. Most existing watermarking methods require access to the underlying LLM's logits, which LLM API providers are loath to share due to fears of model distillation. As such, these watermarks must be implemented independently by each LLM provider. In this paper, we develop PostMark, a modular post-hoc watermarking procedure in which an input-dependent set of words (determined via a semantic embedding) is inserted into the text after the decoding process has completed. Critically, PostMark does not require logit access, which means it can be implemented by a third party. We also show that PostMark is more robust to paraphrasing attacks than existing watermarking methods: our experiments cover eight baseline algorithms, five base LLMs, and three datasets. Finally, we evaluate the impact of PostMark on text quality using both automated and human assessments, highlighting the trade-off between quality and robustness to paraphrasing. We release our code, outputs, and annotations at https://github.com/lilakk/PostMark.
Authors: Assaf Ben-Kish, Itamar Zimerman, Shady Abu-Hussein, Nadav Cohen, Amir Globerson, Lior Wolf, Raja Giryes
Abstract: Long-range sequence processing poses a significant challenge for Transformers due to their quadratic complexity in input length. A promising alternative is Mamba, which demonstrates high performance and achieves Transformer-level capabilities while requiring substantially fewer computational resources. In this paper we explore the length-generalization capabilities of Mamba, which we find to be relatively limited. Through a series of visualizations and analyses we identify that the limitations arise from a restricted effective receptive field, dictated by the sequence length used during training. To address this constraint, we introduce DeciMamba, a context-extension method specifically designed for Mamba. This mechanism, built on top of a hidden filtering mechanism embedded within the S6 layer, enables the trained model to extrapolate well even without additional training. Empirical experiments over real-world long-range NLP tasks show that DeciMamba can extrapolate to context lengths that are 25x times longer than the ones seen during training, and does so without utilizing additional computational resources. We will release our code and models.
Authors: Eleonora Poeta, Flavio Giobergia, Eliana Pastor, Tania Cerquitelli, Elena Baralis
Abstract: Kolmogorov-Arnold Networks (KANs) have very recently been introduced into the world of machine learning, quickly capturing the attention of the entire community. However, KANs have mostly been tested for approximating complex functions or processing synthetic data, while a test on real-world tabular datasets is currently lacking. In this paper, we present a benchmarking study comparing KANs and Multi-Layer Perceptrons (MLPs) on tabular datasets. The study evaluates task performance and training times. From the results obtained on the various datasets, KANs demonstrate superior or comparable accuracy and F1 scores, excelling particularly in datasets with numerous instances, suggesting robust handling of complex data. We also highlight that this performance improvement of KANs comes with a higher computational cost when compared to MLPs of comparable sizes.
Authors: Amrith Setlur, Saurabh Garg, Xinyang Geng, Naman Garg, Virginia Smith, Aviral Kumar
Abstract: Training on model-generated synthetic data is a promising approach for finetuning LLMs, but it remains unclear when it helps or hurts. In this paper, we investigate this question for math reasoning via an empirical study, followed by building a conceptual understanding of our observations. First, we find that while the typical approach of finetuning a model on synthetic correct or positive problem-solution pairs generated by capable models offers modest performance gains, sampling more correct solutions from the finetuned learner itself followed by subsequent fine-tuning on this self-generated data $\textbf{doubles}$ the efficiency of the same synthetic problems. At the same time, training on model-generated positives can amplify various spurious correlations, resulting in flat or even inverse scaling trends as the amount of data increases. Surprisingly, we find that several of these issues can be addressed if we also utilize negative responses, i.e., model-generated responses that are deemed incorrect by a final answer verifier. Crucially, these negatives must be constructed such that the training can appropriately recover the utility or advantage of each intermediate step in the negative response. With this per-step scheme, we are able to attain consistent gains over only positive data, attaining performance similar to amplifying the amount of synthetic data by $\mathbf{8 \times}$. We show that training on per-step negatives can help to unlearn spurious correlations in the positive data, and is equivalent to advantage-weighted reinforcement learning (RL), implying that it inherits robustness benefits of RL over imitating positive data alone.
Authors: Chuqiao Zong, Chaojie Wang, Molei Qin, Lei Feng, Xinrun Wang, Bo An
Abstract: High-frequency trading (HFT) that executes algorithmic trading in short time scales, has recently occupied the majority of cryptocurrency market. Besides traditional quantitative trading methods, reinforcement learning (RL) has become another appealing approach for HFT due to its terrific ability of handling high-dimensional financial data and solving sophisticated sequential decision-making problems, \emph{e.g.,} hierarchical reinforcement learning (HRL) has shown its promising performance on second-level HFT by training a router to select only one sub-agent from the agent pool to execute the current transaction. However, existing RL methods for HFT still have some defects: 1) standard RL-based trading agents suffer from the overfitting issue, preventing them from making effective policy adjustments based on financial context; 2) due to the rapid changes in market conditions, investment decisions made by an individual agent are usually one-sided and highly biased, which might lead to significant loss in extreme markets. To tackle these problems, we propose a novel Memory Augmented Context-aware Reinforcement learning method On HFT, \emph{a.k.a.} MacroHFT, which consists of two training phases: 1) we first train multiple types of sub-agents with the market data decomposed according to various financial indicators, specifically market trend and volatility, where each agent owns a conditional adapter to adjust its trading policy according to market conditions; 2) then we train a hyper-agent to mix the decisions from these sub-agents and output a consistently profitable meta-policy to handle rapid market fluctuations, equipped with a memory mechanism to enhance the capability of decision-making. Extensive experiments on various cryptocurrency markets demonstrate that MacroHFT can achieve state-of-the-art performance on minute-level trading tasks.
Authors: Shengzhe Xu, Cho-Ting Lee, Mandar Sharma, Raquib Bin Yousuf, Nikhil Muralidhar, Naren Ramakrishnan
Abstract: Large language models (LLMs) have demonstrated their prowess in generating synthetic text and images; however, their potential for generating tabular data -- arguably the most common data type in business and scientific applications -- is largely underexplored. This paper demonstrates that LLMs, used as-is, or after traditional fine-tuning, are severely inadequate as synthetic table generators. Due to the autoregressive nature of LLMs, fine-tuning with random order permutation runs counter to the importance of modeling functional dependencies, and renders LLMs unable to model conditional mixtures of distributions (key to capturing real world constraints). We showcase how LLMs can be made to overcome some of these deficiencies by making them permutation-aware.
Authors: Zhengyang Geng, Ashwini Pokle, William Luo, Justin Lin, J. Zico Kolter
Abstract: Consistency models (CMs) are an emerging class of generative models that offer faster sampling than traditional diffusion models. CMs enforce that all points along a sampling trajectory are mapped to the same initial point. But this target leads to resource-intensive training: for example, as of 2024, training a SoTA CM on CIFAR-10 takes one week on 8 GPUs. In this work, we propose an alternative scheme for training CMs, vastly improving the efficiency of building such models. Specifically, by expressing CM trajectories via a particular differential equation, we argue that diffusion models can be viewed as a special case of CMs with a specific discretization. We can thus fine-tune a consistency model starting from a pre-trained diffusion model and progressively approximate the full consistency condition to stronger degrees over the training process. Our resulting method, which we term Easy Consistency Tuning (ECT), achieves vastly improved training times while indeed improving upon the quality of previous methods: for example, ECT achieves a 2-step FID of 2.73 on CIFAR10 within 1 hour on a single A100 GPU, matching Consistency Distillation trained of hundreds of GPU hours. Owing to this computational efficiency, we investigate the scaling law of CMs under ECT, showing that they seem to obey classic power law scaling, hinting at their ability to improve efficiency and performance at larger scales. Code (https://github.com/locuslab/ect) is available.
Authors: Jiajun Cui, Hong Qian, Bo Jiang, Wei Zhang
Abstract: Knowledge tracing (KT) is a crucial task in intelligent education, focusing on predicting students' performance on given questions to trace their evolving knowledge. The advancement of deep learning in this field has led to deep-learning knowledge tracing (DLKT) models that prioritize high predictive accuracy. However, many existing DLKT methods overlook the fundamental goal of tracking students' dynamical knowledge mastery. These models do not explicitly model knowledge mastery tracing processes or yield unreasonable results that educators find difficulty to comprehend and apply in real teaching scenarios. In response, our research conducts a preliminary analysis of mainstream KT approaches to highlight and explain such unreasonableness. We introduce GRKT, a graph-based reasonable knowledge tracing method to address these issues. By leveraging graph neural networks, our approach delves into the mutual influences of knowledge concepts, offering a more accurate representation of how the knowledge mastery evolves throughout the learning process. Additionally, we propose a fine-grained and psychological three-stage modeling process as knowledge retrieval, memory strengthening, and knowledge learning/forgetting, to conduct a more reasonable knowledge tracing process. Comprehensive experiments demonstrate that GRKT outperforms eleven baselines across three datasets, not only enhancing predictive accuracy but also generating more reasonable knowledge tracing results. This makes our model a promising advancement for practical implementation in educational settings. The source code is available at https://github.com/JJCui96/GRKT.
Authors: Yoni Choukroun, Lior Wolf
Abstract: The design of optimal linear block codes capable of being efficiently decoded is of major concern, especially for short block lengths. As near capacity-approaching codes, Low-Density Parity-Check (LDPC) codes possess several advantages over other families of codes, the most notable being its efficient decoding via Belief Propagation. While many LDPC code design methods exist, the development of efficient sparse codes that meet the constraints of modern short code lengths and accommodate new channel models remains a challenge. In this work, we propose for the first time a data-driven approach for the design of sparse codes. We develop locally optimal codes with respect to Belief Propagation decoding via the learning on the Factor graph (also called the Tanner graph) under channel noise simulations. This is performed via a novel tensor representation of the Belief Propagation algorithm, optimized over finite fields via backpropagation coupled with an efficient line-search method. The proposed approach is shown to outperform the decoding performance of existing popular codes by orders of magnitude and demonstrates the power of data-driven approaches for code design.
Authors: A. Gavrikov, V. Cerrone, A. Serafini, R. Brugnera, A. Garfagnini, M. Grassi, B. Jelmini, L. Lastrucci, S. Aiello, G. Andronico, V. Antonelli, A. Barresi, D. Basilico, M. Beretta, A. Bergnoli, M. Borghesi, A. Brigatti, R. Bruno, A. Budano, B. Caccianiga, A. Cammi, R. Caruso, D. Chiesa, C. Clementi, S. Dusini, A. Fabbri, G. Felici, F. Ferraro, M. G. Giammarchi, N. Giugice, R. M. Guizzetti, N. Guardone, C. Landini, I. Lippi, S. Loffredo, L. Loi, P. Lombardi, C. Lombardo, F. Mantovani, S. M. Mari, A. Martini, L. Miramonti, M. Montuschi, M. Nastasi, D. Orestano, F. Ortica, A. Paoloni, E. Percalli, F. Petrucci, E. Previtali, G. Ranucci, A. C. Re, M. Redchuck, B. Ricci, A. Romani, P. Saggese, G. Sava, C. Sirignano, M. Sisti, L. Stanco, E. Stanescu Farilla, V. Strati, M. D. C. Torri, A. Triossi, C. Tuv\'e, C. Venettacci, G. Verde, L. Votano
Abstract: Several neutrino detectors, KamLAND, Daya Bay, Double Chooz, RENO, and the forthcoming large-scale JUNO, rely on liquid scintillator to detect reactor antineutrino interactions. In this context, inverse beta decay represents the golden channel for antineutrino detection, providing a pair of correlated events, thus a strong experimental signature to distinguish the signal from a variety of backgrounds. However, given the low cross-section of antineutrino interactions, the development of a powerful event selection algorithm becomes imperative to achieve effective discrimination between signal and backgrounds. In this study, we introduce a machine learning (ML) model to achieve this goal: a fully connected neural network as a powerful signal-background discriminator for a large liquid scintillator detector. We demonstrate, using the JUNO detector as an example, that, despite the already high efficiency of a cut-based approach, the presented ML model can further improve the overall event selection efficiency. Moreover, it allows for the retention of signal events at the detector edges that would otherwise be rejected because of the overwhelming amount of background events in that region. We also present the first interpretable analysis of the ML approach for event selection in reactor neutrino experiments. This method provides insights into the decision-making process of the model and offers valuable information for improving and updating traditional event selection approaches.
Authors: Petr Boriskov, Vadim Putrolaynen, Andrei Velichko, Kristina Peltonen
Abstract: In this study a new method for analyzing synchronization in oscillator systems is proposed using the example of modeling the dynamics of a circuit of two resistively coupled pulse oscillators. The dynamic characteristic of synchronization is fuzzy entropy (FuzzyEn) calculated a time series composed of the ratios of the number of pulse periods (subharmonic ratio, SHR) during phase-locking intervals. Low entropy values indicate strong synchronization, whereas high entropy values suggest weak synchronization between the two oscillators. This method effectively visualizes synchronized modes of the circuit using entropy maps of synchronization states. Additionally, a classification of synchronization states is proposed based on the dependencies of FuzzyEn on the length of embedding vectors of SHR time series. An extension of this method for analyzing non-relaxation (non-spike) type signals is illustrated using the example of phase-phase coupling rhythms of local field potential of rat hippocampus. The entropy-statistical approach using rational fractions and pulse signal forms makes this method promising for analyzing biosignal synchronization and implementing the algorithm in mobile digital platforms.
Authors: Jan Schr\"oder, Jakub Breier
Abstract: Machine learning (ML) models are used in many safety- and security-critical applications nowadays. It is therefore important to measure the security of a system that uses ML as a component. This paper focuses on the field of ML, particularly the security of autonomous vehicles. For this purpose, a technical framework will be described, implemented, and evaluated in a case study. Based on ISO/IEC 27004:2016, risk indicators are utilized to measure and evaluate the extent of damage and the effort required by an attacker. It is not possible, however, to determine a single risk value that represents the attacker's effort. Therefore, four different values must be interpreted individually.
Authors: Fengqing Jiang, Zhangchen Xu, Luyao Niu, Bill Yuchen Lin, Radha Poovendran
Abstract: Large language models (LLMs) are expected to follow instructions from users and engage in conversations. Techniques to enhance LLMs' instruction-following capabilities typically fine-tune them using data structured according to a predefined chat template. Although chat templates are shown to be effective in optimizing LLM performance, their impact on safety alignment of LLMs has been less understood, which is crucial for deploying LLMs safely at scale. In this paper, we investigate how chat templates affect safety alignment of LLMs. We identify a common vulnerability, named ChatBug, that is introduced by chat templates. Our key insight to identify ChatBug is that the chat templates provide a rigid format that need to be followed by LLMs, but not by users. Hence, a malicious user may not necessarily follow the chat template when prompting LLMs. Instead, malicious users could leverage their knowledge of the chat template and accordingly craft their prompts to bypass safety alignments of LLMs. We develop two attacks to exploit the ChatBug vulnerability. We demonstrate that a malicious user can exploit the ChatBug vulnerability of eight state-of-the-art (SOTA) LLMs and effectively elicit unintended responses from these models. Moreover, we show that ChatBug can be exploited by existing jailbreak attacks to enhance their attack success rates. We investigate potential countermeasures to ChatBug. Our results show that while adversarial training effectively mitigates the ChatBug vulnerability, the victim model incurs significant performance degradation. These results highlight the trade-off between safety alignment and helpfulness. Developing new methods for instruction tuning to balance this trade-off is an open and critical direction for future research
Authors: Robert Flynn, Anton Ragni
Abstract: When there is a mismatch between the training and test domains, current speech recognition systems show significant performance degradation. Self-training methods, such as noisy student teacher training, can help address this and enable the adaptation of models under such domain shifts. However, self-training typically requires a collection of unlabelled target domain data. For settings where this is not practical, we investigate the benefit of performing noisy student teacher training on recordings in the test set as a test-time adaptation approach. Similarly to the dynamic evaluation approach in language modelling, this enables the transfer of information across utterance boundaries and functions as a method of domain adaptation. A range of in-domain and out-of-domain datasets are used for experiments demonstrating large relative gains of up to 32.2%. Interestingly, our method showed larger gains than the typical self-training setup that utilises separate adaptation data.
Authors: Vahid Noroozi, Zhehuai Chen, Somshubra Majumdar, Steve Huang, Jagadeesh Balam, Boris Ginsburg
Abstract: In this paper, we propose three methods for generating synthetic samples to train and evaluate multimodal large language models capable of processing both text and speech inputs. Addressing the scarcity of samples containing both modalities, synthetic data generation emerges as a crucial strategy to enhance the performance of such systems and facilitate the modeling of cross-modal relationships between the speech and text domains. Our process employs large language models to generate textual components and text-to-speech systems to generate speech components. The proposed methods offer a practical and effective means to expand the training dataset for these models. Experimental results show progress in achieving an integrated understanding of text and speech. We also highlight the potential of using unlabeled speech data to generate synthetic samples comparable in quality to those with available transcriptions, enabling the expansion of these models to more languages.
Authors: Matthew John Cossins, Sendy Phang
Abstract: The aim of this project was to develop a new Reservoir Computer implementation, based on a chaotic Chua circuit. In addition to suitable classification and regression benchmarks, the Reservoir Computer was applied to Post-Quantum Cryptography, with its suitability for this application investigated and assessed. The cryptographic algorithm utilised was the Learning with Errors problem, for both encryption and decryption. To achieve this, the Chua circuit was characterised, in simulation, and by physical circuit testing. The Reservoir Computer was designed and implemented using the results of the characterisation. As part of this development, noise was considered and mitigated. The benchmarks demonstrate that the Reservoir Computer can achieve current literature benchmarks with low error. However, the results with Learning with Errors suggest that a Chua-based Reservoir Computer is not sufficiently complex to tackle the high non-linearity in Post-Quantum Cryptography. Future work would involve researching the use of different combinations of multiple Chua Reservoir Computers in larger neural network architectures. Such architectures may produce the required high-dimensional behaviour to achieve the Learning with Errors problem. This project is believed to be only the second instance of a Chua-based Reservoir Computer in academia, and it is the first to be applied to challenging real-world tasks such as Post-Quantum Cryptography. It is also original by its investigation of hitherto unexplored parameters, and their impact on performance. It demonstrates a proof-of-concept for a mass-producible, inexpensive, low-power consumption hardware neural network. It also enables the next stages in research to occur, paving the road for using Chua-based Reservoir Computers across various applications.
Authors: Yuyan Liu, Sirui Ding, Sheng Zhou, Wenqi Fan, Qiaoyu Tan
Abstract: Molecular property prediction (MPP) is a fundamental and crucial task in drug discovery. However, prior methods are limited by the requirement for a large number of labeled molecules and their restricted ability to generalize for unseen and new tasks, both of which are essential for real-world applications. To address these challenges, we present MolecularGPT for few-shot MPP. From a perspective on instruction tuning, we fine-tune large language models (LLMs) based on curated molecular instructions spanning over 1000 property prediction tasks. This enables building a versatile and specialized LLM that can be adapted to novel MPP tasks without any fine-tuning through zero- and few-shot in-context learning (ICL). MolecularGPT exhibits competitive in-context reasoning capabilities across 10 downstream evaluation datasets, setting new benchmarks for few-shot molecular prediction tasks. More importantly, with just two-shot examples, MolecularGPT can outperform standard supervised graph neural network methods on 4 out of 7 datasets. It also excels state-of-the-art LLM baselines by up to 16.6% increase on classification accuracy and decrease of 199.17 on regression metrics (e.g., RMSE) under zero-shot. This study demonstrates the potential of LLMs as effective few-shot molecular property predictors. The code is available at https://github.com/NYUSHCS/MolecularGPT.
Authors: Niels M\"undler, Mark Niklas M\"uller, Jingxuan He, Martin Vechev
Abstract: Rigorous software testing is crucial for developing and maintaining high-quality code, making automated test generation a promising avenue for both improving software quality and boosting the effectiveness of code generation methods. However, while code generation with Large Language Models (LLMs) is an extraordinarily active research area, test generation remains relatively unexplored. We address this gap and investigate the capability of LLM-based Code Agents for formalizing user issues into test cases. To this end, we propose a novel benchmark based on popular GitHub repositories, containing real-world issues, ground-truth patches, and golden tests. We find that LLMs generally perform surprisingly well at generating relevant test cases with Code Agents designed for code repair exceeding the performance of systems designed specifically for test generation. Further, as test generation is a similar but more structured task than code generation, it allows for a more fine-grained analysis using fail-to-pass rate and coverage metrics, providing a dual metric for analyzing systems designed for code repair. Finally, we find that generated tests are an effective filter for proposed code fixes, doubling the precision of SWE-Agent.
Authors: Edith Heiter, Liesbet Martens, Ruth Seurinck, Martin Guilliams, Tijl De Bie, Yvan Saeys, Jefrey Lijffijt
Abstract: This paper presents TRACE, a tool to analyze the quality of 2D embeddings generated through dimensionality reduction techniques. Dimensionality reduction methods often prioritize preserving either local neighborhoods or global distances, but insights from visual structures can be misleading if the objective has not been achieved uniformly. TRACE addresses this challenge by providing a scalable and extensible pipeline for computing both local and global quality measures. The interactive browser-based interface allows users to explore various embeddings while visually assessing the pointwise embedding quality. The interface also facilitates in-depth analysis by highlighting high-dimensional nearest neighbors for any group of points and displaying high-dimensional distances between points. TRACE enables analysts to make informed decisions regarding the most suitable dimensionality reduction method for their specific use case, by showing the degree and location where structure is preserved in the reduced space.
Authors: Md Sirajul Islam, Sanjeev Panta
Abstract: Skin cancer is one of the most common and deadliest types of cancer. Early diagnosis of skin cancer at a benign stage is critical to reducing cancer mortality. To detect skin cancer at an earlier stage an automated system is compulsory that can save the life of many patients. Many previous studies have addressed the problem of skin cancer diagnosis using various deep learning and transfer learning models. However, existing literature has limitations in its accuracy and time-consuming procedure. In this work, we applied five different pre-trained transfer learning approaches for binary classification of skin cancer detection at benign and malignant stages. To increase the accuracy of these models we fine-tune different layers and activation functions. We used a publicly available ISIC dataset to evaluate transfer learning approaches. For model stability, data augmentation techniques are applied to improve the randomness of the input dataset. These approaches are evaluated using different hyperparameters such as batch sizes, epochs, and optimizers. The experimental results show that the ResNet-50 model provides an accuracy of 0.935, F1-score of 0.86, and precision of 0.94.
Authors: Samuel Atkins, Ali Fathi, Sammy Assefa
Abstract: A corporate bond trader in a typical sell side institution such as a bank provides liquidity to the market participants by buying/selling securities and maintaining an inventory. Upon receiving a request for a buy/sell price quote (RFQ), the trader provides a quote by adding a spread over a \textit{prevalent market price}. For illiquid bonds, the market price is harder to observe, and traders often resort to available benchmark bond prices (such as MarketAxess, Bloomberg, etc.). In \cite{Bergault2023ModelingLI}, the concept of \textit{Fair Transfer Price} for an illiquid corporate bond was introduced which is derived from an infinite horizon stochastic optimal control problem (for maximizing the trader's expected P\&L, regularized by the quadratic variation). In this paper, we consider the same optimization objective, however, we approach the estimation of an optimal bid-ask spread quoting strategy in a data driven manner and show that it can be learned using Reinforcement Learning. Furthermore, we perform extensive outcome analysis to examine the reasonableness of the trained agent's behavior.
Authors: Salem Ameen, Ravivarman Balachandran, Theodoros Theodoridis
Abstract: In the intricate field of medical diagnostics, capturing the subtle manifestations of diseases remains a challenge. Traditional methods, often binary in nature, may not encapsulate the nuanced variances that exist in real-world clinical scenarios. This paper introduces a novel approach by leveraging Fuzzy Logic Rules to derive disease classes based on expert domain knowledge from a medical practitioner. By recognizing that diseases do not always fit into neat categories, and that expert knowledge can guide the fuzzification of these boundaries, our methodology offers a more sophisticated and nuanced diagnostic tool. Using a dataset procured from a prominent hospital, containing detailed patient blood count records, we harness Fuzzy Logic Rules, a computational technique celebrated for its ability to handle ambiguity. This approach, moving through stages of fuzzification, rule application, inference, and ultimately defuzzification, produces refined diagnostic predictions. When combined with the Random Forest classifier, the system adeptly predicts hematological conditions using Complete Blood Count (CBC) parameters. Preliminary results showcase high accuracy levels, underscoring the advantages of integrating fuzzy logic into the diagnostic process. When juxtaposed with traditional diagnostic techniques, it becomes evident that Fuzzy Logic, especially when guided by medical expertise, offers significant advancements in the realm of hematological diagnostics. This paper not only paves the path for enhanced patient care but also beckons a deeper dive into the potentialities of fuzzy logic in various medical diagnostic applications.
Authors: Seonghun Park, Manish Bansal
Abstract: We study submodular optimization in adversarial context, applicable to machine learning problems such as feature selection using data susceptible to uncertainties and attacks. We focus on Stackelberg games between an attacker (or interdictor) and a defender where the attacker aims to minimize the defender's objective of maximizing a $k$-submodular function. We allow uncertainties arising from the success of attacks and inherent data noise, and address challenges due to incomplete knowledge of the probability distribution of random parameters. Specifically, we introduce Distributionally Risk-Averse $k$-Submodular Interdiction Problem (DRA $k$-SIP) and Distributionally Risk-Receptive $k$-Submodular Interdiction Problem (DRR $k$-SIP) along with finitely convergent exact algorithms for solving them. The DRA $k$-SIP solution allows risk-averse interdictor to develop robust strategies for real-world uncertainties. Conversely, DRR $k$-SIP solution suggests aggressive tactics for attackers, willing to embrace (distributional) risk to inflict maximum damage, identifying critical vulnerable components, which can be used for the defender's defensive strategies. The optimal values derived from both DRA $k$-SIP and DRR $k$-SIP offer a confidence interval-like range for the expected value of the defender's objective function, capturing distributional ambiguity. We conduct computational experiments using instances of feature selection and sensor placement problems, and Wisconsin breast cancer data and synthetic data, respectively.
Authors: Matthew T. C. Li, Tiangang Cui, Fengyi Li, Youssef Marzouk, Olivier Zahm
Abstract: Identifying low-dimensional structure in high-dimensional probability measures is an essential pre-processing step for efficient sampling. We introduce a method for identifying and approximating a target measure $\pi$ as a perturbation of a given reference measure $\mu$ along a few significant directions of $\mathbb{R}^{d}$. The reference measure can be a Gaussian or a nonlinear transformation of a Gaussian, as commonly arising in generative modeling. Our method extends prior work on minimizing majorizations of the Kullback--Leibler divergence to identify optimal approximations within this class of measures. Our main contribution unveils a connection between the \emph{dimensional} logarithmic Sobolev inequality (LSI) and approximations with this ansatz. Specifically, when the target and reference are both Gaussian, we show that minimizing the dimensional LSI is equivalent to minimizing the KL divergence restricted to this ansatz. For general non-Gaussian measures, the dimensional LSI produces majorants that uniformly improve on previous majorants for gradient-based dimension reduction. We further demonstrate the applicability of this analysis to the squared Hellinger distance, where analogous reasoning shows that the dimensional Poincar\'e inequality offers improved bounds.
Authors: Enoch Adediran, Salem Ameen
Abstract: As the pace of AI technology continues to accelerate, more tools have become available to researchers to solve longstanding problems, Hybrid approaches available today continue to push the computational limits of efficiency and precision. One of such problems is the inverse kinematics of redundant systems. This paper explores the complexities of a 7 degree of freedom manipulator and explores 13 optimization techniques to solve it. Additionally, a novel approach is proposed to contribute to the field of algorithmic research. This was found to be over 200 times faster than the well-known traditional Particle Swarm Optimization technique. This new method may serve as a new field of search that combines the explorative capabilities of Machine Learning with the exploitative capabilities of numerical methods.
Authors: Guillaume Qu\'etant, John Andrew Raine, Matthew Leigh, Debajyoti Sengupta, Tobias Golling
Abstract: This paper presents a novel approach for directly generating full events at detector-level from parton-level information, leveraging cutting-edge machine learning techniques. To address the challenge of multiplicity variations between parton and reconstructed object spaces, we employ transformers, score-based models and normalizing flows. Our method tackles the inherent complexities of the stochastic transition between these two spaces and achieves remarkably accurate results. The combination of innovative techniques and the achieved accuracy demonstrates the potential of our approach in advancing the field and opens avenues for further exploration. This research contributes to the ongoing efforts in high-energy physics and generative modelling, providing a promising direction for enhanced precision in fast detector simulation.
Authors: Julia Gaudio, Nirmit Joshi
Abstract: In this paper, we study the problem of exact community recovery in general, two-community block models considering both Bernoulli and Gaussian matrix models, capturing the Stochastic Block Model, submatrix localization, and $\mathbb{Z}_2$-synchronization as special cases. We also study the settings where $side$ $information$ about community assignment labels is available, modeled as passing the true labels through a noisy channel: either the binary erasure channel (where some community labels are known while others are erased) or the binary symmetric channel (where some labels are flipped). We provide a unified analysis of the effect of side information on the information-theoretic limits of exact recovery, generalizing prior works and extending to new settings. Additionally, we design a simple but optimal spectral algorithm that incorporates side information (when present) along with the eigenvectors of the matrix observation. Using the powerful tool of entrywise eigenvector analysis [Abbe, Fan, Wang, Zhong 2020], we show that our spectral algorithm can mimic the so called $genie$-$aided$ $estimators$, where the $i^{\mathrm{th}}$ genie-aided estimator optimally computes the estimate of the $i^{\mathrm{th}}$ label, when all remaining labels are revealed by a genie. This perspective provides a unified understanding of the optimality of spectral algorithms for various exact recovery problems in a recent line of work.
Authors: Bernd Bohnet, Azade Nova, Aaron T Parisi, Kevin Swersky, Katayoon Goshvadi, Hanjun Dai, Dale Schuurmans, Noah Fiedel, Hanie Sedghi
Abstract: We seek to elevate the planning capabilities of Large Language Models (LLMs)investigating four main directions. First, we construct a comprehensive benchmark suite encompassing both classical planning domains and natural language scenarios. This suite includes algorithms to generate instances with varying levels of difficulty, allowing for rigorous and systematic evaluation of LLM performance. Second, we investigate the use of in-context learning (ICL) to enhance LLM planning, exploring the direct relationship between increased context length and improved planning performance. Third, we demonstrate the positive impact of fine-tuning LLMs on optimal planning paths, as well as the effectiveness of incorporating model-driven search procedures. Finally, we investigate the performance of the proposed methods in out-of-distribution scenarios, assessing the ability to generalize to novel and unseen planning challenges.
Authors: Paul Henderson, Melonie de Almeida, Daniela Ivanova, Titas Anciukevi\v{c}ius
Abstract: We present a latent diffusion model over 3D scenes, that can be trained using only 2D image data. To achieve this, we first design an autoencoder that maps multi-view images to 3D Gaussian splats, and simultaneously builds a compressed latent representation of these splats. Then, we train a multi-view diffusion model over the latent space to learn an efficient generative model. This pipeline does not require object masks nor depths, and is suitable for complex scenes with arbitrary camera positions. We conduct careful experiments on two large-scale datasets of complex real-world scenes -- MVImgNet and RealEstate10K. We show that our approach enables generating 3D scenes in as little as 0.2 seconds, either from scratch, from a single input view, or from sparse input views. It produces diverse and high-quality results while running an order of magnitude faster than non-latent diffusion models and earlier NeRF-based generative models
Authors: Chang Tian, Matthew B. Blaschko, Wenpeng Yin, Mingzhe Xing, Yinliang Yue, Marie-Francine Moens
Abstract: Fine-grained category discovery using only coarse-grained supervision is a cost-effective yet challenging task. Previous training methods focus on aligning query samples with positive samples and distancing them from negatives. They often neglect intra-category and inter-category semantic similarities of fine-grained categories when navigating sample distributions in the embedding space. Furthermore, some evaluation techniques that rely on pre-collected test samples are inadequate for real-time applications. To address these shortcomings, we introduce a method that successfully detects fine-grained clusters of semantically similar texts guided by a novel objective function. The method uses semantic similarities in a logarithmic space to guide sample distributions in the Euclidean space and to form distinct clusters that represent fine-grained categories. We also propose a centroid inference mechanism to support real-time applications. The efficacy of the method is both theoretically justified and empirically confirmed on three benchmark tasks. The proposed objective function is integrated in multiple contrastive learning based neural models. Its results surpass existing state-of-the-art approaches in terms of Accuracy, Adjusted Rand Index and Normalized Mutual Information of the detected fine-grained categories. Code and data will be available at https://github.com/XX upon publication.
URLs: https://github.com/XX
Authors: Peter Eastman, Benjamin P. Pritchard, John D. Chodera, Thomas E. Markland
Abstract: We describe version 2 of the SPICE dataset, a collection of quantum chemistry calculations for training machine learning potentials. It expands on the original dataset by adding much more sampling of chemical space and more data on non-covalent interactions. We train a set of potential energy functions called Nutmeg on it. They use a novel mechanism to improve performance on charged and polar molecules, injecting precomputed partial charges into the model to provide a reference for the large scale charge distribution. Evaluation of the new models shows they do an excellent job of reproducing energy differences between conformations, even on highly charged molecules or ones that are significantly larger than the molecules in the training set. They also produce stable molecular dynamics trajectories, and are fast enough to be useful for routine simulation of small molecules.
Authors: Teja Krishna Cherukuri, Nagur Shareef Shaik, Dong Hye Ye
Abstract: Effectively representing medical images, especially retinal images, presents a considerable challenge due to variations in appearance, size, and contextual information of pathological signs called lesions. Precise discrimination of these lesions is crucial for diagnosing vision-threatening issues such as diabetic retinopathy. While visual attention-based neural networks have been introduced to learn spatial context and channel correlations from retinal images, they often fall short in capturing localized lesion context. Addressing this limitation, we propose a novel attention mechanism called Guided Context Gating, an unique approach that integrates Context Formulation, Channel Correlation, and Guided Gating to learn global context, spatial correlations, and localized lesion context. Our qualitative evaluation against existing attention mechanisms emphasize the superiority of Guided Context Gating in terms of explainability. Notably, experiments on the Zenodo-DR-7 dataset reveal a substantial 2.63% accuracy boost over advanced attention mechanisms & an impressive 6.53% improvement over the state-of-the-art Vision Transformer for assessing the severity grade of retinopathy, even with imbalanced and limited training samples for each class.
Authors: Jo\~ao Pedro Parella, Matheus Viana da Silva, Cesar Henrique Comin
Abstract: Many studies regarding the vasculature of biological tissues involve the segmentation of the blood vessels in a sample followed by the creation of a graph structure to model the vasculature. The graph is then used to extract relevant vascular properties. Small segmentation errors can lead to largely distinct connectivity patterns and a high degree of variability of the extracted properties. Nevertheless, global metrics such as Dice, precision, and recall are commonly applied for measuring the performance of blood vessel segmentation algorithms. These metrics might conceal important information about the accuracy at specific regions of a sample. To tackle this issue, we propose a local vessel salience (LVS) index to quantify the expected difficulty in segmenting specific blood vessel segments. The LVS index is calculated for each vessel pixel by comparing the local intensity of the vessel with the image background around the pixel. The index is then used for defining a new accuracy metric called low-salience recall (LSRecall), which quantifies the performance of segmentation algorithms on blood vessel segments having low salience. The perspective provided by the LVS index is used to define a data augmentation procedure that can be used to improve the segmentation performance of convolutional neural networks. We show that segmentation algorithms having high Dice and recall values can display very low LSRecall values, which reveals systematic errors of these algorithms for vessels having low salience. The proposed data augmentation procedure is able to improve the LSRecall of some samples by as much as 25%. The developed methodology opens up new possibilities for comparing the performance of segmentation algorithms regarding hard-to-detect blood vessels as well as their capabilities for vascular topology preservation.
Authors: Nagur Shareef Shaik, Teja Krishna Cherukuri, Dong Hye Ye
Abstract: Automated retinal image medical description generation is crucial for streamlining medical diagnosis and treatment planning. Existing challenges include the reliance on learned retinal image representations, difficulties in handling multiple imaging modalities, and the lack of clinical context in visual representations. Addressing these issues, we propose the Multi-Modal Medical Transformer (M3T), a novel deep learning architecture that integrates visual representations with diagnostic keywords. Unlike previous studies focusing on specific aspects, our approach efficiently learns contextual information and semantics from both modalities, enabling the generation of precise and coherent medical descriptions for retinal images. Experimental studies on the DeepEyeNet dataset validate the success of M3T in meeting ophthalmologists' standards, demonstrating a substantial 13.5% improvement in BLEU@4 over the best-performing baseline model.
Authors: Sajib Acharjee Dip, Uddip Acharjee Shuvo, Tran Chau, Haoqiu Song, Petra Choi, Xuan Wang, Liqing Zhang
Abstract: Pathogen identification is pivotal in diagnosing, treating, and preventing diseases, crucial for controlling infections and safeguarding public health. Traditional alignment-based methods, though widely used, are computationally intense and reliant on extensive reference databases, often failing to detect novel pathogens due to their low sensitivity and specificity. Similarly, conventional machine learning techniques, while promising, require large annotated datasets and extensive feature engineering and are prone to overfitting. Addressing these challenges, we introduce PathoLM, a cutting-edge pathogen language model optimized for the identification of pathogenicity in bacterial and viral sequences. Leveraging the strengths of pre-trained DNA models such as the Nucleotide Transformer, PathoLM requires minimal data for fine-tuning, thereby enhancing pathogen detection capabilities. It effectively captures a broader genomic context, significantly improving the identification of novel and divergent pathogens. We developed a comprehensive data set comprising approximately 30 species of viruses and bacteria, including ESKAPEE pathogens, seven notably virulent bacterial strains resistant to antibiotics. Additionally, we curated a species classification dataset centered specifically on the ESKAPEE group. In comparative assessments, PathoLM dramatically outperforms existing models like DciPatho, demonstrating robust zero-shot and few-shot capabilities. Furthermore, we expanded PathoLM-Sp for ESKAPEE species classification, where it showed superior performance compared to other advanced deep learning methods, despite the complexities of the task.
Authors: Longfei Ma, Nan Cheng, Xiucheng Wang, Jiong Chen, Yinjun Gao, Dongxiao Zhang, Jun-Jie Zhang
Abstract: The development of Digital Twins (DTs) represents a transformative advance for simulating and optimizing complex systems in a controlled digital space. Despite their potential, the challenge of constructing DTs that accurately replicate and predict the dynamics of real-world systems remains substantial. This paper introduces an intelligent framework for the construction and evaluation of DTs, specifically designed to enhance the accuracy and utility of DTs in testing algorithmic performance. We propose a novel construction methodology that integrates deep learning-based policy gradient techniques to dynamically tune the DT parameters, ensuring high fidelity in the digital replication of physical systems. Moreover, the Mean STate Error (MSTE) is proposed as a robust metric for evaluating the performance of algorithms within these digital space. The efficacy of our framework is demonstrated through extensive simulations that show our DT not only accurately mirrors the physical reality but also provides a reliable platform for algorithm evaluation. This work lays a foundation for future research into DT technologies, highlighting pathways for both theoretical enhancements and practical implementations in various industries.
Authors: Yarden Cohen, Alexandre Khae Wu Navarro, Jes Frellsen, Richard E. Turner, Raziel Riemer, Ari Pakman
Abstract: The need for regression models to predict circular values arises in many scientific fields. In this work we explore a family of expressive and interpretable distributions over circle-valued random functions related to Gaussian processes targeting two Euclidean dimensions conditioned on the unit circle. The resulting probability model has connections with continuous spin models in statistical physics. Moreover, its density is very simple and has maximum-entropy, unlike previous Gaussian process-based approaches, which use wrapping or radial marginalization. For posterior inference, we introduce a new Stratonovich-like augmentation that lends itself to fast Markov Chain Monte Carlo sampling. We argue that transductive learning in these models favors a Bayesian approach to the parameters. We present experiments applying this model to the prediction of (i) wind directions and (ii) the percentage of the running gait cycle as a function of joint angles.
Authors: Agnimitra Dasgupta, Harisankar Ramaswamy, Javier Murgoitio Esandi, Ken Foo, Runze Li, Qifa Zhou, Brendan Kennedy, Assad Oberai
Abstract: We propose a framework to perform Bayesian inference using conditional score-based diffusion models to solve a class of inverse problems in mechanics involving the inference of a specimen's spatially varying material properties from noisy measurements of its mechanical response to loading. Conditional score-based diffusion models are generative models that learn to approximate the score function of a conditional distribution using samples from the joint distribution. More specifically, the score functions corresponding to multiple realizations of the measurement are approximated using a single neural network, the so-called score network, which is subsequently used to sample the posterior distribution using an appropriate Markov chain Monte Carlo scheme based on Langevin dynamics. Training the score network only requires simulating the forward model. Hence, the proposed approach can accommodate black-box forward models and complex measurement noise. Moreover, once the score network has been trained, it can be re-used to solve the inverse problem for different realizations of the measurements. We demonstrate the efficacy of the proposed approach on a suite of high-dimensional inverse problems in mechanics that involve inferring heterogeneous material properties from noisy measurements. Some examples we consider involve synthetic data, while others include data collected from actual elastography experiments. Further, our applications demonstrate that the proposed approach can handle different measurement modalities, complex patterns in the inferred quantities, non-Gaussian and non-additive noise models, and nonlinear black-box forward models. The results show that the proposed framework can solve large-scale physics-based inverse problems efficiently.
Authors: Honghua Dong, Qidong Su, Yubo Gao, Zhaoyu Li, Yangjun Ruan, Gennady Pekhimenko, Chris J. Maddison, Xujie Si
Abstract: Large Language Models (LLMs) have become increasingly capable of handling diverse tasks with the aid of well-crafted prompts and integration of external tools, but as task complexity rises, the workflow involving LLMs can be complicated and thus challenging to implement and maintain. To address this challenge, we propose APPL, A Prompt Programming Language that acts as a bridge between computer programs and LLMs, allowing seamless embedding of prompts into Python functions, and vice versa. APPL provides an intuitive and Python-native syntax, an efficient parallelized runtime with asynchronous semantics, and a tracing module supporting effective failure diagnosis and replaying without extra costs. We demonstrate that APPL programs are intuitive, concise, and efficient through three representative scenarios: Chain-of-Thought with self-consistency (CoT-SC), ReAct tool use agent, and multi-agent chat. Experiments on three parallelizable workflows further show that APPL can effectively parallelize independent LLM calls, with a significant speedup ratio that almost matches the estimation.
Authors: Hejie Cui, Lingjun Mao, Xin Liang, Jieyu Zhang, Hui Ren, Quanzheng Li, Xiang Li, Carl Yang
Abstract: Recent advancements in multimodal foundation models have showcased impressive capabilities in understanding and reasoning with visual and textual information. Adapting these foundation models trained for general usage to specialized domains like biomedicine requires large-scale domain-specific instruction datasets. While existing works have explored curating such datasets automatically, the resultant datasets are not explicitly aligned with domain expertise. In this work, we propose a data-centric framework, Biomedical Visual Instruction Tuning with Clinician Preference Alignment (BioMed-VITAL), that incorporates clinician preferences into both stages of generating and selecting instruction data for tuning biomedical multimodal foundation models. First, during the generation stage, we prompt the GPT-4V generator with a diverse set of clinician-selected demonstrations for preference-aligned data candidate generation. Then, during the selection phase, we train a separate selection model, which explicitly distills clinician and policy-guided model preferences into a rating function to select high-quality data for medical instruction tuning. Results show that the model tuned with the instruction-following data from our method demonstrates a significant improvement in open visual chat (18.5% relatively) and medical VQA (win rate up to 81.73%). Our instruction-following data and models are available at BioMed-VITAL.github.io.
Authors: Naiming Liu, Zichao Wang, Richard Baraniuk
Abstract: Despite rapid advancements in large language models (LLMs), QG remains a challenging problem due to its complicated process, open-ended nature, and the diverse settings in which question generation occurs. A common approach to address these challenges involves fine-tuning smaller, custom models using datasets containing background context, question, and answer. However, obtaining suitable domain-specific datasets with appropriate context is often more difficult than acquiring question-answer pairs. In this paper, we investigate training QG models using synthetic contexts generated by LLMs from readily available question-answer pairs. We conduct a comprehensive study to answer critical research questions related to the performance of models trained on synthetic contexts and their potential impact on QG research and applications. Our empirical results reveal: 1) contexts are essential for QG tasks, even if they are synthetic; 2) fine-tuning smaller language models has the capability of achieving better performances as compared to prompting larger language models; and 3) synthetic context and real context could achieve comparable performances. These findings highlight the effectiveness of synthetic contexts in QG and paves the way for future advancements in the field.
Authors: Hetong Wang, Pasquale Minervini, Edoardo M. Ponti
Abstract: Multilingual Large Language Models (LLMs) achieve remarkable levels of zero-shot cross-lingual transfer performance. We speculate that this is predicated on their ability to align languages without explicit supervision from parallel sentences. While representations of translationally equivalent sentences in different languages are known to be similar after convergence, however, it remains unclear how such cross-lingual alignment emerges during pre-training of LLMs. Our study leverages intrinsic probing techniques, which identify which subsets of neurons encode linguistic features, to correlate the degree of cross-lingual neuron overlap with the zero-shot cross-lingual transfer performance for a given model. In particular, we rely on checkpoints of BLOOM, a multilingual autoregressive LLM, across different training steps and model scales. We observe a high correlation between neuron overlap and downstream performance, which supports our hypothesis on the conditions leading to effective cross-lingual transfer. Interestingly, we also detect a degradation of both implicit alignment and multilingual abilities in certain phases of the pre-training process, providing new insights into the multilingual pretraining dynamics.
Authors: Akchay Srivastava, Atif Memon
Abstract: Open Domain Question Answering (ODQA) within natural language processing involves building systems that answer factual questions using large-scale knowledge corpora. Recent advances stem from the confluence of several factors, such as large-scale training datasets, deep learning techniques, and the rise of large language models. High-quality datasets are used to train models on realistic scenarios and enable the evaluation of the system on potentially unseen data. Standardized metrics facilitate comparisons between different ODQA systems, allowing researchers to objectively track advancements in the field. Our study presents a thorough examination of the current landscape of ODQA benchmarking by reviewing 52 datasets and 20 evaluation techniques across textual and multimodal modalities. We introduce a novel taxonomy for ODQA datasets that incorporates both the modality and difficulty of the question types. Additionally, we present a structured organization of ODQA evaluation metrics along with a critical analysis of their inherent trade-offs. Our study aims to empower researchers by providing a framework for the robust evaluation of modern question-answering systems. We conclude by identifying the current challenges and outlining promising avenues for future research and development.
Authors: Navid Rajabi, Jana Kosecka
Abstract: The ability to understand and reason about spatial relationships between objects in images is an important component of visual reasoning. This skill rests on the ability to recognize and localize objects of interest and determine their spatial relation. Early vision and language models (VLMs) have been shown to struggle to recognize spatial relations. We extend the previously released What'sUp dataset and propose a novel comprehensive evaluation for spatial relationship understanding that highlights the strengths and weaknesses of 27 different models. In addition to the VLMs evaluated in What'sUp, our extensive evaluation encompasses 3 classes of Multimodal LLMs (MLLMs) that vary in their parameter sizes (ranging from 7B to 110B), training/instruction-tuning methods, and visual resolution to benchmark their performances and scrutinize the scaling laws in this task.
Authors: Zhong Guan, Hongke Zhao, Likang Wu, Ming He, Jianpin Fan
Abstract: Recently, large language models (LLMs) have been widely researched in the field of graph machine learning due to their outstanding abilities in language comprehension and learning. However, the significant gap between natural language tasks and topological structure modeling poses a nonnegligible challenge. Specifically, since natural language descriptions are not sufficient for LLMs to understand and process graph-structured data, fine-tuned LLMs perform even worse than some traditional GNN models on graph tasks, lacking inherent modeling capabilities for graph structures. Existing research overly emphasizes LLMs' understanding of semantic information captured by external models, while inadequately exploring graph topological structure modeling, thereby overlooking the genuine capabilities that LLMs lack. Consequently, in this paper, we introduce a new framework, LangTopo, which aligns graph structure modeling with natural language understanding at the token level. LangTopo quantifies the graph structure modeling capabilities of GNNs and LLMs by constructing a codebook for the graph modality and performs consistency maximization. This process aligns the text description of LLM with the topological modeling of GNN, allowing LLM to learn the ability of GNN to capture graph structures, enabling LLM to handle graph-structured data independently. We demonstrate the effectiveness of our proposed method on multiple datasets.
Authors: Caroline Mazini Rodrigues (LIGM, LRE), Nicolas Boutry (LRE), Laurent Najman (LIGM)
Abstract: Challenges persist in providing interpretable explanations for neural network reasoning in explainable AI (xAI). Existing methods like Integrated Gradients produce noisy maps, and LIME, while intuitive, may deviate from the model's reasoning. We introduce a framework that uses hierarchical segmentation techniques for faithful and interpretable explanations of Convolutional Neural Networks (CNNs). Our method constructs model-based hierarchical segmentations that maintain the model's reasoning fidelity and allows both human-centric and model-centric segmentation. This approach offers multiscale explanations, aiding bias identification and enhancing understanding of neural network decision-making. Experiments show that our framework, xAiTrees, delivers highly interpretable and faithful model explanations, not only surpassing traditional xAI methods but shedding new light on a novel approach to enhancing xAI interpretability. Code at: https://github.com/CarolMazini/reasoning_with_trees .
Authors: Michael Wornow, Avanika Narayan, Ben Viggiano, Ishan S. Khare, Tathagat Verma, Tibor Thompson, Miguel Angel Fuentes Hernandez, Sudharsan Sundar, Chloe Trujillo, Krrish Chawla, Rongfei Lu, Justin Shen, Divya Nagaraj, Joshua Martinez, Vardhan Agrawal, Althea Hudson, Nigam H. Shah, Christopher Re
Abstract: Existing ML benchmarks lack the depth and diversity of annotations needed for evaluating models on business process management (BPM) tasks. BPM is the practice of documenting, measuring, improving, and automating enterprise workflows. However, research has focused almost exclusively on one task - full end-to-end automation using agents based on multimodal foundation models (FMs) like GPT-4. This focus on automation ignores the reality of how most BPM tools are applied today - simply documenting the relevant workflow takes 60% of the time of the typical process optimization project. To address this gap we present WONDERBREAD, the first benchmark for evaluating multimodal FMs on BPM tasks beyond automation. Our contributions are: (1) a dataset containing 2928 documented workflow demonstrations; (2) 6 novel BPM tasks sourced from real-world applications ranging from workflow documentation to knowledge transfer to process improvement; and (3) an automated evaluation harness. Our benchmark shows that while state-of-the-art FMs can automatically generate documentation (e.g. recalling 88% of the steps taken in a video demonstration of a workflow), they struggle to re-apply that knowledge towards finer-grained validation of workflow completion (F1 < 0.3). We hope WONDERBREAD encourages the development of more "human-centered" AI tooling for enterprise applications and furthers the exploration of multimodal FMs for the broader universe of BPM tasks. We publish our dataset and experiments here: https://github.com/HazyResearch/wonderbread
Authors: Xikang Yang, Xuehai Tang, Fuqing Zhu, Jizhong Han, Songlin Hu
Abstract: Vision-language models (VLMs) seamlessly integrate visual and textual data to perform tasks such as image classification, caption generation, and visual question answering. However, adversarial images often struggle to deceive all prompts effectively in the context of cross-prompt migration attacks, as the probability distribution of the tokens in these images tends to favor the semantics of the original image rather than the target tokens. To address this challenge, we propose a Contextual-Injection Attack (CIA) that employs gradient-based perturbation to inject target tokens into both visual and textual contexts, thereby improving the probability distribution of the target tokens. By shifting the contextual semantics towards the target tokens instead of the original image semantics, CIA enhances the cross-prompt transferability of adversarial images.Extensive experiments on the BLIP2, InstructBLIP, and LLaVA models show that CIA outperforms existing methods in cross-prompt transferability, demonstrating its potential for more effective adversarial strategies in VLMs.
Authors: Khai Le-Duc
Abstract: Spoken Named Entity Recognition (NER) aims to extracting named entities from speech and categorizing them into types like person, location, organization, etc. In this work, we present VietMed-NER - the first spoken NER dataset in the medical domain. To our best knowledge, our real-world dataset is the largest spoken NER dataset in the world in terms of the number of entity types, featuring 18 distinct types. Secondly, we present baseline results using various state-of-the-art pre-trained models: encoder-only and sequence-to-sequence. We found that pre-trained multilingual models XLM-R outperformed all monolingual models on both reference text and ASR output. Also in general, encoders perform better than sequence-to-sequence models for the NER task. By simply translating, the transcript is applicable not just to Vietnamese but to other languages as well. All code, data and models are made publicly available here: https://github.com/leduckhai/MultiMed
Authors: Jiacheng Du, Zhibo Wang, Kui Ren
Abstract: Language models (LMs) are susceptible to "memorizing" training data, including a large amount of private or copyright-protected content. To safeguard the right to be forgotten (RTBF), machine unlearning has emerged as a promising method for LMs to efficiently "forget" sensitive training content and mitigate knowledge leakage risks. However, despite its good intentions, could the unlearning mechanism be counterproductive? In this paper, we propose the Textual Unlearning Leakage Attack (TULA), where an adversary can infer information about the unlearned data only by accessing the models before and after unlearning. Furthermore, we present variants of TULA in both black-box and white-box scenarios. Through various experimental results, we critically demonstrate that machine unlearning amplifies the risk of knowledge leakage from LMs. Specifically, TULA can increase an adversary's ability to infer membership information about the unlearned data by more than 20% in black-box scenario. Moreover, TULA can even reconstruct the unlearned data directly with more than 60% accuracy with white-box access. Our work is the first to reveal that machine unlearning in LMs can inversely create greater knowledge risks and inspire the development of more secure unlearning mechanisms.
Authors: Edoardo Debenedetti, Jie Zhang, Mislav Balunovi\'c, Luca Beurer-Kellner, Marc Fischer, Florian Tram\`er
Abstract: AI agents aim to solve complex tasks by combining text-based reasoning with external tool calls. Unfortunately, AI agents are vulnerable to prompt injection attacks where data returned by external tools hijacks the agent to execute malicious tasks. To measure the adversarial robustness of AI agents, we introduce AgentDojo, an evaluation framework for agents that execute tools over untrusted data. To capture the evolving nature of attacks and defenses, AgentDojo is not a static test suite, but rather an extensible environment for designing and evaluating new agent tasks, defenses, and adaptive attacks. We populate the environment with 97 realistic tasks (e.g., managing an email client, navigating an e-banking website, or making travel bookings), 629 security test cases, and various attack and defense paradigms from the literature. We find that AgentDojo poses a challenge for both attacks and defenses: state-of-the-art LLMs fail at many tasks (even in the absence of attacks), and existing prompt injection attacks break some security properties but not all. We hope that AgentDojo can foster research on new design principles for AI agents that solve common tasks in a reliable and robust manner. We release the code for AgentDojo at https://github.com/ethz-spylab/agentdojo.
Authors: Zhuoran Li, Chunming Hu, Junfan Chen, Zhijun Chen, Xiaohui Guo, Richong Zhang
Abstract: Code-switching is a data augmentation scheme mixing words from multiple languages into source lingual text. It has achieved considerable generalization performance of cross-lingual transfer tasks by aligning cross-lingual contextual word representations. However, uncontrolled and over-replaced code-switching would augment dirty samples to model training. In other words, the excessive code-switching text samples will negatively hurt the models' cross-lingual transferability. To this end, we propose a Progressive Code-Switching (PCS) method to gradually generate moderately difficult code-switching examples for the model to discriminate from easy to hard. The idea is to incorporate progressively the preceding learned multilingual knowledge using easier code-switching data to guide model optimization on succeeding harder code-switching data. Specifically, we first design a difficulty measurer to measure the impact of replacing each word in a sentence based on the word relevance score. Then a code-switcher generates the code-switching data of increasing difficulty via a controllable temperature variable. In addition, a training scheduler decides when to sample harder code-switching data for model training. Experiments show our model achieves state-of-the-art results on three different zero-shot cross-lingual transfer tasks across ten languages.
Authors: Haowen Hou, Peigen Zeng, Fei Ma, Fei Richard Yu
Abstract: Visual Language Models (VLMs) have rapidly progressed with the recent success of large language models. However, there have been few attempts to incorporate efficient linear Recurrent Neural Networks (RNNs) architectures into VLMs. In this study, we introduce VisualRWKV, the first application of a linear RNN model to multimodal learning tasks, leveraging the pre-trained RWKV language model. We propose a data-dependent recurrence and sandwich prompts to enhance our modeling capabilities, along with a 2D image scanning mechanism to enrich the processing of visual sequences. Extensive experiments demonstrate that VisualRWKV achieves competitive performance compared to Transformer-based models like LLaVA-1.5 on various benchmarks. To facilitate further research and analysis, we have made the checkpoints and the associated code publicly accessible at the following GitHub repository: \href{https://github.com/howard-hou/VisualRWKV}{https://github.com/howard-hou/VisualRWKV}.
URLs: https://github.com/howard-hou/VisualRWKV, https://github.com/howard-hou/VisualRWKV
Authors: Subhadeep Dasgupta, Amal R S, Prabal K. Maiti
Abstract: Recent machine learning models to accurately obtain gas adsorption isotherms focus on polymers or metal-organic frameworks (MOFs) separately. The difficulty in creating a unified model that can predict the adsorption trends in both types of adsorbents is challenging, owing to the diversity in their chemical structures. Moreover, models trained only on single gas adsorption data are incapable of predicting adsorption isotherms for binary gas mixtures. In this work, we address these problems using feature vectors comprising only the physical properties of the gas mixtures and adsorbents. Our model is trained on adsorption isotherms of both single and binary mixed gases inside carbon molecular sieving membrane (CMSM), together with data available from CoRE MOF database. The trained models are capable of accurately predicting the adsorption trends in both classes of materials, for both pure and binary components. ML architecture designed for one class of material, is not suitable for predicting the other class, even after proper training, signifying that the model must be trained jointly for proper predictions and transferability. The model is used to predict with good accuracy the CO2 uptake inside CALF-20 framework. This work opens up a new avenue for predicting complex adsorption processes for gas mixtures in a wide range of materials.
Authors: Banibrata Ghosh, Haripriya Harikumar, Khoa D Doan, Svetha Venkatesh, Santu Rana
Abstract: Learning composite concepts, such as \textquotedbl red car\textquotedbl , from individual examples -- like a white car representing the concept of \textquotedbl car\textquotedbl{} and a red strawberry representing the concept of \textquotedbl red\textquotedbl -- is inherently challenging. This paper introduces a novel method called Composite Concept Extractor (CoCE), which leverages techniques from traditional backdoor attacks to learn these composite concepts in a zero-shot setting, requiring only examples of individual concepts. By repurposing the trigger-based model backdooring mechanism, we create a strategic distortion in the manifold of the target object (e.g., \textquotedbl car\textquotedbl ) induced by example objects with the target property (e.g., \textquotedbl red\textquotedbl ) from objects \textquotedbl red strawberry\textquotedbl , ensuring the distortion selectively affects the target objects with the target property. Contrastive learning is then employed to further refine this distortion, and a method is formulated for detecting objects that are influenced by the distortion. Extensive experiments with in-depth analysis across different datasets demonstrate the utility and applicability of our proposed approach.
Authors: Mat\'eo Mahaut, Laura Aina, Paula Czarnowska, Momchil Hardalov, Thomas M\"uller, Llu\'is M\`arquez
Abstract: Large Language Models (LLMs) tend to be unreliable in the factuality of their answers. To address this problem, NLP researchers have proposed a range of techniques to estimate LLM's confidence over facts. However, due to the lack of a systematic comparison, it is not clear how the different methods compare to one another. To fill this gap, we present a survey and empirical comparison of estimators of factual confidence. We define an experimental framework allowing for fair comparison, covering both fact-verification and question answering. Our experiments across a series of LLMs indicate that trained hidden-state probes provide the most reliable confidence estimates, albeit at the expense of requiring access to weights and training data. We also conduct a deeper assessment of factual confidence by measuring the consistency of model behavior under meaning-preserving variations in the input. We find that the confidence of LLMs is often unstable across semantically equivalent inputs, suggesting that there is much room for improvement of the stability of models' parametric knowledge. Our code is available at (https://github.com/amazon-science/factual-confidence-of-llms).
URLs: https://github.com/amazon-science/factual-confidence-of-llms).
Authors: Roger Ferrod, Luigi Di Caro, Dino Ienco
Abstract: Recently, there has been increasing interest in multimodal applications that integrate text with other modalities, such as images, audio and video, to facilitate natural language interactions with multimodal AI systems. While applications involving standard modalities have been extensively explored, there is still a lack of investigation into specific data modalities such as remote sensing (RS) data. Despite the numerous potential applications of RS data, including environmental protection, disaster monitoring and land planning, available solutions are predominantly focused on specific tasks like classification, captioning and retrieval. These solutions often overlook the unique characteristics of RS data, such as its capability to systematically provide information on the same geographical areas over time. This ability enables continuous monitoring of changes in the underlying landscape. To address this gap, we propose a novel foundation model for bi-temporal RS image pairs, in the context of change detection analysis, leveraging Contrastive Learning and the LEVIR-CC dataset for both captioning and text-image retrieval. By jointly training a contrastive encoder and captioning decoder, our model add text-image retrieval capabilities, in the context of bi-temporal change detection, while maintaining captioning performances that are comparable to the state of the art. We release the source code and pretrained weights at: https://github.com/rogerferrod/RSICRC.
Authors: Qiao Chen, Elise Arnaud, Ricardo Baptista, Olivier Zahm
Abstract: We introduce a new method to jointly reduce the dimension of the input and output space of a high-dimensional function. Choosing a reduced input subspace influences which output subspace is relevant and vice versa. Conventional methods focus on reducing either the input or output space, even though both are often reduced simultaneously in practice. Our coupled approach naturally supports goal-oriented dimension reduction, where either an input or output quantity of interest is prescribed. We consider, in particular, goal-oriented sensor placement and goal-oriented sensitivity analysis, which can be viewed as dimension reduction where the most important output or, respectively, input components are chosen. Both applications present difficult combinatorial optimization problems with expensive objectives such as the expected information gain and Sobol indices. By optimizing gradient-based bounds, we can determine the most informative sensors and most sensitive parameters as the largest diagonal entries of some diagnostic matrices, thus bypassing the combinatorial optimization and objective evaluation.
Authors: Tianyi Ma, Kabir A. Verchand, Richard J. Samworth
Abstract: The minimax risk is often considered as a gold standard against which we can compare specific statistical procedures. Nevertheless, as has been observed recently in robust and heavy-tailed estimation problems, the inherent reduction of the (random) loss to its expectation may entail a significant loss of information regarding its tail behaviour. In an attempt to avoid such a loss, we introduce the notion of a minimax quantile, and seek to articulate its dependence on the quantile level. To this end, we develop high-probability variants of the classical Le Cam and Fano methods, as well as a technique to convert local minimax risk lower bounds to lower bounds on minimax quantiles. To illustrate the power of our framework, we deploy our techniques on several examples, recovering recent results in robust mean estimation and stochastic convex optimisation, as well as obtaining several new results in covariance matrix estimation, sparse linear regression, nonparametric density estimation and isotonic regression. Our overall goal is to argue that minimax quantiles can provide a finer-grained understanding of the difficulty of statistical problems, and that, in wide generality, lower bounds on these quantities can be obtained via user-friendly tools.
Authors: Dan Saattrup Nielsen, Kenneth Enevoldsen, Peter Schneider-Kamp
Abstract: This paper explores the performance of encoder and decoder language models on multilingual Natural Language Understanding (NLU) tasks, with a broad focus on Germanic languages. Building upon the ScandEval benchmark, which initially was restricted to evaluating encoder models, we extend the evaluation framework to include decoder models. We introduce a method for evaluating decoder models on NLU tasks and apply it to the languages Danish, Swedish, Norwegian, Icelandic, Faroese, German, Dutch, and English. Through a series of experiments and analyses, we address key research questions regarding the comparative performance of encoder and decoder models, the impact of NLU task types, and the variation across language resources. Our findings reveal that decoder models can achieve significantly better NLU performance than encoder models, with nuances observed across different tasks and languages. Additionally, we investigate the correlation between decoders and task performance via a UMAP analysis, shedding light on the unique capabilities of decoder and encoder models. This study contributes to a deeper understanding of language model paradigms in NLU tasks and provides valuable insights for model selection and evaluation in multilingual settings.
Authors: Duy Khanh Lam
Abstract: The standard approach for constructing a Mean-Variance portfolio involves estimating parameters for the model using collected samples. However, since the distribution of future data may not resemble that of the training set, the out-of-sample performance of the estimated portfolio is worse than one derived with true parameters, which has prompted several innovations for better estimation. Instead of treating the data without a timing aspect as in the common training-backtest approach, this paper adopts a perspective where data gradually and continuously reveal over time. The original model is recast into an online learning framework, which is free from any statistical assumptions, to propose a dynamic strategy of sequential portfolios such that its empirical utility, Sharpe ratio, and growth rate asymptotically achieve those of the true portfolio, derived with perfect knowledge of the future data. When the distribution of future data has a normal shape, the growth rate of wealth is shown to increase by lifting the portfolio along the efficient frontier through the calibration of risk aversion. Since risk aversion cannot be appropriately predetermined, another proposed algorithm updating this coefficient over time forms a dynamic strategy approaching the optimal empirical Sharpe ratio or growth rate associated with the true coefficient. The performance of these proposed strategies is universally guaranteed under specific stochastic markets. Furthermore, in stationary and ergodic markets, the so-called Bayesian strategy utilizing true conditional distributions, based on observed past market information during investment, almost surely does not perform better than the proposed strategies in terms of empirical utility, Sharpe ratio, or growth rate, which, in contrast, do not rely on conditional distributions.
Authors: Matthew Ashman, Cristiana Diaconu, Adrian Weller, Wessel Bruinsma, Richard E. Turner
Abstract: Equivariant deep learning architectures exploit symmetries in learning problems to improve the sample efficiency of neural-network-based models and their ability to generalise. However, when modelling real-world data, learning problems are often not exactly equivariant, but only approximately. For example, when estimating the global temperature field from weather station observations, local topographical features like mountains break translation equivariance. In these scenarios, it is desirable to construct architectures that can flexibly depart from exact equivariance in a data-driven way. In this paper, we develop a general approach to achieving this using existing equivariant architectures. Our approach is agnostic to both the choice of symmetry group and model architecture, making it widely applicable. We consider the use of approximately equivariant architectures in neural processes (NPs), a popular family of meta-learning models. We demonstrate the effectiveness of our approach on a number of synthetic and real-world regression experiments, demonstrating that approximately equivariant NP models can outperform both their non-equivariant and strictly equivariant counterparts.
Authors: Tao Wu, Xinwen Cao, Chao Wang, Shaojie Qiao, Xingping Xian, Lin Yuan, Canyixing Cui, Yanbing Liu
Abstract: Graph Neural Networks (GNNs) have demonstrated significant application potential in various fields. However, GNNs are still vulnerable to adversarial attacks. Numerous adversarial defense methods on GNNs are proposed to address the problem of adversarial attacks. However, these methods can only serve as a defense before poisoning, but cannot repair poisoned GNN. Therefore, there is an urgent need for a method to repair poisoned GNN. In this paper, we address this gap by introducing the novel concept of model repair for GNNs. We propose a repair framework, Repairing Robustness of Graph Neural Networks via Machine Unlearning (GraphMU), which aims to fine-tune poisoned GNN to forget adversarial samples without the need for complete retraining. We also introduce a unlearning validation method to ensure that our approach effectively forget specified poisoned data. To evaluate the effectiveness of GraphMU, we explore three fine-tuned subgraph construction scenarios based on the available perturbation information: (i) Known Perturbation Ratios, (ii) Known Complete Knowledge of Perturbations, and (iii) Unknown any Knowledge of Perturbations. Our extensive experiments, conducted across four citation datasets and four adversarial attack scenarios, demonstrate that GraphMU can effectively restore the performance of poisoned GNN.
Authors: Guanting Dong, Keming Lu, Chengpeng Li, Tingyu Xia, Bowen Yu, Chang Zhou, Jingren Zhou
Abstract: One core capability of large language models (LLMs) is to follow natural language instructions. However, the issue of automatically constructing high-quality training data to enhance the complex instruction-following abilities of LLMs without manual annotation remains unresolved. In this paper, we introduce AutoIF, the first scalable and reliable method for automatically generating instruction-following training data. AutoIF transforms the validation of instruction-following data quality into code verification, requiring LLMs to generate instructions, the corresponding code to check the correctness of the instruction responses, and unit test samples to verify the code's correctness. Then, execution feedback-based rejection sampling can generate data for Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF) training. AutoIF achieves significant improvements across three training algorithms, SFT, Offline DPO, and Online DPO, when applied to the top open-source LLMs, Qwen2 and LLaMA3, in self-alignment and strong-to-weak distillation settings. Our code is publicly available at https://github.com/QwenLM/AutoIF.
Authors: Yu-Jui Huang, Zachariah Malik
Abstract: This paper approaches the unsupervised learning problem by minimizing the second-order Wasserstein loss (the $W_2$ loss). The minimization is characterized by a distribution-dependent ordinary differential equation (ODE), whose dynamics involves the Kantorovich potential between a current estimated distribution and the true data distribution. A main result shows that the time-marginal law of the ODE converges exponentially to the true data distribution. To prove that the ODE has a unique solution, we first construct explicitly a solution to the associated nonlinear Fokker-Planck equation and show that it coincides with the unique gradient flow for the $W_2$ loss. Based on this, a unique solution to the ODE is built from Trevisan's superposition principle and the exponential convergence results. An Euler scheme is proposed for the distribution-dependent ODE and it is shown to correctly recover the gradient flow for the $W_2$ loss in the limit. An algorithm is designed by following the scheme and applying persistent training, which is natural in our gradient-flow framework. In both low- and high-dimensional experiments, our algorithm converges much faster than and outperforms Wasserstein generative adversarial networks, by increasing the level of persistent training appropriately.
Authors: Guy Yariv, Idan Schwartz, Yossi Adi, Sagie Benaim
Abstract: Commonsense reasoning is fundamentally based on multimodal knowledge. However, existing large language models (LLMs) are primarily trained using textual data only, limiting their ability to incorporate essential visual information. In contrast, Visual Language Models, which excel at visually-oriented tasks, often fail at non-visual tasks such as basic commonsense reasoning. This divergence highlights a critical challenge - the integration of robust visual understanding with foundational text-based language reasoning. To this end, we introduce a method aimed at enhancing LLMs' visual commonsense. Specifically, our method generates multiple images based on the input text prompt and integrates these into the model's decision-making process by mixing their prediction probabilities. To facilitate multimodal grounded language modeling, we employ a late-fusion layer that combines the projected visual features with the output of a pre-trained LLM conditioned on text only. This late-fusion layer enables predictions based on comprehensive image-text knowledge as well as text only when this is required. We evaluate our approach using several visual commonsense reasoning tasks together with traditional NLP tasks, including common sense reasoning and reading comprehension. Our experimental results demonstrate significant superiority over existing baselines. When applied to recent state-of-the-art LLMs (e.g., Llama3), we observe improvements not only in visual common sense but also in traditional NLP benchmarks. Code and models are available under https://github.com/guyyariv/vLMIG.
Authors: Zhepei Wei, Wei-Lin Chen, Yu Meng
Abstract: Retrieval-augmented generation (RAG) has shown promising potential to enhance the accuracy and factuality of language models (LMs). However, imperfect retrievers or noisy corpora can introduce misleading or even erroneous information to the retrieved contents, posing a significant challenge to the generation quality. Existing RAG methods typically address this challenge by directly predicting final answers despite potentially noisy inputs, resulting in an implicit denoising process that is difficult to interpret and verify. On the other hand, the acquisition of explicit denoising supervision is often costly, involving significant human efforts. In this work, we propose InstructRAG, where LMs explicitly learn the denoising process through self-synthesized rationales -- First, we instruct the LM to explain how the ground-truth answer is derived from retrieved documents. Then, these rationales can be used either as demonstrations for in-context learning of explicit denoising or as supervised fine-tuning data to train the model. Compared to standard RAG approaches, InstructRAG requires no additional supervision, allows for easier verification of the predicted answers, and effectively improves generation accuracy. Experiments show InstructRAG consistently outperforms existing RAG methods in both training-free and trainable scenarios, achieving a relative improvement of 8.3% over the best baseline method on average across five knowledge-intensive benchmarks. Extensive analysis indicates that InstructRAG scales well with increased numbers of retrieved documents and consistently exhibits robust denoising ability even in out-of-domain datasets, demonstrating strong generalizability.
Authors: Abrar Anwar, Rohan Gupta, Jesse Thomason
Abstract: Robot evaluations in language-guided, real world settings are time-consuming and often sample only a small space of potential instructions across complex scenes. In this work, we introduce contrast sets for robotics as an approach to make small, but specific, perturbations to otherwise independent, identically distributed (i.i.d.) test instances. We investigate the relationship between experimenter effort to carry out an evaluation and the resulting estimated test performance as well as the insights that can be drawn from performance on perturbed instances. We use contrast sets to characterize policies at reduced experimenter effort in both a simulated manipulation task and a physical robot vision-and-language navigation task. We encourage the use of contrast set evaluations as a more informative alternative to small scale, i.i.d. demonstrations on physical robots, and as a scalable alternative to industry-scale real world evaluations.
Authors: Jialiang Zhao, Yuxiang Ma, Lirui Wang, Edward H. Adelson
Abstract: This paper presents T3: Transferable Tactile Transformers, a framework for tactile representation learning that scales across multi-sensors and multi-tasks. T3 is designed to overcome the contemporary issue that camera-based tactile sensing is extremely heterogeneous, i.e. sensors are built into different form factors, and existing datasets were collected for disparate tasks. T3 captures the shared latent information across different sensor-task pairings by constructing a shared trunk transformer with sensor-specific encoders and task-specific decoders. The pre-training of T3 utilizes a novel Foundation Tactile (FoTa) dataset, which is aggregated from several open-sourced datasets and it contains over 3 million data points gathered from 13 sensors and 11 tasks. FoTa is the largest and most diverse dataset in tactile sensing to date and it is made publicly available in a unified format. Across various sensors and tasks, experiments show that T3 pre-trained with FoTa achieved zero-shot transferability in certain sensor-task pairings, can be further fine-tuned with small amounts of domain-specific data, and its performance scales with bigger network sizes. T3 is also effective as a tactile encoder for long horizon contact-rich manipulation. Results from sub-millimeter multi-pin electronics insertion tasks show that T3 achieved a task success rate 25% higher than that of policies trained with tactile encoders trained from scratch, or 53% higher than without tactile sensing. Data, code, and model checkpoints are open-sourced at https://t3.alanz.info.
URLs: https://t3.alanz.info.
Authors: Jirui Qi, Gabriele Sarti, Raquel Fern\'andez, Arianna Bisazza
Abstract: Ensuring the verifiability of model answers is a fundamental challenge for retrieval-augmented generation (RAG) in the question answering (QA) domain. Recently, self-citation prompting was proposed to make large language models (LLMs) generate citations to supporting documents along with their answers. However, self-citing LLMs often struggle to match the required format, refer to non-existent sources, and fail to faithfully reflect LLMs' context usage throughout the generation. In this work, we present MIRAGE --Model Internals-based RAG Explanations -- a plug-and-play approach using model internals for faithful answer attribution in RAG applications. MIRAGE detects context-sensitive answer tokens and pairs them with retrieved documents contributing to their prediction via saliency methods. We evaluate our proposed approach on a multilingual extractive QA dataset, finding high agreement with human answer attribution. On open-ended QA, MIRAGE achieves citation quality and efficiency comparable to self-citation while also allowing for a finer-grained control of attribution parameters. Our qualitative evaluation highlights the faithfulness of MIRAGE's attributions and underscores the promising application of model internals for RAG answer attribution.
Authors: Mihai-Valentin Dumitru, Vlad-Andrei B\u{a}doiu, Costin Raiciu
Abstract: Languages such as P4 and NPL have enabled a wide and diverse range of networking applications that take advantage of programmable dataplanes. However, software development in these languages is difficult. To address this issue, high-level languages have been designed to offer programmers powerful abstractions that reduce the time, effort and domain-knowledge required for developing networking applications. These languages are then translated by a compiler into P4/NPL code. Inspired by the recent success of Large Language Models (LLMs) in the task of code generation, we propose to raise the level of abstraction even higher, employing LLMs to translate prose into high-level networking code. We analyze the problem, focusing on the motivation and opportunities, as well as the challenges involved and sketch out a roadmap for the development of a system that can generate high-level dataplane code from natural language instructions. We present some promising preliminary results on generating Lucid code from natural language.
Authors: Md Ibrahim Ibne Alam, Parikshit Ram, Soham Dan, Horst Samulowitz, Koushik Kar
Abstract: Large Language Models (LLMs) have been observed to perform well on a wide range of downstream tasks when fine-tuned on domain-specific data. However, such data may not be readily available in many applications, motivating zero-shot or few-shot approaches using domain-adjacent models. While several fine-tuned models for various tasks are available, finding an appropriate domain-adjacent model for a given task is often not straight forward. In this paper, we study DAFT-E, a framework that utilizes an Ensemble of Domain-Adjacent Fine-Tuned Foundation Models for few-shot problems. We show that for zero-shot problems, this ensembling method provides an accuracy performance close to that of the single best model. With few-shot problems, this performance improves further, at which point DEFT-E can outperform any single domain-adjacent model while requiring much less data for domain-specific fine-tuning.
Authors: Zhouzhou Gu, Mathieu Lauri\`ere, Sebastian Merkel, Jonathan Payne
Abstract: We propose and compare new global solution algorithms for continuous time heterogeneous agent economies with aggregate shocks. First, we approximate the agent distribution so that equilibrium in the economy can be characterized by a high, but finite, dimensional non-linear partial differential equation. We consider different approximations: discretizing the number of agents, discretizing the agent state variables, and projecting the distribution onto a finite set of basis functions. Second, we represent the value function using a neural network and train it to solve the differential equation using deep learning tools. We refer to the solution as an Economic Model Informed Neural Network (EMINN). The main advantage of this technique is that it allows us to find global solutions to high dimensional, non-linear problems. We demonstrate our algorithm by solving important models in the macroeconomics and spatial literatures (e.g. Krusell and Smith (1998), Khan and Thomas (2007), Bilal (2023)).
Authors: Amir Saki, Usef Faghihi
Abstract: In this paper, we generalize the Pearl and Neyman-Rubin methodologies in causal inference by introducing a generalized approach that incorporates fuzzy logic. Indeed, we introduce a fuzzy causal inference approach that consider both the vagueness and imprecision inherent in data, as well as the subjective human perspective characterized by fuzzy terms such as 'high', 'medium', and 'low'. To do so, we introduce two fuzzy causal effect formulas: the Fuzzy Average Treatment Effect (FATE) and the Generalized Fuzzy Average Treatment Effect (GFATE), together with their normalized versions: NFATE and NGFATE. When dealing with a binary treatment variable, our fuzzy causal effect formulas coincide with classical Average Treatment Effect (ATE) formula, that is a well-established and popular metric in causal inference. In FATE, all values of the treatment variable are considered equally important. In contrast, GFATE takes into account the rarity and frequency of these values. We show that for linear Structural Equation Models (SEMs), the normalized versions of our formulas, NFATE and NGFATE, are equivalent to ATE. Further, we provide identifiability criteria for these formulas and show their stability with respect to minor variations in the fuzzy subsets and the probability distributions involved. This ensures the robustness of our approach in handling small perturbations in the data. Finally, we provide several experimental examples to empirically validate and demonstrate the practical application of our proposed fuzzy causal inference methods.
Authors: Rushikesh Zawar, Shaurya Dewan, Andrew F. Luo, Margaret M. Henderson, Michael J. Tarr, Leila Wehbe
Abstract: Understanding the semantics of visual scenes is a fundamental challenge in Computer Vision. A key aspect of this challenge is that objects sharing similar semantic meanings or functions can exhibit striking visual differences, making accurate identification and categorization difficult. Recent advancements in text-to-image frameworks have led to models that implicitly capture natural scene statistics. These frameworks account for the visual variability of objects, as well as complex object co-occurrences and sources of noise such as diverse lighting conditions. By leveraging large-scale datasets and cross-attention conditioning, these models generate detailed and contextually rich scene representations. This capability opens new avenues for improving object recognition and scene understanding in varied and challenging environments. Our work presents StableSemantics, a dataset comprising 224 thousand human-curated prompts, processed natural language captions, over 2 million synthetic images, and 10 million attention maps corresponding to individual noun chunks. We explicitly leverage human-generated prompts that correspond to visually interesting stable diffusion generations, provide 10 generations per phrase, and extract cross-attention maps for each image. We explore the semantic distribution of generated images, examine the distribution of objects within images, and benchmark captioning and open vocabulary segmentation methods on our data. To the best of our knowledge, we are the first to release a diffusion dataset with semantic attributions. We expect our proposed dataset to catalyze advances in visual semantic understanding and provide a foundation for developing more sophisticated and effective visual models. Website: https://stablesemantics.github.io/StableSemantics
Authors: Baiqi Li, Zhiqiu Lin, Deepak Pathak, Jiayao Li, Yixin Fei, Kewen Wu, Tiffany Ling, Xide Xia, Pengchuan Zhang, Graham Neubig, Deva Ramanan
Abstract: While text-to-visual models now produce photo-realistic images and videos, they struggle with compositional text prompts involving attributes, relationships, and higher-order reasoning such as logic and comparison. In this work, we conduct an extensive human study on GenAI-Bench to evaluate the performance of leading image and video generation models in various aspects of compositional text-to-visual generation. We also compare automated evaluation metrics against our collected human ratings and find that VQAScore -- a metric measuring the likelihood that a VQA model views an image as accurately depicting the prompt -- significantly outperforms previous metrics such as CLIPScore. In addition, VQAScore can improve generation in a black-box manner (without finetuning) via simply ranking a few (3 to 9) candidate images. Ranking by VQAScore is 2x to 3x more effective than other scoring methods like PickScore, HPSv2, and ImageReward at improving human alignment ratings for DALL-E 3 and Stable Diffusion, especially on compositional prompts that require advanced visio-linguistic reasoning. We will release a new GenAI-Rank benchmark with over 40,000 human ratings to evaluate scoring metrics on ranking images generated from the same prompt. Lastly, we discuss promising areas for improvement in VQAScore, such as addressing fine-grained visual details. We will release all human ratings (over 80,000) to facilitate scientific benchmarking of both generative models and automated metrics.
Authors: Taiming Lu, Philipp Koehn
Abstract: This paper investigates the propagation of harmful information in multilingual large language models (LLMs) and evaluates the efficacy of various unlearning methods. We demonstrate that fake information, regardless of the language it is in, once introduced into these models through training data, can spread across different languages, compromising the integrity and reliability of the generated content. Our findings reveal that standard unlearning techniques, which typically focus on English data, are insufficient in mitigating the spread of harmful content in multilingual contexts and could inadvertently reinforce harmful content across languages. We show that only by addressing harmful responses in both English and the original language of the harmful data can we effectively eliminate generations for all languages. This underscores the critical need for comprehensive unlearning strategies that consider the multilingual nature of modern LLMs to enhance their safety and reliability across diverse linguistic landscapes.
Authors: Neel Patel, Alexander Wong, Ashkan Ebadi
Abstract: Tuberculosis persists as a global health crisis, especially in resource-limited populations and remote regions, with more than 10 million individuals newly infected annually. It stands as a stark symbol of inequity in public health. Tuberculosis impacts roughly a quarter of the global populace, with the majority of cases concentrated in eight countries, accounting for two-thirds of all tuberculosis infections. Although a severe ailment, tuberculosis is both curable and manageable. However, early detection and screening of at-risk populations are imperative. Chest x-ray stands as the predominant imaging technique utilized in tuberculosis screening efforts. However, x-ray screening necessitates skilled radiologists, a resource often scarce, particularly in remote regions with limited resources. Consequently, there is a pressing need for artificial intelligence (AI)-powered systems to support clinicians and healthcare providers in swift screening. However, training a reliable AI model necessitates large-scale high-quality data, which can be difficult and costly to acquire. Inspired by these challenges, in this work, we introduce an explainable self-supervised self-train learning network tailored for tuberculosis case screening. The network achieves an outstanding overall accuracy of 98.14% and demonstrates high recall and precision rates of 95.72% and 99.44%, respectively, in identifying tuberculosis cases, effectively capturing clinically significant features.
Authors: Nayef Shkeir, Tobias Sch\"afer, Tobias Grafke
Abstract: Matrix evolution equations occur in many applications, such as dynamical Lyapunov/Sylvester systems or Riccati equations in optimization and stochastic control, machine learning or data assimilation. In many cases, their tightest stability condition is coming from a linear term. Exponential time differencing (ETD) is known to produce highly stable numerical schemes by treating the linear term in an exact fashion. In particular, for stiff problems, ETD methods are a method of choice. We propose an extension of the class of ETD algorithms to matrix-valued dynamical equations. This allows us to produce highly efficient and stable integration schemes. We show their efficiency and applicability for a variety of real-world problems, from geophysical applications to dynamical problems in machine learning.
Authors: Guanhua Wang, Olatunji Ruwase, Bing Xie, Yuxiong He
Abstract: Model checkpoints are critical Deep Learning (DL) artifacts that enable fault tolerance for training and downstream applications, such as inference. However, writing checkpoints to persistent storage, and other I/O aspects of DL training, are mostly ignored by compute-focused optimization efforts for faster training of rapidly growing models and datasets. Towards addressing this imbalance, we propose FastPersist to accelerate checkpoint creation in DL training. FastPersist combines three novel techniques: (i) NVMe optimizations for faster checkpoint writes to SSDs, (ii) efficient write parallelism using the available SSDs in training environments, and (iii) overlapping checkpointing with independent training computations. Our evaluation using real world dense and sparse DL models shows that FastPersist creates checkpoints in persistent storage up to 116x faster than baseline, and enables per-iteration checkpointing with negligible overhead.
Authors: Pablo Moriano, Steven C. Hespeler, Mingyan Li, Robert A. Bridges
Abstract: Vehicular controller area networks (CANs) are susceptible to masquerade attacks by malicious adversaries. In masquerade attacks, adversaries silence a targeted ID and then send malicious frames with forged content at the expected timing of benign frames. As masquerade attacks could seriously harm vehicle functionality and are the stealthiest attacks to detect in CAN, recent work has devoted attention to compare frameworks for detecting masquerade attacks in CAN. However, most existing works report offline evaluations using CAN logs already collected using simulations that do not comply with domain's real-time constraints. Here we contribute to advance the state of the art by introducing a benchmark study of four different non-deep learning (DL)-based unsupervised online intrusion detection systems (IDS) for masquerade attacks in CAN. Our approach differs from existing benchmarks in that we analyze the effect of controlling streaming data conditions in a sliding window setting. In doing so, we use realistic masquerade attacks being replayed from the ROAD dataset. We show that although benchmarked IDS are not effective at detecting every attack type, the method that relies on detecting changes at the hierarchical structure of clusters of time series produces the best results at the expense of higher computational overhead. We discuss limitations, open challenges, and how the benchmarked methods can be used for practical unsupervised online CAN IDS for masquerade attacks.
Authors: Amelie Gyrard, Seyedali Mohammadi, Manas Gaur, Antonio Kung
Abstract: Sustainable Development Goals (SDGs) give the UN a road map for development with Agenda 2030 as a target. SDG3 "Good Health and Well-Being" ensures healthy lives and promotes well-being for all ages. Digital technologies can support SDG3. Burnout and even depression could be reduced by encouraging better preventive health. Due to the lack of patient knowledge and focus to take care of their health, it is necessary to help patients before it is too late. New trends such as positive psychology and mindfulness are highly encouraged in the USA. Digital Twin (DT) can help with the continuous monitoring of emotion using physiological signals (e.g., collected via wearables). Digital twins facilitate monitoring and provide constant health insight to improve quality of life and well-being with better personalization. Healthcare DT challenges are standardizing data formats, communication protocols, and data exchange mechanisms. To achieve those data integration and knowledge challenges, we designed the Mental Health Knowledge Graph (ontology and dataset) to boost mental health. The Knowledge Graph (KG) acquires knowledge from ontology-based mental health projects classified within the LOV4IoT ontology catalog (Emotion, Depression, and Mental Health). Furthermore, the KG is mapped to standards (e.g., ontologies) when possible. Standards from ETSI SmartM2M, ITU/WHO, ISO, W3C, NIST, and IEEE are relevant to mental health.
Authors: Yufang Hou, Alessandra Pascale, Javier Carnerero-Cano, Tigran Tchrakian, Radu Marinescu, Elizabeth Daly, Inkit Padhi, Prasanna Sattigeri
Abstract: Retrieval-augmented generation (RAG) has emerged as a promising solution to mitigate the limitations of large language models (LLMs), such as hallucinations and outdated information. However, it remains unclear how LLMs handle knowledge conflicts arising from different augmented retrieved passages, especially when these passages originate from the same source and have equal trustworthiness. In this work, we conduct a comprehensive evaluation of LLM-generated answers to questions that have varying answers based on contradictory passages from Wikipedia, a dataset widely regarded as a high-quality pre-training resource for most LLMs. Specifically, we introduce WikiContradict, a benchmark consisting of 253 high-quality, human-annotated instances designed to assess LLM performance when augmented with retrieved passages containing real-world knowledge conflicts. We benchmark a diverse range of both closed and open-source LLMs under different QA scenarios, including RAG with a single passage, and RAG with 2 contradictory passages. Through rigorous human evaluations on a subset of WikiContradict instances involving 5 LLMs and over 3,500 judgements, we shed light on the behaviour and limitations of these models. For instance, when provided with two passages containing contradictory facts, all models struggle to generate answers that accurately reflect the conflicting nature of the context, especially for implicit conflicts requiring reasoning. Since human evaluation is costly, we also introduce an automated model that estimates LLM performance using a strong open-source language model, achieving an F-score of 0.8. Using this automated metric, we evaluate more than 1,500 answers from seven LLMs across all WikiContradict instances. To facilitate future work, we release WikiContradict on: https://ibm.biz/wikicontradict.
Authors: Adriano Pastore, Adri\'an Agust\'in de Dios, \'Alvaro Valcarce
Abstract: We present a Reinforcement Learning (RL) approach to the problem of controlling the Discontinuous Reception (DRX) policy from a Base Transceiver Station (BTS) in a cellular network. We do so by means of optimally timing the transmission of fast Layer-2 signaling messages (a.k.a. Medium Access Layer (MAC) Control Elements (CEs) as specified in 5G New Radio). Unlike more conventional approaches to DRX optimization, which rely on fine-tuning the values of DRX timers, we assess the gains that can be obtained solely by means of this MAC CE signalling. For the simulation part, we concentrate on traffic types typically encountered in Extended Reality (XR) applications, where the need for battery drain minimization and overheating mitigation are particularly pressing. Both 3GPP 5G New Radio (5G NR) compliant and non-compliant ("beyond 5G") MAC CEs are considered. Our simulation results show that our proposed technique strikes an improved trade-off between latency and energy savings as compared to conventional timer-based approaches that are characteristic of most current implementations. Specifically, our RL-based policy can nearly halve the active time for a single User Equipment (UE) with respect to a na\"ive MAC CE transmission policy, and still achieve near 20% active time reduction for 9 simultaneously served UEs.
Authors: Rishabh Anand, Chaitanya K. Joshi, Alex Morehead, Arian R. Jamasb, Charles Harris, Simon V. Mathis, Kieran Didi, Bryan Hooi, Pietro Li\`o
Abstract: We introduce RNA-FrameFlow, the first generative model for 3D RNA backbone design. We build upon SE(3) flow matching for protein backbone generation and establish protocols for data preparation and evaluation to address unique challenges posed by RNA modeling. We formulate RNA structures as a set of rigid-body frames and associated loss functions which account for larger, more conformationally flexible RNA backbones (13 atoms per nucleotide) vs. proteins (4 atoms per residue). Toward tackling the lack of diversity in 3D RNA datasets, we explore training with structural clustering and cropping augmentations. Additionally, we define a suite of evaluation metrics to measure whether the generated RNA structures are globally self-consistent (via inverse folding followed by forward folding) and locally recover RNA-specific structural descriptors. The most performant version of RNA-FrameFlow generates locally realistic RNA backbones of 40-150 nucleotides, over 40% of which pass our validity criteria as measured by a self-consistency TM-score >= 0.45, at which two RNAs have the same global fold. Open-source code: https://github.com/rish-16/rna-backbone-design
Authors: Kyoka Ono, Simon A. Lee
Abstract: Recent research has explored how Language Models (LMs) can be used for feature representation and prediction in tabular machine learning tasks. This involves employing text serialization and supervised fine-tuning (SFT) techniques. Despite the simplicity of these techniques, significant gaps remain in our understanding of the applicability and reliability of LMs in this context. Our study assesses how emerging LM technologies compare with traditional paradigms in tabular machine learning and evaluates the feasibility of adopting similar approaches with these advanced technologies. At the data level, we investigate various methods of data representation and curation of serialized tabular data, exploring their impact on prediction performance. At the classification level, we examine whether text serialization combined with LMs enhances performance on tabular datasets (e.g. class imbalance, distribution shift, biases, and high dimensionality), and assess whether this method represents a state-of-the-art (SOTA) approach for addressing tabular machine learning challenges. Our findings reveal current pre-trained models should not replace conventional approaches.
Authors: Nyaga Fred, I. O. Temkin
Abstract: Software engineering (SE) is a dynamic field that involves multiple phases all of which are necessary to develop sustainable software systems. Machine learning (ML), a branch of artificial intelligence (AI), has drawn a lot of attention in recent years thanks to its ability to analyze massive volumes of data and extract useful patterns from data. Several studies have focused on examining, categorising, and assessing the application of ML in SE processes. We conducted a literature review on primary studies to address this gap. The study was carried out following the objective and the research questions to explore the current state of the art in applying machine learning techniques in software engineering processes. The review identifies the key areas within software engineering where ML has been applied, including software quality assurance, software maintenance, software comprehension, and software documentation. It also highlights the specific ML techniques that have been leveraged in these domains, such as supervised learning, unsupervised learning, and deep learning. Keywords: machine learning, deep learning, software engineering, natural language processing, source code
Authors: Junhyung Lyle Kim, Nai-Hui Chia, Anastasios Kyrillidis
Abstract: Solving systems of linear equations is a fundamental problem, but it can be computationally intensive for classical algorithms in high dimensions. Existing quantum algorithms can achieve exponential speedups for the quantum linear system problem (QLSP) in terms of the problem dimension, but even such a theoretical advantage is bottlenecked by the condition number of the coefficient matrix. In this work, we propose a new quantum algorithm for QLSP inspired by the classical proximal point algorithm (PPA). Our proposed method can be viewed as a meta-algorithm that allows inverting a modified matrix via an existing \texttt{QLSP\_solver}, thereby directly approximating the solution vector instead of approximating the inverse of the coefficient matrix. By carefully choosing the step size $\eta$, the proposed algorithm can effectively precondition the linear system to mitigate the dependence on condition numbers that hindered the applicability of previous approaches.
Authors: Guy Kornowski, Ohad Shamir
Abstract: Recent results show that vanilla gradient descent can be accelerated for smooth convex objectives, merely by changing the stepsize sequence. We show that this can lead to surprisingly large errors indefinitely, and therefore ask: Is there any stepsize schedule for gradient descent that accelerates the classic $\mathcal{O}(1/T)$ convergence rate, at \emph{any} stopping time $T$?
Authors: Yamin Arefeen, Brett Levac, Zach Stoebner, Jonathan Tamir
Abstract: Implicit Neural Representations (INRs) are a learning-based approach to accelerate Magnetic Resonance Imaging (MRI) acquisitions, particularly in scan-specific settings when only data from the under-sampled scan itself are available. Previous work demonstrates that INRs improve rapid MRI through inherent regularization imposed by neural network architectures. Typically parameterized by fully-connected neural networks, INRs support continuous image representations by taking a physical coordinate location as input and outputting the intensity at that coordinate. Previous work has applied unlearned regularization priors during INR training and have been limited to 2D or low-resolution 3D acquisitions. Meanwhile, diffusion based generative models have received recent attention as they learn powerful image priors decoupled from the measurement model. This work proposes INFusion, a technique that regularizes the optimization of INRs from under-sampled MR measurements with pre-trained diffusion models for improved image reconstruction. In addition, we propose a hybrid 3D approach with our diffusion regularization that enables INR application on large-scale 3D MR datasets. 2D experiments demonstrate improved INR training with our proposed diffusion regularization, and 3D experiments demonstrate feasibility of INR training with diffusion regularization on 3D matrix sizes of 256 by 256 by 80.
Authors: Hamdireza Rouzegar, Masoud Makrehchi
Abstract: This study investigates how LLMs, specifically GPT-3.5 and GPT-4, can develop tailored questions for Grade 9 math, aligning with active learning principles. By utilizing an iterative method, these models adjust questions based on difficulty and content, responding to feedback from a simulated 'student' model. A novel aspect of the research involved using GPT-4 as a 'teacher' to create complex questions, with GPT-3.5 as the 'student' responding to these challenges. This setup mirrors active learning, promoting deeper engagement. The findings demonstrate GPT-4's superior ability to generate precise, challenging questions and notable improvements in GPT-3.5's ability to handle more complex problems after receiving instruction from GPT-4. These results underscore the potential of LLMs to mimic and enhance active learning scenarios, offering a promising path for AI in customized education. This research contributes to understanding how AI can support personalized learning experiences, highlighting the need for further exploration in various educational contexts
Authors: Jongyoon Song, Sangwon Yu, Sungroh Yoon
Abstract: In this paper, we identify a new category of bias that induces input-conflicting hallucinations, where large language models (LLMs) generate responses inconsistent with the content of the input context. This issue we have termed the false negative problem refers to the phenomenon where LLMs are predisposed to return negative judgments when assessing the correctness of a statement given the context. In experiments involving pairs of statements that contain the same information but have contradictory factual directions, we observe that LLMs exhibit a bias toward false negatives. Specifically, the model presents greater overconfidence when responding with False. Furthermore, we analyze the relationship between the false negative problem and context and query rewriting and observe that both effectively tackle false negatives in LLMs.
Authors: Tim Tsz-Kit Lau, Weijian Li, Chenwei Xu, Han Liu, Mladen Kolar
Abstract: Modern deep neural networks often require distributed training with many workers due to their large size. As worker numbers increase, communication overheads become the main bottleneck in data-parallel minibatch stochastic gradient methods with per-iteration gradient synchronization. Local gradient methods like Local SGD reduce communication by only syncing after several local steps. Despite understanding their convergence in i.i.d. and heterogeneous settings and knowing the importance of batch sizes for efficiency and generalization, optimal local batch sizes are difficult to determine. We introduce adaptive batch size strategies for local gradient methods that increase batch sizes adaptively to reduce minibatch gradient variance. We provide convergence guarantees under homogeneous data conditions and support our claims with image classification experiments, demonstrating the effectiveness of our strategies in training and generalization.
Authors: Yanke Song, Sohom Bhattacharya, Pragya Sur
Abstract: This paper establishes the generalization error of pooled min-$\ell_2$-norm interpolation in transfer learning where data from diverse distributions are available. Min-norm interpolators emerge naturally as implicit regularized limits of modern machine learning algorithms. Previous work characterized their out-of-distribution risk when samples from the test distribution are unavailable during training. However, in many applications, a limited amount of test data may be available during training, yet properties of min-norm interpolation in this setting are not well-understood. We address this gap by characterizing the bias and variance of pooled min-$\ell_2$-norm interpolation under covariate and model shifts. The pooled interpolator captures both early fusion and a form of intermediate fusion. Our results have several implications: under model shift, for low signal-to-noise ratio (SNR), adding data always hurts. For higher SNR, transfer learning helps as long as the shift-to-signal (SSR) ratio lies below a threshold that we characterize explicitly. By consistently estimating these ratios, we provide a data-driven method to determine: (i) when the pooled interpolator outperforms the target-based interpolator, and (ii) the optimal number of target samples that minimizes the generalization error. Under covariate shift, if the source sample size is small relative to the dimension, heterogeneity between between domains improves the risk, and vice versa. We establish a novel anisotropic local law to achieve these characterizations, which may be of independent interest in random matrix theory. We supplement our theoretical characterizations with comprehensive simulations that demonstrate the finite-sample efficacy of our results.
Authors: Jie Feng, Jun Zhang, Junbo Yan, Xin Zhang, Tianjian Ouyang, Tianhui Liu, Yuwei Du, Siqi Guo, Yong Li
Abstract: Large language models (LLMs) with powerful generalization ability has been widely used in many domains. A systematic and reliable evaluation of LLMs is a crucial step in their development and applications, especially for specific professional fields. In the urban domain, there have been some early explorations about the usability of LLMs, but a systematic and scalable evaluation benchmark is still lacking. The challenge in constructing a systematic evaluation benchmark for the urban domain lies in the diversity of data and scenarios, as well as the complex and dynamic nature of cities. In this paper, we propose CityBench, an interactive simulator based evaluation platform, as the first systematic evaluation benchmark for the capability of LLMs for urban domain. First, we build CitySim to integrate the multi-source data and simulate fine-grained urban dynamics. Based on CitySim, we design 7 tasks in 2 categories of perception-understanding and decision-making group to evaluate the capability of LLMs as city-scale world model for urban domain. Due to the flexibility and ease-of-use of CitySim, our evaluation platform CityBench can be easily extended to any city in the world. We evaluate 13 well-known LLMs including open source LLMs and commercial LLMs in 13 cities around the world. Extensive experiments demonstrate the scalability and effectiveness of proposed CityBench and shed lights for the future development of LLMs in urban domain. The dataset, benchmark and source codes are openly accessible to the research community via https://github.com/tsinghua-fib-lab/CityBench
Authors: Jie Feng, Yuwei Du, Tianhui Liu, Siqi Guo, Yuming Lin, Yong Li
Abstract: Large language models(LLMs) with powerful language generation and reasoning capabilities have already achieved success in many domains, e.g., math and code generation. However, due to the lacking of physical world's corpus and knowledge during training, they usually fail to solve many real-life tasks in the urban space. In this paper, we propose CityGPT, a systematic framework for enhancing the capability of LLMs on understanding urban space and solving the related urban tasks by building a city-scale world model in the model. First, we construct a diverse instruction tuning dataset CityInstruction for injecting urban knowledge and enhancing spatial reasoning capability effectively. By using a mixture of CityInstruction and general instruction data, we fine-tune various LLMs (e.g., ChatGLM3-6B, Qwen1.5 and LLama3 series) to enhance their capability without sacrificing general abilities. To further validate the effectiveness of proposed methods, we construct a comprehensive benchmark CityEval to evaluate the capability of LLMs on diverse urban scenarios and problems. Extensive evaluation results demonstrate that small LLMs trained with CityInstruction can achieve competitive performance with commercial LLMs in the comprehensive evaluation of CityEval. The source codes are openly accessible to the research community via https://github.com/tsinghua-fib-lab/CityGPT.
Authors: Yupei Zhang, Xiaofei Wang, Fangliangzi Meng, Jin Tang, Chao Li
Abstract: Multi-modal learning plays a crucial role in cancer diagnosis and prognosis. Current deep learning based multi-modal approaches are often limited by their abilities to model the complex correlations between genomics and histology data, addressing the intrinsic complexity of tumour ecosystem where both tumour and microenvironment contribute to malignancy. We propose a biologically interpretative and robust multi-modal learning framework to efficiently integrate histology images and genomics by decomposing the feature subspace of histology images and genomics, reflecting distinct tumour and microenvironment features. To enhance cross-modal interactions, we design a knowledge-driven subspace fusion scheme, consisting of a cross-modal deformable attention module and a gene-guided consistency strategy. Additionally, in pursuit of dynamically optimizing the subspace knowledge, we further propose a novel gradient coordination learning strategy. Extensive experiments demonstrate the effectiveness of the proposed method, outperforming state-of-the-art techniques in three downstream tasks of glioma diagnosis, tumour grading, and survival analysis. Our code is available at https://github.com/helenypzhang/Subspace-Multimodal-Learning.
URLs: https://github.com/helenypzhang/Subspace-Multimodal-Learning.
Authors: Qisheng Jiang, Lei Jia, Chundong Wang
Abstract: Graph neural networks (GNNs) gain wide popularity. Large graphs with high-dimensional features become common and training GNNs on them is non-trivial on an ordinary machine. Given a gigantic graph, even sample-based GNN training cannot work efficiently, since it is difficult to keep the graph's entire data in memory during the training process. Leveraging a solid-state drive (SSD) or other storage devices to extend the memory space has been studied in training GNNs. Memory and I/Os are hence critical for effectual disk-based training. We find that state-of-the-art (SoTA) disk-based GNN training systems severely suffer from issues like the memory contention between a graph's topological and feature data, and severe I/O congestion upon loading data from SSD for training. We accordingly develop GNNDrive. GNNDrive 1) minimizes the memory footprint with holistic buffer management across sampling and extracting, and 2) avoids I/O congestion through a strategy of asynchronous feature extraction. It also avoids costly data preparation on the critical path and makes the most of software and hardware resources. Experiments show that GNNDrive achieves superior performance. For example, when training with the Papers100M dataset and GraphSAGE model, GNNDrive is faster than SoTA PyG+, Ginex, and MariusGNN by 16.9x, 2.6x, and 2.7x, respectively.
Authors: Qianhui Wan, Zecheng Zhang, Liheng Jiang, Zhaoqi Wang, Yan Zhou
Abstract: Image anomaly detection is a popular research direction, with many methods emerging in recent years due to rapid advancements in computing. The use of artificial intelligence for image anomaly detection has been widely studied. By analyzing images of athlete posture and movement, it is possible to predict injury status and suggest necessary adjustments. Most existing methods rely on convolutional networks to extract information from irrelevant pixel data, limiting model accuracy. This paper introduces a network combining Residual Network (ResNet) and Bidirectional Gated Recurrent Unit (BiGRU), which can predict potential injury types and provide early warnings by analyzing changes in muscle and bone poses from video images. To address the high complexity of this network, the Sparrow search algorithm was used for optimization. Experiments conducted on four datasets demonstrated that our model has the smallest error in image anomaly detection compared to other models, showing strong adaptability. This provides a new approach for anomaly detection and predictive analysis in images, contributing to the sustainable development of human health and performance.
Authors: Yuepeng Yang, Cong Ma
Abstract: The Rasch model, a classical model in the item response theory, is widely used in psychometrics to model the relationship between individuals' latent traits and their binary responses on assessments or questionnaires. In this paper, we introduce a new likelihood-based estimator -- random pairing maximum likelihood estimator ($\mathsf{RP\text{-}MLE}$) and its bootstrapped variant multiple random pairing MLE ($\mathsf{MRP\text{-}MLE}$) that faithfully estimate the item parameters in the Rasch model. The new estimators have several appealing features compared to existing ones. First, both work for sparse observations, an increasingly important scenario in the big data era. Second, both estimators are provably minimax optimal in terms of finite sample $\ell_{\infty}$ estimation error. Lastly, $\mathsf{RP\text{-}MLE}$ admits precise distributional characterization that allows uncertainty quantification on the item parameters, e.g., construction of confidence intervals of the item parameters. The main idea underlying $\mathsf{RP\text{-}MLE}$ and $\mathsf{MRP\text{-}MLE}$ is to randomly pair user-item responses to form item-item comparisons. This is carefully designed to reduce the problem size while retaining statistical independence. We also provide empirical evidence of the efficacy of the two new estimators using both simulated and real data.
Authors: Mahammed Kamruzzaman, Gene Louis Kim
Abstract: Persona assignment has become a common strategy for customizing LLM use to particular tasks and contexts. In this study, we explore how perceptions of different nations change when LLMs are assigned specific nationality personas. We assign 193 different nationality personas (e.g., an American person) to four LLMs and examine how the LLM perceptions of countries change. We find that all LLM-persona combinations tend to favor Western European nations, though nation-personas push LLM behaviors to focus more on and view more favorably the nation-persona's own region. Eastern European, Latin American, and African nations are viewed more negatively by different nationality personas. Our study provides insight into how biases and stereotypes are realized within LLMs when adopting different national personas. In line with the "Blueprint for an AI Bill of Rights", our findings underscore the critical need for developing mechanisms to ensure LLMs uphold fairness and not over-generalize at a global scale.
Authors: Keita Tokuda, Yuichi Katori
Abstract: Nonlinear and non-stationary processes are prevalent in various natural and physical phenomena, where system dynamics can change qualitatively due to bifurcation phenomena. Traditional machine learning methods have advanced our ability to learn and predict such systems from observed time series data. However, predicting the behavior of systems with temporal parameter variations without knowledge of true parameter values remains a significant challenge. This study leverages the reservoir computing framework to address this problem by unsupervised extraction of slowly varying system parameters from time series data. We propose a model architecture consisting of a slow reservoir with long timescale internal dynamics and a fast reservoir with short timescale dynamics. The slow reservoir extracts the temporal variation of system parameters, which are then used to predict unknown bifurcations in the fast dynamics. Through experiments using data generated from chaotic dynamical systems, we demonstrate the ability to predict bifurcations not present in the training data. Our approach shows potential for applications in fields such as neuroscience, material science, and weather prediction, where slow dynamics influencing qualitative changes are often unobservable.
Authors: Md Shahriar Rahim Siddiqui, Arman Rahmim, Eldad Haber
Abstract: Optimal experimental design is a well studied field in applied science and engineering. Techniques for estimating such a design are commonly used within the framework of parameter estimation. Nonetheless, in recent years parameter estimation techniques are changing rapidly with the introduction of deep learning techniques to replace traditional estimation methods. This in turn requires the adaptation of optimal experimental design that is associated with these new techniques. In this paper we investigate a new experimental design methodology that uses deep learning. We show that the training of a network as a Likelihood Free Estimator can be used to significantly simplify the design process and circumvent the need for the computationally expensive bi-level optimization problem that is inherent in optimal experimental design for non-linear systems. Furthermore, deep design improves the quality of the recovery process for parameter estimation problems. As proof of concept we apply our methodology to two different systems of Ordinary Differential Equations.
Authors: Yuan Wang, Zhiyu Li, Changshuo Zhang, Sirui Chen, Xiao Zhang, Jun Xu, Quan Lin
Abstract: Recommender systems have been widely used in e-commerce, and re-ranking models are playing an increasingly significant role in the domain, which leverages the inter-item influence and determines the final recommendation lists. Online learning methods keep updating a deployed model with the latest available samples to capture the shifting of the underlying data distribution in e-commerce. However, they depend on the availability of real user feedback, which may be delayed by hours or even days, such as item purchases, leading to a lag in model enhancement. In this paper, we propose a novel extension of online learning methods for re-ranking modeling, which we term LAST, an acronym for Learning At Serving Time. It circumvents the requirement of user feedback by using a surrogate model to provide the instructional signal needed to steer model improvement. Upon receiving an online request, LAST finds and applies a model modification on the fly before generating a recommendation result for the request. The modification is request-specific and transient. It means the modification is tailored to and only to the current request to capture the specific context of the request. After a request, the modification is discarded, which helps to prevent error propagation and stabilizes the online learning procedure since the predictions of the surrogate model may be inaccurate. Most importantly, as a complement to feedback-based online learning methods, LAST can be seamlessly integrated into existing online learning systems to create a more adaptive and responsive recommendation experience. Comprehensive experiments, both offline and online, affirm that LAST outperforms state-of-the-art re-ranking models.
Authors: Mandar Sharma, Nikhil Muralidhar, Shengzhe Xu, Raquib Bin Yosuf, Naren Ramakrishnan
Abstract: The pretraining-fine-tuning paradigm has been the de facto strategy for transfer learning in modern language modeling. With the understanding that task adaptation in LMs is often a function of parameters shared across tasks, we argue that a more surgical approach to regularization needs to exist for smoother transfer learning. Towards this end, we investigate how the pretraining loss landscape is affected by these task-sensitive parameters through an information-theoretic lens. We then leverage the findings from our investigations to devise a novel approach to dropout for improved model regularization and better downstream generalization. This approach, named guided dropout, is both task & architecture agnostic and adds no computational overhead to the fine-tuning process. Through empirical evaluations, we showcase that our approach to regularization yields consistently better performance, even in scenarios of data paucity, compared to standardized baselines.
Authors: Asaf Ben Arie, Malka Gorfine
Abstract: Deep learning models have significantly improved prediction accuracy in various fields, gaining recognition across numerous disciplines. Yet, an aspect of deep learning that remains insufficiently addressed is the assessment of prediction uncertainty. Producing reliable uncertainty estimators could be crucial in practical terms. For instance, predictions associated with a high degree of uncertainty could be sent for further evaluation. Recent works in uncertainty quantification of deep learning predictions, including Bayesian posterior credible intervals and a frequentist confidence-interval estimation, have proven to yield either invalid or overly conservative intervals. Furthermore, there is currently no method for quantifying uncertainty that can accommodate deep neural networks for survival (time-to-event) data that involves right-censored outcomes. In this work, we provide a valid non-parametric bootstrap method that correctly disentangles data uncertainty from the noise inherent in the adopted optimization algorithm, ensuring that the resulting point-wise confidence intervals or the simultaneous confidence bands are accurate (i.e., valid and not overly conservative). The proposed ad-hoc method can be easily integrated into any deep neural network without interfering with the training process. The utility of the proposed approach is illustrated by constructing simultaneous confidence bands for survival curves derived from deep neural networks for survival data with right censoring.
Authors: Yongqiang Chen, Quanming Yao, Juzheng Zhang, James Cheng, Yatao Bian
Abstract: Recently there has been a surge of interest in extending the success of large language models (LLMs) to graph modality, such as social networks and molecules. As LLMs are predominantly trained with 1D text data, most existing approaches adopt a graph neural network to represent a graph as a series of node tokens and feed these tokens to LLMs for graph-language alignment. Despite achieving some successes, existing approaches have overlooked the hierarchical structures that are inherent in graph data. Especially, in molecular graphs, the high-order structural information contains rich semantics of molecular functional groups, which encode crucial biochemical functionalities of the molecules. We establish a simple benchmark showing that neglecting the hierarchical information in graph tokenization will lead to subpar graph-language alignment and severe hallucination in generated outputs. To address this problem, we propose a novel strategy called HIerarchical GrapH Tokenization (HIGHT). HIGHT employs a hierarchical graph tokenizer that extracts and encodes the hierarchy of node, motif, and graph levels of informative tokens to improve the graph perception of LLMs. HIGHT also adopts an augmented graph-language supervised fine-tuning dataset, enriched with the hierarchical graph information, to further enhance the graph-language alignment. Extensive experiments on 7 molecule-centric benchmarks confirm the effectiveness of HIGHT in reducing hallucination by 40%, as well as significant improvements in various molecule-language downstream tasks.
Authors: Alexandre Seiller (APTIKAL), \'Eric Gaussier (APTIKAL), Emilie Devijver (APTIKAL), Marianne Clausel (IECL), Sami Alkhoury
Abstract: Tree-based ensemble methods such as random forests, gradient-boosted trees, and Bayesianadditive regression trees have been successfully used for regression problems in many applicationsand research studies. In this paper, we study ensemble versions of probabilisticregression trees that provide smooth approximations of the objective function by assigningeach observation to each region with respect to a probability distribution. We prove thatthe ensemble versions of probabilistic regression trees considered are consistent, and experimentallystudy their bias-variance trade-off and compare them with the state-of-the-art interms of performance prediction.
Authors: Omar Chehab, Anna Korba
Abstract: Diffusion models are state-of-the-art methods in generative modeling when samples from a target probability distribution are available, and can be efficiently sampled, using score matching to estimate score vectors guiding a Langevin process. However, in the setting where samples from the target are not available, e.g. when this target's density is known up to a normalization constant, the score estimation task is challenging. Previous approaches rely on Monte Carlo estimators that are either computationally heavy to implement or sample-inefficient. In this work, we propose a computationally attractive alternative, relying on the so-called dilation path, that yields score vectors that are available in closed-form. This path interpolates between a Dirac and the target distribution using a convolution. We propose a simple implementation of Langevin dynamics guided by the dilation path, using adaptive step-sizes. We illustrate the results of our sampling method on a range of tasks, and shows it performs better than classical alternatives.
Authors: Jalmari Passilahti, Anton Vladyka, Johannes Niskanen
Abstract: Encoder-decoder neural networks (EDNN) condense information most relevant to the output of the feedforward network to activation values at a bottleneck layer. We study the use of this architecture in emulation and interpretation of simulated X-ray spectroscopic data with the aim to identify key structural characteristics for the spectra, previously studied using emulator-based component analysis (ECA). We find an EDNN to outperform ECA in covered target variable variance, but also discover complications in interpreting the latent variables in physical terms. As a compromise of the benefits of these two approaches, we develop a network where the linear projection of ECA is used, thus maintaining the beneficial characteristics of vector expansion from the latent variables for their interpretation. These results underline the necessity of information recovery after its condensation and identification of decisive structural degrees for the output spectra for a justified interpretation.
Authors: H\'edi Hadiji (UvA), Sarah Sachs (UvA), Crist\'obal Guzm\'an (UC)
Abstract: Tracking the solution of time-varying variational inequalities is an important problem with applications in game theory, optimization, and machine learning. Existing work considers time-varying games or time-varying optimization problems. For strongly convex optimization problems or strongly monotone games, these results provide tracking guarantees under the assumption that the variation of the time-varying problem is restrained, that is, problems with a sublinear solution path. In this work we extend existing results in two ways: In our first result, we provide tracking bounds for (1) variational inequalities with a sublinear solution path but not necessarily monotone functions, and (2) for periodic time-varying variational inequalities that do not necessarily have a sublinear solution path-length. Our second main contribution is an extensive study of the convergence behavior and trajectory of discrete dynamical systems of periodic time-varying VI. We show that these systems can exhibit provably chaotic behavior or can converge to the solution. Finally, we illustrate our theoretical results with experiments.
Authors: Ziyi Huang, Henry Lam, Haofeng Zhang
Abstract: Bayesian bandit algorithms with approximate Bayesian inference have been widely used in real-world applications. Nevertheless, their theoretical justification is less investigated in the literature, especially for contextual bandit problems. To fill this gap, we propose a general theoretical framework to analyze stochastic linear bandits in the presence of approximate inference and conduct regret analysis on two Bayesian bandit algorithms, Linear Thompson sampling (LinTS) and the extension of Bayesian Upper Confidence Bound, namely Linear Bayesian Upper Confidence Bound (LinBUCB). We demonstrate that both LinTS and LinBUCB can preserve their original rates of regret upper bound but with a sacrifice of larger constant terms when applied with approximate inference. These results hold for general Bayesian inference approaches, under the assumption that the inference error measured by two different $\alpha$-divergences is bounded. Additionally, by introducing a new definition of well-behaved distributions, we show that LinBUCB improves the regret rate of LinTS from $\tilde{O}(d^{3/2}\sqrt{T})$ to $\tilde{O}(d\sqrt{T})$, matching the minimax optimal rate. To our knowledge, this work provides the first regret bounds in the setting of stochastic linear bandits with bounded approximate inference errors.
Authors: Qinfeng Zhu, Yuanzhi Cai, Lei Fan
Abstract: Recent advancements in autoregressive networks with linear complexity have driven significant research progress, demonstrating exceptional performance in large language models. A representative model is the Extended Long Short-Term Memory (xLSTM), which incorporates gating mechanisms and memory structures, performing comparably to Transformer architectures in long-sequence language tasks. Autoregressive networks such as xLSTM can utilize image serialization to extend their application to visual tasks such as classification and segmentation. Although existing studies have demonstrated Vision-LSTM's impressive results in image classification, its performance in image semantic segmentation remains unverified. Our study represents the first attempt to evaluate the effectiveness of Vision-LSTM in the semantic segmentation of remotely sensed images. This evaluation is based on a specifically designed encoder-decoder architecture named Seg-LSTM, and comparisons with state-of-the-art segmentation networks. Our study found that Vision-LSTM's performance in semantic segmentation was limited and generally inferior to Vision-Transformers-based and Vision-Mamba-based models in most comparative tests. Future research directions for enhancing Vision-LSTM are recommended. The source code is available from https://github.com/zhuqinfeng1999/Seg-LSTM.
Authors: Cassio F. Dantas (EVERGREEN, INRAE), Raffaele Gaetano (EVERGREEN), Dino Ienco (EVERGREEN)
Abstract: Semi-supervised domain adaptation methods leverage information from a source labelled domain with the goal of generalizing over a scarcely labelled target domain. While this setting already poses challenges due to potential distribution shifts between domains, an even more complex scenario arises when source and target data differs in modality representation (e.g. they are acquired by sensors with different characteristics). For instance, in remote sensing, images may be collected via various acquisition modes (e.g. optical or radar), different spectral characteristics (e.g. RGB or multi-spectral) and spatial resolutions. Such a setting is denoted as Semi-Supervised Heterogeneous Domain Adaptation (SSHDA) and it exhibits an even more severe distribution shift due to modality heterogeneity across domains.To cope with the challenging SSHDA setting, here we introduce SHeDD (Semi-supervised Heterogeneous Domain Adaptation via Disentanglement) an end-to-end neural framework tailored to learning a target domain classifier by leveraging both labelled and unlabelled data from heterogeneous data sources. SHeDD is designed to effectively disentangle domain-invariant representations, relevant for the downstream task, from domain-specific information, that can hinder the cross-modality transfer. Additionally, SHeDD adopts an augmentation-based consistency regularization mechanism that takes advantages of reliable pseudo-labels on the unlabelled target samples to further boost its generalization ability on the target domain. Empirical evaluations on two remote sensing benchmarks, encompassing heterogeneous data in terms of acquisition modes and spectral/spatial resolutions, demonstrate the quality of SHeDD compared to both baseline and state-of-the-art competing approaches. Our code is publicly available here: https://github.com/tanodino/SSHDA/
Authors: Zhiyu Mei, Wei Fu, Kaiwei Li, Guangju Wang, Huanchen Zhang, Yi Wu
Abstract: Reinforcement Learning from Human Feedback (RLHF) stands as a pivotal technique in empowering large language model (LLM) applications. Since RLHF involves diverse computational workloads and intricate dependencies among multiple LLMs, directly adopting parallelization techniques from supervised training can result in sub-optimal performance. To overcome this limitation, we propose a novel approach named parameter ReaLlocation, which dynamically redistributes LLM parameters in the cluster and adapts parallelization strategies during training. Building upon this idea, we introduce ReaLHF, a pioneering system capable of automatically discovering and running efficient execution plans for RLHF training given the desired algorithmic and hardware configurations. ReaLHF formulates the execution plan for RLHF as an augmented dataflow graph. Based on this formulation, ReaLHF employs a tailored search algorithm with a lightweight cost estimator to discover an efficient execution plan. Subsequently, the runtime engine deploys the selected plan by effectively parallelizing computations and redistributing parameters. We evaluate ReaLHF on the LLaMA-2 models with up to $4\times70$ billion parameters and 128 GPUs. The experiment results showcase ReaLHF's substantial speedups of $2.0-10.6\times$ compared to baselines. Furthermore, the execution plans generated by ReaLHF exhibit an average of $26\%$ performance improvement over heuristic approaches based on Megatron-LM. The source code of ReaLHF is publicly available at https://github.com/openpsi-project/ReaLHF .
Authors: Igor G. Smit, Jianan Zhou, Robbert Reijnen, Yaoxin Wu, Jian Chen, Cong Zhang, Zaharah Bukhsh, Wim Nuijten, Yingqian Zhang
Abstract: Job shop scheduling problems (JSSPs) represent a critical and challenging class of combinatorial optimization problems. Recent years have witnessed a rapid increase in the application of graph neural networks (GNNs) to solve JSSPs, albeit lacking a systematic survey of the relevant literature. This paper aims to thoroughly review prevailing GNN methods for different types of JSSPs and the closely related flow-shop scheduling problems (FSPs), especially those leveraging deep reinforcement learning (DRL). We begin by presenting the graph representations of various JSSPs, followed by an introduction to the most commonly used GNN architectures. We then review current GNN-based methods for each problem type, highlighting key technical elements such as graph representations, GNN architectures, GNN tasks, and training algorithms. Finally, we summarize and analyze the advantages and limitations of GNNs in solving JSSPs and provide potential future research opportunities. We hope this survey can motivate and inspire innovative approaches for more powerful GNN-based approaches in tackling JSSPs and other scheduling problems.
Authors: Kathrin Hanauer, Monika Henzinger, Robin M\"unk, Harald R\"acke, Maximilian V\"otsch
Abstract: Expander decompositions of graphs have significantly advanced the understanding of many classical graph problems and led to numerous fundamental theoretical results. However, their adoption in practice has been hindered due to their inherent intricacies and large hidden factors in their asymptotic running times. Here, we introduce the first practically efficient algorithm for computing expander decompositions and their hierarchies and demonstrate its effectiveness and utility by incorporating it as the core component in a novel solver for the normalized cut graph clustering objective. Our extensive experiments on a variety of large graphs show that our expander-based algorithm outperforms state-of-the-art solvers for normalized cut with respect to solution quality by a large margin on a variety of graph classes such as citation, e-mail, and social networks or web graphs while remaining competitive in running time.
Authors: Minsang Kim, Seungjun Baek
Abstract: Compute-efficient training of large language models (LLMs) has become an important research problem. In this work, we consider data pruning as a method of data-efficient training of LLMs, where we take a data compression view on data pruning. We argue that the amount of information of a sample, or the achievable compression on its description length, represents its sample importance. The key idea is that, less informative samples are likely to contain redundant information, and thus should be pruned first. We leverage log-likelihood function of trained models as a surrogate to measure information content of samples. Experiments reveal a surprising insight that information-based pruning can enhance the generalization capability of the model, improves upon language modeling and downstream tasks as compared to the model trained on the entire dataset.
Authors: Michail Chatzianastasis, George Dasoulas, Michalis Vazirgiannis
Abstract: Protein representation learning aims to learn informative protein embeddings capable of addressing crucial biological questions, such as protein function prediction. Although sequence-based transformer models have shown promising results by leveraging the vast amount of protein sequence data in a self-supervised way, there is still a gap in applying these methods to 3D protein structures. In this work, we propose a pre-training scheme going beyond trivial masking methods leveraging 3D and hierarchical structures of proteins. We propose a novel self-supervised method to pretrain 3D graph neural networks on 3D protein structures, by predicting the distances between local geometric centroids of protein subgraphs and the global geometric centroid of the protein. The motivation for this method is twofold. First, the relative spatial arrangements and geometric relationships among different regions of a protein are crucial for its function. Moreover, proteins are often organized in a hierarchical manner, where smaller substructures, such as secondary structure elements, assemble into larger domains. By considering subgraphs and their relationships to the global protein structure, the model can learn to reason about these hierarchical levels of organization. We experimentally show that our proposed pertaining strategy leads to significant improvements in the performance of 3D GNNs in various protein classification tasks.
Authors: Jianhui Chen, Xiaozhi Wang, Zijun Yao, Yushi Bai, Lei Hou, Juanzi Li
Abstract: Large language models (LLMs) excel in various capabilities but also pose safety risks such as generating harmful content and misinformation, even after safety alignment. In this paper, we explore the inner mechanisms of safety alignment from the perspective of mechanistic interpretability, focusing on identifying and analyzing safety neurons within LLMs that are responsible for safety behaviors. We propose generation-time activation contrasting to locate these neurons and dynamic activation patching to evaluate their causal effects. Experiments on multiple recent LLMs show that: (1) Safety neurons are sparse and effective. We can restore $90$% safety performance with intervention only on about $5$% of all the neurons. (2) Safety neurons encode transferrable mechanisms. They exhibit consistent effectiveness on different red-teaming datasets. The finding of safety neurons also interprets "alignment tax". We observe that the identified key neurons for safety and helpfulness significantly overlap, but they require different activation patterns of the shared neurons. Furthermore, we demonstrate an application of safety neurons in detecting unsafe outputs before generation. Our findings may promote further research on understanding LLM alignment. The source codes will be publicly released to facilitate future research.
Authors: Vivin Vinod, Peter Zaspel
Abstract: Progress in both Machine Learning (ML) and conventional Quantum Chemistry (QC) computational methods have resulted in high accuracy ML models for QC properties ranging from atomization energies to excitation energies. Various datasets such as MD17, MD22, and WS22, which consist of properties calculated at some level of QC method, or fidelity, have been generated to benchmark such ML models. The term fidelity refers to the accuracy of the chosen QC method to the actual real value of the property. The higher the fidelity, the more accurate the calculated property, albeit at a higher computational cost. Research in multifidelity ML (MFML) methods, where ML models are trained on data from more than one numerical QC method, has shown the effectiveness of such models over single fidelity methods. Much research is progressing in this direction for diverse applications ranging from energy band gaps to excitation energies. A major hurdle for effective research in this field of research in the community is the lack of a diverse multifidelity dataset for benchmarking. Here, we present a comprehensive multifidelity dataset drawn from the WS22 molecular conformations. We provide the quantum Chemistry MultiFidelity (CheMFi) dataset consisting of five fidelities calculated with the TD-DFT formalism. The fidelities differ in their basis set choice and are namely: STO-3G, 3-21G, 6-31G, def2-SVP, and def2-TZVP. CheMFi offers to the community a variety of QC properties including vertical excitation energies, oscillator strengths, molecular dipole moments, and ground state energies. In addition to the dataset, multifidelity benchmarks are set with state-of-the-art MFML and optimized-MFML
Authors: David Hartmann, Amin Oueslati, Dimitri Staufer
Abstract: Online platforms face the challenge of moderating an ever-increasing volume of content, including harmful hate speech. In the absence of clear legal definitions and a lack of transparency regarding the role of algorithms in shaping decisions on content moderation, there is a critical need for external accountability. Our study contributes to filling this gap by systematically evaluating four leading cloud-based content moderation services through a third-party audit, highlighting issues such as biases against minorities and vulnerable groups that may arise through over-reliance on these services. Using a black-box audit approach and four benchmark data sets, we measure performance in explicit and implicit hate speech detection as well as counterfactual fairness through perturbation sensitivity analysis and present disparities in performance for certain target identity groups and data sets. Our analysis reveals that all services had difficulties detecting implicit hate speech, which relies on more subtle and codified messages. Moreover, our results point to the need to remove group-specific bias. It seems that biases towards some groups, such as Women, have been mostly rectified, while biases towards other groups, such as LGBTQ+ and PoC remain.
Authors: Eric Mazumdar, Kishan Panaganti, Laixi Shi
Abstract: A significant roadblock to the development of principled multi-agent reinforcement learning is the fact that desired solution concepts like Nash equilibria may be intractable to compute. To overcome this obstacle, we take inspiration from behavioral economics and show that -- by imbuing agents with important features of human decision-making like risk aversion and bounded rationality -- a class of risk-averse quantal response equilibria (RQE) become tractable to compute in all $n$-player matrix and finite-horizon Markov games. In particular, we show that they emerge as the endpoint of no-regret learning in suitably adjusted versions of the games. Crucially, the class of computationally tractable RQE is independent of the underlying game structure and only depends on agents' degree of risk-aversion and bounded rationality. To validate the richness of this class of solution concepts we show that it captures peoples' patterns of play in a number of 2-player matrix games previously studied in experimental economics. Furthermore, we give a first analysis of the sample complexity of computing these equilibria in finite-horizon Markov games when one has access to a generative model and validate our findings on a simple multi-agent reinforcement learning benchmark.
Authors: Amit Sharma, Hua Li, Xue Li, Jian Jiao
Abstract: Given an input query, a recommendation model is trained using user feedback data (e.g., click data) to output a ranked list of items. In real-world systems, besides accuracy, an important consideration for a new model is novelty of its top-k recommendations w.r.t. an existing deployed model. However, novelty of top-k items is a difficult goal to optimize a model for, since it involves a non-differentiable sorting operation on the model's predictions. Moreover, novel items, by definition, do not have any user feedback data. Given the semantic capabilities of large language models, we address these problems using a reinforcement learning (RL) formulation where large language models provide feedback for the novel items. However, given millions of candidate items, the sample complexity of a standard RL algorithm can be prohibitively high. To reduce sample complexity, we reduce the top-k list reward to a set of item-wise rewards and reformulate the state space to consist of
Authors: Miao Su, ZiXuan Li, Zhuo Chen, Long Bai, Xiaolong Jin, Jiafeng Guo
Abstract: Knowledge Base Question Answering (KBQA) has been a long-standing field to answer questions based on knowledge bases. Recently, the evolving dynamics of knowledge have attracted a growing interest in Temporal Knowledge Graph Question Answering (TKGQA), an emerging task to answer temporal questions. However, this field grapples with ambiguities in defining temporal questions and lacks a systematic categorization of existing methods for TKGQA. In response, this paper provides a thorough survey from two perspectives: the taxonomy of temporal questions and the methodological categorization for TKGQA. Specifically, we first establish a detailed taxonomy of temporal questions engaged in prior studies. Subsequently, we provide a comprehensive review of TKGQA techniques of two categories: semantic parsing-based and TKG embedding-based. Building on this review, the paper outlines potential research directions aimed at advancing the field of TKGQA. This work aims to serve as a comprehensive reference for TKGQA and to stimulate further research.
Authors: Chen Zheng
Abstract: Structural magnetic resonance imaging (MRI) studies have shown that Alzheimer's Disease (AD) induces both localised and widespread neural degenerative changes throughout the brain. However, the absence of segmentation that highlights brain degenerative changes presents unique challenges for training CNN-based classifiers in a supervised fashion. In this work, we evaluated several unsupervised methods to train a feature extractor for downstream AD vs. CN classification. Using the 3D T1-weighted MRI data of cognitive normal (CN) subjects from the synthetic neuroimaging LDM100K dataset, lightweight 3D CNN-based models are trained for brain age prediction, brain image rotation classification, brain image reconstruction and a multi-head task combining all three tasks into one. Feature extractors trained on the LDM100K synthetic dataset achieved similar performance compared to the same model using real-world data. This supports the feasibility of utilising large-scale synthetic data for pretext task training. All the training and testing splits are performed on the subject-level to prevent data leakage issues. Alongside the simple preprocessing steps, the random cropping data augmentation technique shows consistent improvement across all experiments.
Authors: Ilham Adi Panuntun, Ying-Nong Chen, Ilham Jamaluddin, Thi Linh Chi Tran
Abstract: In the rise of climate change, land cover mapping has become such an urgent need in environmental monitoring. The accuracy of land cover classification has gotten increasingly based on the improvement of remote sensing data. Land cover classification using satellite imageries has been explored and become more prevalent in recent years, but the methodologies remain some drawbacks of subjective and time-consuming. Some deep learning techniques have been utilized to overcome these limitations. However, most studies implemented just one image type to evaluate algorithms for land cover mapping. Therefore, our study conducted deep learning semantic segmentation in multispectral, hyperspectral, and high spatial aerial image datasets for landcover mapping. This research implemented a semantic segmentation method such as Unet, Linknet, FPN, and PSPnet for categorizing vegetation, water, and others (i.e., soil and impervious surface). The LinkNet model obtained high accuracy in IoU (Intersection Over Union) at 0.92 in all datasets, which is comparable with other mentioned techniques. In evaluation with different image types, the multispectral images showed higher performance with the IoU, and F1-score are 0.993 and 0.997, respectively. Our outcome highlighted the efficiency and broad applicability of LinkNet and multispectral image on land cover classification. This research contributes to establishing an approach on landcover segmentation via open source for long-term future application.
Authors: Maren Philipps, Antonia K\"orner, Jakob Vanhoefer, Dilan Pathirana, Jan Hasenauer
Abstract: Universal differential equations (UDEs) leverage the respective advantages of mechanistic models and artificial neural networks and combine them into one dynamic model. However, these hybrid models can suffer from unrealistic solutions, such as negative values for biochemical quantities. We present non-negative UDE (nUDEs), a constrained UDE variant that guarantees non-negative values. Furthermore, we explore regularisation techniques to improve generalisation and interpretability of UDEs.
Authors: Mengcheng Lan, Min Meng, Jun Yu, Jigang Wu
Abstract: Domain adaptation has shown appealing performance by leveraging knowledge from a source domain with rich annotations. However, for a specific target task, it is cumbersome to collect related and high-quality source domains. In real-world scenarios, large-scale datasets corrupted with noisy labels are easy to collect, stimulating a great demand for automatic recognition in a generalized setting, i.e., weakly-supervised partial domain adaptation (WS-PDA), which transfers a classifier from a large source domain with noises in labels to a small unlabeled target domain. As such, the key issues of WS-PDA are: 1) how to sufficiently discover the knowledge from the noisy labeled source domain and the unlabeled target domain, and 2) how to successfully adapt the knowledge across domains. In this paper, we propose a simple yet effective domain adaptation approach, termed as self-paced transfer classifier learning (SP-TCL), to address the above issues, which could be regarded as a well-performing baseline for several generalized domain adaptation tasks. The proposed model is established upon the self-paced learning scheme, seeking a preferable classifier for the target domain. Specifically, SP-TCL learns to discover faithful knowledge via a carefully designed prudent loss function and simultaneously adapts the learned knowledge to the target domain by iteratively excluding source examples from training under the self-paced fashion. Extensive evaluations on several benchmark datasets demonstrate that SP-TCL significantly outperforms state-of-the-art approaches on several generalized domain adaptation tasks.
Authors: Soroush Oskouei, Marit Valla, Andr\'e Pedersen, Erik Smistad, Vibeke Grotnes Dale, Maren H{\o}ib{\o}, Sissel Gyrid Freim Wahl, Mats Dehli Haugum, Thomas Lang{\o}, Maria Paula Ramnefjell, Lars Andreas Akslen, Gabriel Kiss, Hanne Sorger
Abstract: Considering the increased workload in pathology laboratories today, automated tools such as artificial intelligence models can help pathologists with their tasks and ease the workload. In this paper, we are proposing a segmentation model (DRU-Net) that can provide a delineation of human non-small cell lung carcinomas and an augmentation method that can improve classification results. The proposed model is a fused combination of truncated pre-trained DenseNet201 and ResNet101V2 as a patch-wise classifier followed by a lightweight U-Net as a refinement model. We have used two datasets (Norwegian Lung Cancer Biobank and Haukeland University Hospital lung cancer cohort) to create our proposed model. The DRU-Net model achieves an average of 0.91 Dice similarity coefficient. The proposed spatial augmentation method (multi-lens distortion) improved the network performance by 3%. Our findings show that choosing image patches that specifically include regions of interest leads to better results for the patch-wise classifier compared to other sampling methods. The qualitative analysis showed that the DRU-Net model is generally successful in detecting the tumor. On the test set, some of the cases showed areas of false positive and false negative segmentation in the periphery, particularly in tumors with inflammatory and reactive changes.
Authors: Rasika Vijithasena, Rafaela Scaciota, Mehdi Bennis, Sumudu Samarakoon
Abstract: Achieving control stability is one of the key design challenges of scalable Wireless Networked Control Systems (WNCS) under limited communication and computing resources. This paper explores the use of an alternative control concept defined as tail-based control, which extends the classical Linear Quadratic Regulator (LQR) cost function for multiple dynamic control systems over a shared wireless network. We cast the control of multiple control systems as a network-wide optimization problem and decouple it in terms of sensor scheduling, plant state prediction, and control policies. Toward this, we propose a solution consisting of a scheduling algorithm based on Lyapunov optimization for sensing, a mechanism based on Gaussian Process Regression (GPR) for state prediction and uncertainty estimation, and a control policy based on Reinforcement Learning (RL) to ensure tail-based control stability. A set of discrete time-invariant mountain car control systems is used to evaluate the proposed solution and is compared against four variants that use state-of-the-art scheduling, prediction, and control methods. The experimental results indicate that the proposed method yields 22% reduction in overall cost in terms of communication and control resource utilization compared to state-of-the-art methods.
Authors: Patrik Reizinger, Siyuan Guo, Ferenc Husz\'ar, Bernhard Sch\"olkopf, Wieland Brendel
Abstract: Identifying latent representations or causal structures is important for good generalization and downstream task performance. However, both fields have been developed rather independently. We observe that several methods in both representation and causal structure learning rely on the same data-generating process (DGP), namely, exchangeable but not i.i.d. (independent and identically distributed) data. We provide a unified framework, termed Identifiable Exchangeable Mechanisms (IEM), for representation and structure learning under the lens of exchangeability. IEM provides new insights that let us relax the necessary conditions for causal structure identification in exchangeable non--i.i.d. data. We also demonstrate the existence of a duality condition in identifiable representation learning, leading to new identifiability results. We hope this work will pave the way for further research in causal representation learning.
Authors: Kwanseok Oh, Eunjin Jeon, Da-Woon Heo, Yooseung Shin, Heung-Il Suk
Abstract: Single-source domain generalization (SDG) in medical image segmentation (MIS) aims to generalize a model using data from only one source domain to segment data from an unseen target domain. Despite substantial advances in SDG with data augmentation, existing methods often fail to fully consider the details and uncertain areas prevalent in MIS, leading to mis-segmentation. This paper proposes a Fourier-based semantic augmentation method called FIESTA using uncertainty guidance to enhance the fundamental goals of MIS in an SDG context by manipulating the amplitude and phase components in the frequency domain. The proposed Fourier augmentative transformer addresses semantic amplitude modulation based on meaningful angular points to induce pertinent variations and harnesses the phase spectrum to ensure structural coherence. Moreover, FIESTA employs epistemic uncertainty to fine-tune the augmentation process, improving the ability of the model to adapt to diverse augmented data and concentrate on areas with higher ambiguity. Extensive experiments across three cross-domain scenarios demonstrate that FIESTA surpasses recent state-of-the-art SDG approaches in segmentation performance and significantly contributes to boosting the applicability of the model in medical imaging modalities.
Authors: Chris Foulon, Marcela Ovando-Tellez, Lia Talozzi, Maurizio Corbetta, Anna Matsulevits, Michel Thiebaut de Schotten
Abstract: Understanding complex phenomena often requires analyzing high-dimensional data to uncover emergent properties that arise from multifactorial interactions. Here, we present EMUSES (Emerging-properties Mapping Using Spatial Embedding Statistics), an innovative approach employing Uniform Manifold Approximation and Projection (UMAP) to create high-dimensional embeddings that reveal latent structures within data. EMUSES facilitates the exploration and prediction of emergent properties by statistically analyzing these latent spaces. Using three distinct datasets--a handwritten digits dataset from the National Institute of Standards and Technology (NIST, E. Alpaydin, 1998), the Chicago Face Database (Ma et al., 2015), and brain disconnection data post-stroke (Talozzi et al., 2023)--we demonstrate EMUSES' effectiveness in detecting and interpreting emergent properties. Our method not only predicts outcomes with high accuracy but also provides clear visualizations and statistical insights into the underlying interactions within the data. By bridging the gap between predictive accuracy and interpretability, EMUSES offers researchers a powerful tool to understand the multifactorial origins of complex phenomena.
Authors: Lynn Chua, Badih Ghazi, Yangsibo Huang, Pritish Kamath, Daogao Liu, Pasin Manurangsi, Amer Sinha, Chiyuan Zhang
Abstract: Large language models (LLMs) have emerged as powerful tools for tackling complex tasks across diverse domains, but they also raise privacy concerns when fine-tuned on sensitive data due to potential memorization. While differential privacy (DP) offers a promising solution by ensuring models are `almost indistinguishable' with or without any particular privacy unit, current evaluations on LLMs mostly treat each example (text record) as the privacy unit. This leads to uneven user privacy guarantees when contributions per user vary. We therefore study user-level DP motivated by applications where it necessary to ensure uniform privacy protection across users. We present a systematic evaluation of user-level DP for LLM fine-tuning on natural language generation tasks. Focusing on two mechanisms for achieving user-level DP guarantees, Group Privacy and User-wise DP-SGD, we investigate design choices like data selection strategies and parameter tuning for the best privacy-utility tradeoff.
Authors: Harald Semmelrock, Tony Ross-Hellauer, Simone Kopeinik, Dieter Theiler, Armin Haberl, Stefan Thalmann, Dominik Kowald
Abstract: Research in various fields is currently experiencing challenges regarding the reproducibility of results. This problem is also prevalent in machine learning (ML) research. The issue arises primarily due to unpublished data and/or source code and the sensitivity of ML training conditions. Although different solutions have been proposed to address this issue, such as using ML platforms, the level of reproducibility in ML-driven research remains unsatisfactory. Therefore, in this article, we discuss the reproducibility of ML-driven research with three main aims: (i) identify the barriers to reproducibility when applying ML in research as well as categorize the barriers to different types of reproducibility (description, code, data, and experiment reproducibility), (ii) identify potential drivers such as tools, practices, and interventions that support ML reproducibility as well as distinguish between technology-driven drivers, procedural drivers, and drivers related to awareness and education, and (iii) map the drivers to the barriers. With this work, we hope to provide insights and contribute to the decision-making process regarding the adoption of different solutions to support ML reproducibility.
Authors: Steffen Dereich, Arnulf Jentzen, Adrian Riekert
Abstract: It is known that the standard stochastic gradient descent (SGD) optimization method, as well as accelerated and adaptive SGD optimization methods such as the Adam optimizer fail to converge if the learning rates do not converge to zero (as, for example, in the situation of constant learning rates). Numerical simulations often use human-tuned deterministic learning rate schedules or small constant learning rates. The default learning rate schedules for SGD optimization methods in machine learning implementation frameworks such as TensorFlow and Pytorch are constant learning rates. In this work we propose and study a learning-rate-adaptive approach for SGD optimization methods in which the learning rate is adjusted based on empirical estimates for the values of the objective function of the considered optimization problem (the function that one intends to minimize). In particular, we propose a learning-rate-adaptive variant of the Adam optimizer and implement it in case of several neural network learning problems, particularly, in the context of deep learning approximation methods for partial differential equations such as deep Kolmogorov methods, physics-informed neural networks, and deep Ritz methods. In each of the presented learning problems the proposed learning-rate-adaptive variant of the Adam optimizer faster reduces the value of the objective function than the Adam optimizer with the default learning rate. For a simple class of quadratic minimization problems we also rigorously prove that a learning-rate-adaptive variant of the SGD optimization method converges to the minimizer of the considered minimization problem. Our convergence proof is based on an analysis of the laws of invariant measures of the SGD method as well as on a more general convergence analysis for SGD with random but predictable learning rates which we develop in this work.
Authors: Kuzma Khrabrov, Anton Ber, Artem Tsypin, Konstantin Ushenin, Egor Rumiantsev, Alexander Telepov, Dmitry Protasov, Ilya Shenbin, Anton Alekseev, Mikhail Shirokikh, Sergey Nikolenko, Elena Tutubalina, Artur Kadurin
Abstract: Methods of computational quantum chemistry provide accurate approximations of molecular properties crucial for computer-aided drug discovery and other areas of chemical science. However, high computational complexity limits the scalability of their applications. Neural network potentials (NNPs) are a promising alternative to quantum chemistry methods, but they require large and diverse datasets for training. This work presents a new dataset and benchmark called $\nabla^2$DFT that is based on the nablaDFT. It contains twice as much molecular structures, three times more conformations, new data types and tasks, and state-of-the-art models. The dataset includes energies, forces, 17 molecular properties, Hamiltonian and overlap matrices, and a wavefunction object. All calculations were performed at the DFT level ($\omega$B97X-D/def2-SVP) for each conformation. Moreover, $\nabla^2$DFT is the first dataset that contains relaxation trajectories for a substantial number of drug-like molecules. We also introduce a novel benchmark for evaluating NNPs in molecular property prediction, Hamiltonian prediction, and conformational optimization tasks. Finally, we propose an extendable framework for training NNPs and implement 10 models within it.
Authors: Niccol\`o Marini, Stefano Marchesin, Lluis Borras Ferris, Simon P\"uttmann, Marek Wodzinski, Riccardo Fratti, Damian Podareanu, Alessandro Caputo, Svetla Boytcheva, Simona Vatrano, Filippo Fraggetta, Iris Nagtegaal, Gianmaria Silvello, Manfredo Atzori, Henning M\"uller
Abstract: The increasing availability of biomedical data is helping to design more robust deep learning (DL) algorithms to analyze biomedical samples. Currently, one of the main limitations to train DL algorithms to perform a specific task is the need for medical experts to label data. Automatic methods to label data exist, however automatic labels can be noisy and it is not completely clear when automatic labels can be adopted to train DL models. This paper aims to investigate under which circumstances automatic labels can be adopted to train a DL model on the classification of Whole Slide Images (WSI). The analysis involves multiple architectures, such as Convolutional Neural Networks (CNN) and Vision Transformer (ViT), and over 10000 WSIs, collected from three use cases: celiac disease, lung cancer and colon cancer, which one including respectively binary, multiclass and multilabel data. The results allow identifying 10% as the percentage of noisy labels that lead to train competitive models for the classification of WSIs. Therefore, an algorithm generating automatic labels needs to fit this criterion to be adopted. The application of the Semantic Knowledge Extractor Tool (SKET) algorithm to generate automatic labels leads to performance comparable to the one obtained with manual labels, since it generates a percentage of noisy labels between 2-5%. Automatic labels are as effective as manual ones, reaching solid performance comparable to the one obtained training models with manual labels.
Authors: Ruohan Zhan, Shichao Han, Yuchen Hu, Zhenling Jiang
Abstract: Recommender systems are essential for content-sharing platforms by curating personalized content. To evaluate updates of recommender systems targeting content creators, platforms frequently engage in creator-side randomized experiments to estimate treatment effect, defined as the difference in outcomes when a new (vs. the status quo) algorithm is deployed on the platform. We show that the standard difference-in-means estimator can lead to a biased treatment effect estimate. This bias arises because of recommender interference, which occurs when treated and control creators compete for exposure through the recommender system. We propose a "recommender choice model" that captures how an item is chosen among a pool comprised of both treated and control content items. By combining a structural choice model with neural networks, the framework directly models the interference pathway in a microfounded way while accounting for rich viewer-content heterogeneity. Using the model, we construct a double/debiased estimator of the treatment effect that is consistent and asymptotically normal. We demonstrate its empirical performance with a field experiment on Weixin short-video platform: besides the standard creator-side experiment, we carry out a costly blocked double-sided randomization design to obtain a benchmark estimate without interference bias. We show that the proposed estimator significantly reduces the bias in treatment effect estimates compared to the standard difference-in-means estimator.
Authors: Xiaohan Lin, Qingxing Cao, Yinya Huang, Haiming Wang, Jianqiao Lu, Zhengying Liu, Linqi Song, Xiaodan Liang
Abstract: Formal verification (FV) has witnessed growing significance with current emerging program synthesis by the evolving large language models (LLMs). However, current formal verification mainly resorts to symbolic verifiers or hand-craft rules, resulting in limitations for extensive and flexible verification. On the other hand, formal languages for automated theorem proving, such as Isabelle, as another line of rigorous verification, are maintained with comprehensive rules and theorems. In this paper, we propose FVEL, an interactive Formal Verification Environment with LLMs. Specifically, FVEL transforms a given code to be verified into Isabelle, and then conducts verification via neural automated theorem proving with an LLM. The joined paradigm leverages the rigorous yet abundant formulated and organized rules in Isabelle and is also convenient for introducing and adjusting cutting-edge LLMs. To achieve this goal, we extract a large-scale FVELER3. The FVELER dataset includes code dependencies and verification processes that are formulated in Isabelle, containing 758 theories, 29,125 lemmas, and 200,646 proof steps in total with in-depth dependencies. We benchmark FVELER in the FVEL environment by first fine-tuning LLMs with FVELER and then evaluating them on Code2Inv and SV-COMP. The results show that FVEL with FVELER fine-tuned Llama3- 8B solves 17.39% (69 -> 81) more problems, and Mistral-7B 12% (75 -> 84) more problems in SV-COMP. And the proportion of proof errors is reduced. Project page: https://fveler.github.io/.
Authors: Hunter Schofield, Hamidreza Mirkhani, Mohammed Elmahgiubi, Kasra Rezaee, Jinjun Shan
Abstract: For an autonomous vehicle to plan a path in its environment, it must be able to accurately forecast the trajectory of all dynamic objects in its proximity. While many traditional methods encode observations in the scene to solve this problem, there are few approaches that consider the effect of the ego vehicle's behavior on the future state of the world. In this paper, we introduce VRD, a vectorized world model-inspired approach to the multi-agent motion forecasting problem. Our method combines a traditional open-loop training regime with a novel dreamed closed-loop training pipeline that leverages a kinematic reconstruction task to imagine the trajectory of all agents, conditioned on the action of the ego vehicle. Quantitative and qualitative experiments are conducted on the Argoverse 2 multi-world forecasting evaluation dataset and the intersection drone (inD) dataset to demonstrate the performance of our proposed model. Our model achieves state-of-the-art performance on the single prediction miss rate metric on the Argoverse 2 dataset and performs on par with the leading models for the single prediction displacement metrics.
Authors: Ferdi Kossmann, Ziniu Wu, Alex Turk, Nesime Tatbul, Lei Cao, Samuel Madden
Abstract: Machine learning (ML) models are increasingly deployed to production, calling for efficient inference serving systems. Efficient inference serving is complicated by two challenges: (i) ML models incur high computational costs, and (ii) the request arrival rates of practical applications have frequent, high, and sudden variations which make it hard to correctly provision hardware. Model cascades are positioned to tackle both of these challenges, as they (i) save work while maintaining accuracy, and (ii) expose a high-resolution trade-off between work and accuracy, allowing for fine-grained adjustments to request arrival rates. Despite their potential, model cascades haven't been used inside an online serving system. This comes with its own set of challenges, including workload adaption, model replication onto hardware, inference scheduling, request batching, and more. In this work, we propose CascadeServe, which automates and optimizes end-to-end inference serving with cascades. CascadeServe operates in an offline and online phase. In the offline phase, the system pre-computes a gear plan that specifies how to serve inferences online. In the online phase, the gear plan allows the system to serve inferences while making near-optimal adaptations to the query load at negligible decision overheads. We find that CascadeServe saves 2-3x in cost across a wide spectrum of the latency-accuracy space when compared to state-of-the-art baselines on different workloads.
Authors: Gayane Ghazaryan, Erik Arakelyan, Pasquale Minervini, Isabelle Augenstein
Abstract: Question Answering (QA) datasets have been instrumental in developing and evaluating Large Language Model (LLM) capabilities. However, such datasets are scarce for languages other than English due to the cost and difficulties of collection and manual annotation. This means that producing novel models and measuring the performance of multilingual LLMs in low-resource languages is challenging. To mitigate this, we propose $\textbf{S}$yn$\textbf{DAR}$in, a method for generating and validating QA datasets for low-resource languages. We utilize parallel content mining to obtain $\textit{human-curated}$ paragraphs between English and the target language. We use the English data as context to $\textit{generate}$ synthetic multiple-choice (MC) question-answer pairs, which are automatically translated and further validated for quality. Combining these with their designated non-English $\textit{human-curated}$ paragraphs form the final QA dataset. The method allows to maintain the content quality, reduces the likelihood of factual errors, and circumvents the need for costly annotation. To test the method, we created a QA dataset with $1.2$K samples for the Armenian language. The human evaluation shows that $98\%$ of the generated English data maintains quality and diversity in the question types and topics, while the translation validation pipeline can filter out $\sim70\%$ of data with poor quality. We use the dataset to benchmark state-of-the-art LLMs, showing their inability to achieve human accuracy with some model performances closer to random chance. This shows that the generated dataset is non-trivial and can be used to evaluate reasoning capabilities in low-resource language.
Authors: Leon Klein, Frank No\'e
Abstract: The generation of equilibrium samples of molecular systems has been a long-standing problem in statistical physics. Boltzmann Generators are a generative machine learning method that addresses this issue by learning a transformation via a normalizing flow from a simple prior distribution to the target Boltzmann distribution of interest. Recently, flow matching has been employed to train Boltzmann Generators for small molecular systems in Cartesian coordinates. We extend this work and propose a first framework for Boltzmann Generators that are transferable across chemical space, such that they predict zero-shot Boltzmann distributions for test molecules without being retrained for these systems. These transferable Boltzmann Generators allow approximate sampling from the target distribution of unseen systems, as well as efficient reweighting to the target Boltzmann distribution. The transferability of the proposed framework is evaluated on dipeptides, where we show that it generalizes efficiently to unseen systems. Furthermore, we demonstrate that our proposed architecture enhances the efficiency of Boltzmann Generators trained on single molecular systems.
Authors: Cheng Zhang
Abstract: Traditional methods for point forecasting in univariate random walks often fail to surpass naive benchmarks due to data unpredictability. This study introduces a novel forecasting method that fuses movement prediction (binary classification) with naive forecasts for accurate one-step-ahead point forecasting. The method's efficacy is demonstrated through theoretical analysis, simulations, and real-world data experiments. It reliably exceeds naive forecasts with movement prediction accuracies as low as 0.55, outperforming baseline models like ARIMA, linear regression, MLP, and LSTM networks in forecasting the S\&P 500 index and Bitcoin prices. This method is particularly advantageous when accurate point predictions are challenging but accurate movement predictions are attainable, translating movement predictions into point forecasts in random walk contexts.
Authors: Jiachen Jiang, Jinxin Zhou, Zhihui Zhu
Abstract: Analyzing the similarity of internal representations within and across different models has been an important technique for understanding the behavior of deep neural networks. Most existing methods for analyzing the similarity between representations of high dimensions, such as those based on Canonical Correlation Analysis (CCA) and widely used Centered Kernel Alignment (CKA), rely on statistical properties of the representations for a set of data points. In this paper, we focus on transformer models and study the similarity of representations between the hidden layers of individual transformers. In this context, we show that a simple sample-wise cosine similarity metric is capable of capturing the similarity and aligns with the complicated CKA. Our experimental results on common transformers reveal that representations across layers are positively correlated, albeit the similarity decreases when layers are far apart. We then propose an aligned training approach to enhance the similarity between internal representations, with trained models that enjoy the following properties: (1) the last-layer classifier can be directly applied right after any hidden layers, yielding intermediate layer accuracies much higher than those under standard training, (2) the layer-wise accuracies monotonically increase and reveal the minimal depth needed for the given task, (3) when served as multi-exit models, they achieve on-par performance with standard multi-exit architectures which consist of additional classifiers designed for early exiting in shallow layers. To our knowledge, our work is the first to show that one common classifier is sufficient for multi-exit models. We conduct experiments on both vision and NLP tasks to demonstrate the performance of the proposed aligned training.
Authors: Adriano Vinhas, Jo\~ao Correia, Penousal Machado
Abstract: Deep Neural Networks (DNNs) have been successfully applied to a wide range of problems. However, two main limitations are commonly pointed out. The first one is that they require long time to design. The other is that they heavily rely on labelled data, which can sometimes be costly and hard to obtain. In order to address the first problem, neuroevolution has been proved to be a plausible option to automate the design of DNNs. As for the second problem, self-supervised learning has been used to leverage unlabelled data to learn representations. Our goal is to study how neuroevolution can help self-supervised learning to bridge the gap to supervised learning in terms of performance. In this work, we propose a framework that is able to evolve deep neural networks using self-supervised learning. Our results on the CIFAR-10 dataset show that it is possible to evolve adequate neural networks while reducing the reliance on labelled data. Moreover, an analysis to the structure of the evolved networks suggests that the amount of labelled data fed to them has less effect on the structure of networks that learned via self-supervised learning, when compared to individuals that relied on supervised learning.
Authors: Luxi He, Yangsibo Huang, Weijia Shi, Tinghao Xie, Haotian Liu, Yue Wang, Luke Zettlemoyer, Chiyuan Zhang, Danqi Chen, Peter Henderson
Abstract: Recent studies show that image and video generation models can be prompted to reproduce copyrighted content from their training data, raising serious legal concerns around copyright infringement. Copyrighted characters, in particular, pose a difficult challenge for image generation services, with at least one lawsuit already awarding damages based on the generation of these characters. Yet, little research has empirically examined this issue. We conduct a systematic evaluation to fill this gap. First, we build CopyCat, an evaluation suite consisting of diverse copyrighted characters and a novel evaluation pipeline. Our evaluation considers both the detection of similarity to copyrighted characters and generated image's consistency with user input. Our evaluation systematically shows that both image and video generation models can still generate characters even if characters' names are not explicitly mentioned in the prompt, sometimes with only two generic keywords (e.g., prompting with "videogame, plumber" consistently generates Nintendo's Mario character). We then introduce techniques to semi-automatically identify such keywords or descriptions that trigger character generation. Using our evaluation suite, we study runtime mitigation strategies, including both existing methods and new strategies we propose. Our findings reveal that commonly employed strategies, such as prompt rewriting in the DALL-E system, are not sufficient as standalone guardrails. These strategies must be coupled with other approaches, like negative prompting, to effectively reduce the unintended generation of copyrighted characters. Our work provides empirical grounding to the discussion of copyright mitigation strategies and offers actionable insights for model deployers actively implementing them.
Authors: Johannes Treutlein, Dami Choi, Jan Betley, Cem Anil, Samuel Marks, Roger Baker Grosse, Owain Evans
Abstract: One way to address safety risks from large language models (LLMs) is to censor dangerous knowledge from their training data. While this removes the explicit information, implicit information can remain scattered across various training documents. Could an LLM infer the censored knowledge by piecing together these implicit hints? As a step towards answering this question, we study inductive out-of-context reasoning (OOCR), a type of generalization in which LLMs infer latent information from evidence distributed across training documents and apply it to downstream tasks without in-context learning. Using a suite of five tasks, we demonstrate that frontier LLMs can perform inductive OOCR. In one experiment we finetune an LLM on a corpus consisting only of distances between an unknown city and other known cities. Remarkably, without in-context examples or Chain of Thought, the LLM can verbalize that the unknown city is Paris and use this fact to answer downstream questions. Further experiments show that LLMs trained only on individual coin flip outcomes can verbalize whether the coin is biased, and those trained only on pairs $(x,f(x))$ can articulate a definition of $f$ and compute inverses. While OOCR succeeds in a range of cases, we also show that it is unreliable, particularly for smaller LLMs learning complex structures. Overall, the ability of LLMs to "connect the dots" without explicit in-context learning poses a potential obstacle to monitoring and controlling the knowledge acquired by LLMs.
Authors: Sunny Duan, Mikail Khona, Abhiram Iyer, Rylan Schaeffer, Ila R Fiete
Abstract: The proliferation of large language models has revolutionized natural language processing tasks, yet it raises profound concerns regarding data privacy and security. Language models are trained on extensive corpora including potentially sensitive or proprietary information, and the risk of data leakage -- where the model response reveals pieces of such information -- remains inadequately understood. This study examines susceptibility to data leakage by quantifying the phenomenon of memorization in machine learning models, focusing on the evolution of memorization patterns over training. We investigate how the statistical characteristics of training data influence the memories encoded within the model by evaluating how repetition influences memorization. We reproduce findings that the probability of memorizing a sequence scales logarithmically with the number of times it is present in the data. Furthermore, we find that sequences which are not apparently memorized after the first encounter can be uncovered throughout the course of training even without subsequent encounters. The presence of these latent memorized sequences presents a challenge for data privacy since they may be hidden at the final checkpoint of the model. To this end, we develop a diagnostic test for uncovering these latent memorized sequences by considering their cross entropy loss.
Authors: Hasan Abed Al Kader Hammoud, Umberto Michieli, Fabio Pizzati, Philip Torr, Adel Bibi, Bernard Ghanem, Mete Ozay
Abstract: Merging Large Language Models (LLMs) is a cost-effective technique for combining multiple expert LLMs into a single versatile model, retaining the expertise of the original ones. However, current approaches often overlook the importance of safety alignment during merging, leading to highly misaligned models. This work investigates the effects of model merging on alignment. We evaluate several popular model merging techniques, demonstrating that existing methods do not only transfer domain expertise but also propagate misalignment. We propose a simple two-step approach to address this problem: (i) generating synthetic safety and domain-specific data, and (ii) incorporating these generated data into the optimization process of existing data-aware model merging techniques. This allows us to treat alignment as a skill that can be maximized in the resulting merged LLM. Our experiments illustrate the effectiveness of integrating alignment-related data during merging, resulting in models that excel in both domain expertise and alignment.
Authors: Dongruo Zhou, Jinghui Chen, Yuan Cao, Ziyan Yang, Quanquan Gu
Abstract: Adaptive gradient methods are workhorses in deep learning. However, the convergence guarantees of adaptive gradient methods for nonconvex optimization have not been thoroughly studied. In this paper, we provide a fine-grained convergence analysis for a general class of adaptive gradient methods including AMSGrad, RMSProp and AdaGrad. For smooth nonconvex functions, we prove that adaptive gradient methods in expectation converge to a first-order stationary point. Our convergence rate is better than existing results for adaptive gradient methods in terms of dimension. In addition, we also prove high probability bounds on the convergence rates of AMSGrad, RMSProp as well as AdaGrad, which have not been established before. Our analyses shed light on better understanding the mechanism behind adaptive gradient methods in optimizing nonconvex objectives.
Authors: Nina M. Gottschling, Vegard Antun, Anders C. Hansen, Ben Adcock
Abstract: Methods inspired by Artificial Intelligence (AI) are starting to fundamentally change computational science and engineering through breakthrough performances on challenging problems. However, reliability and trustworthiness of such techniques is a major concern. In inverse problems in imaging, the focus of this paper, there is increasing empirical evidence that methods may suffer from hallucinations, i.e., false, but realistic-looking artifacts; instability, i.e., sensitivity to perturbations in the data; and unpredictable generalization, i.e., excellent performance on some images, but significant deterioration on others. This paper provides a theoretical foundation for these phenomena. We give mathematical explanations for how and when such effects arise in arbitrary reconstruction methods, with several of our results taking the form of `no free lunch' theorems. Specifically, we show that (i) methods that overperform on a single image can wrongly transfer details from one image to another, creating a hallucination, (ii) methods that overperform on two or more images can hallucinate or be unstable, (iii) optimizing the accuracy-stability trade-off is generally difficult, (iv) hallucinations and instabilities, if they occur, are not rare events, and may be encouraged by standard training, (v) it may be impossible to construct optimal reconstruction maps for certain problems. Our results trace these effects to the kernel of the forward operator whenever it is nontrivial, but also apply to the case when the forward operator is ill-conditioned. Based on these insights, our work aims to spur research into new ways to develop robust and reliable AI-based methods for inverse problems in imaging.
Authors: Levi McClenny, Ulisses Braga-Neto
Abstract: Physics-Informed Neural Networks (PINNs) have emerged recently as a promising application of deep neural networks to the numerical solution of nonlinear partial differential equations (PDEs). However, it has been recognized that adaptive procedures are needed to force the neural network to fit accurately the stubborn spots in the solution of "stiff" PDEs. In this paper, we propose a fundamentally new way to train PINNs adaptively, where the adaptation weights are fully trainable and applied to each training point individually, so the neural network learns autonomously which regions of the solution are difficult and is forced to focus on them. The self-adaptation weights specify a soft multiplicative soft attention mask, which is reminiscent of similar mechanisms used in computer vision. The basic idea behind these SA-PINNs is to make the weights increase as the corresponding losses increase, which is accomplished by training the network to simultaneously minimize the losses and maximize the weights. In addition, we show how to build a continuous map of self-adaptive weights using Gaussian Process regression, which allows the use of stochastic gradient descent in problems where conventional gradient descent is not enough to produce accurate solutions. Finally, we derive the Neural Tangent Kernel matrix for SA-PINNs and use it to obtain a heuristic understanding of the effect of the self-adaptive weights on the dynamics of training in the limiting case of infinitely-wide PINNs, which suggests that SA-PINNs work by producing a smooth equalization of the eigenvalues of the NTK matrix corresponding to the different loss terms. In numerical experiments with several linear and nonlinear benchmark problems, the SA-PINN outperformed other state-of-the-art PINN algorithm in L2 error, while using a smaller number of training epochs.
Authors: Tao Fan, Weijing Chen, Guoqiang Ma, Yan Kang, Lixin Fan, Qiang Yang
Abstract: Gradient boosting decision tree (GBDT) is an ensemble machine learning algorithm, which is widely used in industry, due to its good performance and easy interpretation. Due to the problem of data isolation and the requirement of privacy, many works try to use vertical federated learning to train machine learning models collaboratively with privacy guarantees between different data owners. SecureBoost is one of the most popular vertical federated learning algorithms for GBDT. However, in order to achieve privacy preservation, SecureBoost involves complex training procedures and time-consuming cryptography operations. This causes SecureBoost to be slow to train and does not scale to large scale data. In this work, we propose SecureBoost+, a large-scale and high-performance vertical federated gradient boosting decision tree framework. SecureBoost+ is secure in the semi-honest model, which is the same as SecureBoost. SecureBoost+ can be scaled up to tens of millions of data samples easily. SecureBoost+ achieves high performance through several novel optimizations for SecureBoost, including ciphertext operation optimization, the introduction of new training mechanisms, and multi-classification training optimization. The experimental results show that SecureBoost+ is 6-35x faster than SecureBoost, but with the same accuracy and can be scaled up to tens of millions of data samples and thousands of feature dimensions.
Authors: Luca Cosmo, Giorgia Minello, Alessandro Bicciato, Michael Bronstein, Emanuele Rodol\`a, Luca Rossi, Andrea Torsello
Abstract: The convolution operator at the core of many modern neural architectures can effectively be seen as performing a dot product between an input matrix and a filter. While this is readily applicable to data such as images, which can be represented as regular grids in the Euclidean space, extending the convolution operator to work on graphs proves more challenging, due to their irregular structure. In this paper, we propose to use graph kernels, i.e. kernel functions that compute an inner product on graphs, to extend the standard convolution operator to the graph domain. This allows us to define an entirely structural model that does not require computing the embedding of the input graph. Our architecture allows to plug-in any type of graph kernels and has the added benefit of providing some interpretability in terms of the structural masks that are learned during the training process, similarly to what happens for convolutional masks in traditional convolutional neural networks. We perform an extensive ablation study to investigate the model hyper-parameters' impact and show that our model achieves competitive performance on standard graph classification and regression datasets.
Authors: Omar Besbes, Will Ma, Omar Mouchtaki
Abstract: How should one leverage historical data when past observations are not perfectly indicative of the future, e.g., due to the presence of unobserved confounders which one cannot "correct" for? Motivated by this question, we study a data-driven decision-making framework in which historical samples are generated from unknown and different distributions assumed to lie in a heterogeneity ball with known radius and centered around the (also) unknown future (out-of-sample) distribution on which the performance of a decision will be evaluated. This work aims at analyzing the performance of central data-driven policies but also near-optimal ones in these heterogeneous environments and understanding key drivers of performance. We establish a first result which allows to upper bound the asymptotic worst-case regret of a broad class of policies. Leveraging this result, for any integral probability metric, we provide a general analysis of the performance achieved by Sample Average Approximation (SAA) as a function of the radius of the heterogeneity ball. This analysis is centered around the approximation parameter, a notion of complexity we introduce to capture how the interplay between the heterogeneity and the problem structure impacts the performance of SAA. In turn, we illustrate through several widely-studied problems -- e.g., newsvendor, pricing -- how this methodology can be applied and find that the performance of SAA varies considerably depending on the combinations of problem classes and heterogeneity. The failure of SAA for certain instances motivates the design of alternative policies to achieve rate-optimality. We derive problem-dependent policies achieving strong guarantees for the illustrative problems described above and provide initial results towards a principled approach for the design and analysis of general rate-optimal algorithms.
Authors: Zhiqi Bu, Yu-Xiang Wang, Sheng Zha, George Karypis
Abstract: We study the problem of differentially private (DP) fine-tuning of large pre-trained models -- a recent privacy-preserving approach suitable for solving downstream tasks with sensitive data. Existing work has demonstrated that high accuracy is possible under strong privacy constraint, yet requires significant computational overhead or modifications to the network architecture. We propose differentially private bias-term fine-tuning (DP-BiTFiT), which matches the state-of-the-art accuracy for DP algorithms and the efficiency of the standard BiTFiT. DP-BiTFiT is model agnostic (not modifying the network architecture), parameter efficient (only training about 0.1% of the parameters), and computation efficient (almost removing the overhead caused by DP, in both the time and space complexity). On a wide range of tasks, DP-BiTFiT is 2~30X faster and uses 2~8X less memory than DP full fine-tuning, even faster than the standard full fine-tuning. This amazing efficiency enables us to conduct DP fine-tuning on language and vision tasks with long-sequence texts and high-resolution images, which were computationally difficult using existing methods. We open-source our code at FastDP (https://github.com/awslabs/fast-differential-privacy).
URLs: https://github.com/awslabs/fast-differential-privacy).
Authors: Ariel Neufeld, Julian Sester
Abstract: We present a novel $Q$-learning algorithm tailored to solve distributionally robust Markov decision problems where the corresponding ambiguity set of transition probabilities for the underlying Markov decision process is a Wasserstein ball around a (possibly estimated) reference measure. We prove convergence of the presented algorithm and provide several examples also using real data to illustrate both the tractability of our algorithm as well as the benefits of considering distributional robustness when solving stochastic optimal control problems, in particular when the estimated distributions turn out to be misspecified in practice.
Authors: Gen Li, Yanxi Chen, Yu Huang, Yuejie Chi, H. Vincent Poor, Yuxin Chen
Abstract: Efficient computation of the optimal transport distance between two distributions serves as an algorithm subroutine that empowers various applications. This paper develops a scalable first-order optimization-based method that computes optimal transport to within $\varepsilon$ additive accuracy with runtime $\widetilde{O}( n^2/\varepsilon)$, where $n$ denotes the dimension of the probability distributions of interest. Our algorithm achieves the state-of-the-art computational guarantees among all first-order methods, while exhibiting favorable numerical performance compared to classical algorithms like Sinkhorn and Greenkhorn. Underlying our algorithm designs are two key elements: (a) converting the original problem into a bilinear minimax problem over probability distributions; (b) exploiting the extragradient idea -- in conjunction with entropy regularization and adaptive learning rates -- to accelerate convergence.
Authors: Yinsong Wang, Shahin Shahrampour
Abstract: This paper addresses a cross-modal learning framework, where the objective is to enhance the performance of supervised learning in the primary modality using an unlabeled, unpaired secondary modality. Taking a probabilistic approach for missing information estimation, we show that the extra information contained in the secondary modality can be estimated via Nadaraya-Watson (NW) kernel regression, which can further be expressed as a kernelized cross-attention module (under linear transformation). This expression lays the foundation for introducing The Attention Patch (TAP), a simple neural network add-on that can be trained to allow data-level knowledge transfer from the unlabeled modality. We provide extensive numerical simulations using real-world datasets to show that TAP can provide statistically significant improvement in generalization across different domains and different neural network architectures, making use of seemingly unusable unlabeled cross-modal data.
Authors: Taofeng Xie, Chentao Cao, Zhuoxu Cui, Yu Guo, Caiying Wu, Xuemei Wang, Qingneng Li, Zhanli Hu, Tao Sun, Ziru Sang, Yihang Zhou, Yanjie Zhu, Dong Liang, Qiyu Jin, Hongwu Zeng, Guoqing Chen, Haifeng Wang
Abstract: MRI and PET are crucial diagnostic tools for brain diseases, as they provide complementary information on brain structure and function. However, PET scanning is costly and involves radioactive exposure, resulting in a lack of PET. Moreover, simultaneous PET and MRI at ultra-high-field are currently hardly infeasible. Ultra-high-field imaging has unquestionably proven valuable in both clinical and academic settings, especially in the field of cognitive neuroimaging. These motivate us to propose a method for synthetic PET from high-filed MRI and ultra-high-field MRI. From a statistical perspective, the joint probability distribution (JPD) is the most direct and fundamental means of portraying the correlation between PET and MRI. This paper proposes a novel joint diffusion attention model which has the joint probability distribution and attention strategy, named JDAM. JDAM has a diffusion process and a sampling process. The diffusion process involves the gradual diffusion of PET to Gaussian noise by adding Gaussian noise, while MRI remains fixed. JPD of MRI and noise-added PET was learned in the diffusion process. The sampling process is a predictor-corrector. PET images were generated from MRI by JPD of MRI and noise-added PET. The predictor is a reverse diffusion process and the corrector is Langevin dynamics. Experimental results on the public Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrate that the proposed method outperforms state-of-the-art CycleGAN for high-field MRI (3T MRI). Finally, synthetic PET images from the ultra-high-field (5T MRI and 7T MRI) be attempted, providing a possibility for ultra-high-field PET-MRI imaging.
Authors: Chia-Hao Li, Niraj K. Jha
Abstract: Modern advances in machine learning (ML) and wearable medical sensors (WMSs) in edge devices have enabled ML-driven disease detection for smart healthcare. Conventional ML-driven methods for disease detection rely on customizing individual models for each disease and its corresponding WMS data. However, such methods lack adaptability to distribution shifts and new task classification classes. In addition, they need to be rearchitected and retrained from scratch for each new disease. Moreover, installing multiple ML models in an edge device consumes excessive memory, drains the battery faster, and complicates the detection process. To address these challenges, we propose DOCTOR, a multi-disease detection continual learning (CL) framework based on WMSs. It employs a multi-headed deep neural network (DNN) and a replay-style CL algorithm. The CL algorithm enables the framework to continually learn new missions where different data distributions, classification classes, and disease detection tasks are introduced sequentially. It counteracts catastrophic forgetting with a data preservation method and a synthetic data generation (SDG) module. The data preservation method preserves the most informative subset of real training data from previous missions for exemplar replay. The SDG module models the probability distribution of the real training data and generates synthetic data for generative replay while retaining data privacy. The multi-headed DNN enables DOCTOR to detect multiple diseases simultaneously based on user WMS data. We demonstrate DOCTOR's efficacy in maintaining high disease classification accuracy with a single DNN model in various CL experiments. In complex scenarios, DOCTOR achieves 1.43 times better average test accuracy, 1.25 times better F1-score, and 0.41 higher backward transfer than the naive fine-tuning framework with a small model size of less than 350KB.
Authors: Mingyang Zhang, Hao Chen, Chunhua Shen, Zhen Yang, Linlin Ou, Xinyi Yu, Bohan Zhuang
Abstract: Large Language Models (LLMs), such as LLaMA and T5, have shown exceptional performance across various tasks through fine-tuning. Although low-rank adaption (LoRA) has emerged to cheaply fine-tune these LLMs on downstream tasks, their deployment is still hindered by the vast model scale and computational costs. Post-training model pruning offers a way to compress LLMs. However, the current pruning methods designed for LLMs are not compatible with LoRA. This is due to their utilization of unstructured pruning on LLMs, impeding the merging of LoRA weights, or their dependence on the gradients of pre-trained weights to guide pruning, which can impose significant memory overhead. To this end, we propose LoRAPrune, a new framework that delivers an accurate structured pruned model in a highly memory-efficient manner. Specifically, we first design a LoRA-guided pruning criterion, which uses the weights and gradients of LoRA, rather than the gradients of pre-trained weights for importance estimation. We subsequently integrate this criterion into an iterative pruning process, effectively removing redundant channels and heads. Extensive experimental results demonstrate the superior performance of our LoRAPrune over existing approaches on the LLaMA series models. At a 50\% compression rate, LoRAPrune demonstrates superior performance over LLM-Pruner, achieving a reduction in perplexity by 4.81 on WikiText2 and 3.46 on PTB, while also decreasing memory usage by 52.6%. Besides, LoRAPrune also matches semi-structural pruning across multiple LLMs, proving its wide applicability. The code is available at https://github.com/aim-uofa/LoRAPrune.
Authors: Etash Kumar Guha
Abstract: Reinforcement Learning is a powerful framework for training agents to navigate different situations, but it is susceptible to changes in environmental dynamics. However, solving Markov Decision Processes that are robust to changes is difficult due to nonconvexity and size of action or state spaces. While most works have analyzed this problem by taking different assumptions on the problem, a general and efficient theoretical analysis is still missing. However, we generate a simple framework for improving robustness by solving a minimax iterative optimization problem where a policy player and an environmental dynamics player are playing against each other. Leveraging recent results in online nonconvex learning and techniques from improving policy gradient methods, we yield an algorithm that maximizes the robustness of the Value Function on the order of $\mathcal{O}\left(\frac{1}{T^{\frac{1}{2}}}\right)$ where $T$ is the number of iterations of the algorithm.
Authors: Vinod Raman, Unique Subedi, Ambuj Tewari
Abstract: We study a variant of online multiclass classification where the learner predicts a single label but receives a \textit{set of labels} as feedback. In this model, the learner is penalized for not outputting a label contained in the revealed set. We show that unlike online multiclass learning with single-label feedback, deterministic and randomized online learnability are \textit{not equivalent} even in the realizable setting with set-valued feedback. Accordingly, we give two new combinatorial dimensions, named the Set Littlestone and Measure Shattering dimension, that tightly characterize deterministic and randomized online learnability respectively in the realizable setting. In addition, we show that the Measure Shattering dimension characterizes online learnability in the agnostic setting and tightly quantifies the minimax regret. Finally, we use our results to establish bounds on the minimax regret for three practical learning settings: online multilabel ranking, online multilabel classification, and real-valued prediction with interval-valued response.
Authors: Sana Ebrahimi, Rishi Advani, Abolfazl Asudeh
Abstract: The training process of neural networks is known to be time-consuming, and having a deep architecture only aggravates the issue. This process consists mostly of matrix operations, among which matrix multiplication is the bottleneck. Several sampling-based techniques have been proposed for speeding up the training time of deep neural networks by approximating the matrix products. These techniques fall under two categories: (i) sampling a subset of nodes in every hidden layer as active at every iteration and (ii) sampling a subset of nodes from the previous layer to approximate the current layer's activations using the edges from the sampled nodes. In both cases, the matrix products are computed using only the selected samples. In this paper, we evaluate the feasibility of these approaches on CPU machines with limited computational resources. Making a connection between the two research directions as special cases of approximating matrix multiplications in the context of neural networks, we provide a negative theoretical analysis that shows feedforward approximation is an obstacle against scalability. We conduct comprehensive experimental evaluations that demonstrate the most pressing challenges and limitations associated with the studied approaches. We observe that the hashing-based node selection method is not scalable to a large number of layers, confirming our theoretical analysis. Finally, we identify directions for future research.
Authors: Qi Yan, Zhengyang Liang, Yang Song, Renjie Liao, Lele Wang
Abstract: Diffusion models based on permutation-equivariant networks can learn permutation-invariant distributions for graph data. However, in comparison to their non-invariant counterparts, we have found that these invariant models encounter greater learning challenges since 1) their effective target distributions exhibit more modes; 2) their optimal one-step denoising scores are the score functions of Gaussian mixtures with more components. Motivated by this analysis, we propose a non-invariant diffusion model, called $\textit{SwinGNN}$, which employs an efficient edge-to-edge 2-WL message passing network and utilizes shifted window based self-attention inspired by SwinTransformers. Further, through systematic ablations, we identify several critical training and sampling techniques that significantly improve the sample quality of graph generation. At last, we introduce a simple post-processing trick, $\textit{i.e.}$, randomly permuting the generated graphs, which provably converts any graph generative model to a permutation-invariant one. Extensive experiments on synthetic and real-world protein and molecule datasets show that our SwinGNN achieves state-of-the-art performances. Our code is released at https://github.com/qiyan98/SwinGNN.
Authors: Madelyne Xiao, Jonathan Mayer
Abstract: We examine the disconnect between scholarship and practice in applying machine learning to trust and safety problems, using misinformation detection as a case study. We survey literature on automated detection of misinformation across a corpus of 248 well-cited papers in the field. We then examine subsets of papers for data and code availability, design missteps, reproducibility, and generalizability. Our paper corpus includes published work in security, natural language processing, and computational social science. Across these disparate disciplines, we identify common errors in dataset and method design. In general, detection tasks are often meaningfully distinct from the challenges that online services actually face. Datasets and model evaluation are often non-representative of real-world contexts, and evaluation frequently is not independent of model training. We demonstrate the limitations of current detection methods in a series of three representative replication studies. Based on the results of these analyses and our literature survey, we conclude that the current state-of-the-art in fully-automated misinformation detection has limited efficacy in detecting human-generated misinformation. We offer recommendations for evaluating applications of machine learning to trust and safety problems and recommend future directions for research.
Authors: Zhenjiang Mao, Carson Sobolewski, Ivan Ruchkin
Abstract: End-to-end learning has emerged as a major paradigm for developing autonomous systems. Unfortunately, with its performance and convenience comes an even greater challenge of safety assurance. A key factor of this challenge is the absence of the notion of a low-dimensional and interpretable dynamical state, around which traditional assurance methods revolve. Focusing on the online safety prediction problem, this paper proposes a configurable family of learning pipelines based on generative world models, which do not require low-dimensional states. To implement these pipelines, we overcome the challenges of learning safety-informed latent representations and missing safety labels under prediction-induced distribution shift. These pipelines come with statistical calibration guarantees on their safety chance predictions based on conformal prediction. We perform an extensive evaluation of the proposed learning pipelines on two case studies of image-controlled systems: a racing car and a cartpole.
Authors: Samiul Alam, Tuo Zhang, Tiantian Feng, Hui Shen, Zhichao Cao, Dong Zhao, JeongGil Ko, Kiran Somasundaram, Shrikanth S. Narayanan, Salman Avestimehr, Mi Zhang
Abstract: There is a significant relevance of federated learning (FL) in the realm of Artificial Intelligence of Things (AIoT). However, most existing FL works do not use datasets collected from authentic IoT devices and thus do not capture unique modalities and inherent challenges of IoT data. To fill this critical gap, in this work, we introduce FedAIoT, an FL benchmark for AIoT. FedAIoT includes eight datasets collected from a wide range of IoT devices. These datasets cover unique IoT modalities and target representative applications of AIoT. FedAIoT also includes a unified end-to-end FL framework for AIoT that simplifies benchmarking the performance of the datasets. Our benchmark results shed light on the opportunities and challenges of FL for AIoT. We hope FedAIoT could serve as an invaluable resource to foster advancements in the important field of FL for AIoT. The repository of FedAIoT is maintained at https://github.com/AIoT-MLSys-Lab/FedAIoT.
Authors: Qingsong Xu, Yilei Shi, Jonathan Bamber, Ye Tuo, Ralf Ludwig, Xiao Xiang Zhu
Abstract: Accurate hydrological understanding and water cycle prediction are crucial for addressing scientific and societal challenges associated with the management of water resources, particularly under the dynamic influence of anthropogenic climate change. Existing reviews predominantly concentrate on the development of machine learning (ML) in this field, yet there is a clear distinction between hydrology and ML as separate paradigms. Here, we introduce physics-aware ML as a transformative approach to overcome the perceived barrier and revolutionize both fields. Specifically, we present a comprehensive review of the physics-aware ML methods, building a structured community (PaML) of existing methodologies that integrate prior physical knowledge or physics-based modeling into ML. We systematically analyze these PaML methodologies with respect to four aspects: physical data-guided ML, physics-informed ML, physics-embedded ML, and physics-aware hybrid learning. PaML facilitates ML-aided hypotheses, accelerating insights from big data and fostering scientific discoveries. We first conduct a systematic review of hydrology in PaML, including rainfall-runoff hydrological processes and hydrodynamic processes, and highlight the most promising and challenging directions for different objectives and PaML methods. Finally, a new PaML-based hydrology platform, termed HydroPML, is released as a foundation for hydrological applications. HydroPML enhances the explainability and causality of ML and lays the groundwork for the digital water cycle's realization. The HydroPML platform is publicly available at https://hydropml.github.io/.
Authors: Pengyu Li, Xiao Li, Yutong Wang, Qing Qu
Abstract: We study deep neural networks for the multi-label classification (MLab) task through the lens of neural collapse (NC). Previous works have been restricted to the multi-class classification setting and discovered a prevalent NC phenomenon comprising of the following properties for the last-layer features: (i) the variability of features within every class collapses to zero, (ii) the set of feature means form an equi-angular tight frame (ETF), and (iii) the last layer classifiers collapse to the feature mean upon some scaling. We generalize the study to multi-label learning, and prove for the first time that a generalized NC phenomenon holds with the "pick-all-label" formulation, which we term as MLab NC. While the ETF geometry remains consistent for features with a single label, multi-label scenarios introduce a unique combinatorial aspect we term the "tag-wise average" property, where the means of features with multiple labels are the scaled averages of means for single-label instances. Theoretically, under proper assumptions on the features, we establish that the only global optimizer of the pick-all-label cross-entropy loss satisfy the multi-label NC. In practice, we demonstrate that our findings can lead to better test performance with more efficient training techniques for MLab learning.
Authors: James K Ruffle, Henry Watkins, Robert J Gray, Harpreet Hyare, Michel Thiebaut de Schotten, Parashkev Nachev
Abstract: The architecture of the brain is too complex to be intuitively surveyable without the use of compressed representations that project its variation into a compact, navigable space. The task is especially challenging with high-dimensional data, such as gene expression, where the joint complexity of anatomical and transcriptional patterns demands maximum compression. Established practice is to use standard principal component analysis (PCA), whose computational felicity is offset by limited expressivity, especially at great compression ratios. Employing whole-brain, voxel-wise Allen Brain Atlas transcription data, here we systematically compare compressed representations based on the most widely supported linear and non-linear methods-PCA, kernel PCA, non-negative matrix factorization (NMF), t-stochastic neighbour embedding (t-SNE), uniform manifold approximation and projection (UMAP), and deep auto-encoding-quantifying reconstruction fidelity, anatomical coherence, and predictive utility with respect to signalling, microstructural, and metabolic targets. We show that deep auto-encoders yield superior representations across all metrics of performance and target domains, supporting their use as the reference standard for representing transcription patterns in the human brain.
Authors: Vinod Raman, Unique Subedi, Ananth Raman, Ambuj Tewari
Abstract: In online binary classification under \emph{apple tasting} feedback, the learner only observes the true label if it predicts ``1". First studied by \cite{helmbold2000apple}, we revisit this classical partial-feedback setting and study online learnability from a combinatorial perspective. We show that the Littlestone dimension continues to provide a tight quantitative characterization of apple tasting in the agnostic setting, closing an open question posed by \cite{helmbold2000apple}. In addition, we give a new combinatorial parameter, called the Effective width, that tightly quantifies the minimax expected mistakes in the realizable setting. As a corollary, we use the Effective width to establish a \emph{trichotomy} of the minimax expected number of mistakes in the realizable setting. In particular, we show that in the realizable setting, the expected number of mistakes of any learner, under apple tasting feedback, can be $\Theta(1), \Theta(\sqrt{T})$, or $\Theta(T)$. This is in contrast to the full-information realizable setting where only $\Theta(1)$ and $\Theta(T)$ are possible.
Authors: Moshe Eliasof, Davide Murari, Ferdia Sherry, Carola-Bibiane Sch\"onlieb
Abstract: Graph Neural Networks (GNNs) have established themselves as a key component in addressing diverse graph-based tasks. Despite their notable successes, GNNs remain susceptible to input perturbations in the form of adversarial attacks. This paper introduces an innovative approach to fortify GNNs against adversarial perturbations through the lens of contractive dynamical systems. Our method introduces graph neural layers based on differential equations with contractive properties, which, as we show, improve the robustness of GNNs. A distinctive feature of the proposed approach is the simultaneous learned evolution of both the node features and the adjacency matrix, yielding an intrinsic enhancement of model robustness to perturbations in the input features and the connectivity of the graph. We mathematically derive the underpinnings of our novel architecture and provide theoretical insights to reason about its expected behavior. We demonstrate the efficacy of our method through numerous real-world benchmarks, reading on par or improved performance compared to existing methods.
Authors: Hao Zhu, Brice De La Crompe, Gabriel Kalweit, Artur Schneider, Maria Kalweit, Ilka Diester, Joschka Boedecker
Abstract: In advancing the understanding of natural decision-making processes, inverse reinforcement learning (IRL) methods have proven instrumental in reconstructing animal's intentions underlying complex behaviors. Given the recent development of a continuous-time multi-intention IRL framework, there has been persistent inquiry into inferring discrete time-varying rewards with IRL. To address this challenge, we introduce the class of hierarchical inverse Q-learning (HIQL) algorithms. Through an unsupervised learning process, HIQL divides expert trajectories into multiple intention segments, and solves the IRL problem independently for each. Applying HIQL to simulated experiments and several real animal behavior datasets, our approach outperforms current benchmarks in behavior prediction and produces interpretable reward functions. Our results suggest that the intention transition dynamics underlying complex decision-making behavior is better modeled by a step function instead of a smoothly varying function. This advancement holds promise for neuroscience and cognitive science, contributing to a deeper understanding of decision-making and uncovering underlying brain mechanisms.
Authors: Abhishek Sinha, Himanshi Tibrewal, Mansi Gupta, Nikhar Waghela, Shivank Garg
Abstract: In this evolving era of machine learning security, membership inference attacks have emerged as a potent threat to the confidentiality of sensitive data. In this attack, adversaries aim to determine whether a particular point was used during the training of a target model. This paper proposes a new method to gauge a data point's membership in a model's training set. Instead of correlating loss with membership, as is traditionally done, we have leveraged the fact that training examples generally exhibit higher confidence values when classified into their actual class. During training, the model is essentially being 'fit' to the training data and might face particular difficulties in generalization to unseen data. This asymmetry leads to the model achieving higher confidence on the training data as it exploits the specific patterns and noise present in the training data. Our proposed approach leverages the confidence values generated by the machine learning model. These confidence values provide a probabilistic measure of the model's certainty in its predictions and can further be used to infer the membership of a given data point. Additionally, we also introduce another variant of our method that allows us to carry out this attack without knowing the ground truth(true class) of a given data point, thus offering an edge over existing label-dependent attack methods.
Authors: Sungbin Shin, Dongyeop Lee, Maksym Andriushchenko, Namhoon Lee
Abstract: Training an overparameterized neural network can yield minimizers of different generalization capabilities despite the same level of training loss. Meanwhile, with evidence that suggests a strong correlation between the sharpness of minima and their generalization errors, increasing efforts have been made to develop optimization methods to explicitly find flat minima as more generalizable solutions. Despite its contemporary relevance to overparameterization, however, this sharpness-aware minimization (SAM) strategy has not been studied much yet as to exactly how it is affected by overparameterization. Hence, in this work, we analyze SAM under overparameterization of varying degrees and present both empirical and theoretical results that indicate a critical influence of overparameterization on SAM. At first, we conduct extensive numerical experiments across vision, language, graph, and reinforcement learning domains and show that SAM consistently improves with overparameterization. Next, we attribute this phenomenon to the interplay between the enlarged solution space and increased implicit bias from overparameterization. Further, we prove multiple theoretical benefits of overparameterization for SAM to attain (i) minima with more uniform Hessian moments compared to SGD, (ii) much faster convergence at a linear rate, and (iii) lower test error for two-layer networks. Last but not least, we discover that the effect of overparameterization is more significantly pronounced in practical settings of label noise and sparsity, and yet, sufficient regularization is necessary.
Authors: Matthew Lau, Ismaila Seck, Athanasios P Meliopoulos, Wenke Lee, Eugene Ndiaye
Abstract: The inability to linearly classify XOR has motivated much of deep learning. We revisit this age-old problem and show that linear classification of XOR is indeed possible. Instead of separating data between halfspaces, we propose a slightly different paradigm, equality separation, that adapts the SVM objective to distinguish data within or outside the margin. Our classifier can then be integrated into neural network pipelines with a smooth approximation. From its properties, we intuit that equality separation is suitable for anomaly detection. To formalize this notion, we introduce closing numbers, a quantitative measure on the capacity for classifiers to form closed decision regions for anomaly detection. Springboarding from this theoretical connection between binary classification and anomaly detection, we test our hypothesis on supervised anomaly detection experiments, showing that equality separation can detect both seen and unseen anomalies.
Authors: Alexandru Tifrea, Preethi Lahoti, Ben Packer, Yoni Halpern, Ahmad Beirami, Flavien Prost
Abstract: Despite achieving promising fairness-error trade-offs, in-processing mitigation techniques for group fairness cannot be employed in numerous practical applications with limited computation resources or no access to the training pipeline of the prediction model. In these situations, post-processing is a viable alternative. However, current methods are tailored to specific problem settings and fairness definitions and hence, are not as broadly applicable as in-processing. In this work, we propose a framework that turns any regularized in-processing method into a post-processing approach. This procedure prescribes a way to obtain post-processing techniques for a much broader range of problem settings than the prior post-processing literature. We show theoretically and through extensive experiments that our framework preserves the good fairness-error trade-offs achieved with in-processing and can improve over the effectiveness of prior post-processing methods. Finally, we demonstrate several advantages of a modular mitigation strategy that disentangles the training of the prediction model from the fairness mitigation, including better performance on tasks with partial group labels.
Authors: Xingrun Xing, Li Du, Xinyuan Wang, Xianlin Zeng, Yequan Wang, Zheng Zhang, Jiajun Zhang
Abstract: Pretrained foundation models offer substantial benefits for a wide range of downstream tasks, which can be one of the most potential techniques to access artificial general intelligence. However, scaling up foundation transformers for maximal task-agnostic knowledge has brought about computational challenges, especially on resource-limited devices such as mobiles. This work proposes the first Binary Pretrained Foundation Transformer (BiPFT) for natural language understanding (NLU) tasks, which remarkably saves 56 times operations and 28 times memory. In contrast to previous task-specific binary transformers, BiPFT exhibits a substantial enhancement in the learning capabilities of binary neural networks (BNNs), promoting BNNs into the era of pre-training. Benefiting from extensive pretraining data, we further propose a data-driven binarization method. Specifically, we first analyze the binarization error in self-attention operations and derive the polynomials of binarization error. To simulate full-precision self-attention, we define binarization error as binarization residual polynomials, and then introduce low-rank estimators to model these polynomials. Extensive experiments validate the effectiveness of BiPFTs, surpassing task-specific baseline by 15.4% average performance on the GLUE benchmark. BiPFT also demonstrates improved robustness to hyperparameter changes, improved optimization efficiency, and reduced reliance on downstream distillation, which consequently generalize on various NLU tasks and simplify the downstream pipeline of BNNs. Our code and pretrained models are publicly available at https://github.com/Xingrun-Xing/BiPFT.
Authors: Jiachuan Wang, Shimin Di, Lei Chen, Charles Wang Wai Ng
Abstract: Recently, emergence has received widespread attention from the research community along with the success of large-scale models. Different from the literature, we hypothesize a key factor that promotes the performance during the increase of scale: the reduction of monosemantic neurons that can only form one-to-one correlations with specific features. Monosemantic neurons tend to be sparser and have negative impacts on the performance in large models. Inspired by this insight, we propose an intuitive idea to identify monosemantic neurons and inhibit them. However, achieving this goal is a non-trivial task as there is no unified quantitative evaluation metric and simply banning monosemantic neurons does not promote polysemanticity in neural networks. Therefore, we first propose a new metric to measure the monosemanticity of neurons with the guarantee of efficiency for online computation, then introduce a theoretically supported method to suppress monosemantic neurons and proactively promote the ratios of polysemantic neurons in training neural networks. We validate our conjecture that monosemanticity brings about performance change at different model scales on a variety of neural networks and benchmark datasets in different areas, including language, image, and physics simulation tasks. Further experiments validate our analysis and theory regarding the inhibition of monosemanticity.
Authors: Viacheslav Sinii, Alexander Nikulin, Vladislav Kurenkov, Ilya Zisman, Sergey Kolesnikov
Abstract: Recently, it has been shown that transformers pre-trained on diverse datasets with multi-episode contexts can generalize to new reinforcement learning tasks in-context. A key limitation of previously proposed models is their reliance on a predefined action space size and structure. The introduction of a new action space often requires data re-collection and model re-training, which can be costly for some applications. In our work, we show that it is possible to mitigate this issue by proposing the Headless-AD model that, despite being trained only once, is capable of generalizing to discrete action spaces of variable size, semantic content and order. By experimenting with Bernoulli and contextual bandits, as well as a gridworld environment, we show that Headless-AD exhibits significant capability to generalize to action spaces it has never encountered, even outperforming specialized models trained for a specific set of actions on several environment configurations. Implementation is available at: https://github.com/corl-team/headless-ad.
Authors: Subhodip Panda, Prathosh AP
Abstract: The heightened emphasis on the regulation of deep generative models, propelled by escalating concerns pertaining to privacy and compliance with regulatory frameworks, underscores the imperative need for precise control mechanisms over these models. This urgency is particularly underscored by instances in which generative models generate outputs that encompass objectionable, offensive, or potentially injurious content. In response, machine unlearning has emerged to selectively forget specific knowledge or remove the influence of undesirable data subsets from pre-trained models. However, modern machine unlearning approaches typically assume access to model parameters and architectural details during unlearning, which is not always feasible. In multitude of downstream tasks, these models function as black-box systems, with inaccessible pre-trained parameters, architectures, and training data. In such scenarios, the possibility of filtering undesired outputs becomes a practical alternative. The primary goal of this study is twofold: first, to elucidate the relationship between filtering and unlearning processes, and second, to formulate a methodology aimed at mitigating the display of undesirable outputs generated from models characterized as black-box systems. Theoretical analysis in this study demonstrates that, in the context of black-box models, filtering can be seen as a form of weak unlearning. Our proposed \textbf{\textit{Feature Aware Similarity Thresholding(FAST)}} method effectively suppresses undesired outputs by systematically encoding the representation of unwanted features in the latent space.
Authors: Michael Kohler, Adam Krzyzak
Abstract: One of the most recent and fascinating breakthroughs in artificial intelligence is ChatGPT, a chatbot which can simulate human conversation. ChatGPT is an instance of GPT4, which is a language model based on generative gredictive gransformers. So if one wants to study from a theoretical point of view, how powerful such artificial intelligence can be, one approach is to consider transformer networks and to study which problems one can solve with these networks theoretically. Here it is not only important what kind of models these network can approximate, or how they can generalize their knowledge learned by choosing the best possible approximation to a concrete data set, but also how well optimization of such transformer network based on concrete data set works. In this article we consider all these three different aspects simultaneously and show a theoretical upper bound on the missclassification probability of a transformer network fitted to the observed data. For simplicity we focus in this context on transformer encoder networks which can be applied to define an estimate in the context of a classification problem involving natural language.
Authors: Shuhan Zheng, Ziqiang Li, Kantaro Fujiwara, Gouhei Tanaka
Abstract: Dynamical behaviors of complex interacting systems, including brain activities, financial price movements, and physical collective phenomena, are associated with underlying interactions between the system's components. The issue of uncovering interaction relations in such systems using observable dynamics is called relational inference. In this study, we propose a Diffusion model for Relational Inference (DiffRI), inspired by a self-supervised method for probabilistic time series imputation. DiffRI learns to infer the probability of the presence of connections between components through conditional diffusion modeling.
Authors: Hans-Werner Wiesbrock, J\"urgen Gro{\ss}mann
Abstract: This article proposes a test procedure that can be used to test ML models and ML-based systems independently of the actual training process. In this way, the typical quality statements such as accuracy and precision of these models and system can be verified independently, taking into account their black box character and the immanent stochastic properties of ML models and their training data. The article presents first results from a set of test experiments and suggest extensions to existing test methods reflecting the stochastic nature of ML models and ML-based systems.
Authors: Wei Ju, Siyu Yi, Yifan Wang, Qingqing Long, Junyu Luo, Zhiping Xiao, Ming Zhang
Abstract: Graph-structured data, prevalent in domains ranging from social networks to biochemical analysis, serve as the foundation for diverse real-world systems. While graph neural networks demonstrate proficiency in modeling this type of data, their success is often reliant on significant amounts of labeled data, posing a challenge in practical scenarios with limited annotation resources. To tackle this problem, tremendous efforts have been devoted to enhancing graph machine learning performance under low-resource settings by exploring various approaches to minimal supervision. In this paper, we introduce a novel concept of Data-Efficient Graph Learning (DEGL) as a research frontier, and present the first survey that summarizes the current progress of DEGL. We initiate by highlighting the challenges inherent in training models with large labeled data, paving the way for our exploration into DEGL. Next, we systematically review recent advances on this topic from several key aspects, including self-supervised graph learning, semi-supervised graph learning, and few-shot graph learning. Also, we state promising directions for future research, contributing to the evolution of graph machine learning.
Authors: Xisen Jin, Xiang Ren
Abstract: Language models deployed in the wild make errors. However, simply updating the model with the corrected error instances causes catastrophic forgetting -- the updated model makes errors on instances learned during the instruction tuning or upstream training phase. Randomly replaying upstream data yields unsatisfactory performance and often comes with high variance and poor controllability. To this end, we try to forecast upstream examples that will be forgotten due to a model update for improved controllability of the replay process and interpretability. We train forecasting models given a collection of online learned examples and corresponding forgotten upstream pre-training examples. We propose a partially interpretable forecasting model based on the observation that changes in pre-softmax logit scores of pretraining examples resemble that of online learned examples, which performs decently on BART but fails on T5 models. We further show a black-box classifier based on inner products of example representations achieves better forecasting performance over a series of setups. Finally, we show that we reduce forgetting of upstream pretraining examples by replaying examples that are forecasted to be forgotten, demonstrating the practical utility of forecasting example forgetting.
Authors: Zhiyu Zhang, David Bombara, Heng Yang
Abstract: We study online learning in adversarial nonstationary environments. Since the future can be very different from the past, a critical challenge is to gracefully forget the history while new data comes in. To formalize this intuition, we revisit the discounted regret in online convex optimization, and propose an adaptive (i.e., instance optimal), FTRL-based algorithm that improves the widespread non-adaptive baseline -- gradient descent with a constant learning rate. From a practical perspective, this refines the classical idea of regularization in lifelong learning: we show that designing good regularizers can be guided by the principled theory of adaptive online optimization. Complementing this result, we also consider the (Gibbs and Cand\`es, 2021)-style online conformal prediction problem, where the goal is to sequentially predict the uncertainty sets of a black-box machine learning model. We show that the FTRL nature of our algorithm can simplify the conventional gradient-descent-based analysis, leading to instance-dependent performance guarantees.
Authors: Yuji Roh, Qingyun Liu, Huan Gui, Zhe Yuan, Yujin Tang, Steven Euijong Whang, Liang Liu, Shuchao Bi, Lichan Hong, Ed H. Chi, Zhe Zhao
Abstract: Fine-tuning is becoming widely used for leveraging the power of pre-trained foundation models in new downstream tasks. While there are many successes of fine-tuning on various tasks, recent studies have observed challenges in the generalization of fine-tuned models to unseen distributions (i.e., out-of-distribution; OOD). To improve OOD generalization, some previous studies identify the limitations of fine-tuning data and regulate fine-tuning to preserve the general representation learned from pre-training data. However, potential limitations in the pre-training data and models are often ignored. In this paper, we contend that overly relying on the pre-trained representation may hinder fine-tuning from learning essential representations for downstream tasks and thus hurt its OOD generalization. It can be especially catastrophic when new tasks are from different (sub)domains compared to pre-training data. To address the issues in both pre-training and fine-tuning data, we propose a novel generalizable fine-tuning method LEVI (Layer-wise Ensemble of different VIews), where the pre-trained model is adaptively ensembled layer-wise with a small task-specific model, while preserving its efficiencies. By combining two complementing models, LEVI effectively suppresses problematic features in both the fine-tuning data and pre-trained model and preserves useful features for new tasks. Broad experiments with large language and vision models show that LEVI greatly improves fine-tuning generalization via emphasizing different views from fine-tuning data and pre-trained features.
Authors: Myeongseob Ko, Feiyang Kang, Weiyan Shi, Ming Jin, Zhou Yu, Ruoxi Jia
Abstract: Large-scale black-box models have become ubiquitous across numerous applications. Understanding the influence of individual training data sources on predictions made by these models is crucial for improving their trustworthiness. Current influence estimation techniques involve computing gradients for every training point or repeated training on different subsets. These approaches face obvious computational challenges when scaled up to large datasets and models. In this paper, we introduce and explore the Mirrored Influence Hypothesis, highlighting a reciprocal nature of influence between training and test data. Specifically, it suggests that evaluating the influence of training data on test predictions can be reformulated as an equivalent, yet inverse problem: assessing how the predictions for training samples would be altered if the model were trained on specific test samples. Through both empirical and theoretical validations, we demonstrate the wide applicability of our hypothesis. Inspired by this, we introduce a new method for estimating the influence of training data, which requires calculating gradients for specific test samples, paired with a forward pass for each training point. This approach can capitalize on the common asymmetry in scenarios where the number of test samples under concurrent examination is much smaller than the scale of the training dataset, thus gaining a significant improvement in efficiency compared to existing approaches. We demonstrate the applicability of our method across a range of scenarios, including data attribution in diffusion models, data leakage detection, analysis of memorization, mislabeled data detection, and tracing behavior in language models. Our code will be made available at https://github.com/ruoxi-jia-group/Forward-INF.
Authors: Jiaxi Hu, Yuehong Hu, Wei Chen, Ming Jin, Shirui Pan, Qingsong Wen, Yuxuan Liang
Abstract: In long-term time series forecasting (LTSF) tasks, an increasing number of models have acknowledged that discrete time series originate from continuous dynamic systems and have attempted to model their dynamical structures. Recognizing the chaotic nature of real-world data, our model, \textbf{\textit{Attraos}}, incorporates chaos theory into LTSF, perceiving real-world time series as observations from unknown high-dimensional chaotic dynamic systems. Under the concept of attractor invariance, Attraos utilizes non-parametric Phase Space Reconstruction embedding and the proposed multi-scale dynamic memory unit to memorize historical dynamics structure and predicts by a frequency-enhanced local evolution strategy. Detailed theoretical analysis and abundant empirical evidence consistently show that Attraos outperforms various LTSF methods on mainstream LTSF datasets and chaotic datasets with only one-twelfth of the parameters compared to PatchTST.
Authors: Gautam Machiraju, Alexander Derry, Arjun Desai, Neel Guha, Amir-Hossein Karimi, James Zou, Russ Altman, Christopher R\'e, Parag Mallick
Abstract: Feature attribution, the ability to localize regions of the input data that are relevant for classification, is an important capability for ML models in scientific and biomedical domains. Current methods for feature attribution, which rely on "explaining" the predictions of end-to-end classifiers, suffer from imprecise feature localization and are inadequate for use with small sample sizes and high-dimensional datasets due to computational challenges. We introduce prospector heads, an efficient and interpretable alternative to explanation-based attribution methods that can be applied to any encoder and any data modality. Prospector heads generalize across modalities through experiments on sequences (text), images (pathology), and graphs (protein structures), outperforming baseline attribution methods by up to 26.3 points in mean localization AUPRC. We also demonstrate how prospector heads enable improved interpretation and discovery of class-specific patterns in input data. Through their high performance, flexibility, and generalizability, prospectors provide a framework for improving trust and transparency for ML models in complex domains.
Authors: Maurice Kraus, David Steinmann, Antonia W\"ust, Andre Kokozinski, Kristian Kersting
Abstract: The reliability of deep time series models is often compromised by their tendency to rely on confounding factors, which may lead to incorrect outputs. Our newly recorded, naturally confounded dataset named P2S from a real mechanical production line emphasizes this. To avoid "Clever-Hans" moments in time series, i.e., to mitigate confounders, we introduce the method Right on Time (RioT). RioT enables, for the first time, interactions with model explanations across both the time and frequency domain. Feedback on explanations in both domains is then used to constrain the model, steering it away from the annotated confounding factors. The dual-domain interaction strategy is crucial for effectively addressing confounders in time series datasets. We empirically demonstrate that RioT can effectively guide models away from the wrong reasons in P2S as well as popular time series classification and forecasting datasets.
Authors: Aiqing Zhu, Qianxiao Li
Abstract: Learning unknown stochastic differential equations (SDEs) from observed data is a significant and challenging task with applications in various fields. Current approaches often use neural networks to represent drift and diffusion functions, and construct likelihood-based loss by approximating the transition density to train these networks. However, these methods often rely on one-step stochastic numerical schemes, necessitating data with sufficiently high time resolution. In this paper, we introduce novel approximations to the transition density of the parameterized SDE: a Gaussian density approximation inspired by the random perturbation theory of dynamical systems, and its extension, the dynamical Gaussian mixture approximation (DynGMA). Benefiting from the robust density approximation, our method exhibits superior accuracy compared to baseline methods in learning the fully unknown drift and diffusion functions and computing the invariant distribution from trajectory data. And it is capable of handling trajectory data with low time resolution and variable, even uncontrollable, time step sizes, such as data generated from Gillespie's stochastic simulations. We then conduct several experiments across various scenarios to verify the advantages and robustness of the proposed method.
Authors: Jonas H\"ubotter, Bhavya Sukhija, Lenart Treven, Yarden As, Andreas Krause
Abstract: We study the question: How can we select the right data for fine-tuning to a specific task? We call this data selection problem active fine-tuning and show that it is an instance of transductive active learning, a novel generalization of classical active learning. We propose ITL, short for information-based transductive learning, an approach which samples adaptively to maximize information gained about the specified task. We are the first to show, under general regularity assumptions, that such decision rules converge uniformly to the smallest possible uncertainty obtainable from the accessible data. We apply ITL to the few-shot fine-tuning of large neural networks and show that fine-tuning with ITL learns the task with significantly fewer examples than the state-of-the-art.
Authors: Zehua Zhang, Zijie Li, Amir Barati Farimani
Abstract: We propose a mask pretraining method for Graph Neural Networks (GNNs) to improve their performance on fitting potential energy surfaces, particularly in water systems. GNNs are pretrained by recovering spatial information related to masked-out atoms from molecules, then transferred and finetuned on atomic forcefields. Through such pretraining, GNNs learn meaningful prior about structural and underlying physical information of molecule systems that are useful for downstream tasks. From comprehensive experiments and ablation studies, we show that the proposed method improves the accuracy and convergence speed compared to GNNs trained from scratch or using other pretraining techniques such as denoising. On the other hand, our pretraining method is suitable for both energy-centric and force-centric GNNs. This approach showcases its potential to enhance the performance and data efficiency of GNNs in fitting molecular force fields.
Authors: Haoyu Lei, Amin Gohari, Farzan Farnia
Abstract: Fair supervised learning algorithms assigning labels with little dependence on a sensitive attribute have attracted great attention in the machine learning community. While the demographic parity (DP) notion has been frequently used to measure a model's fairness in training fair classifiers, several studies in the literature suggest potential impacts of enforcing DP in fair learning algorithms. In this work, we analytically study the effect of standard DP-based regularization methods on the conditional distribution of the predicted label given the sensitive attribute. Our analysis shows that an imbalanced training dataset with a non-uniform distribution of the sensitive attribute could lead to a classification rule biased toward the sensitive attribute outcome holding the majority of training data. To control such inductive biases in DP-based fair learning, we propose a sensitive attribute-based distributionally robust optimization (SA-DRO) method improving robustness against the marginal distribution of the sensitive attribute. Finally, we present several numerical results on the application of DP-based learning methods to standard centralized and distributed learning problems. The empirical findings support our theoretical results on the inductive biases in DP-based fair learning algorithms and the debiasing effects of the proposed SA-DRO method.
Authors: Rhea Sanjay Sukthanker, Arber Zela, Benedikt Staffler, Samuel Dooley, Josif Grabocka, Frank Hutter
Abstract: Pareto front profiling in multi-objective optimization (MOO), i.e. finding a diverse set of Pareto optimal solutions, is challenging, especially with expensive objectives like neural network training. Typically, in MOO neural architecture search (NAS), we aim to balance performance and hardware metrics across devices. Prior NAS approaches simplify this task by incorporating hardware constraints into the objective function, but profiling the Pareto front necessitates a computationally expensive search for each constraint. In this work, we propose a novel NAS algorithm that encodes user preferences for the trade-off between performance and hardware metrics, and yields representative and diverse architectures across multiple devices in just one search run. To this end, we parameterize the joint architectural distribution across devices and multiple objectives via a hypernetwork that can be conditioned on hardware features and preference vectors, enabling zero-shot transferability to new devices. Extensive experiments with up to 19 hardware devices and 3 objectives showcase the effectiveness and scalability of our method. Finally, we show that, without extra costs, our method outperforms existing MOO NAS methods across a broad range of qualitatively different search spaces and datasets, including MobileNetV3 on ImageNet-1k, an encoder-decoder transformer space for machine translation and a decoder-only transformer space for language modelling.
Authors: Javad Aliakbari, Johan \"Ostman, Alexandre Graell i Amat
Abstract: We address the challenge of federated learning on graph-structured data distributed across multiple clients. Specifically, we focus on the prevalent scenario of interconnected subgraphs, where interconnections between different clients play a critical role. We present a novel framework for this scenario, named FedStruct, that harnesses deep structural dependencies. To uphold privacy, unlike existing methods, FedStruct eliminates the necessity of sharing or generating sensitive node features or embeddings among clients. Instead, it leverages explicit global graph structure information to capture inter-node dependencies. We validate the effectiveness of FedStruct through experimental results conducted on six datasets for semi-supervised node classification, showcasing performance close to the centralized approach across various scenarios, including different data partitioning methods, varying levels of label availability, and number of clients.
Authors: Michal Nauman, Micha{\l} Bortkiewicz, Piotr Mi{\l}o\'s, Tomasz Trzci\'nski, Mateusz Ostaszewski, Marek Cygan
Abstract: Recent advancements in off-policy Reinforcement Learning (RL) have significantly improved sample efficiency, primarily due to the incorporation of various forms of regularization that enable more gradient update steps than traditional agents. However, many of these techniques have been tested in limited settings, often on tasks from single simulation benchmarks and against well-known algorithms rather than a range of regularization approaches. This limits our understanding of the specific mechanisms driving RL improvements. To address this, we implemented over 60 different off-policy agents, each integrating established regularization techniques from recent state-of-the-art algorithms. We tested these agents across 14 diverse tasks from 2 simulation benchmarks, measuring training metrics related to overestimation, overfitting, and plasticity loss -- issues that motivate the examined regularization techniques. Our findings reveal that while the effectiveness of a specific regularization setup varies with the task, certain combinations consistently demonstrate robust and superior performance. Notably, a simple Soft Actor-Critic agent, appropriately regularized, reliably finds a better-performing policy within the training regime, which previously was achieved mainly through model-based approaches.
Authors: Tianheng Ling, Julian Hoever, Chao Qian, Gregor Schiele
Abstract: In industrial and environmental monitoring, achieving real-time and precise fluid flow measurement remains a critical challenge. This study applies linear quantization in FPGA-based soft sensors for fluid flow estimation, significantly enhancing Neural Network model precision by overcoming the limitations of traditional fixed-point quantization. Our approach achieves up to a 10.10% reduction in Mean Squared Error and a notable 9.39% improvement in inference speed through targeted hardware optimizations. Validated across multiple data sets, our findings demonstrate that the optimized FPGA-based quantized models can provide efficient, accurate real-time inference, offering a viable alternative to cloud-based processing in pervasive autonomous systems.
Authors: Ali Beikmohammadi, Sarit Khirirat, Sindri Magn\'usson
Abstract: Data similarity assumptions have traditionally been relied upon to understand the convergence behaviors of federated learning methods. Unfortunately, this approach often demands fine-tuning step sizes based on the level of data similarity. When data similarity is low, these small step sizes result in an unacceptably slow convergence speed for federated methods. In this paper, we present a novel and unified framework for analyzing the convergence of federated learning algorithms without the need for data similarity conditions. Our analysis centers on an inequality that captures the influence of step sizes on algorithmic convergence performance. By applying our theorems to well-known federated algorithms, we derive precise expressions for three widely used step size schedules: fixed, diminishing, and step-decay step sizes, which are independent of data similarity conditions. Finally, we conduct comprehensive evaluations of the performance of these federated learning algorithms, employing the proposed step size strategies to train deep neural network models on benchmark datasets under varying data similarity conditions. Our findings demonstrate significant improvements in convergence speed and overall performance, marking a substantial advancement in federated learning research.
Authors: Fabian Otto, Philipp Becker, Ngo Anh Vien, Gerhard Neumann
Abstract: Existing off-policy reinforcement learning algorithms often rely on an explicit state-action-value function representation, which can be problematic in high-dimensional action spaces due to the curse of dimensionality. This reliance results in data inefficiency as maintaining a state-action-value function in such spaces is challenging. We present an efficient approach that utilizes only a state-value function as the critic for off-policy deep reinforcement learning. This approach, which we refer to as Vlearn, effectively circumvents the limitations of existing methods by eliminating the necessity for an explicit state-action-value function. To this end, we introduce a novel importance sampling loss for learning deep value functions from off-policy data. While this is common for linear methods, it has not been combined with deep value function networks. This transfer to deep methods is not straightforward and requires novel design choices such as robust policy updates, twin value function networks to avoid an optimization bias, and importance weight clipping. We also present a novel analysis of the variance of our estimate compared to commonly used importance sampling estimators such as V-trace. Our approach improves sample complexity as well as final performance and ensures consistent and robust performance across various benchmark tasks. Eliminating the state-action-value function in Vlearn facilitates a streamlined learning process, enabling more effective exploration and exploitation in complex environments.
Authors: Etash Guha, Vihan Lakshman
Abstract: While deep neural networks have demonstrated groundbreaking performance in various settings, these models often suffer from \emph{catastrophic forgetting} when trained on new tasks in sequence. Several works have empirically demonstrated that increasing the width of a neural network leads to a decrease in catastrophic forgetting but have yet to characterize the exact relationship between width and continual learning. We design one of the first frameworks to analyze Continual Learning Theory and prove that width is directly related to forgetting in Feed-Forward Networks (FFN). Specifically, we demonstrate that increasing network widths to reduce forgetting yields diminishing returns. We empirically verify our claims at widths hitherto unexplored in prior studies where the diminishing returns are clearly observed as predicted by our theory.
Authors: Rudy Semola, Julio Hurtado, Vincenzo Lomonaco, Davide Bacciu
Abstract: Hyperparameter selection in continual learning scenarios is a challenging and underexplored aspect, especially in practical non-stationary environments. Traditional approaches, such as grid searches with held-out validation data from all tasks, are unrealistic for building accurate lifelong learning systems. This paper aims to explore the role of hyperparameter selection in continual learning and the necessity of continually and automatically tuning them according to the complexity of the task at hand. Hence, we propose leveraging the nature of sequence task learning to improve Hyperparameter Optimization efficiency. By using the functional analysis of variance-based techniques, we identify the most crucial hyperparameters that have an impact on performance. We demonstrate empirically that this approach, agnostic to continual scenarios and strategies, allows us to speed up hyperparameters optimization continually across tasks and exhibit robustness even in the face of varying sequential task orders. We believe that our findings can contribute to the advancement of continual learning methodologies towards more efficient, robust and adaptable models for real-world applications.
Authors: Jongsuk Kim, Hyeongkeun Lee, Kyeongha Rho, Junmo Kim, Joon Son Chung
Abstract: Recent advancements in self-supervised audio-visual representation learning have demonstrated its potential to capture rich and comprehensive representations. However, despite the advantages of data augmentation verified in many learning methods, audio-visual learning has struggled to fully harness these benefits, as augmentations can easily disrupt the correspondence between input pairs. To address this limitation, we introduce EquiAV, a novel framework that leverages equivariance for audio-visual contrastive learning. Our approach begins with extending equivariance to audio-visual learning, facilitated by a shared attention-based transformation predictor. It enables the aggregation of features from diverse augmentations into a representative embedding, providing robust supervision. Notably, this is achieved with minimal computational overhead. Extensive ablation studies and qualitative results verify the effectiveness of our method. EquiAV outperforms previous works across various audio-visual benchmarks. The code is available on https://github.com/JongSuk1/EquiAV.
Authors: Mohammod N. I. Suvon, Prasun C. Tripathi, Wenrui Fan, Shuo Zhou, Xianyuan Liu, Samer Alabed, Venet Osmani, Andrew J. Swift, Chen Chen, Haiping Lu
Abstract: Recent advancements in non-invasive detection of cardiac hemodynamic instability (CHDI) primarily focus on applying machine learning techniques to a single data modality, e.g. cardiac magnetic resonance imaging (MRI). Despite their potential, these approaches often fall short especially when the size of labeled patient data is limited, a common challenge in the medical domain. Furthermore, only a few studies have explored multimodal methods to study CHDI, which mostly rely on costly modalities such as cardiac MRI and echocardiogram. In response to these limitations, we propose a novel multimodal variational autoencoder ($\text{CardioVAE}_\text{X,G}$) to integrate low-cost chest X-ray (CXR) and electrocardiogram (ECG) modalities with pre-training on a large unlabeled dataset. Specifically, $\text{CardioVAE}_\text{X,G}$ introduces a novel tri-stream pre-training strategy to learn both shared and modality-specific features, thus enabling fine-tuning with both unimodal and multimodal datasets. We pre-train $\text{CardioVAE}_\text{X,G}$ on a large, unlabeled dataset of $50,982$ subjects from a subset of MIMIC database and then fine-tune the pre-trained model on a labeled dataset of $795$ subjects from the ASPIRE registry. Comprehensive evaluations against existing methods show that $\text{CardioVAE}_\text{X,G}$ offers promising performance (AUROC $=0.79$ and Accuracy $=0.77$), representing a significant step forward in non-invasive prediction of CHDI. Our model also excels in producing fine interpretations of predictions directly associated with clinical features, thereby supporting clinical decision-making.
Authors: Saeid Asgari Taghanaki, Joseph Lambourne
Abstract: The advent of generative AI models has revolutionized digital content creation, yet it introduces challenges in maintaining copyright integrity due to generative parroting, where models mimic their training data too closely. Our research presents a novel approach to tackle this issue by employing an overfitted Masked Autoencoder (MAE) to detect such parroted samples effectively. We establish a detection threshold based on the mean loss across the training dataset, allowing for the precise identification of parroted content in modified datasets. Preliminary evaluations demonstrate promising results, suggesting our method's potential to ensure ethical use and enhance the legal compliance of generative models.
Authors: Ali Behrouz, Michele Santacatterina, Ramin Zabih
Abstract: Recent advances in deep learning have mainly relied on Transformers due to their data dependency and ability to learn at scale. The attention module in these architectures, however, exhibits quadratic time and space in input size, limiting their scalability for long-sequence modeling. State Space Models (SSMs), and more specifically Selective SSMs (S6), with efficient hardware-aware implementation, have shown promising potential for long causal sequence modeling. They, however, use separate blocks for each channel and fail to filter irrelevant channels and capture inter-channel dependencies. Natural attempt to mix information across channels using MLP, attention, or SSMs results in further instability in the training of SSMs for large networks and/or nearly double the number of parameters. We present the MambaMixer block, a new SSM-based architecture with data-dependent weights that uses a dual selection mechanism across tokens and channels-called Selective Token and Channel Mixer. To mitigate doubling the number of parameters, we present a new non-causal heuristic of the S6 block with a hardware-friendly implementation. We further present an efficient variant of MambaMixer, called QSMixer, that mixes information along both sequence and embedding dimensions. As a proof of concept, we design Vision MambaMixer (ViM2) and Vision QSMixer (ViQS) architectures. To enhance their ability to capture spatial information in images, we present Switch of Scans (SoS) that dynamically uses a set of useful image scans to traverse image patches. We evaluate the performance of our methods in image classification, segmentation, and object detection. Our results underline the importance of selectively mixing across both tokens and channels and show the competitive (resp. superior) performance of our methods with well-established vision models (resp. SSM-based models).
Authors: Xiangfei Qiu, Jilin Hu, Lekui Zhou, Xingjian Wu, Junyang Du, Buang Zhang, Chenjuan Guo, Aoying Zhou, Christian S. Jensen, Zhenli Sheng, Bin Yang
Abstract: Time series are generated in diverse domains such as economic, traffic, health, and energy, where forecasting of future values has numerous important applications. Not surprisingly, many forecasting methods are being proposed. To ensure progress, it is essential to be able to study and compare such methods empirically in a comprehensive and reliable manner. To achieve this, we propose TFB, an automated benchmark for Time Series Forecasting (TSF) methods. TFB advances the state-of-the-art by addressing shortcomings related to datasets, comparison methods, and evaluation pipelines: 1) insufficient coverage of data domains, 2) stereotype bias against traditional methods, and 3) inconsistent and inflexible pipelines. To achieve better domain coverage, we include datasets from 10 different domains: traffic, electricity, energy, the environment, nature, economic, stock markets, banking, health, and the web. We also provide a time series characterization to ensure that the selected datasets are comprehensive. To remove biases against some methods, we include a diverse range of methods, including statistical learning, machine learning, and deep learning methods, and we also support a variety of evaluation strategies and metrics to ensure a more comprehensive evaluations of different methods. To support the integration of different methods into the benchmark and enable fair comparisons, TFB features a flexible and scalable pipeline that eliminates biases. Next, we employ TFB to perform a thorough evaluation of 21 Univariate Time Series Forecasting (UTSF) methods on 8,068 univariate time series and 14 Multivariate Time Series Forecasting (MTSF) methods on 25 datasets. The benchmark code and data are available at https://github.com/decisionintelligence/TFB.
Authors: Tom\'as Vergara-Browne, \'Alvaro Soto, Akiko Aizawa
Abstract: We introduce eigenpruning, a method that removes singular values from weight matrices in an LLM to improve its performance in a particular task. This method is inspired by interpretability methods designed to automatically find subnetworks of a model which solve a specific task. In our tests, the pruned model outperforms the original model by a large margin, while only requiring minimal computation to prune the weight matrices. In the case of a small synthetic task in integer multiplication, the Phi-2 model can improve its accuracy in the test set from 13.75% to 97.50%. Interestingly, these results seem to indicate the existence of a computation path that can solve the task very effectively, but it was not being used by the original model. Finally, we publicly release our implementation.
Authors: Mario Guevara
Abstract: Development of a spatial-temporal and data-driven model of soil respiration at the global scale based on soil temperature, yearly soil moisture, and soil organic carbon (C) estimates. Prediction of soil respiration on an annual basis (1991-2018) with relatively high accuracy (NSE 0.69, CCC 0.82). Lower soil respiration trends, higher soil respiration magnitudes, and higher soil organic C stocks across areas experiencing the presence of sustainable soil management practices.
Authors: Christian Marius Lillelund, Martin Magris, Christian Fischer Pedersen
Abstract: Variational Inference (VI) is a commonly used technique for approximate Bayesian inference and uncertainty estimation in deep learning models, yet it comes at a computational cost, as it doubles the number of trainable parameters to represent uncertainty. This rapidly becomes challenging in high-dimensional settings and motivates the use of alternative techniques for inference, such as Monte Carlo Dropout (MCD) or Spectral-normalized Neural Gaussian Process (SNGP). However, such methods have seen little adoption in survival analysis, and VI remains the prevalent approach for training probabilistic neural networks. In this paper, we investigate how to train deep probabilistic survival models in large datasets without introducing additional overhead in model complexity. To achieve this, we adopt three probabilistic approaches, namely VI, MCD, and SNGP, and evaluate them in terms of their prediction performance, calibration performance, and model complexity. In the context of probabilistic survival analysis, we investigate whether non-VI techniques can offer comparable or possibly improved prediction performance and uncertainty calibration compared to VI. In the MIMIC-IV dataset, we find that MCD aligns with VI in terms of the concordance index (0.748 vs. 0.743) and mean absolute error (254.9 vs. 254.7) using hinge loss, while providing C-calibrated uncertainty estimates. Moreover, our SNGP implementation provides D-calibrated survival functions in all datasets compared to VI (4/4 vs. 2/4, respectively). Our work encourages the use of techniques alternative to VI for survival analysis in high-dimensional datasets, where computational efficiency and overhead are of concern.
Authors: A. Ren\'e Geist, Jonas Frey, Mikel Zobro, Anna Levina, Georg Martius
Abstract: Many settings in machine learning require the selection of a rotation representation. However, choosing a suitable representation from the many available options is challenging. This paper acts as a survey and guide through rotation representations. We walk through their properties that harm or benefit deep learning with gradient-based optimization. By consolidating insights from rotation-based learning, we provide a comprehensive overview of learning functions with rotation representations. We provide guidance on selecting representations based on whether rotations are in the model's input or output and whether the data primarily comprises small angles.
Authors: Jan Simson, Alessandro Fabris, Christoph Kern
Abstract: Data practices shape research and practice on fairness in machine learning (fair ML). Critical data studies offer important reflections and critiques for the responsible advancement of the field by highlighting shortcomings and proposing recommendations for improvement. In this work, we present a comprehensive analysis of fair ML datasets, demonstrating how unreflective yet common practices hinder the reach and reliability of algorithmic fairness findings. We systematically study protected information encoded in tabular datasets and their usage in 280 experiments across 142 publications. Our analyses identify three main areas of concern: (1) a \textbf{lack of representation for certain protected attributes} in both data and evaluations; (2) the widespread \textbf{exclusion of minorities} during data preprocessing; and (3) \textbf{opaque data processing} threatening the generalization of fairness research. By conducting exemplary analyses on the utilization of prominent datasets, we demonstrate how unreflective data decisions disproportionately affect minority groups, fairness metrics, and resultant model comparisons. Additionally, we identify supplementary factors such as limitations in publicly available data, privacy considerations, and a general lack of awareness, which exacerbate these challenges. To address these issues, we propose a set of recommendations for data usage in fairness research centered on transparency and responsible inclusion. This study underscores the need for a critical reevaluation of data practices in fair ML and offers directions to improve both the sourcing and usage of datasets.
Authors: Yinghan Cheng, Qi Zhang, Chongyang Shi, Liang Xiao, Shufeng Hao, Liang Hu
Abstract: Stance detection seeks to identify the viewpoints of individuals either in favor or against a given target or a controversial topic. Current advanced neural models for stance detection typically employ fully parametric softmax classifiers. However, these methods suffer from several limitations, including lack of explainability, insensitivity to the latent data structure, and unimodality, which greatly restrict their performance and applications. To address these challenges, we present a novel collaborative stance detection framework called (CoSD) which leverages contrastive heterogeneous topic graph learning to learn topic-aware semantics and collaborative signals among texts, topics, and stance labels for enhancing stance detection. During training, we construct a heterogeneous graph to structurally organize texts and stances through implicit topics via employing latent Dirichlet allocation. We then perform contrastive graph learning to learn heterogeneous node representations, aggregating informative multi-hop collaborative signals via an elaborate Collaboration Propagation Aggregation (CPA) module. During inference, we introduce a hybrid similarity scoring module to enable the comprehensive incorporation of topic-aware semantics and collaborative signals for stance detection. Extensive experiments on two benchmark datasets demonstrate the state-of-the-art detection performance of CoSD, verifying the effectiveness and explainability of our collaborative framework.
Authors: Matt Raymond, Angela Violi, Clayton Scott
Abstract: Tree ensembles achieve state-of-the-art performance on numerous prediction tasks. We propose Joint Optimization of Piecewise Linear ENsembles (JOPLEN), which jointly fits piecewise linear models at all leaf nodes of an existing tree ensemble. In addition to enhancing the expressiveness of an ensemble, JOPLEN allows several common penalties, including sparsity-promoting matrix norms and subspace-norms, to be applied to nonlinear prediction. We demonstrate the performance of JOPLEN on over 100 regression and classification datasets and with a variety of penalties. JOPLEN leads to improved prediction performance relative to not only standard random forest and gradient boosted tree ensembles, but also other methods for enhancing tree ensembles. We demonstrate that JOPLEN with a nuclear norm penalty learns subspace-aligned functions. Additionally, JOPLEN combined with a Dirty LASSO penalty is an effective feature selection method for nonlinear prediction in multitask learning.
Authors: Luise Ge, Brendan Juba, Yevgeniy Vorobeychik
Abstract: We study learnability of linear utility functions from pairwise comparison queries. In particular, we consider two learning objectives. The first objective is to predict out-of-sample responses to pairwise comparisons, whereas the second is to approximately recover the true parameters of the utility function. We show that in the passive learning setting, linear utilities are efficiently learnable with respect to the first objective, both when query responses are uncorrupted by noise, and under Tsybakov noise when the distributions are sufficiently "nice". In contrast, we show that utility parameters are not learnable for a large set of data distributions without strong modeling assumptions, even when query responses are noise-free. Next, we proceed to analyze the learning problem in an active learning setting. In this case, we show that even the second objective is efficiently learnable, and present algorithms for both the noise-free and noisy query response settings. Our results thus exhibit a qualitative learnability gap between passive and active learning from pairwise preference queries, demonstrating the value of the ability to select pairwise queries for utility learning.
Authors: Zhuohua Li, Maoli Liu, John C. S. Lui
Abstract: Conversational recommender systems have emerged as a potent solution for efficiently eliciting user preferences. These systems interactively present queries associated with "key terms" to users and leverage user feedback to estimate user preferences more efficiently. Nonetheless, most existing algorithms adopt a centralized approach. In this paper, we introduce FedConPE, a phase elimination-based federated conversational bandit algorithm, where $M$ agents collaboratively solve a global contextual linear bandit problem with the help of a central server while ensuring secure data management. To effectively coordinate all the clients and aggregate their collected data, FedConPE uses an adaptive approach to construct key terms that minimize uncertainty across all dimensions in the feature space. Furthermore, compared with existing federated linear bandit algorithms, FedConPE offers improved computational and communication efficiency as well as enhanced privacy protections. Our theoretical analysis shows that FedConPE is minimax near-optimal in terms of cumulative regret. We also establish upper bounds for communication costs and conversation frequency. Comprehensive evaluations demonstrate that FedConPE outperforms existing conversational bandit algorithms while using fewer conversations.
Authors: Wei Deng, Weijian Luo, Yixin Tan, Marin Bilo\v{s}, Yu Chen, Yuriy Nevmyvaka, Ricky T. Q. Chen
Abstract: Schr\"odinger bridge (SB) has emerged as the go-to method for optimizing transportation plans in diffusion models. However, SB requires estimating the intractable forward score functions, inevitably resulting in the costly implicit training loss based on simulated trajectories. To improve the scalability while preserving efficient transportation plans, we leverage variational inference to linearize the forward score functions (variational scores) of SB and restore simulation-free properties in training backward scores. We propose the variational Schr\"odinger diffusion model (VSDM), where the forward process is a multivariate diffusion and the variational scores are adaptively optimized for efficient transport. Theoretically, we use stochastic approximation to prove the convergence of the variational scores and show the convergence of the adaptively generated samples based on the optimal variational scores. Empirically, we test the algorithm in simulated examples and observe that VSDM is efficient in generations of anisotropic shapes and yields straighter sample trajectories compared to the single-variate diffusion. We also verify the scalability of the algorithm in real-world data and achieve competitive unconditional generation performance in CIFAR10 and conditional generation in time series modeling. Notably, VSDM no longer depends on warm-up initializations and has become tuning-friendly in training large-scale experiments.
Authors: Jarek Duda
Abstract: Popular artificial neural networks (ANN) optimize parameters for unidirectional value propagation, assuming some arbitrary parametrization type like Multi-Layer Perceptron (MLP) or Kolmogorov-Arnold Network (KAN). In contrast, for biological neurons e.g. "it is not uncommon for axonal propagation of action potentials to happen in both directions"~\cite{axon} - suggesting they are optimized to continuously operate in multidirectional way. Additionally, statistical dependencies a single neuron could model is not just (expected) value dependence, but entire joint distributions including also higher moments. Such more agnostic joint distribution neuron would allow for multidirectional propagation (of distributions or values) e.g. $\rho(x|y,z)$ or $\rho(y,z|x)$ by substituting to $\rho(x,y,z)$ and normalizing. There will be discussed Hierarchical Correlation Reconstruction (HCR) for such neuron model: assuming $\rho(x,y,z)=\sum_{ijk} a_{ijk} f_i(x) f_j(y) f_k(z)$ type parametrization of joint distribution in polynomial basis $f_i$, which allows for flexible, inexpensive processing including nonlinearities, direct model estimation and update, trained through standard backpropagation or novel ways for such structure up to tensor decomposition or information bottleneck approach. Using only pairwise (input-output) dependencies, its expected value prediction becomes KAN-like with trained activation functions as polynomials, can be extended by adding higher order dependencies through included products - in conscious interpretable way, allowing for multidirectional propagation of both values and probability densities.
Authors: Liad Erez, Alon Cohen, Tomer Koren, Yishay Mansour, Shay Moran
Abstract: We revisit the classical problem of multiclass classification with bandit feedback (Kakade, Shalev-Shwartz and Tewari, 2008), where each input classifies to one of $K$ possible labels and feedback is restricted to whether the predicted label is correct or not. Our primary inquiry is with regard to the dependency on the number of labels $K$, and whether $T$-step regret bounds in this setting can be improved beyond the $\smash{\sqrt{KT}}$ dependence exhibited by existing algorithms. Our main contribution is in showing that the minimax regret of bandit multiclass is in fact more nuanced, and is of the form $\smash{\widetilde{\Theta}\left(\min \left\{|H| + \sqrt{T}, \sqrt{KT \log |H|} \right\} \right) }$, where $H$ is the underlying (finite) hypothesis class. In particular, we present a new bandit classification algorithm that guarantees regret $\smash{\widetilde{O}(|H|+\sqrt{T})}$, improving over classical algorithms for moderately-sized hypothesis classes, and give a matching lower bound establishing tightness of the upper bounds (up to log-factors) in all parameter regimes.
Authors: Satvik Golechha
Abstract: Grokking, a phenomenon where machine learning models generalize long after overfitting, has been primarily observed and studied in algorithmic tasks. This paper explores grokking in real-world datasets using deep neural networks for classification under the cross-entropy loss. We challenge the prevalent hypothesis that the $L_2$ norm of weights is the primary cause of grokking by demonstrating that grokking can occur outside the expected range of weight norms. To better understand grokking, we introduce three new progress measures: activation sparsity, absolute weight entropy, and approximate local circuit complexity. These measures are conceptually related to generalization and demonstrate a stronger correlation with grokking in real-world datasets compared to weight norms. Our findings suggest that while weight norms might usually correlate with grokking and our progress measures, they are not causative, and our proposed measures provide a better understanding of the dynamics of grokking.
Authors: Yunzheng Lyu, Feng Bao
Abstract: Kernel learning forward backward SDE filter is an iterative and adaptive meshfree approach to solve the nonlinear filtering problem. It builds from forward backward SDE for Fokker-Planker equation, which defines evolving density for the state variable, and employs KDE to approximate density. This algorithm has shown more superior performance than mainstream particle filter method, in both convergence speed and efficiency of solving high dimension problems. However, this method has only been shown to converge empirically. In this paper, we present a rigorous analysis to demonstrate its local and global convergence, and provide theoretical support for its empirical results.
Authors: Bobby Yan, Alexander J. Root, Trevor Gale, David Broman, Fredrik Kjolstad
Abstract: The rapid growth in the size of deep learning models strains the capabilities of traditional dense computation paradigms. Leveraging sparse computation has become increasingly popular for training and deploying large-scale models, but existing deep learning frameworks lack extensive support for sparse operations. To bridge this gap, we introduce Scorch, a library that seamlessly integrates efficient sparse tensor computation into the PyTorch ecosystem, with an initial focus on inference workloads on CPUs. Scorch provides a flexible and intuitive interface for sparse tensors, supporting diverse sparse data structures. Scorch introduces a compiler stack that automates key optimizations, including automatic loop ordering, tiling, and format inference. Combined with a runtime that adapts its execution to both dense and sparse data, Scorch delivers substantial speedups over hand-written PyTorch Sparse (torch.sparse) operations without sacrificing usability. More importantly, Scorch enables efficient computation of complex sparse operations that lack hand-optimized PyTorch implementations. This flexibility is crucial for exploring novel sparse architectures. We demonstrate Scorch's ease of use and performance gains on diverse deep learning models across multiple domains. With only minimal code changes, Scorch achieves 1.05-5.78x speedups over PyTorch Sparse on end-to-end tasks. Scorch's seamless integration and performance gains make it a valuable addition to the PyTorch ecosystem. We believe Scorch will enable wider exploration of sparsity as a tool for scaling deep learning and inform the development of other sparse libraries.
Authors: Yuki Iwamoto, Ken Kaneiwa
Abstract: Rule-induction models have demonstrated great power in the inductive setting of knowledge graph completion. In this setting, the models are tested on a knowledge graph entirely composed of unseen entities. These models learn relation patterns as rules by utilizing subgraphs. Providing the same inputs with different rules leads to differences in the model's predictions. In this paper, we focus on the behavior of such models. We propose a re-ranking-based model called ReDistLP (Re-ranking with a Distinct Model for Link Prediction). This model enhances the effectiveness of re-ranking by leveraging the difference in the predictions between the initial retriever and the re-ranker. ReDistLP outperforms the state-of-the-art methods in 2 out of 3 benchmarks.
Authors: Tao Zou, Yuhao Mao, Junchen Ye, Bowen Du
Abstract: Dynamic graph learning equips the edges with time attributes and allows multiple links between two nodes, which is a crucial technology for understanding evolving data scenarios like traffic prediction and recommendation systems. Existing works obtain the evolving patterns mainly depending on the most recent neighbor sequences. However, we argue that whether two nodes will have interaction with each other in the future is highly correlated with the same interaction that happened in the past. Only considering the recent neighbors overlooks the phenomenon of repeat behavior and fails to accurately capture the temporal evolution of interactions. To fill this gap, this paper presents RepeatMixer, which considers evolving patterns of first and high-order repeat behavior in the neighbor sampling strategy and temporal information learning. Firstly, we define the first-order repeat-aware nodes of the source node as the destination nodes that have interacted historically and extend this concept to high orders as nodes in the destination node's high-order neighbors. Then, we extract neighbors of the source node that interacted before the appearance of repeat-aware nodes with a slide window strategy as its neighbor sequence. Next, we leverage both the first and high-order neighbor sequences of source and destination nodes to learn temporal patterns of interactions via an MLP-based encoder. Furthermore, considering the varying temporal patterns on different orders, we introduce a time-aware aggregation mechanism that adaptively aggregates the temporal representations from different orders based on the significance of their interaction time sequences. Experimental results demonstrate the superiority of RepeatMixer over state-of-the-art models in link prediction tasks, underscoring the effectiveness of the proposed repeat-aware neighbor sampling strategy.
Authors: Derek Lim, Moe Putterman, Robin Walters, Haggai Maron, Stefanie Jegelka
Abstract: Many algorithms and observed phenomena in deep learning appear to be affected by parameter symmetries -- transformations of neural network parameters that do not change the underlying neural network function. These include linear mode connectivity, model merging, Bayesian neural network inference, metanetworks, and several other characteristics of optimization or loss-landscapes. However, theoretical analysis of the relationship between parameter space symmetries and these phenomena is difficult. In this work, we empirically investigate the impact of neural parameter symmetries by introducing new neural network architectures that have reduced parameter space symmetries. We develop two methods, with some provable guarantees, of modifying standard neural networks to reduce parameter space symmetries. With these new methods, we conduct a comprehensive experimental study consisting of multiple tasks aimed at assessing the effect of removing parameter symmetries. Our experiments reveal several interesting observations on the empirical impact of parameter symmetries; for instance, we observe linear mode connectivity between our networks without alignment of weight spaces, and we find that our networks allow for faster and more effective Bayesian neural network training.
Authors: Ahmed M. Ahmed, Rafael Rafailov, Stepan Sharkov, Xuechen Li, Sanmi Koyejo
Abstract: Reinforcement Learning from Human Feedback (RLHF) has enabled significant advancements within language modeling for powerful, instruction-following models. However, the alignment of these models remains a pressing challenge as the policy tends to overfit the learned ``proxy" reward model past an inflection point of utility as measured by a ``gold" reward model that is more performant -- a phenomenon known as overoptimisation. Prior work has mitigated this issue by computing a pessimistic statistic over an ensemble of reward models, which is common in Offline Reinforcement Learning but incredibly costly for language models with high memory requirements, making such approaches infeasible for sufficiently large models. To this end, we propose using a shared encoder but separate linear heads. We find this leads to similar performance as the full ensemble while allowing tremendous savings in memory and time required for training for models of similar size.
Authors: Bart Cox, Abele M\u{a}lan, Lydia Y. Chen, J\'er\'emie Decouchant
Abstract: Federated learning (FL) enables a set of geographically distributed clients to collectively train a model through a server. Classically, the training process is synchronous, but can be made asynchronous to maintain its speed in presence of slow clients and in heterogeneous networks. The vast majority of Byzantine fault-tolerant FL systems however rely on a synchronous training process. Our solution is one of the first Byzantine-resilient and asynchronous FL algorithms that does not require an auxiliary server dataset and is not delayed by stragglers, which are shortcomings of previous works. Intuitively, the server in our solution waits to receive a minimum number of updates from clients on its latest model to safely update it, and is later able to safely leverage the updates that late clients might send. We compare the performance of our solution with state-of-the-art algorithms on both image and text datasets under gradient inversion, perturbation, and backdoor attacks. Our results indicate that our solution trains a model faster than previous synchronous FL solution, and maintains a higher accuracy, up to 1.54x and up to 1.75x for perturbation and gradient inversion attacks respectively, in the presence of Byzantine clients than previous asynchronous FL solutions.
Authors: Yuncong Zuo, Bart Cox, Lydia Y. Chen, J\'er\'emie Decouchant
Abstract: Federated learning (FL) systems enable multiple clients to train a machine learning model iteratively through synchronously exchanging the intermediate model weights with a single server. The scalability of such FL systems can be limited by two factors: server idle time due to synchronous communication and the risk of a single server becoming the bottleneck. In this paper, we propose a new FL architecture, to our knowledge, the first multi-server FL system that is entirely asynchronous, and therefore addresses these two limitations simultaneously. Our solution keeps both servers and clients continuously active. As in previous multi-server methods, clients interact solely with their nearest server, ensuring efficient update integration into the model. Differently, however, servers also periodically update each other asynchronously, and never postpone interactions with clients. We compare our solution to three representative baselines - FedAvg, FedAsync and HierFAVG - on the MNIST and CIFAR-10 image classification datasets and on the WikiText-2 language modeling dataset. Our solution converges to similar or higher accuracy levels than previous baselines and requires 61% less time to do so in geo-distributed settings.
Authors: Chenyi Zi, Haihong Zhao, Xiangguo Sun, Yiqing Lin, Hong Cheng, Jia Li
Abstract: Artificial general intelligence on graphs has shown significant advancements across various applications, yet the traditional 'Pre-train & Fine-tune' paradigm faces inefficiencies and negative transfer issues, particularly in complex and few-shot settings. Graph prompt learning emerges as a promising alternative, leveraging lightweight prompts to manipulate data and fill the task gap by reformulating downstream tasks to the pretext. However, several critical challenges still remain: how to unify diverse graph prompt models, how to evaluate the quality of graph prompts, and to improve their usability for practical comparisons and selection. In response to these challenges, we introduce the first comprehensive benchmark for graph prompt learning. Our benchmark integrates SIX pre-training methods and FIVE state-of-the-art graph prompt techniques, evaluated across FIFTEEN diverse datasets to assess performance, flexibility, and efficiency. We also present 'ProG', an easy-to-use open-source library that streamlines the execution of various graph prompt models, facilitating objective evaluations. Additionally, we propose a unified framework that categorizes existing graph prompt methods into two main approaches: prompts as graphs and prompts as tokens. This framework enhances the applicability and comparison of graph prompt techniques. The code is available at: https://github.com/sheldonresearch/ProG.
Authors: Alexandre Hayderi, Amin Saberi, Ellen Vitercik, Anders Wikum
Abstract: Online Bayesian bipartite matching is a central problem in digital marketplaces and exchanges, including advertising, crowdsourcing, ridesharing, and kidney exchange. We introduce a graph neural network (GNN) approach that emulates the problem's combinatorially-complex optimal online algorithm, which selects actions (e.g., which nodes to match) by computing each action's value-to-go (VTG) -- the expected weight of the final matching if the algorithm takes that action, then acts optimally in the future. We train a GNN to estimate VTG and show empirically that this GNN returns high-weight matchings across a variety of tasks. Moreover, we identify a common family of graph distributions in spatial crowdsourcing applications, such as rideshare, under which VTG can be efficiently approximated by aggregating information within local neighborhoods in the graphs. This structure matches the local behavior of GNNs, providing theoretical justification for our approach.
Authors: Yelysei Bondarenko, Riccardo Del Chiaro, Markus Nagel
Abstract: Large language models (LLMs) are omnipresent, however their practical deployment is challenging due to their ever increasing computational and memory demands. Quantization is one of the most effective ways to make them more compute and memory efficient. Quantization-aware training (QAT) methods, generally produce the best quantized performance, however it comes at the cost of potentially long training time and excessive memory usage, making it impractical when applying for LLMs. Inspired by parameter-efficient fine-tuning (PEFT) and low-rank adaptation (LoRA) literature, we propose LR-QAT -- a lightweight and memory-efficient QAT algorithm for LLMs. LR-QAT employs several components to save memory without sacrificing predictive performance: (a) low-rank auxiliary weights that are aware of the quantization grid; (b) a downcasting operator using fixed-point or double-packed integers and (c) checkpointing. Unlike most related work, our method (i) is inference-efficient, leading to no additional overhead compared to traditional PTQ; (ii) can be seen as a general extended pretraining framework, meaning that the resulting model can still be utilized for any downstream task afterwards; (iii) can be applied across a wide range of quantization settings, such as different choices quantization granularity, activation quantization, and seamlessly combined with many PTQ techniques. We apply LR-QAT to LLaMA-2/3 and Mistral model families and validate its effectiveness on several downstream tasks. Our method outperforms common post-training quantization (PTQ) approaches and reaches the same model performance as full-model QAT at the fraction of its memory usage. Specifically, we can train a 7B LLM on a single consumer grade GPU with 24GB of memory.
Authors: Nicole Hayes, Ekaterina Merkurjev, Guo-Wei Wei
Abstract: Data sets with imbalanced class sizes, often where one class size is much smaller than that of others, occur extremely often in various applications, including those with biological foundations, such as drug discovery and disease diagnosis. Thus, it is extremely important to be able to identify data elements of classes of various sizes, as a failure to detect can result in heavy costs. However, many data classification algorithms do not perform well on imbalanced data sets as they often fail to detect elements belonging to underrepresented classes. In this paper, we propose the BTDT-MBO algorithm, incorporating Merriman-Bence-Osher (MBO) techniques and a bidirectional transformer, as well as distance correlation and decision threshold adjustments, for data classification problems on highly imbalanced molecular data sets, where the sizes of the classes vary greatly. The proposed method not only integrates adjustments in the classification threshold for the MBO algorithm in order to help deal with the class imbalance, but also uses a bidirectional transformer model based on an attention mechanism for self-supervised learning. Additionally, the method implements distance correlation as a weight function for the similarity graph-based framework on which the adjusted MBO algorithm operates. The proposed model is validated using six molecular data sets, and we also provide a thorough comparison to other competing algorithms. The computational experiments show that the proposed method performs better than competing techniques even when the class imbalance ratio is very high.
Authors: Li-Wen Chang, Wenlei Bao, Qi Hou, Chengquan Jiang, Ningxin Zheng, Yinmin Zhong, Xuanrun Zhang, Zuquan Song, Ziheng Jiang, Haibin Lin, Xin Jin, Xin Liu
Abstract: Large deep learning models have demonstrated strong ability to solve many tasks across a wide range of applications. Those large models typically require training and inference to be distributed. Tensor parallelism is a common technique partitioning computation of an operation or layer across devices to overcome the memory capacity limitation of a single processor, and/or to accelerate computation to meet a certain latency requirement. However, this kind of parallelism introduces additional communication that might contribute a significant portion of overall runtime. Thus limits scalability of this technique within a group of devices with high speed interconnects, such as GPUs with NVLinks in a node. This paper proposes a novel method, Flux, to significantly hide communication latencies with dependent computations for GPUs. Flux over-decomposes communication and computation operations into much finer-grained operations and further fuses them into a larger kernel to effectively hide communication without compromising kernel efficiency. Flux can potentially overlap up to 96% of communication given a fused kernel. Overall, it can achieve up to 1.24x speedups for training over Megatron-LM on a cluster of 128 GPUs with various GPU generations and interconnects, and up to 1.66x and 1.30x speedups for prefill and decoding inference over vLLM on a cluster with 8 GPUs with various GPU generations and interconnects.
Authors: Yuchao Lin, Jacob Helwig, Shurui Gui, Shuiwang Ji
Abstract: We consider achieving equivariance in machine learning systems via frame averaging. Current frame averaging methods involve a costly sum over large frames or rely on sampling-based approaches that only yield approximate equivariance. Here, we propose Minimal Frame Averaging (MFA), a mathematical framework for constructing provably minimal frames that are exactly equivariant. The general foundations of MFA also allow us to extend frame averaging to more groups than previously considered, including the Lorentz group for describing symmetries in space-time, and the unitary group for complex-valued domains. Results demonstrate the efficiency and effectiveness of encoding symmetries via MFA across a diverse range of tasks, including $n$-body simulation, top tagging in collider physics, and relaxed energy prediction. Our code is available at https://github.com/divelab/MFA.
Authors: Xihao Piao, Zheng Chen, Taichi Murayama, Yasuko Matsubara, Yasushi Sakurai
Abstract: The Transformer model has shown leading performance in time series forecasting. Nevertheless, in some complex scenarios, it tends to learn low-frequency features in the data and overlook high-frequency features, showing a frequency bias. This bias prevents the model from accurately capturing important high-frequency data features. In this paper, we undertook empirical analyses to understand this bias and discovered that frequency bias results from the model disproportionately focusing on frequency features with higher energy. Based on our analysis, we formulate this bias and propose Fredformer, a Transformer-based framework designed to mitigate frequency bias by learning features equally across different frequency bands. This approach prevents the model from overlooking lower amplitude features important for accurate forecasting. Extensive experiments show the effectiveness of our proposed approach, which can outperform other baselines in different real-world time-series datasets. Furthermore, we introduce a lightweight variant of the Fredformer with an attention matrix approximation, which achieves comparable performance but with much fewer parameters and lower computation costs. The code is available at: https://github.com/chenzRG/Fredformer
Authors: Jiawen Qin, Haonan Yuan, Qingyun Sun, Lyujin Xu, Jiaqi Yuan, Pengfeng Huang, Zhaonan Wang, Xingcheng Fu, Hao Peng, Jianxin Li, Philip S. Yu
Abstract: Deep graph learning has gained grand popularity over the past years due to its versatility and success in representing graph data across a wide range of domains. However, the pervasive issue of imbalanced graph data distributions, where certain parts exhibit disproportionally abundant data while others remain sparse, undermines the efficacy of conventional graph learning algorithms, leading to biased outcomes. To address this challenge, Imbalanced Graph Learning (IGL) has garnered substantial attention, enabling more balanced data distributions and better task performance. Despite the proliferation of IGL algorithms, the absence of consistent experimental protocols and fair performance comparisons pose a significant barrier to comprehending advancements in this field. To bridge this gap, we introduce IGL-Bench, a foundational comprehensive benchmark for imbalanced graph learning, embarking on 16 diverse graph datasets and 24 distinct IGL algorithms with uniform data processing and splitting strategies. Specifically, IGL-Bench systematically investigates state-of-the-art IGL algorithms in terms of effectiveness, robustness, and efficiency on node-level and graph-level tasks, with the scope of class-imbalance and topology-imbalance. Extensive experiments demonstrate the potential benefits of IGL algorithms on various imbalanced conditions, offering insights and opportunities in the IGL field. Further, we have developed an open-sourced and unified package to facilitate reproducible evaluation and inspire further innovative research, which is available at https://github.com/RingBDStack/IGL-Bench.
Authors: Zhentao Tan, Yadong Mu
Abstract: Recently various optimization problems, such as Mixed Integer Linear Programming Problems (MILPs), have undergone comprehensive investigation, leveraging the capabilities of machine learning. This work focuses on learning-based solutions for efficiently solving the Quadratic Assignment Problem (QAPs), which stands as a formidable challenge in combinatorial optimization. While many instances of simpler problems admit fully polynomial-time approximate solution (FPTAS), QAP is shown to be strongly NP-hard. Even finding a FPTAS for QAP is difficult, in the sense that the existence of a FPTAS implies $P = NP$. Current research on QAPs suffer from limited scale and computational inefficiency. To attack the aforementioned issues, we here propose the first solution of its kind for QAP in the learn-to-improve category. This work encodes facility and location nodes separately, instead of forming computationally intensive association graphs prevalent in current approaches. This design choice enables scalability to larger problem sizes. Furthermore, a \textbf{S}olution \textbf{AW}are \textbf{T}ransformer (SAWT) architecture integrates the incumbent solution matrix with the attention score to effectively capture higher-order information of the QAPs. Our model's effectiveness is validated through extensive experiments on self-generated QAP instances of varying sizes and the QAPLIB benchmark.
Authors: Micha{\l} Derezi\'nski, Michael W. Mahoney
Abstract: Large matrices arise in many machine learning and data analysis applications, including as representations of datasets, graphs, model weights, and first and second-order derivatives. Randomized Numerical Linear Algebra (RandNLA) is an area which uses randomness to develop improved algorithms for ubiquitous matrix problems. The area has reached a certain level of maturity; but recent hardware trends, efforts to incorporate RandNLA algorithms into core numerical libraries, and advances in machine learning, statistics, and random matrix theory, have lead to new theoretical and practical challenges. This article provides a self-contained overview of RandNLA, in light of these developments.
Authors: Jason Gross, Rajashree Agrawal, Thomas Kwa, Euan Ong, Chun Hei Yip, Alex Gibson, Soufiane Noubir, Lawrence Chan
Abstract: In this work, we propose using mechanistic interpretability -- techniques for reverse engineering model weights into human-interpretable algorithms -- to derive and compactly prove formal guarantees on model performance. We prototype this approach by formally proving lower bounds on the accuracy of 151 small transformers trained on a Max-of-$K$ task. We create 102 different computer-assisted proof strategies and assess their length and tightness of bound on each of our models. Using quantitative metrics, we find that shorter proofs seem to require and provide more mechanistic understanding. Moreover, we find that more faithful mechanistic understanding leads to tighter performance bounds. We confirm these connections by qualitatively examining a subset of our proofs. Finally, we identify compounding structureless noise as a key challenge for using mechanistic interpretability to generate compact proofs on model performance.
Authors: Xi Chen, Chuan Qin, Chuyu Fang, Chao Wang, Chen Zhu, Fuzhen Zhuang, Hengshu Zhu, Hui Xiong
Abstract: In a rapidly evolving job market, skill demand forecasting is crucial as it enables policymakers and businesses to anticipate and adapt to changes, ensuring that workforce skills align with market needs, thereby enhancing productivity and competitiveness. Additionally, by identifying emerging skill requirements, it directs individuals towards relevant training and education opportunities, promoting continuous self-learning and development. However, the absence of comprehensive datasets presents a significant challenge, impeding research and the advancement of this field. To bridge this gap, we present Job-SDF, a dataset designed to train and benchmark job-skill demand forecasting models. Based on 10.35 million public job advertisements collected from major online recruitment platforms in China between 2021 and 2023, this dataset encompasses monthly recruitment demand for 2,324 types of skills across 521 companies. Our dataset uniquely enables evaluating skill demand forecasting models at various granularities, including occupation, company, and regional levels. We benchmark a range of models on this dataset, evaluating their performance in standard scenarios, in predictions focused on lower value ranges, and in the presence of structural breaks, providing new insights for further research. Our code and dataset are publicly accessible via the https://github.com/Job-SDF/benchmark.
Authors: Pankayaraj Pathmanathan, Souradip Chakraborty, Xiangyu Liu, Yongyuan Liang, Furong Huang
Abstract: Recent advancements in Reinforcement Learning with Human Feedback (RLHF) have significantly impacted the alignment of Large Language Models (LLMs). The sensitivity of reinforcement learning algorithms such as Proximal Policy Optimization (PPO) has led to new line work on Direct Policy Optimization (DPO), which treats RLHF in a supervised learning framework. The increased practical use of these RLHF methods warrants an analysis of their vulnerabilities. In this work, we investigate the vulnerabilities of DPO to poisoning attacks under different scenarios and compare the effectiveness of preference poisoning, a first of its kind. We comprehensively analyze DPO's vulnerabilities under different types of attacks, i.e., backdoor and non-backdoor attacks, and different poisoning methods across a wide array of language models, i.e., LLama 7B, Mistral 7B, and Gemma 7B. We find that unlike PPO-based methods, which, when it comes to backdoor attacks, require at least 4\% of the data to be poisoned to elicit harmful behavior, we exploit the true vulnerabilities of DPO more simply so we can poison the model with only as much as 0.5\% of the data. We further investigate the potential reasons behind the vulnerability and how well this vulnerability translates into backdoor vs non-backdoor attacks.
Authors: Wenda Xu, Jiachen Li, William Yang Wang, Lei Li
Abstract: Direct alignment from preferences (DAP) has emerged as a promising paradigm for aligning large language models (LLMs) to human desiderata from pre-collected, offline preference datasets. While recent studies indicate that existing offline DAP methods can directly benefit from online training samples, we highlight the need to develop specific online DAP algorithms to fully harness the power of online training. Specifically, we identify that the learned LLM should adhere to the proximity of the behavior LLM, which collects the training samples. To this end, we propose online Preference Optimization in proximity to the Behavior LLM (BPO), emphasizing the importance of constructing a proper trust region for LLM alignment. We conduct extensive experiments to validate the effectiveness and applicability of our approach by integrating it with various DAP methods, resulting in significant performance improvements across a wide range of tasks when training with the same amount of preference data. Even when only introducing one additional data collection phase, our online BPO improves its offline DAP baseline from 72.0% to 80.2% on TL;DR and from 82.2% to 89.1% on Anthropic Helpfulness in terms of win rate against human reference text.
Authors: Byung-Kwan Lee, Sangyun Chung, Chae Won Kim, Beomchan Park, Yong Man Ro
Abstract: Large language and vision models (LLVMs) have been driven by the generalization power of large language models (LLMs) and the advent of visual instruction tuning. Along with scaling them up directly, these models enable LLVMs to showcase powerful vision language (VL) performances by covering diverse tasks via natural language instructions. However, existing open-source LLVMs that perform comparably to closed-source LLVMs such as GPT-4V are often considered too large (e.g., 26B, 34B, and 110B parameters), having a larger number of layers. These large models demand costly, high-end resources for both training and inference. To address this issue, we present a new efficient LLVM family with 1.8B, 3.8B, and 7B LLM model sizes, Traversal of Layers (TroL), which enables the reuse of layers in a token-wise manner. This layer traversing technique simulates the effect of looking back and retracing the answering stream while increasing the number of forward propagation layers without physically adding more layers. We demonstrate that TroL employs a simple layer traversing approach yet efficiently outperforms the open-source LLVMs with larger model sizes and rivals the performances of the closed-source LLVMs with substantial sizes.
Authors: Hengyi Wang, Shiwei Tan, Hao Wang
Abstract: Vision transformers (ViTs) have emerged as a significant area of focus, particularly for their capacity to be jointly trained with large language models and to serve as robust vision foundation models. Yet, the development of trustworthy explanation methods for ViTs has lagged, particularly in the context of post-hoc interpretations of ViT predictions. Existing sub-image selection approaches, such as feature-attribution and conceptual models, fall short in this regard. This paper proposes five desiderata for explaining ViTs -- faithfulness, stability, sparsity, multi-level structure, and parsimony -- and demonstrates the inadequacy of current methods in meeting these criteria comprehensively. We introduce a variational Bayesian explanation framework, dubbed ProbAbilistic Concept Explainers (PACE), which models the distributions of patch embeddings to provide trustworthy post-hoc conceptual explanations. Our qualitative analysis reveals the distributions of patch-level concepts, elucidating the effectiveness of ViTs by modeling the joint distribution of patch embeddings and ViT's predictions. Moreover, these patch-level explanations bridge the gap between image-level and dataset-level explanations, thus completing the multi-level structure of PACE. Through extensive experiments on both synthetic and real-world datasets, we demonstrate that PACE surpasses state-of-the-art methods in terms of the defined desiderata.
Authors: Hang Yuan, Shing Chan, Andrew P. Creagh, Catherine Tong, Aidan Acquah, David A. Clifton, Aiden Doherty
Abstract: Advances in deep learning for human activity recognition have been relatively limited due to the lack of large labelled datasets. In this study, we leverage self-supervised learning techniques on the UK-Biobank activity tracker dataset--the largest of its kind to date--containing more than 700,000 person-days of unlabelled wearable sensor data. Our resulting activity recognition model consistently outperformed strong baselines across seven benchmark datasets, with an F1 relative improvement of 2.5%-100% (median 18.4%), the largest improvements occurring in the smaller datasets. In contrast to previous studies, our results generalise across external datasets, devices, and environments. Our open-source model will help researchers and developers to build customisable and generalisable activity classifiers with high performance.
Authors: Hesameddin Mohammadi, Meisam Razaviyayn, Mihailo R. Jovanovi\'c
Abstract: We study momentum-based first-order optimization algorithms in which the iterations utilize information from the two previous steps and are subject to an additive white noise. This setup uses noise to account for uncertainty in either gradient evaluation or iteration updates, and it includes Polyak's heavy-ball and Nesterov's accelerated methods as special cases. For strongly convex quadratic problems, we use the steady-state variance of the error in the optimization variable to quantify noise amplification and identify fundamental stochastic performance tradeoffs. Our approach utilizes the Jury stability criterion to provide a novel geometric characterization of conditions for linear convergence, and it reveals the relation between the noise amplification and convergence rate as well as their dependence on the condition number and the constant algorithmic parameters. This geometric insight leads to simple alternative proofs of standard convergence results and allows us to establish ``uncertainty principle'' of strongly convex optimization: for the two-step momentum method with linear convergence rate, the lower bound on the product between the settling time and noise amplification scales quadratically with the condition number. Our analysis also identifies a key difference between the gradient and iterate noise models: while the amplification of gradient noise can be made arbitrarily small by sufficiently decelerating the algorithm, the best achievable variance for the iterate noise model increases linearly with the settling time in the decelerating regime. Finally, we introduce two parameterized families of algorithms that strike a balance between noise amplification and settling time while preserving order-wise Pareto optimality for both noise models.
Authors: Wouter van Loon, Marjolein Fokkema, Frank de Vos, Marisa Koini, Reinhold Schmidt, Mark de Rooij
Abstract: Data for which a set of objects is described by multiple distinct feature sets (called views) is known as multi-view data. When missing values occur in multi-view data, all features in a view are likely to be missing simultaneously. This may lead to very large quantities of missing data which, especially when combined with high-dimensionality, can make the application of conditional imputation methods computationally infeasible. However, the multi-view structure could be leveraged to reduce the complexity and computational load of imputation. We introduce a new imputation method based on the existing stacked penalized logistic regression (StaPLR) algorithm for multi-view learning. It performs imputation in a dimension-reduced space to address computational challenges inherent to the multi-view context. We compare the performance of the new imputation method with several existing imputation algorithms in simulated data sets and a real data application. The results show that the new imputation method leads to competitive results at a much lower computational cost, and makes the use of advanced imputation algorithms such as missForest and predictive mean matching possible in settings where they would otherwise be computationally infeasible.
Authors: Philipp Pilar, Niklas Wahlstr\"om
Abstract: Physics-informed neural networks (PINNs) constitute a flexible approach to both finding solutions and identifying parameters of partial differential equations. Most works on the topic assume noiseless data, or data contaminated with weak Gaussian noise. We show that the standard PINN framework breaks down in case of non-Gaussian noise. We give a way of resolving this fundamental issue and we propose to jointly train an energy-based model (EBM) to learn the correct noise distribution. We illustrate the improved performance of our approach using multiple examples.
Authors: Cheng Tan, Zhangyang Gao, Hanqun Cao, Xingran Chen, Ge Wang, Lirong Wu, Jun Xia, Jiangbin Zheng, Stan Z. Li
Abstract: The secondary structure of ribonucleic acid (RNA) is more stable and accessible in the cell than its tertiary structure, making it essential for functional prediction. Although deep learning has shown promising results in this field, current methods suffer from poor generalization and high complexity. In this work, we reformulate the RNA secondary structure prediction as a K-Rook problem, thereby simplifying the prediction process into probabilistic matching within a finite solution space. Building on this innovative perspective, we introduce RFold, a simple yet effective method that learns to predict the most matching K-Rook solution from the given sequence. RFold employs a bi-dimensional optimization strategy that decomposes the probabilistic matching problem into row-wise and column-wise components to reduce the matching complexity, simplifying the solving process while guaranteeing the validity of the output. Extensive experiments demonstrate that RFold achieves competitive performance and about eight times faster inference efficiency than the state-of-the-art approaches. The code and Colab demo are available in (http://github.com/A4Bio/RFold).
Authors: Derek DeSantis, Ayan Biswas, Earl Lawrence, Phillip Wolfram
Abstract: We propose a new method for combining in situ buoy measurements with Earth system models (ESMs) to improve the accuracy of temperature predictions in the ocean. The technique utilizes the dynamics \textit{and} modes identified in ESMs alongside buoy measurements to improve accuracy while preserving features such as seasonality. We use this technique, which we call Dynamic Basis Function Interpolation, to correct errors in localized temperature predictions made by the Model for Prediction Across Scales Ocean component (MPAS-O) with the Global Drifter Program's in situ ocean buoy dataset.
Authors: Suman Adhya, Debarshi Kumar Sanyal
Abstract: Topic modeling is a dominant method for exploring document collections on the web and in digital libraries. Recent approaches to topic modeling use pretrained contextualized language models and variational autoencoders. However, large neural topic models have a considerable memory footprint. In this paper, we propose a knowledge distillation framework to compress a contextualized topic model without loss in topic quality. In particular, the proposed distillation objective is to minimize the cross-entropy of the soft labels produced by the teacher and the student models, as well as to minimize the squared 2-Wasserstein distance between the latent distributions learned by the two models. Experiments on two publicly available datasets show that the student trained with knowledge distillation achieves topic coherence much higher than that of the original student model, and even surpasses the teacher while containing far fewer parameters than the teacher's. The distilled model also outperforms several other competitive topic models on topic coherence.
Authors: Niccol\`o Tosato, Lorenzo Basile, Emanuele Ballarin, Giuseppe de Alteriis, Alberto Cazzaniga, Alessio Ansuini
Abstract: The Backpropagation algorithm has often been criticised for its lack of biological realism. In an attempt to find a more biologically plausible alternative, the recently introduced Forward-Forward algorithm replaces the forward and backward passes of Backpropagation with two forward passes. In this work, we show that the internal representations obtained by the Forward-Forward algorithm can organise into category-specific ensembles exhibiting high sparsity - composed of a low number of active units. This situation is reminiscent of what has been observed in cortical sensory areas, where neuronal ensembles are suggested to serve as the functional building blocks for perception and action. Interestingly, while this sparse pattern does not typically arise in models trained with standard Backpropagation, it can emerge in networks trained with Backpropagation on the same objective proposed for the Forward-Forward algorithm. These results suggest that the learning procedure proposed by Forward-Forward may be superior to Backpropagation in modelling learning in the cortex, even when a backward pass is used.
Authors: Valter Uotila
Abstract: In recent years, advances in quantum computing have led to accelerating research on quantum applications across fields. Here, we introduce a quantum machine learning model as a potential solution to the classical question in database research: the estimation of metrics for SQL queries. This work employs a quantum natural language processing (QNLP)-inspired approach for constructing a quantum machine learning model that can classify SQL queries with respect to their cardinalities, costs, and execution times. The model consists of an encoding mechanism and a training phase, including classical and quantum subroutines. The encoding mechanism encodes SQL queries as parametrized quantum circuits. In the training phase, we utilize classical optimization algorithms, such as SPSA and Adam, to optimize the circuit parameters to make predictions about the query metrics. We conclude that our model reaches an accuracy equivalent to that of the QNLP model in the binary classification tasks. Moreover, we extend the previous work by adding 4-class classification tasks and compare the cardinality estimation results to the state-of-the-art databases. We perform a theoretical analysis of the quantum machine learning model by calculating its expressibility and entangling capabilities. The analysis shows that the model has advantageous properties that make it expressible but also not too complex to be executed on the existing quantum hardware.
Authors: Pedro Zattoni Scroccaro, Piet van Beek, Peyman Mohajerin Esfahani, Bilge Atasoy
Abstract: We propose a method for learning decision-makers' behavior in routing problems using Inverse Optimization (IO). The IO framework falls into the supervised learning category and builds on the premise that the target behavior is an optimizer of an unknown cost function. This cost function is to be learned through historical data, and in the context of routing problems, can be interpreted as the routing preferences of the decision-makers. In this view, the main contributions of this study are to propose an IO methodology with a hypothesis function, loss function, and stochastic first-order algorithm tailored to routing problems. We further test our IO approach in the Amazon Last Mile Routing Research Challenge, where the goal is to learn models that replicate the routing preferences of human drivers, using thousands of real-world routing examples. Our final IO-learned routing model achieves a score that ranks 2nd compared with the 48 models that qualified for the final round of the challenge. Our examples and results showcase the flexibility and real-world potential of the proposed IO methodology to learn from decision-makers' decisions in routing problems.
Authors: Kanchan Poudel, Manish Dhakal, Prasiddha Bhandari, Rabin Adhikari, Safal Thapaliya, Bishesh Khanal
Abstract: Medical image segmentation allows quantifying target structure size and shape, aiding in disease diagnosis, prognosis, surgery planning, and comprehension.Building upon recent advancements in foundation Vision-Language Models (VLMs) from natural image-text pairs, several studies have proposed adapting them to Vision-Language Segmentation Models (VLSMs) that allow using language text as an additional input to segmentation models. Introducing auxiliary information via text with human-in-the-loop prompting during inference opens up unique opportunities, such as open vocabulary segmentation and potentially more robust segmentation models against out-of-distribution data. Although transfer learning from natural to medical images has been explored for image-only segmentation models, the joint representation of vision-language in segmentation problems remains underexplored. This study introduces the first systematic study on transferring VLSMs to 2D medical images, using carefully curated $11$ datasets encompassing diverse modalities and insightful language prompts and experiments. Our findings demonstrate that although VLSMs show competitive performance compared to image-only models for segmentation after finetuning in limited medical image datasets, not all VLSMs utilize the additional information from language prompts, with image features playing a dominant role. While VLSMs exhibit enhanced performance in handling pooled datasets with diverse modalities and show potential robustness to domain shifts compared to conventional segmentation models, our results suggest that novel approaches are required to enable VLSMs to leverage the various auxiliary information available through language prompts. The code and datasets are available at https://github.com/naamiinepal/medvlsm.
Authors: Jan Simson, Florian Pfisterer, Christoph Kern
Abstract: A vast number of systems across the world use algorithmic decision making (ADM) to (partially) automate decisions that have previously been made by humans. The downstream effects of ADM systems critically depend on the decisions made during a systems' design, implementation, and evaluation, as biases in data can be mitigated or reinforced along the modeling pipeline. Many of these decisions are made implicitly, without knowing exactly how they will influence the final system. To study this issue, we draw on insights from the field of psychology and introduce the method of multiverse analysis for algorithmic fairness. In our proposed method, we turn implicit decisions during design and evaluation into explicit ones and demonstrate their fairness implications. By combining decisions, we create a grid of all possible "universes" of decision combinations. For each of these universes, we compute metrics of fairness and performance. Using the resulting dataset, one can investigate the variability and robustness of fairness scores and see how and which decisions impact fairness. We demonstrate how multiverse analyses can be used to better understand fairness implications of design and evaluation decisions using an exemplary case study of predicting public health care coverage for vulnerable populations. Our results highlight how decisions regarding the evaluation of a system can lead to vastly different fairness metrics for the same model. This is problematic, as a nefarious actor could optimise or "hack" a fairness metric to portray a discriminating model as fair merely by changing how it is evaluated. We illustrate how a multiverse analysis can help to address this issue.
Authors: Asmaa Shati, Ghulam Mubashar Hassan, Amitava Datta
Abstract: A wide range of respiratory diseases, such as cold and flu, asthma, and COVID-19, affect people's daily lives worldwide. In medical practice, respiratory sounds are widely used in medical services to diagnose various respiratory illnesses and lung disorders. The traditional diagnosis of such sounds requires specialized knowledge, which can be costly and reliant on human expertise. Despite this, recent advancements, such as cough audio recordings, have emerged as a means to automate the detection of respiratory conditions. Therefore, this research aims to explore various acoustic features that enhance the performance of machine learning (ML) models in detecting COVID-19 from cough signals. It investigates the efficacy of three feature extraction techniques, including Mel Frequency Cepstral Coefficients (MFCC), Chroma, and Spectral Contrast features, when applied to two machine learning algorithms, Support Vector Machine (SVM) and Multilayer Perceptron (MLP), and therefore proposes an efficient CovCepNet detection system. The proposed system provides a practical solution and demonstrates state-of-the-art classification performance, with an AUC of 0.843 on the COUGHVID dataset and 0.953 on the Virufy dataset for COVID-19 detection from cough audio signals.
Authors: Francesco Immorlano, Veronika Eyring, Thomas le Monnier de Gouville, Gabriele Accarino, Donatello Elia, Giovanni Aloisio, Pierre Gentine
Abstract: Accurate and precise climate projections are required for climate adaptation and mitigation, but Earth system models still exhibit great uncertainties. Several approaches have been developed to reduce the spread of climate projections and feedbacks, yet those methods cannot capture the non-linear complexity inherent in the climate system. Using a Transfer Learning approach, we show that Machine Learning can be used to optimally leverage and merge the knowledge gained from Earth system models simulations and historical observations to more accurately project global surface air temperature fields in the 21st century. We reach an uncertainty reduction of more than 50% with respect to state-of-the-art approaches. We give evidence that our novel method provides narrower projection uncertainty together with more accurate mean climate projections, urgently required for climate adaptation.
Authors: Simon Yu, Jie He, V\'ictor Guti\'errez-Basulto, Jeff Z. Pan
Abstract: Hierarchical multi-label text classification (HMTC) aims at utilizing a label hierarchy in multi-label classification. Recent approaches to HMTC deal with the problem of imposing an over-constrained premise on the output space by using contrastive learning on generated samples in a semi-supervised manner to bring text and label embeddings closer. However, the generation of samples tends to introduce noise as it ignores the correlation between similar samples in the same batch. One solution to this issue is supervised contrastive learning, but it remains an underexplored topic in HMTC due to its complex structured labels. To overcome this challenge, we propose $\textbf{HJCL}$, a $\textbf{H}$ierarchy-aware $\textbf{J}$oint Supervised $\textbf{C}$ontrastive $\textbf{L}$earning method that bridges the gap between supervised contrastive learning and HMTC. Specifically, we employ both instance-wise and label-wise contrastive learning techniques and carefully construct batches to fulfill the contrastive learning objective. Extensive experiments on four multi-path HMTC datasets demonstrate that HJCL achieves promising results and the effectiveness of Contrastive Learning on HMTC.
Authors: Xueren Ge, Satpathy Abhishek, Ronald Dean Williams, John A. Stankovic, Homa Alemzadeh
Abstract: Multi-label text classification (MLTC) tasks in the medical domain often face the long-tail label distribution problem. Prior works have explored hierarchical label structures to find relevant information for few-shot classes, but mostly neglected to incorporate external knowledge from medical guidelines. This paper presents DKEC, Domain Knowledge Enhanced Classification for diagnosis prediction with two innovations: (1) automated construction of heterogeneous knowledge graphs from external sources to capture semantic relations among diverse medical entities, (2) incorporating the heterogeneous knowledge graphs in few-shot classification using a label-wise attention mechanism. We construct DKEC using three online medical knowledge sources and evaluate it on a real-world Emergency Medical Services (EMS) dataset and a public electronic health record (EHR) dataset. Results show that DKEC outperforms the state-of-the-art label-wise attention networks and transformer models of different sizes, particularly for the few-shot classes. More importantly, it helps the smaller language models achieve comparable performance to large language models.
Authors: Haoxian Chen, Henry Lam
Abstract: Bayesian Optimization is a popular approach for optimizing expensive black-box functions. Its key idea is to use a surrogate model to approximate the objective and, importantly, quantify the associated uncertainty that allows a sequential search of query points that balance exploitation-exploration. Gaussian process (GP) has been a primary candidate for the surrogate model, thanks to its Bayesian-principled uncertainty quantification power and modeling flexibility. However, its challenges have also spurred an array of alternatives whose convergence properties could be more opaque. Motivated by these, we study in this paper an axiomatic framework that elicits the minimal requirements to guarantee black-box optimization convergence that could apply beyond GP-based methods. Moreover, we leverage the design freedom in our framework, which we call Pseudo-Bayesian Optimization, to construct empirically superior algorithms. In particular, we show how using simple local regression, and a suitable "randomized prior" construction to quantify uncertainty, not only guarantees convergence but also consistently outperforms state-of-the-art benchmarks in examples ranging from high-dimensional synthetic experiments to realistic hyperparameter tuning and robotic applications.
Authors: Yuduo Wang, Pedram Ghamisi
Abstract: In recent years, with the rapid advancement of transformer models, transformer-based multimodal architectures have found wide application in various downstream tasks, including but not limited to Image Captioning, Visual Question Answering (VQA), and Image-Text Generation. However, contemporary approaches to Remote Sensing (RS) VQA often involve resource-intensive techniques, such as full fine-tuning of large models or the extraction of image-text features from pre-trained multimodal models, followed by modality fusion using decoders. These approaches demand significant computational resources and time, and a considerable number of trainable parameters are introduced. To address these challenges, we introduce a novel method known as RSAdapter, which prioritizes runtime and parameter efficiency. RSAdapter comprises two key components: the Parallel Adapter and an additional linear transformation layer inserted after each fully connected (FC) layer within the Adapter. This approach not only improves adaptation to pre-trained multimodal models but also allows the parameters of the linear transformation layer to be integrated into the preceding FC layers during inference, reducing inference costs. To demonstrate the effectiveness of RSAdapter, we conduct an extensive series of experiments using three distinct RS-VQA datasets and achieve state-of-the-art results on all three datasets. The code for RSAdapter is available online at https://github.com/Y-D-Wang/RSAdapter.
Authors: Petros Karypis, Julian McAuley, George Karypis
Abstract: Effectively training language models on long inputs poses many technical challenges. As a cost consideration, languages models are pretrained on a fixed sequence length before being adapted to longer sequences. We explore various methods for adapting models to longer inputs by training on segmented sequences and an interpolation-based method for extending absolute positional embeddings. We develop a training procedure to extend the input context size of pretrained models with no architectural changes and no additional memory costs than training on the original input lengths. By sub-sampling segments from long inputs while maintaining their original position the model is able to learn new positional interactions. Our method benefits both models trained with absolute positional embeddings, by extending their input contexts, as well as popular relative positional embedding methods showing a reduced perplexity on sequences longer than they were trained on. We demonstrate our method can extend input contexts by a factor of 4x while improving perplexity.
Authors: Luca Ambrogioni
Abstract: Generative diffusion models have achieved spectacular performance in many areas of machine learning and generative modeling. While the fundamental ideas behind these models come from non-equilibrium physics, variational inference and stochastic calculus, in this paper we show that many aspects of these models can be understood using the tools of equilibrium statistical mechanics. Using this reformulation, we show that generative diffusion models undergo second-order phase transitions corresponding to symmetry breaking phenomena. We show that these phase-transitions are always in a mean-field universality class, as they are the result of a self-consistency condition in the generative dynamics. We argue that the critical instability that arises from the phase transitions lies at the heart of their generative capabilities, which are characterized by a set of mean-field critical exponents. Finally, we show that the dynamic equation of the generative process can be interpreted as a stochastic adiabatic transformation that minimizes the free energy while keeping the system in thermal equilibrium.
Authors: Derek Lilienthal, Paul Mello, Magdalini Eirinaki, Stas Tiomkin
Abstract: While recommender systems have become an integral component of the Web experience, their heavy reliance on user data raises privacy and security concerns. Substituting user data with synthetic data can address these concerns, but accurately replicating these real-world datasets has been a notoriously challenging problem. Recent advancements in generative AI have demonstrated the impressive capabilities of diffusion models in generating realistic data across various domains. In this work we introduce a Score-based Diffusion Recommendation Module (SDRM), which captures the intricate patterns of real-world datasets required for training highly accurate recommender systems. SDRM allows for the generation of synthetic data that can replace existing datasets to preserve user privacy, or augment existing datasets to address excessive data sparsity. Our method outperforms competing baselines such as generative adversarial networks, variational autoencoders, and recently proposed diffusion models in synthesizing various datasets to replace or augment the original data by an average improvement of 4.30% in Recall@k and 4.65% in NDCG@k.
Authors: Matthias Caro, Tom Gur, Cambyse Rouz\'e, Daniel Stilck Fran\c{c}a, Sathyawageeswar Subramanian
Abstract: Learning tasks play an increasingly prominent role in quantum information and computation. They range from fundamental problems such as state discrimination and metrology over the framework of quantum probably approximately correct (PAC) learning, to the recently proposed shadow variants of state tomography. However, the many directions of quantum learning theory have so far evolved separately. We propose a general mathematical formalism for describing quantum learning by training on classical-quantum data and then testing how well the learned hypothesis generalizes to new data. In this framework, we prove bounds on the expected generalization error of a quantum learner in terms of classical and quantum information-theoretic quantities measuring how strongly the learner's hypothesis depends on the specific data seen during training. To achieve this, we use tools from quantum optimal transport and quantum concentration inequalities to establish non-commutative versions of decoupling lemmas that underlie recent information-theoretic generalization bounds for classical machine learning. Our framework encompasses and gives intuitively accessible generalization bounds for a variety of quantum learning scenarios such as quantum state discrimination, PAC learning quantum states, quantum parameter estimation, and quantumly PAC learning classical functions. Thereby, our work lays a foundation for a unifying quantum information-theoretic perspective on quantum learning.
Authors: Matthias Karlbauer, Nathaniel Cresswell-Clay, Dale R. Durran, Raul A. Moreno, Thorsten Kurth, Boris Bonev, Noah Brenowitz, Martin V. Butz
Abstract: We present a parsimonious deep learning weather prediction model to forecast seven atmospheric variables with 3-h time resolution for up to one-year lead times on a 110-km global mesh using the Hierarchical Equal Area isoLatitude Pixelization (HEALPix). In comparison to state-of-the-art (SOTA) machine learning (ML) weather forecast models, such as Pangu-Weather and GraphCast, our DLWP-HPX model uses coarser resolution and far fewer prognostic variables. Yet, at one-week lead times, its skill is only about one day behind both SOTA ML forecast models and the SOTA numerical weather prediction model from the European Centre for Medium-Range Weather Forecasts. We report several improvements in model design, including switching from the cubed sphere to the HEALPix mesh, inverting the channel depth of the U-Net, and introducing gated recurrent units (GRU) on each level of the U-Net hierarchy. The consistent east-west orientation of all cells on the HEALPix mesh facilitates the development of location-invariant convolution kernels that successfully propagate weather patterns across the globe without requiring separate kernels for the polar and equatorial faces of the cube sphere. Without any loss of spectral power after the first two days, the model can be unrolled autoregressively for hundreds of steps into the future to generate realistic states of the atmosphere that respect seasonal trends, as showcased in one-year simulations.
Authors: Keunsu Kim, Hanbaek Lyu, Jinsu Kim, Jae-Hun Jung
Abstract: We propose a novel methodology for forecasting spatio-temporal data using supervised semi-nonnegative matrix factorization (SSNMF) with frequency regularization. Matrix factorization is employed to decompose spatio-temporal data into spatial and temporal components. To improve clarity in the temporal patterns, we introduce a nonnegativity constraint on the time domain along with regularization in the frequency domain. Specifically, regularization in the frequency domain involves selecting features in the frequency space, making an interpretation in the frequency domain more convenient. We propose two methods in the frequency domain: soft and hard regularizations, and provide convergence guarantees to first-order stationary points of the corresponding constrained optimization problem. While our primary motivation stems from geophysical data analysis based on GRACE (Gravity Recovery and Climate Experiment) data, our methodology has the potential for wider application. Consequently, when applying our methodology to GRACE data, we find that the results with the proposed methodology are comparable to previous research in the field of geophysical sciences but offer clearer interpretability.
Authors: Syed Farhan Abbas, Nguyen Thanh Duc, Yoonguu Song, Kyungwon Kim, Ekta Srivastava, Boreom Lee
Abstract: Due to the lack of automated methods, to diagnose cerebrovascular disease, time-of-flight magnetic resonance angiography (TOF-MRA) is assessed visually, making it time-consuming. The commonly used encoder-decoder architectures for cerebrovascular segmentation utilize redundant features, eventually leading to the extraction of low-level features multiple times. Additionally, convolutional neural networks (CNNs) suffer from performance degradation when the batch size is small, and deeper networks experience the vanishing gradient problem. Methods: In this paper, we attempt to solve these limitations and propose the 3D cerebrovascular attention UNet method, named CV-AttentionUNet, for precise extraction of brain vessel images. We proposed a sequence of preprocessing techniques followed by deeply supervised UNet to improve the accuracy of segmentation of the brain vessels leading to a stroke. To combine the low and high semantics, we applied the attention mechanism. This mechanism focuses on relevant associations and neglects irrelevant anatomical information. Furthermore, the inclusion of deep supervision incorporates different levels of features that prove to be beneficial for network convergence. Results: We demonstrate the efficiency of the proposed method by cross-validating with an unlabeled dataset, which was further labeled by us. We believe that the novelty of this algorithm lies in its ability to perform well on both labeled and unlabeled data with image processing-based enhancement. The results indicate that our method performed better than the existing state-of-the-art methods on the TubeTK dataset. Conclusion: The proposed method will help in accurate segmentation of cerebrovascular structure leading to stroke
Authors: Mulah Moriah, Franck Vermet, Arthur Charpentier
Abstract: The non-life insurance sector operates within a highly competitive and tightly regulated framework, confronting a pivotal juncture in the formulation of pricing strategies. Insurers are compelled to harness a range of statistical methodologies and available data to construct optimal pricing structures that align with the overarching corporate strategy while accommodating the dynamics of market competition. Given the fundamental societal role played by insurance, premium rates are subject to rigorous scrutiny by regulatory authorities. These rates must conform to principles of transparency, explainability, and ethical considerations. Consequently, the act of pricing transcends mere statistical calculations and carries the weight of strategic and societal factors. These multifaceted concerns may drive insurers to establish equitable premiums, taking into account various variables. For instance, regulations mandate the provision of equitable premiums, considering factors such as policyholder gender or mutualist group dynamics in accordance with respective corporate strategies. Age-based premium fairness is also mandated. In certain insurance domains, variables such as the presence of serious illnesses or disabilities are emerging as new dimensions for evaluating fairness. Regardless of the motivating factor prompting an insurer to adopt fairer pricing strategies for a specific variable, the insurer must possess the capability to define, measure, and ultimately mitigate any ethical biases inherent in its pricing practices while upholding standards of consistency and performance. This study seeks to provide a comprehensive set of tools for these endeavors and assess their effectiveness through practical application in the context of automobile insurance.
Authors: Zhenyu Tao, Wei Xu, Yongming Huang, Xiaoyun Wang, Xiaohu You
Abstract: Digital twin, which enables emulation, evaluation, and optimization of physical entities through synchronized digital replicas, has gained increasing attention as a promising technology for intricate wireless networks. For 6G, numerous innovative wireless technologies and network architectures have posed new challenges in establishing wireless network digital twins. To tackle these challenges, artificial intelligence (AI), particularly the flourishing generative AI, emerges as a potential solution. In this article, we discuss emerging prerequisites for wireless network digital twins considering the complicated network architecture, tremendous network scale, extensive coverage, and diversified application scenarios in the 6G era. We further explore the applications of generative AI, such as Transformer and diffusion model, to empower the 6G digital twin from multiple perspectives including physical-digital modeling, synchronization, and slicing capability. Subsequently, we propose a hierarchical generative AI-enabled wireless network digital twin at both the message-level and policy-level, and provide a typical use case with numerical results to validate the effectiveness and efficiency. Finally, open research issues for wireless network digital twins in the 6G era are discussed.
Authors: Yumou Wei, Ryan F. Forelli, Chris Hansen, Jeffrey P. Levesque, Nhan Tran, Joshua C. Agar, Giuseppe Di Guglielmo, Michael E. Mauel, Gerald A. Navratil
Abstract: Active feedback control in magnetic confinement fusion devices is desirable to mitigate plasma instabilities and enable robust operation. Optical high-speed cameras provide a powerful, non-invasive diagnostic and can be suitable for these applications. In this study, we process fast camera data, at rates exceeding 100kfps, on $\textit{in situ}$ Field Programmable Gate Array (FPGA) hardware to track magnetohydrodynamic (MHD) mode evolution and generate control signals in real-time. Our system utilizes a convolutional neural network (CNN) model which predicts the $n$=1 MHD mode amplitude and phase using camera images with better accuracy than other tested non-deep-learning-based methods. By implementing this model directly within the standard FPGA readout hardware of the high-speed camera diagnostic, our mode tracking system achieves a total trigger-to-output latency of 17.6$\mu$s and a throughput of up to 120kfps. This study at the High Beta Tokamak-Extended Pulse (HBT-EP) experiment demonstrates an FPGA-based high-speed camera data acquisition and processing system, enabling application in real-time machine-learning-based tokamak diagnostic and control as well as potential applications in other scientific domains.
Authors: Bokun Wang, Tianbao Yang
Abstract: This paper revisits a class of convex Finite-Sum Coupled Compositional Stochastic Optimization (cFCCO) problems with many applications, including group distributionally robust optimization (GDRO), learning with imbalanced data, reinforcement learning, and learning to rank. To better solve these problems, we introduce an efficient single-loop primal-dual block-coordinate proximal algorithm, dubbed ALEXR. This algorithm leverages block-coordinate stochastic mirror ascent updates for the dual variable and stochastic proximal gradient descent updates for the primal variable. We establish the convergence rates of ALEXR in both convex and strongly convex cases under smoothness and non-smoothness conditions of involved functions, which not only improve the best rates in previous works on smooth cFCCO problems but also expand the realm of cFCCO for solving more challenging non-smooth problems such as the dual form of GDRO. Finally, we present lower complexity bounds to demonstrate that the convergence rates of ALEXR are optimal among first-order block-coordinate stochastic algorithms for the considered class of cFCCO problems.
Authors: Parand A. Alamdari, Toryn Q. Klassen, Elliot Creager, Sheila A. McIlraith
Abstract: Fair decision making has largely been studied with respect to a single decision. Here we investigate the notion of fairness in the context of sequential decision making where multiple stakeholders can be affected by the outcomes of decisions. We observe that fairness often depends on the history of the sequential decision-making process, and in this sense that it is inherently non-Markovian. We further observe that fairness often needs to be assessed at time points within the process, not just at the end of the process. To advance our understanding of this class of fairness problems, we explore the notion of non-Markovian fairness in the context of sequential decision making. We identify properties of non-Markovian fairness, including notions of long-term, anytime, periodic, and bounded fairness. We explore the interplay between non-Markovian fairness and memory and how memory can support construction of fair policies. Finally, we introduce the FairQCM algorithm, which can automatically augment its training data to improve sample efficiency in the synthesis of fair policies via reinforcement learning.
Authors: Motoya Ohnishi, Iretiayo Akinola, Jie Xu, Ajay Mandlekar, Fabio Ramos
Abstract: Path signatures have been proposed as a powerful representation of paths that efficiently captures the path's analytic and geometric characteristics, having useful algebraic properties including fast concatenation of paths through tensor products. Signatures have recently been widely adopted in machine learning problems for time series analysis. In this work we establish connections between value functions typically used in optimal control and intriguing properties of path signatures. These connections motivate our novel control framework with signature transforms that efficiently generalizes the Bellman equation to the space of trajectories. We analyze the properties and advantages of the framework, termed signature control. In particular, we demonstrate that (i) it can naturally deal with varying/adaptive time steps; (ii) it propagates higher-level information more efficiently than value function updates; (iii) it is robust to dynamical system misspecification over long rollouts. As a specific case of our framework, we devise a model predictive control method for path tracking. This method generalizes integral control, being suitable for problems with unknown disturbances. The proposed algorithms are tested in simulation, with differentiable physics models including typical control and robotics tasks such as point-mass, curve following for an ant model, and a robotic manipulator.
Authors: Prakhar Srivastava, Ruihan Yang, Gavin Kerrigan, Gideon Dresdner, Jeremy McGibbon, Christopher Bretherton, Stephan Mandt
Abstract: In climate science and meteorology, high-resolution local precipitation (rain and snowfall) predictions are limited by the computational costs of simulation-based methods. Statistical downscaling, or super-resolution, is a common workaround where a low-resolution prediction is improved using statistical approaches. Unlike traditional computer vision tasks, weather and climate applications require capturing the accurate conditional distribution of high-resolution given low-resolution patterns to assure reliable ensemble averages and unbiased estimates of extreme events, such as heavy rain. This work extends recent video diffusion models to precipitation super-resolution, employing a deterministic downscaler followed by a temporally-conditioned diffusion model to capture noise characteristics and high-frequency patterns. We test our approach on FV3GFS output, an established large-scale global atmosphere model, and compare it against six state-of-the-art baselines. Our analysis, capturing CRPS, MSE, precipitation distributions, and qualitative aspects using California and the Himalayas as examples, establishes our method as a new standard for data-driven precipitation downscaling.
Authors: Tanvi Sharma, Mustafa Ali, Indranil Chakraborty, Kaushik Roy
Abstract: Compute-in-memory (CiM) has emerged as a highly energy efficient solution for performing matrix multiplication during Machine Learning (ML) inference. However, integrating compute in memory poses key questions, such as 1) What type of CiM to use: Given a multitude of CiM design characteristics, determining their suitability from architecture perspective is needed. 2) When to use CiM: ML inference includes workloads with a variety of memory and compute requirements, making it difficult to identify when CiM is more beneficial. 3) Where to integrate CiM: Each memory level has different bandwidth and capacity, creating different data reuse opportunities for CiM integration. To answer such questions regarding on-chip CiM integration for accelerating ML workloads, we use an analytical architecture evaluation methodology where we tailor the dataflow mapping. The mapping algorithm aims to achieve highest weight reuse and reduced data movements for a given CiM prototype and workload. Our experiments show that CiM integrated memory improves energy efficiency by up to 3.4x and throughput by up to 15.6x compared to tensor-core-like baseline architecture, with INT-8 precision under iso-area constraints. We believe the proposed work provides insights into what type of CiM to use, and when and where to optimally integrate it in the cache hierarchy for efficient matrix multiplication.
Authors: AmirEhsan Khorashadizadeh, Valentin Debarnot, Tianlin Liu, Ivan Dokmani\'c
Abstract: Deep learning is the current de facto state of the art in tomographic imaging. A common approach is to feed the result of a simple inversion, for example the backprojection, to a convolutional neural network (CNN) which then computes the reconstruction. Despite strong results on 'in-distribution' test data similar to the training data, backprojection from sparse-view data delocalizes singularities, so these approaches require a large receptive field to perform well. As a consequence, they overfit to certain global structures which leads to poor generalization on out-of-distribution (OOD) samples. Moreover, their memory complexity and training time scale unfavorably with image resolution, making them impractical for application at realistic clinical resolutions, especially in 3D: a standard U-Net requires a substantial 140GB of memory and 2600 seconds per epoch on a research-grade GPU when training on 1024x1024 images. In this paper, we introduce GLIMPSE, a local processing neural network for computed tomography which reconstructs a pixel value by feeding only the measurements associated with the neighborhood of the pixel to a simple MLP. While achieving comparable or better performance with successful CNNs like the U-Net on in-distribution test data, GLIMPSE significantly outperforms them on OOD samples while maintaining a memory footprint almost independent of image resolution; 5GB memory suffices to train on 1024x1024 images. Further, we built GLIMPSE to be fully differentiable, which enables feats such as recovery of accurate projection angles if they are out of calibration.
Authors: Mehil B. Shah, Mohammad Masudur Rahman, Foutse Khomh
Abstract: Context: Deep learning has achieved remarkable progress in various domains. However, like any software system, deep learning systems contain bugs, some of which can have severe impacts, as evidenced by crashes involving autonomous vehicles. Despite substantial advancements in deep learning techniques, little research has focused on reproducing deep learning bugs, which is an essential step for their resolution. Existing literature suggests that only 3% of deep learning bugs are reproducible, underscoring the need for further research. Objective: This paper examines the reproducibility of deep learning bugs. We identify edit actions and useful information that could improve the reproducibility of deep learning bugs. Method: First, we construct a dataset of 668 deep-learning bugs from Stack Overflow and GitHub across three frameworks and 22 architectures. Second, out of the 668 bugs, we select 165 bugs using stratified sampling and attempt to determine their reproducibility. While reproducing these bugs, we identify edit actions and useful information for their reproduction. Third, we used the Apriori algorithm to identify useful information and edit actions required to reproduce specific types of bugs. Finally, we conducted a user study involving 22 developers to assess the effectiveness of our findings in real-life settings. Results: We successfully reproduced 148 out of 165 bugs attempted. We identified ten edit actions and five useful types of component information that can help us reproduce the deep learning bugs. With the help of our findings, the developers were able to reproduce 22.92% more bugs and reduce their reproduction time by 24.35%. Conclusions: Our research addresses the critical issue of deep learning bug reproducibility. Practitioners and researchers can leverage our findings to improve deep learning bug reproducibility.
Authors: Haoyu Li, Shichang Zhang, Longwen Tang, Mathieu Bauchy, Yizhou Sun
Abstract: Metallic Glasses (MGs) are widely used materials that are stronger than steel while being shapeable as plastic. While understanding the structure-property relationship of MGs remains a challenge in materials science, studying their energy barriers (EBs) as an intermediary step shows promise. In this work, we utilize Graph Neural Networks (GNNs) to model MGs and study EBs. We contribute a new dataset for EB prediction and a novel Symmetrized GNN (SymGNN) model that is E(3)-invariant in expectation. SymGNN handles invariance by aggregating over orthogonal transformations of the graph structure. When applied to EB prediction, SymGNN are more accurate than molecular dynamics (MD) local-sampling methods and other machine-learning models. Compared to precise MD simulations, SymGNN reduces the inference time on new MGs from roughly 41 days to less than one second. We apply explanation algorithms to reveal the relationship between structures and EBs. The structures that we identify through explanations match the medium-range order (MRO) hypothesis and possess unique topological properties. Our work enables effective prediction and interpretation of MG EBs, bolstering material science research.
Authors: Weide Liu, Huijing Zhan, Hao Chen, Fengmao Lv
Abstract: Multimodal sentiment analysis aims to identify the emotions expressed by individuals through visual, language, and acoustic cues. However, most of the existing research efforts assume that all modalities are available during both training and testing, making their algorithms susceptible to the missing modality scenario. In this paper, we propose a novel knowledge-transfer network to translate between different modalities to reconstruct the missing audio modalities. Moreover, we develop a cross-modality attention mechanism to retain the maximal information of the reconstructed and observed modalities for sentiment prediction. Extensive experiments on three publicly available datasets demonstrate significant improvements over baselines and achieve comparable results to the previous methods with complete multi-modality supervision.
Authors: Moshe Babaioff, Amitai Frey, Noam Nisan
Abstract: We study the problem of designing a two-sided market (double auction) to maximize the gains from trade (social welfare) under the constraints of (dominant-strategy) incentive compatibility and budget-balance. Our goal is to do so for an unknown distribution from which we are given a polynomial number of samples. Our first result is a general impossibility for the case of correlated distributions of values even between just one seller and two buyers, in contrast to the case of one seller and one buyer (bilateral trade) where this is possible. Our second result is an efficient learning algorithm for one seller and two buyers in the case of independent distributions which is based on a novel algorithm for computing optimal mechanisms for finitely supported and explicitly given independent distributions. Both results rely heavily on characterizations of (dominant-strategy) incentive compatible mechanisms that are strongly budget-balanced.
Authors: Tereso del R\'io, Matthew England
Abstract: Symbolic Computation algorithms and their implementation in computer algebra systems often contain choices which do not affect the correctness of the output but can significantly impact the resources required: such choices can benefit from having them made separately for each problem via a machine learning model. This study reports lessons on such use of machine learning in symbolic computation, in particular on the importance of analysing datasets prior to machine learning and on the different machine learning paradigms that may be utilised. We present results for a particular case study, the selection of variable ordering for cylindrical algebraic decomposition, but expect that the lessons learned are applicable to other decisions in symbolic computation. We utilise an existing dataset of examples derived from applications which was found to be imbalanced with respect to the variable ordering decision. We introduce an augmentation technique for polynomial systems problems that allows us to balance and further augment the dataset, improving the machine learning results by 28\% and 38\% on average, respectively. We then demonstrate how the existing machine learning methodology used for the problem $-$ classification $-$ might be recast into the regression paradigm. While this does not have a radical change on the performance, it does widen the scope in which the methodology can be applied to make choices.
Authors: Fotios Lygerakis, Vedant Dave, Elmar Rueckert
Abstract: One of the most critical aspects of multimodal Reinforcement Learning (RL) is the effective integration of different observation modalities. Having robust and accurate representations derived from these modalities is key to enhancing the robustness and sample efficiency of RL algorithms. However, learning representations in RL settings for visuotactile data poses significant challenges, particularly due to the high dimensionality of the data and the complexity involved in correlating visual and tactile inputs with the dynamic environment and task objectives. To address these challenges, we propose Multimodal Contrastive Unsupervised Reinforcement Learning (M2CURL). Our approach employs a novel multimodal self-supervised learning technique that learns efficient representations and contributes to faster convergence of RL algorithms. Our method is agnostic to the RL algorithm, thus enabling its integration with any available RL algorithm. We evaluate M2CURL on the Tactile Gym 2 simulator and we show that it significantly enhances the learning efficiency in different manipulation tasks. This is evidenced by faster convergence rates and higher cumulative rewards per episode, compared to standard RL algorithms without our representation learning approach.
Authors: Jacob Fein-Ashley, Tian Ye, Sachini Wickramasinghe, Bingyi Zhang, Rajgopal Kannan, Viktor Prasanna
Abstract: Image classifiers often rely on convolutional neural networks (CNN) for their tasks, which, for image classification, experience high latency due to the number of operations they perform, which can be problematic in real-time applications. Additionally, many image classification models work on both RGB and grayscale datasets. Classifiers that operate solely on grayscale images are much less common. Grayscale image classification has diverse applications, including but not limited to medical image classification and synthetic aperture radar (SAR) automatic target recognition (ATR). Thus, we present a novel grayscale image classification approach using a vectorized view of images. We exploit the lightweightness of MLPs by viewing images as vectors and reducing our problem setting to the grayscale image classification setting. We find that using a single graph convolutional layer batch-wise increases accuracy and reduces variance in the performance of our model. Moreover, we develop a customized accelerator on FPGA for the proposed model with several optimizations to improve its performance. Our experimental results on benchmark grayscale image datasets demonstrate the effectiveness of the proposed model, achieving vastly lower latency (up to 16$\times$ less) and competitive or leading performance compared to other state-of-the-art image classification models on various domain-specific grayscale image classification datasets.
Authors: Soojung Yang, Juno Nam, Johannes C. B. Dietschreit, Rafael G\'omez-Bombarelli
Abstract: In molecular dynamics simulations, rare events, such as protein folding, are typically studied using enhanced sampling techniques, most of which are based on the definition of a collective variable (CV) along which acceleration occurs. Obtaining an expressive CV is crucial, but often hindered by the lack of information about the particular event, e.g., the transition from unfolded to folded conformation. We propose a simulation-free data augmentation strategy using physics-inspired metrics to generate geodesic interpolations resembling protein folding transitions, thereby improving sampling efficiency without true transition state samples. This new data can be used to improve the accuracy of classifier-based methods. Alternatively, a regression-based learning scheme for CV models can be adopted by leveraging the interpolation progress parameter.
Authors: Md Ferdous Pervej, Andreas F. Molisch
Abstract: Backhaul traffic congestion caused by the video traffic of a few popular files can be alleviated by storing the to-be-requested content at various levels in wireless video caching networks. Typically, content service providers (CSPs) own the content, and the users request their preferred content from the CSPs using their (wireless) internet service providers (ISPs). As these parties do not reveal their private information and business secrets, traditional techniques may not be readily used to predict the dynamic changes in users' future demands. Motivated by this, we propose a novel resource-aware hierarchical federated learning (RawHFL) solution for predicting user's future content requests. A practical data acquisition technique is used that allows the user to update its local training dataset based on its requested content. Besides, since networking and other computational resources are limited, considering that only a subset of the users participate in the model training, we derive the convergence bound of the proposed algorithm. Based on this bound, we minimize a weighted utility function for jointly configuring the controllable parameters to train the RawHFL energy efficiently under practical resource constraints. Our extensive simulation results validate the proposed algorithm's superiority, in terms of test accuracy and energy cost, over existing baselines.
Authors: Haolun Wu, Ye Yuan, Liana Mikaelyan, Alexander Meulemans, Xue Liu, James Hensman, Bhaskar Mitra
Abstract: Recent advances in machine learning have significantly impacted the field of information extraction, with Language Models (LMs) playing a pivotal role in extracting structured information from unstructured text. Prior works typically represent information extraction as triplet-centric and use classical metrics such as precision and recall for evaluation. We reformulate the task to be entity-centric, enabling the use of diverse metrics that can provide more insights from various perspectives. We contribute to the field by introducing Structured Entity Extraction and proposing the Approximate Entity Set OverlaP (AESOP) metric, designed to appropriately assess model performance. Later, we introduce a new model that harnesses the power of LMs for enhanced effectiveness and efficiency by decomposing the extraction task into multiple stages. Quantitative and human side-by-side evaluations confirm that our model outperforms baselines, offering promising directions for future advancements in structured entity extraction.
Authors: Margaux Br\'eg\`ere (LPSM), Julie Keisler (CRIStAL, EDF R\&D)
Abstract: This work formulates model selection as an infinite-armed bandit problem, namely, a problem in which a decision maker iteratively selects one of an infinite number of fixed choices (i.e., arms) when the properties of each choice are only partially known at the time of allocation and may become better understood over time, via the attainment of rewards.Here, the arms are machine learning models to train and selecting an arm corresponds to a partial training of the model (resource allocation).The reward is the accuracy of the selected model after its partial training.We aim to identify the best model at the end of a finite number of resource allocations and thus consider the best arm identification setup. We propose the algorithm Mutant-UCB that incorporates operators from evolutionary algorithms into the UCB-E (Upper Confidence Bound Exploration) bandit algorithm introduced by Audiber et al.Tests carried out on three open source image classification data sets attest to the relevance of this novel combining approach, which outperforms the state-of-the-art for a fixed budget.
Authors: Nicholas Konz, Yuwen Chen, Haoyu Dong, Maciej A. Mazurowski
Abstract: Diffusion models have enabled remarkably high-quality medical image generation, yet it is challenging to enforce anatomical constraints in generated images. To this end, we propose a diffusion model-based method that supports anatomically-controllable medical image generation, by following a multi-class anatomical segmentation mask at each sampling step. We additionally introduce a random mask ablation training algorithm to enable conditioning on a selected combination of anatomical constraints while allowing flexibility in other anatomical areas. We compare our method ("SegGuidedDiff") to existing methods on breast MRI and abdominal/neck-to-pelvis CT datasets with a wide range of anatomical objects. Results show that our method reaches a new state-of-the-art in the faithfulness of generated images to input anatomical masks on both datasets, and is on par for general anatomical realism. Finally, our model also enjoys the extra benefit of being able to adjust the anatomical similarity of generated images to real images of choice through interpolation in its latent space. SegGuidedDiff has many applications, including cross-modality translation, and the generation of paired or counterfactual data. Our code is available at https://github.com/mazurowski-lab/segmentation-guided-diffusion.
URLs: https://github.com/mazurowski-lab/segmentation-guided-diffusion.
Authors: Daniel Beaglehole, Ioannis Mitliagkas, Atish Agarwala
Abstract: Understanding the mechanisms through which neural networks extract statistics from input-label pairs through feature learning is one of the most important unsolved problems in supervised learning. Prior works demonstrated that the gram matrices of the weights (the neural feature matrices, NFM) and the average gradient outer products (AGOP) become correlated during training, in a statement known as the neural feature ansatz (NFA). Through the NFA, the authors introduce mapping with the AGOP as a general mechanism for neural feature learning. However, these works do not provide a theoretical explanation for this correlation or its origins. In this work, we further clarify the nature of this correlation, and explain its emergence. We show that this correlation is equivalent to alignment between the left singular structure of the weight matrices and the newly defined pre-activation tangent features at each layer. We further establish that the alignment is driven by the interaction of weight changes induced by SGD with the pre-activation features, and analyze the resulting dynamics analytically at early times in terms of simple statistics of the inputs and labels. Finally, motivated by the observation that the NFA is driven by this centered correlation, we introduce a simple optimization rule that dramatically increases the NFA correlations at any given layer and improves the quality of features learned.
Authors: Yuepeng Yang, Antares Chen, Lorenzo Orecchia, Cong Ma
Abstract: In this paper, we address the top-$K$ ranking problem with a monotone adversary. We consider the scenario where a comparison graph is randomly generated and the adversary is allowed to add arbitrary edges. The statistician's goal is then to accurately identify the top-$K$ preferred items based on pairwise comparisons derived from this semi-random comparison graph. The main contribution of this paper is to develop a weighted maximum likelihood estimator (MLE) that achieves near-optimal sample complexity, up to a $\log^2(n)$ factor, where $n$ denotes the number of items under comparison. This is made possible through a combination of analytical and algorithmic innovations. On the analytical front, we provide a refined~$\ell_\infty$ error analysis of the weighted MLE that is more explicit and tighter than existing analyses. It relates the~$\ell_\infty$ error with the spectral properties of the weighted comparison graph. Motivated by this, our algorithmic innovation involves the development of an SDP-based approach to reweight the semi-random graph and meet specified spectral properties. Additionally, we propose a first-order method based on the Matrix Multiplicative Weight Update (MMWU) framework. This method efficiently solves the resulting SDP in nearly-linear time relative to the size of the semi-random comparison graph.
Authors: Zhiwei Zhao, Changqing Liu, Yingguang Li, Zhibin Chen, Xu Liu
Abstract: In scientific and engineering applications, solving partial differential equations (PDEs) across various parameters and domains normally relies on resource-intensive numerical methods. Neural operators based on deep learning offered a promising alternative to PDEs solving by directly learning physical laws from data. However, the current neural operator methods were limited to solve PDEs on fixed domains. Expanding neural operators to solve PDEs on various domains hold significant promise in medical imaging, engineering design and manufacturing applications, where geometric and parameter changes are essential. This paper presents a novel neural operator learning framework for solving PDEs with various domains and parameters defined for physical systems, named diffeomorphism neural operator (DNO). The main idea is that a neural operator learns in a generic domain which is diffeomorphically mapped from various physics domains expressed by the same PDE. In this way, the challenge of operator learning on various domains is transformed into operator learning on the generic domain. The generalization performance of DNO on different domains can be assessed by a proposed method which evaluates the geometric similarity between a new domain and the domains of training dataset after diffeomorphism. Experiments on Darcy flow, pipe flow, airfoil flow and mechanics were carried out, where harmonic and volume parameterization were used as the diffeomorphism for 2D and 3D domains. The DNO framework demonstrated robust learning capabilities and strong generalization performance across various domains and parameters.
Authors: Liyan Xu, Zhenlin Su, Mo Yu, Jin Xu, Jinho D. Choi, Jie Zhou, Fei Liu
Abstract: Factual inconsistencies pose a significant hurdle for the faithful summarization by generative models. While a major direction to enhance inconsistency detection is to derive stronger Natural Language Inference (NLI) models, we propose an orthogonal aspect that underscores the importance of incorporating task-specific taxonomy into the inference. To this end, we consolidate key error types of inconsistent facts in summaries, and incorporate them to facilitate both the zero-shot and supervised paradigms of LLMs. Extensive experiments on ten datasets of five distinct domains suggest that, zero-shot LLM inference could benefit from the explicit solution space depicted by the error type taxonomy, and achieves state-of-the-art performance overall, surpassing specialized non-LLM baselines, as well as recent LLM baselines. We further distill models that fuse the taxonomy into parameters through our designed prompt completions and supervised training strategies, efficiently substituting state-of-the-art zero-shot inference with much larger LLMs.
Authors: Daniel Holmberg, Manu Airaksinen, Viviana Marchi, Andrea Guzzetta, Anna Kivi, Leena Haataja, Sampsa Vanhatalo, Teemu Roos
Abstract: Reliable methods for the neurodevelopmental assessment of infants are essential for early detection of medical issues that may need prompt interventions. Spontaneous motor activity, or 'kinetics', is shown to provide a powerful surrogate measure of upcoming neurodevelopment. However, its assessment is by and large qualitative and subjective, focusing on visually identified, age-specific gestures. Here, we follow an alternative approach, predicting infants' neurodevelopmental maturation based on data-driven evaluation of individual motor patterns. We utilize 3D video recordings of infants processed with pose-estimation to extract spatio-temporal series of anatomical landmarks, and apply adaptive graph convolutional networks to predict the actual age. We show that our data-driven approach achieves improvement over traditional machine learning baselines based on manually engineered features.
Authors: Oliver Bentham, Nathan Stringham, Ana Marasovi\'c
Abstract: Understanding the extent to which Chain-of-Thought (CoT) generations align with a large language model's (LLM) internal computations is critical for deciding whether to trust an LLM's output. As a proxy for CoT faithfulness, Lanham et al. (2023) propose a metric that measures a model's dependence on its CoT for producing an answer. Within a single family of proprietary models, they find that LLMs exhibit a scaling-then-inverse-scaling relationship between model size and their measure of faithfulness, and that a 13 billion parameter model exhibits increased faithfulness compared to models ranging from 810 million to 175 billion parameters in size. We evaluate whether these results generalize as a property of all LLMs. We replicate their experimental setup with three different families of models and, under specific conditions, successfully reproduce the scaling trends for CoT faithfulness they report. However, we discover that simply changing the order of answer choices in the prompt can reduce the metric by 73 percentage points. The faithfulness metric is also highly correlated ($R^2$ = 0.91) with accuracy, raising doubts about its validity for evaluating faithfulness.
Authors: Shijing Si, Yuwei Wu, Le Tang, Yugui Zhang, Jedrek Wosik
Abstract: Email continues to be a pivotal and extensively utilized communication medium within professional and commercial domains. Nonetheless, the prevalence of spam emails poses a significant challenge for users, disrupting their daily routines and diminishing productivity. Consequently, accurately identifying and filtering spam based on content has become crucial for cybersecurity. Recent advancements in natural language processing, particularly with large language models like ChatGPT, have shown remarkable performance in tasks such as question answering and text generation. However, its potential in spam identification remains underexplored. To fill in the gap, this study attempts to evaluate ChatGPT's capabilities for spam identification in both English and Chinese email datasets. We employ ChatGPT for spam email detection using in-context learning, which requires a prompt instruction and a few demonstrations. We also investigate how the number of demonstrations in the prompt affects the performance of ChatGPT. For comparison, we also implement five popular benchmark methods, including naive Bayes, support vector machines (SVM), logistic regression (LR), feedforward dense neural networks (DNN), and BERT classifiers. Through extensive experiments, the performance of ChatGPT is significantly worse than deep supervised learning methods in the large English dataset, while it presents superior performance on the low-resourced Chinese dataset.
Authors: Fanjin Zhang, Shijie Shi, Yifan Zhu, Bo Chen, Yukuo Cen, Jifan Yu, Yelin Chen, Lulu Wang, Qingfei Zhao, Yuqing Cheng, Tianyi Han, Yuwei An, Dan Zhang, Weng Lam Tam, Kun Cao, Yunhe Pang, Xinyu Guan, Huihui Yuan, Jian Song, Xiaoyan Li, Yuxiao Dong, Jie Tang
Abstract: With the rapid proliferation of scientific literature, versatile academic knowledge services increasingly rely on comprehensive academic graph mining. Despite the availability of public academic graphs, benchmarks, and datasets, these resources often fall short in multi-aspect and fine-grained annotations, are constrained to specific task types and domains, or lack underlying real academic graphs. In this paper, we present OAG-Bench, a comprehensive, multi-aspect, and fine-grained human-curated benchmark based on the Open Academic Graph (OAG). OAG-Bench covers 10 tasks, 20 datasets, 70+ baselines, and 120+ experimental results to date. We propose new data annotation strategies for certain tasks and offer a suite of data pre-processing codes, algorithm implementations, and standardized evaluation protocols to facilitate academic graph mining. Extensive experiments reveal that even advanced algorithms like large language models (LLMs) encounter difficulties in addressing key challenges in certain tasks, such as paper source tracing and scholar profiling. We also introduce the Open Academic Graph Challenge (OAG-Challenge) to encourage community input and sharing. We envisage that OAG-Bench can serve as a common ground for the community to evaluate and compare algorithms in academic graph mining, thereby accelerating algorithm development and advancement in this field. OAG-Bench is accessible at https://www.aminer.cn/data/.
Authors: Jacob Spainhour, Korben Smart, Stephen Becker, Nick Bottenus
Abstract: Objective: The transmit encoding model for synthetic aperture imaging is a robust and flexible framework for understanding the effects of acoustic transmission on ultrasound image reconstruction. Our objective is to use machine learning (ML) to construct scanning sequences, parameterized by time delays and apodization weights, that produce high-quality B-mode images. Approach: We use a custom ML model in PyTorch with simulated RF data from Field II to probe the space of possible encoding sequences for those that minimize a loss function that describes image quality. This approach is made computationally feasible by a novel formulation of the derivative for delay-and-sum beamforming. Main Results: When trained for a specified experimental setting (imaging domain, hardware restrictions, etc.), our ML model produces optimized encoding sequences that, when deployed in the REFoCUS imaging framework, improve a number of standard quality metrics over conventional sequences including resolution, field of view, and contrast. We demonstrate these results experimentally on both wire targets and a tissue-mimicking phantom. Significance: This work demonstrates that the set of commonly used encoding schemes represent only a narrow subset of those available. Additionally, it demonstrates the value for ML tasks in synthetic transmit aperture imaging to consider the beamformer within the model, instead of purely as a post-processing step.
Authors: Sungho Ko, Hyunjin Cho, Hyungjoo Chae, Jinyoung Yeo, Dongha Lee
Abstract: Recent studies have investigated utilizing Knowledge Graphs (KGs) to enhance Quesetion Answering (QA) performance of Large Language Models (LLMs), yet structured KG verbalization remains challengin. Existing methods, such as triple-form or free-form textual conversion of triple-form facts, encounter several issues. These include reduced evidence density due to duplicated entities or relationships, and reduced evidence clarity due to an inability to emphasize crucial evidence. To address these issues, we propose EFSum, an Evidence-focused Fact Summarization framework for enhanced QA with knowledge-augmented LLMs. We optimize an open-source LLM as a fact summarizer through distillation and preference alignment. Our extensive experiments show that EFSum improves LLM's zero-shot QA performance, and it is possible to ensure both the helpfulness and faithfulness of the summary.
Authors: Masahiro Kato, Akihiro Oga, Wataru Komatsubara, Ryo Inokuchi
Abstract: This study designs an adaptive experiment for efficiently estimating average treatment effects (ATEs). In each round of our adaptive experiment, an experimenter sequentially samples an experimental unit, assigns a treatment, and observes the corresponding outcome immediately. At the end of the experiment, the experimenter estimates an ATE using the gathered samples. The objective is to estimate the ATE with a smaller asymptotic variance. Existing studies have designed experiments that adaptively optimize the propensity score (treatment-assignment probability). As a generalization of such an approach, we propose optimizing the covariate density as well as the propensity score. First, we derive the efficient covariate density and propensity score that minimize the semiparametric efficiency bound and find that optimizing both covariate density and propensity score minimizes the semiparametric efficiency bound more effectively than optimizing only the propensity score. Next, we design an adaptive experiment using the efficient covariate density and propensity score sequentially estimated during the experiment. Lastly, we propose an ATE estimator whose asymptotic variance aligns with the minimized semiparametric efficiency bound.
Authors: Sara Abdali, Richard Anarfi, CJ Barberan, Jia He
Abstract: Large Language Models (LLMs) have revolutionized the field of Natural Language Generation (NLG) by demonstrating an impressive ability to generate human-like text. However, their widespread usage introduces challenges that necessitate thoughtful examination, ethical scrutiny, and responsible practices. In this study, we delve into these challenges, explore existing strategies for mitigating them, with a particular emphasis on identifying AI-generated text as the ultimate solution. Additionally, we assess the feasibility of detection from a theoretical perspective and propose novel research directions to address the current limitations in this domain.
Authors: Hengyuan Zhang, Zitao Liu, Chenming Shang, Dawei Li, Yong Jiang
Abstract: Knowledge tracing (KT) plays a crucial role in predicting students' future performance by analyzing their historical learning processes. Deep neural networks (DNNs) have shown great potential in solving the KT problem. However, there still exist some important challenges when applying deep learning techniques to model the KT process. The first challenge lies in taking the individual information of the question into modeling. This is crucial because, despite questions sharing the same knowledge component (KC), students' knowledge acquisition on homogeneous questions can vary significantly. The second challenge lies in interpreting the prediction results from existing deep learning-based KT models. In real-world applications, while it may not be necessary to have complete transparency and interpretability of the model parameters, it is crucial to present the model's prediction results in a manner that teachers find interpretable. This makes teachers accept the rationale behind the prediction results and utilize them to design teaching activities and tailored learning strategies for students. However, the inherent black-box nature of deep learning techniques often poses a hurdle for teachers to fully embrace the model's prediction results. To address these challenges, we propose a Question-centric Multi-experts Contrastive Learning framework for KT called Q-MCKT. We have provided all the datasets and code on our website at https://github.com/rattlesnakey/Q-MCKT.
Authors: Carmelo Sferrazza, Dun-Ming Huang, Xingyu Lin, Youngwoon Lee, Pieter Abbeel
Abstract: Humanoid robots hold great promise in assisting humans in diverse environments and tasks, due to their flexibility and adaptability leveraging human-like morphology. However, research in humanoid robots is often bottlenecked by the costly and fragile hardware setups. To accelerate algorithmic research in humanoid robots, we present a high-dimensional, simulated robot learning benchmark, HumanoidBench, featuring a humanoid robot equipped with dexterous hands and a variety of challenging whole-body manipulation and locomotion tasks. Our findings reveal that state-of-the-art reinforcement learning algorithms struggle with most tasks, whereas a hierarchical learning approach achieves superior performance when supported by robust low-level policies, such as walking or reaching. With HumanoidBench, we provide the robotics community with a platform to identify the challenges arising when solving diverse tasks with humanoid robots, facilitating prompt verification of algorithms and ideas. The open-source code is available at https://humanoid-bench.github.io.
Authors: Francesco Paissan, Mirco Ravanelli, Cem Subakan
Abstract: Despite the impressive performance of deep learning models across diverse tasks, their complexity poses challenges for interpretation. This challenge is particularly evident for audio signals, where conveying interpretations becomes inherently difficult. To address this issue, we introduce Listenable Maps for Audio Classifiers (L-MAC), a posthoc interpretation method that generates faithful and listenable interpretations. L-MAC utilizes a decoder on top of a pretrained classifier to generate binary masks that highlight relevant portions of the input audio. We train the decoder with a loss function that maximizes the confidence of the classifier decision on the masked-in portion of the audio while minimizing the probability of model output for the masked-out portion. Quantitative evaluations on both in-domain and out-of-domain data demonstrate that L-MAC consistently produces more faithful interpretations than several gradient and masking-based methodologies. Furthermore, a user study confirms that, on average, users prefer the interpretations generated by the proposed technique.
Authors: Fan Wang, Yating Wang, Wing Tat Leung, Zongben Xu
Abstract: Multiscale problems can usually be approximated through numerical homogenization by an equation with some effective parameters that can capture the macroscopic behavior of the original system on the coarse grid to speed up the simulation. However, this approach usually assumes scale separation and that the heterogeneity of the solution can be approximated by the solution average in each coarse block. For complex multiscale problems, the computed single effective properties/continuum might be inadequate. In this paper, we propose a novel learning-based multi-continuum model to enrich the homogenized equation and improve the accuracy of the single continuum model for multiscale problems with some given data. Without loss of generalization, we consider a two-continuum case. The first flow equation keeps the information of the original homogenized equation with an additional interaction term. The second continuum is newly introduced, and the effective permeability in the second flow equation is determined by a neural network. The interaction term between the two continua aligns with that used in the Dual-porosity model but with a learnable coefficient determined by another neural network. The new model with neural network terms is then optimized using trusted data. We discuss both direct back-propagation and the adjoint method for the PDE-constraint optimization problem. Our proposed learning-based multi-continuum model can resolve multiple interacted media within each coarse grid block and describe the mass transfer among them, and it has been demonstrated to significantly improve the simulation results through numerical experiments involving both linear and nonlinear flow equations.
Authors: Taha Koleilat, Hojat Asgariandehkordi, Hassan Rivaz, Yiming Xiao
Abstract: Medical image segmentation of anatomical structures and pathology is crucial in modern clinical diagnosis, disease study, and treatment planning. To date, great progress has been made in deep learning-based segmentation techniques, but most methods still lack data efficiency, generalizability, and interactability. Consequently, the development of new, precise segmentation methods that demand fewer labeled datasets is of utmost importance in medical image analysis. Recently, the emergence of foundation models, such as CLIP and Segment-Anything-Model (SAM), with comprehensive cross-domain representation opened the door for interactive and universal image segmentation. However, exploration of these models for data-efficient medical image segmentation is still limited, but is highly necessary. In this paper, we propose a novel framework, called MedCLIP-SAM that combines CLIP and SAM models to generate segmentation of clinical scans using text prompts in both zero-shot and weakly supervised settings. To achieve this, we employed a new Decoupled Hard Negative Noise Contrastive Estimation (DHN-NCE) loss to fine-tune the BiomedCLIP model and the recent gScoreCAM to generate prompts to obtain segmentation masks from SAM in a zero-shot setting. Additionally, we explored the use of zero-shot segmentation labels in a weakly supervised paradigm to improve the segmentation quality further. By extensively testing three diverse segmentation tasks and medical image modalities (breast tumor ultrasound, brain tumor MRI, and lung X-ray), our proposed framework has demonstrated excellent accuracy. Code is available at https://github.com/HealthX-Lab/MedCLIP-SAM.
Authors: Chin-Yun Yu, Christopher Mitcheltree, Alistair Carson, Stefan Bilbao, Joshua D. Reiss, Gy\"orgy Fazekas
Abstract: Infinite impulse response filters are an essential building block of many time-varying audio systems, such as audio effects and synthesisers. However, their recursive structure impedes end-to-end training of these systems using automatic differentiation. Although non-recursive filter approximations like frequency sampling and frame-based processing have been proposed and widely used in previous works, they cannot accurately reflect the gradient of the original system. We alleviate this difficulty by re-expressing a time-varying all-pole filter to backpropagate the gradients through itself, so the filter implementation is not bound to the technical limitations of automatic differentiation frameworks. This implementation can be employed within audio systems containing filters with poles for efficient gradient evaluation. We demonstrate its training efficiency and expressive capabilities for modelling real-world dynamic audio systems on a phaser, time-varying subtractive synthesiser, and feed-forward compressor. We make our code and audio samples available and provide the trained audio effect and synth models in a VST plugin at https://diffapf.github.io/web/.
Authors: Simone Tedeschi, Felix Friedrich, Patrick Schramowski, Kristian Kersting, Roberto Navigli, Huu Nguyen, Bo Li
Abstract: When building Large Language Models (LLMs), it is paramount to bear safety in mind and protect them with guardrails. Indeed, LLMs should never generate content promoting or normalizing harmful, illegal, or unethical behavior that may contribute to harm to individuals or society. This principle applies to both normal and adversarial use. In response, we introduce ALERT, a large-scale benchmark to assess safety based on a novel fine-grained risk taxonomy. It is designed to evaluate the safety of LLMs through red teaming methodologies and consists of more than 45k instructions categorized using our novel taxonomy. By subjecting LLMs to adversarial testing scenarios, ALERT aims to identify vulnerabilities, inform improvements, and enhance the overall safety of the language models. Furthermore, the fine-grained taxonomy enables researchers to perform an in-depth evaluation that also helps one to assess the alignment with various policies. In our experiments, we extensively evaluate 10 popular open- and closed-source LLMs and demonstrate that many of them still struggle to attain reasonable levels of safety.
Authors: Yiming Zhang, Zhuokai Zhao, Zhaorun Chen, Zhili Feng, Zenghui Ding, Yining Sun
Abstract: Self-supervised contrastive learning models, such as CLIP, have set new benchmarks for vision-language models in many downstream tasks. However, their dependency on rigid one-to-one mappings overlooks the complex and often multifaceted relationships between and within texts and images. To this end, we introduce RANKCLIP, a novel pretraining method that extends beyond the rigid one-to-one matching framework of CLIP and its variants. By extending the traditional pair-wise loss to list-wise, and leveraging both in-modal and cross-modal ranking consistency, RANKCLIP improves the alignment process, enabling it to capture the nuanced many-to-many relationships between and within each modality. Through comprehensive experiments, we demonstrate the effectiveness of RANKCLIP in various downstream tasks, notably achieving significant gains in zero-shot classifications over state-of-the-art methods, underscoring the importance of this enhanced learning process.
Authors: Ricard Puig-i-Valls, Marc Drudis, Supanut Thanasilp, Zo\"e Holmes
Abstract: The barren plateau phenomenon, characterized by loss gradients that vanish exponentially with system size, poses a challenge to scaling variational quantum algorithms. Here we explore the potential of warm starts, whereby one initializes closer to a solution in the hope of enjoying larger loss variances. Focusing on an iterative variational method for learning shorter-depth circuits for quantum real and imaginary time evolution we conduct a case study to elucidate the potential and limitations of warm starts. We start by proving that the iterative variational algorithm will exhibit substantial (at worst vanishing polynomially in system size) gradients in a small region around the initializations at each time-step. Convexity guarantees for these regions are then established, suggesting trainability for polynomial size time-steps. However, our study highlights scenarios where a good minimum shifts outside the region with trainability guarantees. Our analysis leaves open the question whether such minima jumps necessitate optimization across barren plateau landscapes or whether there exist gradient flows, i.e., fertile valleys away from the plateau with substantial gradients, that allow for training.
Authors: Andrew B. Kahng, Zhiang Wang
Abstract: Global placement is a fundamental step in VLSI physical design. The wide use of 2D processing element (PE) arrays in machine learning accelerators poses new challenges of scalability and Quality of Results (QoR) for state-of-the-art academic global placers. In this work, we develop DG-RePlAce, a new and fast GPU-accelerated global placement framework built on top of the OpenROAD infrastructure, which exploits the inherent dataflow and datapath structures of machine learning accelerators. Experimental results with a variety of machine learning accelerators using a commercial 12nm enablement show that, compared with RePlAce (DREAMPlace), our approach achieves an average reduction in routed wirelength by 10% (7%) and total negative slack (TNS) by 31% (34%), with faster global placement and on-par total runtimes relative to DREAMPlace. Empirical studies on the TILOS MacroPlacement Benchmarks further demonstrate that post-route improvements over RePlAce and DREAMPlace may reach beyond the motivating application to machine learning accelerators.
Authors: Anej Svete, Ryan Cotterell
Abstract: Existing work has analyzed the representational capacity of the transformer architecture by means of formal models of computation. However, the focus so far has been on analyzing the architecture in terms of language \emph{acceptance}. We contend that this is an ill-suited problem in the study of \emph{language models} (LMs), which are definitionally \emph{probability distributions} over strings. In this paper, we focus on the relationship between transformer LMs and $n$-gram LMs, a simple and historically relevant class of language models. We show that transformer LMs using the hard or sparse attention mechanisms can exactly represent any $n$-gram LM, giving us a concrete lower bound on their probabilistic representational capacity. This provides a first step towards understanding the mechanisms that transformer LMs can use to represent probability distributions over strings.
Authors: Md Kamran Chowdhury Shisher, Yin Sun, I-Hong Hou
Abstract: In this paper, we analyze the impact of data freshness on remote inference systems, where a pre-trained neural network blue infers a time-varying target (e.g., the locations of vehicles and pedestrians) based on features (e.g., video frames) observed at a sensing node (e.g., a camera). One might expect that the performance of a remote inference system degrades monotonically as the feature becomes stale. Using an information-theoretic analysis, we show that this is true if the feature and target data sequence can be closely approximated as a Markov chain, whereas it is not true if the data sequence is far from being Markovian. Hence, the inference error is a function of Age of Information (AoI), where the function could be non-monotonic. To minimize the inference error in real-time, we propose a new "selection-from-buffer" model for sending the features, which is more general than the "generate-at-will" model used in earlier studies. In addition, we design low-complexity scheduling policies to improve inference performance. For single-source, single-channel systems, we provide an optimal scheduling policy. In multi-source, multi-channel systems, the scheduling problem becomes a multi-action restless multi-armed bandit problem. For this setting, we design a new scheduling policy by integrating Whittle index-based source selection and duality-based feature selection-from-buffer algorithms. This new scheduling policy is proven to be asymptotically optimal. These scheduling results hold for minimizing general AoI functions (monotonic or non-monotonic). Data-driven evaluations demonstrate the significant advantages of our proposed scheduling policies.
Authors: Zhiyu Guo, Hidetaka Kamigaito, Taro Wanatnabe
Abstract: The rapid growth in the scale of Large Language Models (LLMs) has led to significant computational and memory costs, making model compression techniques such as network pruning increasingly crucial for their efficient deployment. Recent LLMs such as LLaMA2 and Mistral have adopted GLU-based MLP architectures. However, current LLM pruning strategies are primarily based on insights from older LLM architectures, necessitating a reevaluation of these strategies to suit the new architectural characteristics. Contrary to traditional beliefs, we find that outliers play a diminished role in the input projections of GLU-based MLPs. Leveraging this new insight, we propose Dependency-aware Semi-structured Sparsity (DaSS), a novel pruning method for GLU-based LLMs. DaSS balances the flexibility of unstructured pruning and the structural consistency of dependency-based structured pruning by considering both of weight magnitude and corresponding intermediate activation norms in weight pruning metric. Empirical evaluations on the Mistral, Gemma, and LLaMA2 model families demonstrate the consistent effectiveness of DaSS in the prevailing GLU variants.
Authors: Ruihan Zhang, Jun Sun
Abstract: Adversarial examples pose a security threat to many critical systems built on neural networks. While certified training improves robustness, it also decreases accuracy noticeably. Despite various proposals for addressing this issue, the significant accuracy drop remains. More importantly, it is not clear whether there is a certain fundamental limit on achieving robustness whilst maintaining accuracy. In this work, we offer a novel perspective based on Bayes errors. By adopting Bayes error to robustness analysis, we investigate the limit of certified robust accuracy, taking into account data distribution uncertainties. We first show that the accuracy inevitably decreases in the pursuit of robustness due to changed Bayes error in the altered data distribution. Subsequently, we establish an upper bound for certified robust accuracy, considering the distribution of individual classes and their boundaries. Our theoretical results are empirically evaluated on real-world datasets and are shown to be consistent with the limited success of existing certified training results, e.g., for CIFAR10, our analysis results in an upper bound (of certified robust accuracy) of 67.49\%, meanwhile existing approaches are only able to increase it from 53.89\% in 2017 to 62.84\% in 2023.
Authors: Yuxi Li, Yi Liu, Yuekang Li, Ling Shi, Gelei Deng, Shengquan Chen, Kailong Wang
Abstract: Large language models (LLMs) have transformed the field of natural language processing, but they remain susceptible to jailbreaking attacks that exploit their capabilities to generate unintended and potentially harmful content. Existing token-level jailbreaking techniques, while effective, face scalability and efficiency challenges, especially as models undergo frequent updates and incorporate advanced defensive measures. In this paper, we introduce JailMine, an innovative token-level manipulation approach that addresses these limitations effectively. JailMine employs an automated "mining" process to elicit malicious responses from LLMs by strategically selecting affirmative outputs and iteratively reducing the likelihood of rejection. Through rigorous testing across multiple well-known LLMs and datasets, we demonstrate JailMine's effectiveness and efficiency, achieving a significant average reduction of 86% in time consumed while maintaining high success rates averaging 95%, even in the face of evolving defensive strategies. Our work contributes to the ongoing effort to assess and mitigate the vulnerability of LLMs to jailbreaking attacks, underscoring the importance of continued vigilance and proactive measures to enhance the security and reliability of these powerful language models.
Authors: Xiaodong Liu
Abstract: This paper presents a significant improvement on the previous conference paper known as DefSent. The prior study seeks to improve sentence embeddings of language models by projecting definition sentences into the vector space of dictionary entries. We discover that this approach is not fully explored due to the methodological limitation of using word embeddings of language models to represent dictionary entries. This leads to two hindrances. First, dictionary entries are constrained by the single-word vocabulary, and thus cannot be fully exploited. Second, semantic representations of language models are known to be anisotropic, but pre-processing word embeddings for DefSent is not allowed because its weight is frozen during training and tied to the prediction layer. In this paper, we propose a novel method to progressively build entry embeddings not subject to the limitations. As a result, definition sentences can be projected into a quasi-isotropic or isotropic vector space of unlimited dictionary entries, so that sentence embeddings of noticeably better quality are attainable. We abbreviate our approach as DefSent+ (a plus version of DefSent), involving the following strengths: 1) the task performance on measuring sentence similarities is significantly improved compared to DefSent; 2) when DefSent+ is used to further train data-augmented models like SIMCSE, SNCSE, and SynCSE, state-of-the-art performance on measuring sentence similarities can be achieved among the approaches without using manually labeled datasets; 3) DefSent+ is also competitive in feature-based transfer for NLP downstream tasks.
Authors: Jiesong Lian, Yucong Huang, Mingzhi Wang, Chengdong Ma, Yixue Hao, Ying Wen, Yaodong Yang
Abstract: A popular approach for solving zero-sum games is to maintain populations of policies to approximate the Nash Equilibrium (NE). Previous studies have shown that Policy Space Response Oracle (PSRO) algorithm is an effective multi-agent reinforcement learning framework for solving such games. However, repeatedly training new policies from scratch to approximate Best Response (BR) to opponents' mixed policies at each iteration is both inefficient and costly. While some PSRO variants initialize a new policy by inheriting from past BR policies, this approach limits the exploration of new policies, especially against challenging opponents. To address this issue, we propose Fusion-PSRO, which employs policy fusion to initialize policies for better approximation to BR. By selecting high-quality base policies from meta-NE, policy fusion fuses the base policies into a new policy through model averaging. This approach allows the initialized policies to incorporate multiple expert policies, making it easier to handle difficult opponents compared to inheriting from past BR policies or initializing from scratch. Moreover, our method only modifies the policy initialization phase, allowing its application to nearly all PSRO variants without additional training overhead. Our experiments on non-transitive matrix games, Leduc Poker, and the more complex Liars Dice demonstrate that Fusion-PSRO enhances the performance of nearly all PSRO variants, achieving lower exploitability.
Authors: Guojin Chen, Keren Zhu, Seunggeun Kim, Hanqing Zhu, Yao Lai, Bei Yu, David Z. Pan
Abstract: Analog layout synthesis faces significant challenges due to its dependence on manual processes, considerable time requirements, and performance instability. Current Bayesian Optimization (BO)-based techniques for analog layout synthesis, despite their potential for automation, suffer from slow convergence and extensive data needs, limiting their practical application. This paper presents the \texttt{LLANA} framework, a novel approach that leverages Large Language Models (LLMs) to enhance BO by exploiting the few-shot learning abilities of LLMs for more efficient generation of analog design-dependent parameter constraints. Experimental results demonstrate that \texttt{LLANA} not only achieves performance comparable to state-of-the-art (SOTA) BO methods but also enables a more effective exploration of the analog circuit design space, thanks to LLM's superior contextual understanding and learning efficiency. The code is available at https://github.com/dekura/LLANA.
Authors: Arya Akhavan, Karim Lounici, Massimiliano Pontil, Alexandre B. Tsybakov
Abstract: We study the contextual continuum bandits problem, where the learner sequentially receives a side information vector and has to choose an action in a convex set, minimizing a function associated to the context. The goal is to minimize all the underlying functions for the received contexts, leading to a dynamic (contextual) notion of regret, which is stronger than the standard static regret. Assuming that the objective functions are H\"older with respect to the contexts, we demonstrate that any algorithm achieving a sub-linear static regret can be extended to achieve a sub-linear dynamic regret. We further study the case of strongly convex and smooth functions when the observations are noisy. Inspired by the interior point method and employing self-concordant barriers, we propose an algorithm achieving a sub-linear dynamic regret. Lastly, we present a minimax lower bound, implying two key facts. First, no algorithm can achieve sub-linear dynamic regret over functions that are not continuous with respect to the context. Second, for strongly convex and smooth functions, the algorithm that we propose achieves, up to a logarithmic factor, the minimax optimal rate of dynamic regret as a function of the number of queries.
Authors: Julia Kruk, Michela Marchini, Rijul Magu, Caleb Ziems, David Muchlinski, Diyi Yang
Abstract: A dog whistle is a form of coded communication that carries a secondary meaning to specific audiences and is often weaponized for racial and socioeconomic discrimination. Dog whistling historically originated from United States politics, but in recent years has taken root in social media as a means of evading hate speech detection systems and maintaining plausible deniability. In this paper, we present an approach for word-sense disambiguation of dog whistles from standard speech using Large Language Models (LLMs), and leverage this technique to create a dataset of 16,550 high-confidence coded examples of dog whistles used in formal and informal communication. Silent Signals is the largest dataset of disambiguated dog whistle usage, created for applications in hate speech detection, neology, and political science. The dataset can be found at https://huggingface.co/datasets/SALT-NLP/silent_signals.
URLs: https://huggingface.co/datasets/SALT-NLP/silent_signals.
Authors: Tatsuya Itoi, Kazuho Amishiki, Sangwon Lee, Taro Yaoyama
Abstract: A novel framework for Bayesian structural model updating is presented in this study. The proposed method utilizes the surrogate unimodal encoders of a multimodal variational autoencoder (VAE). The method facilitates an approximation of the likelihood when dealing with a small number of observations. It is particularly suitable for high-dimensional correlated simultaneous observations applicable to various dynamic analysis models. The proposed approach was benchmarked using a numerical model of a single-story frame building with acceleration and dynamic strain measurements. Additionally, an example involving a Bayesian update of nonlinear model parameters for a three-degree-of-freedom lumped mass model demonstrates computational efficiency when compared to using the original VAE, while maintaining adequate accuracy for practical applications.
Authors: Yifan Wu, Jason Hartline
Abstract: Scoring rules evaluate probabilistic forecasts of an unknown state against the realized state and are a fundamental building block in the incentivized elicitation of information and the training of machine learning models. This paper develops mechanisms for scoring elicited text against ground truth text using domain-knowledge-free queries to a large language model (specifically ChatGPT) and empirically evaluates their alignment with human preferences. The empirical evaluation is conducted on peer reviews from a peer-grading dataset and in comparison to manual instructor scores for the peer reviews.
Authors: Valdes Gonzalo
Abstract: This study introduces a novel approach to ensure the existence and uniqueness of optimal parameters in neural networks. The paper details how a recurrent neural networks (RNN) can be transformed into a contraction in a domain where its parameters are linear. It then demonstrates that a prediction problem modeled through an RNN, with a specific regularization term in the loss function, can have its first-order conditions expressed analytically. This system of equations is reduced to two matrix equations involving Sylvester equations, which can be partially solved. We establish that, if certain conditions are met, optimal parameters exist, are unique, and can be found through a straightforward algorithm to any desired precision. Also, as the number of neurons grows the conditions of convergence become easier to fulfill. Feedforward neural networks (FNNs) are also explored by including linear constraints on parameters. According to our model, incorporating loops (with fixed or variable weights) will produce loss functions that train easier, because it assures the existence of a region where an iterative method converges.
Authors: Orson Mengara
Abstract: With the growing use of voice-activated systems and speech recognition technologies, the danger of backdoor attacks on audio data has grown significantly. This research looks at a specific type of attack, known as a Stochastic investment-based backdoor attack (MarketBack), in which adversaries strategically manipulate the stylistic properties of audio to fool speech recognition systems. The security and integrity of machine learning models are seriously threatened by backdoor attacks, in order to maintain the reliability of audio applications and systems, the identification of such attacks becomes crucial in the context of audio data. Experimental results demonstrated that MarketBack is feasible to achieve an average attack success rate close to 100% in seven victim models when poisoning less than 1% of the training data.
Authors: Kevin Leyton-Brown, Yoav Shoham
Abstract: Motivated by the rapid ascent of Large Language Models (LLMs) and debates about the extent to which they possess human-level qualities, we propose a framework for testing whether any agent (be it a machine or a human) understands a subject matter. In Turing-test fashion, the framework is based solely on the agent's performance, and specifically on how well it answers questions. Elements of the framework include circumscribing the set of questions (the "scope of understanding"), requiring general competence ("passing grade"), avoiding "ridiculous answers", but still allowing wrong and "I don't know" answers to some questions. Reaching certainty about these conditions requires exhaustive testing of the questions which is impossible for nontrivial scopes, but we show how high confidence can be achieved via random sampling and the application of probabilistic confidence bounds. We also show that accompanying answers with explanations can improve the sample complexity required to achieve acceptable bounds, because an explanation of an answer implies the ability to answer many similar questions. According to our framework, current LLMs cannot be said to understand nontrivial domains, but as the framework provides a practical recipe for testing understanding, it thus also constitutes a tool for building AI agents that do understand.
Authors: Jin Ma, Gaozhan Wang, Jianfeng Zhang
Abstract: In this paper we provide a simple proof from scratch for the convergence of Policy Improvement Algorithm (PIA) for a continuous time entropy-regularized stochastic control problem. Such convergence has been established by Huang-Wang-Zhou(2023) by using sophisticated PDE estimates for the iterative PDEs involved in the PIA. Our approach builds on some Feynman-Kac type probabilistic representation formulae for solutions of PDEs and their derivatives. Moreover, in the infinite horizon model with a large discount factor and in the finite horizon model, we obtain the exponential rate of convergence with similar arguments. Finally, in the one dimensional setting, we extend the convergence result to the diffusion control case.
Authors: Yanming Liu, Xinyue Peng, Jiannan Cao, Yuwei Zhang, Chen Ma, Songhang Deng, Mengchen Fu, Xuhong Zhang, Sheng Cheng, Xun Wang, Jianwei Yin, Tianyu Du
Abstract: Large language models have consistently demonstrated remarkable performance across a wide spectrum of applications. Nonetheless, the deployment of these models can inadvertently expose user privacy to potential risks. The substantial memory demands of these models during training represent a significant resource consumption challenge. The sheer size of these models imposes a considerable burden on memory resources, which is a matter of significant concern in practice. In this paper, we present an innovative training framework MemDPT that not only reduces the memory cost of large language models but also places a strong emphasis on safeguarding user data privacy. MemDPT provides edge network and reverse network designs to accommodate various differential privacy memory-efficient fine-tuning schemes. Our approach not only achieves $2 \sim 3 \times$ memory optimization but also provides robust privacy protection, ensuring that user data remains secure and confidential. Extensive experiments have demonstrated that MemDPT can effectively provide differential privacy efficient fine-tuning across various task scenarios.
Authors: Sri Harsha Dumpala, Aman Jaiswal, Chandramouli Sastry, Evangelos Milios, Sageev Oore, Hassan Sajjad
Abstract: Despite their remarkable successes, state-of-the-art large language models (LLMs), including vision-and-language models (VLMs) and unimodal language models (ULMs), fail to understand precise semantics. For example, semantically equivalent sentences expressed using different lexical compositions elicit diverging representations. The degree of this divergence and its impact on encoded semantics is not very well understood. In this paper, we introduce the SUGARCREPE++ dataset to analyze the sensitivity of VLMs and ULMs to lexical and semantic alterations. Each sample in SUGARCREPE++ dataset consists of an image and a corresponding triplet of captions: a pair of semantically equivalent but lexically different positive captions and one hard negative caption. This poses a 3-way semantic (in)equivalence problem to the language models. We comprehensively evaluate VLMs and ULMs that differ in architecture, pre-training objectives and datasets to benchmark the performance of SUGARCREPE++ dataset. Experimental results highlight the difficulties of VLMs in distinguishing between lexical and semantic variations, particularly in object attributes and spatial relations. Although VLMs with larger pre-training datasets, model sizes, and multiple pre-training objectives achieve better performance on SUGARCREPE++, there is a significant opportunity for improvement. We show that all the models which achieve better performance on compositionality datasets need not perform equally well on SUGARCREPE++, signifying that compositionality alone may not be sufficient for understanding semantic and lexical alterations. Given the importance of the property that the SUGARCREPE++ dataset targets, it serves as a new challenge to the vision-and-language community.
Authors: Romina Yalovetzky, Niraj Kumar, Changhao Li, Marco Pistoia
Abstract: Random Forest (RF) is a popular tree-ensemble method for supervised learning, prized for its ease of use and flexibility. Online RF models require to account for new training data to maintain model accuracy. This is particularly important in applications where data is periodically and sequentially generated over time in data streams, such as auto-driving systems, and credit card payments. In this setting, performing periodic model retraining with the old and new data accumulated is beneficial as it fully captures possible drifts in the data distribution over time. However, this is unpractical with state-of-the-art classical algorithms for RF as they scale linearly with the accumulated number of samples. We propose QC-Forest, a classical-quantum algorithm designed to time-efficiently retrain RF models in the streaming setting for multi-class classification and regression, achieving a runtime poly-logarithmic in the total number of accumulated samples. QC-Forest leverages Des-q, a quantum algorithm for single tree construction and retraining proposed by Kumar et al. by expanding to multi-class classification, as the original proposal was limited to binary classes, and introducing an exact classical method to replace an underlying quantum subroutine incurring a finite error, while maintaining the same poly-logarithmic dependence. Finally, we showcase that QC-Forest achieves competitive accuracy in comparison to state-of-the-art RF methods on widely used benchmark datasets with up to 80,000 samples, while significantly speeding up the model retrain.
Authors: Jiasheng Zhang, Jialin Chen, Menglin Yang, Aosong Feng, Shuang Liang, Jie Shao, Rex Ying
Abstract: Dynamic text-attributed graphs (DyTAGs) are prevalent in various real-world scenarios, where each node and edge are associated with text descriptions, and both the graph structure and text descriptions evolve over time. Despite their broad applicability, there is a notable scarcity of benchmark datasets tailored to DyTAGs, which hinders the potential advancement in many research fields. To address this gap, we introduce Dynamic Text-attributed Graph Benchmark (DTGB), a collection of large-scale, time-evolving graphs from diverse domains, with nodes and edges enriched by dynamically changing text attributes and categories. To facilitate the use of DTGB, we design standardized evaluation procedures based on four real-world use cases: future link prediction, destination node retrieval, edge classification, and textual relation generation. These tasks require models to understand both dynamic graph structures and natural language, highlighting the unique challenges posed by DyTAGs. Moreover, we conduct extensive benchmark experiments on DTGB, evaluating 7 popular dynamic graph learning algorithms and their variants of adapting to text attributes with LLM embeddings, along with 6 powerful large language models (LLMs). Our results show the limitations of existing models in handling DyTAGs. Our analysis also demonstrates the utility of DTGB in investigating the incorporation of structural and textual dynamics. The proposed DTGB fosters research on DyTAGs and their broad applications. It offers a comprehensive benchmark for evaluating and advancing models to handle the interplay between dynamic graph structures and natural language. The dataset and source code are available at https://github.com/zjs123/DTGB.
Authors: Eldar Kurtic, Amir Moeini, Dan Alistarh
Abstract: We introduce Mathador-LM, a new benchmark for evaluating the mathematical reasoning on large language models (LLMs), combining ruleset interpretation, planning, and problem-solving. This benchmark is inspired by the Mathador game, where the objective is to reach a target number using basic arithmetic operations on a given set of base numbers, following a simple set of rules. We show that, across leading LLMs, we obtain stable average performance while generating benchmark instances dynamically, following a target difficulty level. Thus, our benchmark alleviates concerns about test-set leakage into training data, an issue that often undermines popular benchmarks. Additionally, we conduct a comprehensive evaluation of both open and closed-source state-of-the-art LLMs on Mathador-LM. Our findings reveal that contemporary models struggle with Mathador-LM, scoring significantly lower than average 3rd graders. This stands in stark contrast to their strong performance on popular mathematical reasoning benchmarks.
Authors: Scott Pesme, Radu-Alexandru Dragomir, Nicolas Flammarion
Abstract: We examine the continuous-time counterpart of mirror descent, namely mirror flow, on classification problems which are linearly separable. Such problems are minimised `at infinity' and have many possible solutions; we study which solution is preferred by the algorithm depending on the mirror potential. For exponential tailed losses and under mild assumptions on the potential, we show that the iterates converge in direction towards a $\phi_\infty$-maximum margin classifier. The function $\phi_\infty$ is the $\textit{horizon function}$ of the mirror potential and characterises its shape `at infinity'. When the potential is separable, a simple formula allows to compute this function. We analyse several examples of potentials and provide numerical experiments highlighting our results.
Authors: Siemen Brussee, Giorgio Buzzanca, Anne M. R. Schrader, Jesper Kers
Abstract: Histopathological analysis of Whole Slide Images (WSIs) has seen a surge in the utilization of deep learning methods, particularly Convolutional Neural Networks (CNNs). However, CNNs often fall short in capturing the intricate spatial dependencies inherent in WSIs. Graph Neural Networks (GNNs) present a promising alternative, adept at directly modeling pairwise interactions and effectively discerning the topological tissue and cellular structures within WSIs. Recognizing the pressing need for deep learning techniques that harness the topological structure of WSIs, the application of GNNs in histopathology has experienced rapid growth. In this comprehensive review, we survey GNNs in histopathology, discuss their applications, and explore emerging trends that pave the way for future advancements in the field. We begin by elucidating the fundamentals of GNNs and their potential applications in histopathology. Leveraging quantitative literature analysis, we identify four emerging trends: Hierarchical GNNs, Adaptive Graph Structure Learning, Multimodal GNNs, and Higher-order GNNs. Through an in-depth exploration of these trends, we offer insights into the evolving landscape of GNNs in histopathological analysis. Based on our findings, we propose future directions to propel the field forward. Our analysis serves to guide researchers and practitioners towards innovative approaches and methodologies, fostering advancements in histopathological analysis through the lens of graph neural networks.