Authors: Longwei Zou, Han Zhang, Yangdong Deng
Abstract: The fast growing capabilities of large-scale deep learning models, such as Bert, GPT and ViT, are revolutionizing the landscape of NLP, CV and many other domains. Training such models, however, poses an unprecedented demand for computing power, which incurs exponentially increasing energy cost and carbon dioxide emissions. It is thus critical to develop efficient training solutions to reduce the training costs. Motivated by a set of key observations of inter- and intra-layer similarities among feature maps and attentions that can be identified from typical training processes, we propose a multi-level framework for training acceleration. Specifically, the framework is based on three basic operators, Coalescing, De-coalescing and Interpolation, which can be orchestrated to build a multi-level training framework. The framework consists of a V-cycle training process, which progressively down- and up-scales the model size and projects the parameters between adjacent levels of models via coalescing and de-coalescing. The key idea is that a smaller model that can be trained for fast convergence and the trained parameters provides high-qualities intermediate solutions for the next level larger network. The interpolation operator is designed to break the symmetry of neurons incurred by de-coalescing for better convergence performance. Our experiments on transformer-based language models (e.g. Bert, GPT) as well as a vision model (e.g. DeiT) prove that the proposed framework reduces the computational cost by about 20% on training BERT/GPT-Base models and up to 51.6% on training the BERT-Large model while preserving the performance.
Authors: Michal Pinos, Lukas Sekanina, Vojtech Mrazek
Abstract: Integrating the principles of approximate computing into the design of hardware-aware deep neural networks (DNN) has led to DNNs implementations showing good output quality and highly optimized hardware parameters such as low latency or inference energy. In this work, we present ApproxDARTS, a neural architecture search (NAS) method enabling the popular differentiable neural architecture search method called DARTS to exploit approximate multipliers and thus reduce the power consumption of generated neural networks. We showed on the CIFAR-10 data set that the ApproxDARTS is able to perform a complete architecture search within less than $10$ GPU hours and produce competitive convolutional neural networks (CNN) containing approximate multipliers in convolutional layers. For example, ApproxDARTS created a CNN showing an energy consumption reduction of (a) $53.84\%$ in the arithmetic operations of the inference phase compared to the CNN utilizing the native $32$-bit floating-point multipliers and (b) $5.97\%$ compared to the CNN utilizing the exact $8$-bit fixed-point multipliers, in both cases with a negligible accuracy drop. Moreover, the ApproxDARTS is $2.3\times$ faster than a similar but evolutionary algorithm-based method called EvoApproxNAS.
Authors: Guangchen Lan, Dong-Jun Han, Abolfazl Hashemi, Vaneet Aggarwal, Christopher G. Brinton
Abstract: To improve the efficiency of reinforcement learning, we propose a novel asynchronous federated reinforcement learning framework termed AFedPG, which constructs a global model through collaboration among $N$ agents using policy gradient (PG) updates. To handle the challenge of lagged policies in asynchronous settings, we design delay-adaptive lookahead and normalized update techniques that can effectively handle the heterogeneous arrival times of policy gradients. We analyze the theoretical global convergence bound of AFedPG, and characterize the advantage of the proposed algorithm in terms of both the sample complexity and time complexity. Specifically, our AFedPG method achieves $\mathcal{O}(\frac{{\epsilon}^{-2.5}}{N})$ sample complexity at each agent on average. Compared to the single agent setting with $\mathcal{O}(\epsilon^{-2.5})$ sample complexity, it enjoys a linear speedup with respect to the number of agents. Moreover, compared to synchronous FedPG, AFedPG improves the time complexity from $\mathcal{O}(\frac{t_{\max}}{N})$ to $\mathcal{O}(\frac{1}{\sum_{i=1}^{N} \frac{1}{t_{i}}})$, where $t_{i}$ denotes the time consumption in each iteration at the agent $i$, and $t_{\max}$ is the largest one. The latter complexity $\mathcal{O}(\frac{1}{\sum_{i=1}^{N} \frac{1}{t_{i}}})$ is always smaller than the former one, and this improvement becomes significant in large-scale federated settings with heterogeneous computing powers ($t_{\max}\gg t_{\min}$). Finally, we empirically verify the improved performances of AFedPG in three MuJoCo environments with varying numbers of agents. We also demonstrate the improvements with different computing heterogeneity.
Authors: Yuhao Luo, Kehua Chen, Meixin Zhu
Abstract: As a vital component in autonomous driving, accurate trajectory prediction effectively prevents traffic accidents and improves driving efficiency. To capture complex spatial-temporal dynamics and social interactions, recent studies developed models based on advanced deep-learning methods. On the other hand, recent studies have explored the use of deep generative models to further account for trajectory uncertainties. However, the current approaches demonstrating indeterminacy involve inefficient and time-consuming practices such as sampling from trained models. To fill this gap, we proposed a novel model named Graph Recurrent Attentive Neural Process (GRANP) for vehicle trajectory prediction while efficiently quantifying prediction uncertainty. In particular, GRANP contains an encoder with deterministic and latent paths, and a decoder for prediction. The encoder, including stacked Graph Attention Networks, LSTM and 1D convolutional layers, is employed to extract spatial-temporal relationships. The decoder is used to learn a latent distribution and thus quantify prediction uncertainty. To reveal the effectiveness of our model, we evaluate the performance of GRANP on the highD dataset. Extensive experiments show that GRANP achieves state-of-the-art results and can efficiently quantify uncertainties. Additionally, we undertake an intuitive case study that showcases the interpretability of the proposed approach. The code is available at https://github.com/joy-driven/GRANP.
Authors: Afzal Ahmad, Linfeng Du, Zhiyao Xie, Wei Zhang
Abstract: One of the primary challenges impeding the progress of Neural Architecture Search (NAS) is its extensive reliance on exorbitant computational resources. NAS benchmarks aim to simulate runs of NAS experiments at zero cost, remediating the need for extensive compute. However, existing NAS benchmarks use synthetic datasets and model proxies that make simplified assumptions about the characteristics of these datasets and models, leading to unrealistic evaluations. We present a technique that allows searching for training proxies that reduce the cost of benchmark construction by significant margins, making it possible to construct realistic NAS benchmarks for large-scale datasets. Using this technique, we construct an open-source bi-objective NAS benchmark for the ImageNet2012 dataset combined with the on-device performance of accelerators, including GPUs, TPUs, and FPGAs. Through extensive experimentation with various NAS optimizers and hardware platforms, we show that the benchmark is accurate and allows searching for state-of-the-art hardware-aware models at zero cost.
Authors: Bingqing Liu
Abstract: Electronic Health Records (EHR) can be represented as temporal sequences that record the events (medical visits) from patients. Neural temporal point process (NTPP) has achieved great success in modeling event sequences that occur in continuous time space. However, due to the black-box nature of neural networks, existing NTPP models fall short in explaining the dependencies between different event types. In this paper, inspired by word2vec and Hawkes process, we propose an interpretable framework inf2vec for event sequence modelling, where the event influences are directly parameterized and can be learned end-to-end. In the experiment, we demonstrate the superiority of our model on event prediction as well as type-type influences learning.
Authors: Kehua Feng, Keyan Ding, Kede Ma, Zhihua Wang, Qiang Zhang, Huajun Chen
Abstract: The past years have witnessed a proliferation of large language models (LLMs). Yet, automated and unbiased evaluation of LLMs is challenging due to the inaccuracy of standard metrics in reflecting human preferences and the inefficiency in sampling informative and diverse test examples. While human evaluation remains the gold standard, it is expensive and time-consuming, especially when dealing with a large number of testing samples. To address this problem, we propose a sample-efficient human evaluation method based on MAximum Discrepancy (MAD) competition. MAD automatically selects a small set of informative and diverse instructions, each adapted to two LLMs, whose responses are subject to three-alternative forced choice by human subjects. The pairwise comparison results are then aggregated into a global ranking using the Elo rating system. We select eight representative LLMs and compare them in terms of four skills: knowledge understanding, mathematical reasoning, writing, and coding. Experimental results show that the proposed method achieves a reliable and sensible ranking of LLMs' capabilities, identifies their relative strengths and weaknesses, and offers valuable insights for further LLM advancement.
Authors: Lianqiang Li, Chenqian Yan, Yefei Chen
Abstract: To accelerate and compress deep neural networks (DNNs), many network quantization algorithms have been proposed. Although the quantization strategy of any algorithm from the state-of-the-arts may outperform others in some network architectures, it is hard to prove the strategy is always better than others, and even cannot judge that the strategy is always the best choice for all layers in a network. In other words, existing quantization algorithms are suboptimal as they ignore the different characteristics of different layers and quantize all layers by a uniform quantization strategy. To solve the issue, in this paper, we propose a differentiable quantization strategy search (DQSS) to assign optimal quantization strategy for individual layer by taking advantages of the benefits of different quantization algorithms. Specifically, we formulate DQSS as a differentiable neural architecture search problem and adopt an efficient convolution to efficiently explore the mixed quantization strategies from a global perspective by gradient-based optimization. We conduct DQSS for post-training quantization to enable their performance to be comparable with that in full precision models. We also employ DQSS in quantization-aware training for further validating the effectiveness of DQSS. To circumvent the expensive optimization cost when employing DQSS in quantization-aware training, we update the hyper-parameters and the network parameters in a single forward-backward pass. Besides, we adjust the optimization process to avoid the potential under-fitting problem. Comprehensive experiments on high level computer vision task, i.e., image classification, and low level computer vision task, i.e., image super-resolution, with various network architectures show that DQSS could outperform the state-of-the-arts.
Authors: Dongdong Ren, Wenbin Li, Tianyu Ding, Lei Wang, Qi Fan, Jing Huo, Hongbing Pan, Yang Gao
Abstract: Recent advancements in model pruning have focused on developing new algorithms and improving upon benchmarks. However, the practical application of these algorithms across various models and platforms remains a significant challenge. To address this challenge, we propose ONNXPruner, a versatile pruning adapter designed for the ONNX format models. ONNXPruner streamlines the adaptation process across diverse deep learning frameworks and hardware platforms. A novel aspect of ONNXPruner is its use of node association trees, which automatically adapt to various model architectures. These trees clarify the structural relationships between nodes, guiding the pruning process, particularly highlighting the impact on interconnected nodes. Furthermore, we introduce a tree-level evaluation method. By leveraging node association trees, this method allows for a comprehensive analysis beyond traditional single-node evaluations, enhancing pruning performance without the need for extra operations. Experiments across multiple models and datasets confirm ONNXPruner's strong adaptability and increased efficacy. Our work aims to advance the practical application of model pruning.
Authors: Ming Cheng, Bowen Zhang, Ziyu Wang, Ziyi Zhou, Weiqi Feng, Yi Lyu, Xingjian Diao
Abstract: Trajectory similarity search plays an essential role in autonomous driving, as it enables vehicles to analyze the information and characteristics of different trajectories to make informed decisions and navigate safely in dynamic environments. Existing work on the trajectory similarity search task primarily utilizes sequence-processing algorithms or Recurrent Neural Networks (RNNs), which suffer from the inevitable issues of complicated architecture and heavy training costs. Considering the intricate connections between trajectories, using Graph Neural Networks (GNNs) for data modeling is feasible. However, most methods directly use existing mathematical graph structures as the input instead of constructing specific graphs from certain vehicle trajectory data. This ignores such data's unique and dynamic characteristics. To bridge such a research gap, we propose VeTraSS -- an end-to-end pipeline for Vehicle Trajectory Similarity Search. Specifically, VeTraSS models the original trajectory data into multi-scale graphs, and generates comprehensive embeddings through a novel multi-layer attention-based GNN. The learned embeddings can be used for searching similar vehicle trajectories. Extensive experiments on the Porto and Geolife datasets demonstrate the effectiveness of VeTraSS, where our model outperforms existing work and reaches the state-of-the-art. This demonstrates the potential of VeTraSS for trajectory analysis and safe navigation in self-driving vehicles in the real world.
Authors: M. Jaleed Khan, Ioana Duta, Beth Albert, William Cooke, Manu Vatish, Gabriel Davis Jones
Abstract: The rapid advancement of Artificial Intelligence (AI) in healthcare presents a unique opportunity for advancements in obstetric care, particularly through the analysis of cardiotocography (CTG) for fetal monitoring. However, the effectiveness of such technologies depends upon the availability of large, high-quality datasets that are suitable for machine learning. This paper introduces the Oxford Maternity (OxMat) dataset, the world's largest curated dataset of CTGs, featuring raw time series CTG data and extensive clinical data for both mothers and babies, which is ideally placed for machine learning. The OxMat dataset addresses the critical gap in women's health data by providing over 177,211 unique CTG recordings from 51,036 pregnancies, carefully curated and reviewed since 1991. The dataset also comprises over 200 antepartum, intrapartum and postpartum clinical variables, ensuring near-complete data for crucial outcomes such as stillbirth and acidaemia. While this dataset also covers the intrapartum stage, around 94% of the constituent CTGS are antepartum. This allows for a unique focus on the underserved antepartum period, in which early detection of at-risk fetuses can significantly improve health outcomes. Our comprehensive review of existing datasets reveals the limitations of current datasets: primarily, their lack of sufficient volume, detailed clinical data and antepartum data. The OxMat dataset lays a foundation for future AI-driven prenatal care, offering a robust resource for developing and testing algorithms aimed at improving maternal and fetal health outcomes.
Authors: Faisal Ahmed, Myungjin Lee, Suresh Subramaniam, Motoharu Matsuura, Hiroshi Hasegawa, Shih-Chun Lin
Abstract: Federated Learning (FL) has garnered significant interest recently due to its potential as an effective solution for tackling many challenges in diverse application scenarios, for example, data privacy in network edge traffic classification. Despite its recognized advantages, FL encounters obstacles linked to statistical data heterogeneity and labeled data scarcity during the training of single-task models for machine learning-based traffic classification, leading to hindered learning performance. In response to these challenges, adopting a hard-parameter sharing multi-task learning model with auxiliary tasks proves to be a suitable approach. Such a model has the capability to reduce communication and computation costs, navigate statistical complexities inherent in FL contexts, and overcome labeled data scarcity by leveraging knowledge derived from interconnected auxiliary tasks. This paper introduces a new framework for federated auxiliary hard-parameter sharing multi-task learning, namely, FedAuxHMTL. The introduced framework incorporates model parameter exchanges between edge server and base stations, enabling base stations from distributed areas to participate in the FedAuxHMTL process and enhance the learning performance of the main task-network edge traffic classification. Empirical experiments are conducted to validate and demonstrate the FedAuxHMTL's effectiveness in terms of accuracy, total global loss, communication costs, computing time, and energy consumption compared to its counterparts.
Authors: Bardia Nadimi, Hao Zheng
Abstract: Recently, there has been a surging interest in using large language models (LLMs) for Verilog code generation. However, the existing approaches are limited in terms of the quality of the generated Verilog code. To address such limitations, this paper introduces an innovative multi-expert LLM architecture for Verilog code generation (MEV-LLM). Our architecture uniquely integrates multiple LLMs, each specifically fine-tuned with a dataset that is categorized with respect to a distinct level of design complexity. It allows more targeted learning, directly addressing the nuances of generating Verilog code for each category. Empirical evidence from experiments highlights notable improvements in terms of the percentage of generated Verilog outputs that are syntactically and functionally correct. These findings underscore the efficacy of our approach, promising a forward leap in the field of automated hardware design through machine learning.
Authors: Keivan Faghih Niresi, Hugo Bissig, Henri Baumann, Olga Fink
Abstract: The Industrial Internet of Things (IIoT) is reshaping manufacturing, industrial processes, and infrastructure management. By fostering new levels of automation, efficiency, and predictive maintenance, IIoT is transforming traditional industries into intelligent, seamlessly interconnected ecosystems. However, achieving highly reliable IIoT can be hindered by factors such as the cost of installing large numbers of sensors, limitations in retrofitting existing systems with sensors, or harsh environmental conditions that may make sensor installation impractical. Soft (virtual) sensing leverages mathematical models to estimate variables from physical sensor data, offering a solution to these challenges. Data-driven and physics-based modeling are the two main methodologies widely used for soft sensing. The choice between these strategies depends on the complexity of the underlying system, with the data-driven approach often being preferred when the physics-based inference models are intricate and present challenges for state estimation. However, conventional deep learning models are typically hindered by their inability to explicitly represent the complex interactions among various sensors. To address this limitation, we adopt Graph Neural Networks (GNNs), renowned for their ability to effectively capture the complex relationships between sensor measurements. In this research, we propose physics-enhanced GNNs, which integrate principles of physics into graph-based methodologies. This is achieved by augmenting additional nodes in the input graph derived from the underlying characteristics of the physical processes. Our evaluation of the proposed methodology on the case study of district heating networks reveals significant improvements over purely data-driven GNNs, even in the presence of noise and parameter inaccuracies.
Authors: Ali Al-Lawati, Elsayed Eshra, Prasenjit Mitra
Abstract: Trajectory generation is an important task in movement studies; it circumvents the privacy, ethical, and technical challenges of collecting real trajectories from the target population. In particular, real trajectories in the wildlife domain are scarce as a result of ethical and environmental constraints of the collection process. In this paper, we consider the problem of generating long-horizon trajectories, akin to wildlife migration, based on a small set of real samples. We propose a hierarchical approach to learn the global movement characteristics of the real dataset and recursively refine localized regions. Our solution, WildGraph, discretizes the geographic path into a prototype network of H3 (https://www.uber.com/blog/h3/) regions and leverages a recurrent variational auto-encoder to probabilistically generate paths over the regions, based on occupancy. WildGraph successfully generates realistic months-long trajectories using a sample size as small as 60. Experiments performed on two wildlife migration datasets demonstrate that our proposed method improves the generalization of the generated trajectories in comparison to existing work while achieving superior or comparable performance in several benchmark metrics. Our code is published on the following repository: \url{https://github.com/aliwister/wildgraph}.
URLs: https://www.uber.com/blog/h3/), https://github.com/aliwister/wildgraph
Authors: Brian Bell, Michael Geyer, David Glickenstein, Keaton Hamm, Carlos Scheidegger, Amanda Fernandez, Juston Moore
Abstract: There are a number of hypotheses underlying the existence of adversarial examples for classification problems. These include the high-dimensionality of the data, high codimension in the ambient space of the data manifolds of interest, and that the structure of machine learning models may encourage classifiers to develop decision boundaries close to data points. This article proposes a new framework for studying adversarial examples that does not depend directly on the distance to the decision boundary. Similarly to the smoothed classifier literature, we define a (natural or adversarial) data point to be $(\gamma,\sigma)$-stable if the probability of the same classification is at least $\gamma$ for points sampled in a Gaussian neighborhood of the point with a given standard deviation $\sigma$. We focus on studying the differences between persistence metrics along interpolants of natural and adversarial points. We show that adversarial examples have significantly lower persistence than natural examples for large neural networks in the context of the MNIST and ImageNet datasets. We connect this lack of persistence with decision boundary geometry by measuring angles of interpolants with respect to decision boundaries. Finally, we connect this approach with robustness by developing a manifold alignment gradient metric and demonstrating the increase in robustness that can be achieved when training with the addition of this metric.
Authors: Nastaran Saadati, Minh Pham, Nasla Saleem, Joshua R. Waite, Aditya Balu, Zhanhong Jiang, Chinmay Hegde, Soumik Sarkar
Abstract: Recent advances in decentralized deep learning algorithms have demonstrated cutting-edge performance on various tasks with large pre-trained models. However, a pivotal prerequisite for achieving this level of competitiveness is the significant communication and computation overheads when updating these models, which prohibits the applications of them to real-world scenarios. To address this issue, drawing inspiration from advanced model merging techniques without requiring additional training, we introduce the Decentralized Iterative Merging-And-Training (DIMAT) paradigm--a novel decentralized deep learning framework. Within DIMAT, each agent is trained on their local data and periodically merged with their neighboring agents using advanced model merging techniques like activation matching until convergence is achieved. DIMAT provably converges with the best available rate for nonconvex functions with various first-order methods, while yielding tighter error bounds compared to the popular existing approaches. We conduct a comprehensive empirical analysis to validate DIMAT's superiority over baselines across diverse computer vision tasks sourced from multiple datasets. Empirical results validate our theoretical claims by showing that DIMAT attains faster and higher initial gain in accuracy with independent and identically distributed (IID) and non-IID data, incurring lower communication overhead. This DIMAT paradigm presents a new opportunity for the future decentralized learning, enhancing its adaptability to real-world with sparse and light-weight communication and computation.
Authors: Tanmay Gautam, Youngsuk Park, Hao Zhou, Parameswaran Raman, Wooseok Ha
Abstract: Fine-tuning language models (LMs) has demonstrated success in a wide array of downstream tasks. However, as LMs are scaled up, the memory requirements for backpropagation become prohibitively high. Zeroth-order (ZO) optimization methods can leverage memory-efficient forward passes to estimate gradients. More recently, MeZO, an adaptation of ZO-SGD, has been shown to consistently outperform zero-shot and in-context learning when combined with suitable task prompts. In this work, we couple ZO methods with variance reduction techniques to enhance stability and convergence for inference-based LM fine-tuning. We introduce Memory-Efficient Zeroth-Order Stochastic Variance-Reduced Gradient (MeZO-SVRG) and demonstrate its efficacy across multiple LM fine-tuning tasks, eliminating the reliance on task-specific prompts. Evaluated across a range of both masked and autoregressive LMs on benchmark GLUE tasks, MeZO-SVRG outperforms MeZO with up to 20% increase in test accuracies in both full- and partial-parameter fine-tuning settings. MeZO-SVRG benefits from reduced computation time as it often surpasses MeZO's peak test accuracy with a $2\times$ reduction in GPU-hours. MeZO-SVRG significantly reduces the required memory footprint compared to first-order SGD, i.e. by $2\times$ for autoregressive models. Our experiments highlight that MeZO-SVRG's memory savings progressively improve compared to SGD with larger batch sizes.
Authors: Yang Hu, Haitong Ma, Bo Dai, Na Li
Abstract: The pursuit of robustness has recently been a popular topic in reinforcement learning (RL) research, yet the existing methods generally suffer from efficiency issues that obstruct their real-world implementation. In this paper, we introduce duple perturbation robustness, i.e. perturbation on both the feature and factor vectors for low-rank Markov decision processes (MDPs), via a novel characterization of $(\xi,\eta)$-ambiguity sets. The novel robust MDP formulation is compatible with the function representation view, and therefore, is naturally applicable to practical RL problems with large or even continuous state-action spaces. Meanwhile, it also gives rise to a provably efficient and practical algorithm with theoretical convergence rate guarantee. Examples are designed to justify the new robustness concept, and algorithmic efficiency is supported by both theoretical bounds and numerical simulations.
Authors: Indu Kant Deo, Akash Venkateshwaran, Rajeev K. Jaiman
Abstract: There is a significant need for precise and reliable forecasting of the far-field noise emanating from shipping vessels. Conventional full-order models based on the Navier-Stokes equations are unsuitable, and sophisticated model reduction methods may be ineffective for accurately predicting far-field noise in environments with seamounts and significant variations in bathymetry. Recent advances in reduced-order models, particularly those based on convolutional and recurrent neural networks, offer a faster and more accurate alternative. These models use convolutional neural networks to reduce data dimensions effectively. However, current deep-learning models face challenges in predicting wave propagation over long periods and for remote locations, often relying on auto-regressive prediction and lacking far-field bathymetry information. This research aims to improve the accuracy of deep-learning models for predicting underwater radiated noise in far-field scenarios. We propose a novel range-conditional convolutional neural network that incorporates ocean bathymetry data into the input. By integrating this architecture into a continual learning framework, we aim to generalize the model for varying bathymetry worldwide. To demonstrate the effectiveness of our approach, we analyze our model on several test cases and a benchmark scenario involving far-field prediction over Dickin's seamount in the Northeast Pacific. Our proposed architecture effectively captures transmission loss over a range-dependent, varying bathymetry profile. This architecture can be integrated into an adaptive management system for underwater radiated noise, providing real-time end-to-end mapping between near-field ship noise sources and received noise at the marine mammal's location.
Authors: Krzysztof Kotowski, Irena Roterman, Katarzyna Stapor
Abstract: The prediction of intrinsic disorder regions has significant implications for understanding protein function, structure, and dynamics. It can help to discover novel functions or protein-protein interactions essential to designing new drugs, therapies, or enzymes. Recently, a new generation of predictors based on protein language models is emerging. These algorithms reach state-of-the-art accuracy without calculating time-consuming multiple sequence alignments (MSAs). The article pre-sents a new protein intrinsic disorder predictor DisorderUnetLM based on the Attention U-Net convolutional neural network using features from the protein language model ProtTrans. DisorderUnetLM shows top results in the direct comparison with flDPnn and IDP-CRF predictors using MSAs and with the SETH predictor using features from the same ProtTrans model. Moreover, among 41 predictors from the latest Critical Assessment of Protein Intrinsic Disorder Prediction (CAID-2) benchmark, it ranks 9th for the Disorder-PDB subset (with ROC-AUC of 0.924) and 1st for the Disorder-NOX subset (with ROC-AUC of 0.844) which confirms its potential to perform well in the upcoming CAID-3 challenge for which Disor-derUnetLM was submitted.
Authors: Wojciech Czaja, Sanghoon Na
Abstract: We present a post-training quantization algorithm with error estimates relying on ideas originating from frame theory. Specifically, we use first-order Sigma-Delta ($\Sigma\Delta$) quantization for finite unit-norm tight frames to quantize weight matrices and biases in a neural network. In our scenario, we derive an error bound between the original neural network and the quantized neural network in terms of step size and the number of frame elements. We also demonstrate how to leverage the redundancy of frames to achieve a quantized neural network with higher accuracy.
Authors: Runqi Lin, Chaojian Yu, Tongliang Liu
Abstract: Single-step adversarial training (SSAT) has demonstrated the potential to achieve both efficiency and robustness. However, SSAT suffers from catastrophic overfitting (CO), a phenomenon that leads to a severely distorted classifier, making it vulnerable to multi-step adversarial attacks. In this work, we observe that some adversarial examples generated on the SSAT-trained network exhibit anomalous behaviour, that is, although these training samples are generated by the inner maximization process, their associated loss decreases instead, which we named abnormal adversarial examples (AAEs). Upon further analysis, we discover a close relationship between AAEs and classifier distortion, as both the number and outputs of AAEs undergo a significant variation with the onset of CO. Given this observation, we re-examine the SSAT process and uncover that before the occurrence of CO, the classifier already displayed a slight distortion, indicated by the presence of few AAEs. Furthermore, the classifier directly optimizing these AAEs will accelerate its distortion, and correspondingly, the variation of AAEs will sharply increase as a result. In such a vicious circle, the classifier rapidly becomes highly distorted and manifests as CO within a few iterations. These observations motivate us to eliminate CO by hindering the generation of AAEs. Specifically, we design a novel method, termed Abnormal Adversarial Examples Regularization (AAER), which explicitly regularizes the variation of AAEs to hinder the classifier from becoming distorted. Extensive experiments demonstrate that our method can effectively eliminate CO and further boost adversarial robustness with negligible additional computational overhead.
Authors: Etash Guha, Shlok Natarajan, Thomas M\"ollenhoff, Mohammad Emtiyaz Khan, Eugene Ndiaye
Abstract: Conformal prediction (CP) for regression can be challenging, especially when the output distribution is heteroscedastic, multimodal, or skewed. Some of the issues can be addressed by estimating a distribution over the output, but in reality, such approaches can be sensitive to estimation error and yield unstable intervals.~Here, we circumvent the challenges by converting regression to a classification problem and then use CP for classification to obtain CP sets for regression.~To preserve the ordering of the continuous-output space, we design a new loss function and make necessary modifications to the CP classification techniques.~Empirical results on many benchmarks shows that this simple approach gives surprisingly good results on many practical problems.
Authors: Patrice B\'echard, Orlando Marquez Ayala
Abstract: A common and fundamental limitation of Generative AI (GenAI) is its propensity to hallucinate. While large language models (LLM) have taken the world by storm, without eliminating or at least reducing hallucinations, real-world GenAI systems may face challenges in user adoption. In the process of deploying an enterprise application that produces workflows based on natural language requirements, we devised a system leveraging Retrieval Augmented Generation (RAG) to greatly improve the quality of the structured output that represents such workflows. Thanks to our implementation of RAG, our proposed system significantly reduces hallucinations in the output and improves the generalization of our LLM in out-of-domain settings. In addition, we show that using a small, well-trained retriever encoder can reduce the size of the accompanying LLM, thereby making deployments of LLM-based systems less resource-intensive.
Authors: Jocelyn Dzuong, Zichong Wang, Wenbin Zhang
Abstract: In the rapidly evolving landscape of generative artificial intelligence (AI), the increasingly pertinent issue of copyright infringement arises as AI advances to generate content from scraped copyrighted data, prompting questions about ownership and protection that impact professionals across various careers. With this in mind, this survey provides an extensive examination of copyright infringement as it pertains to generative AI, aiming to stay abreast of the latest developments and open problems. Specifically, it will first outline methods of detecting copyright infringement in mediums such as text, image, and video. Next, it will delve an exploration of existing techniques aimed at safeguarding copyrighted works from generative models. Furthermore, this survey will discuss resources and tools for users to evaluate copyright violations. Finally, insights into ongoing regulations and proposals for AI will be explored and compared. Through combining these disciplines, the implications of AI-driven content and copyright are thoroughly illustrated and brought into question.
Authors: Haili Sun, Yan Huang, Lansheng Han, Cai Fu, Chunjie Zhou
Abstract: Multivariate Time Series (MTS) anomaly detection focuses on pinpointing samples that diverge from standard operational patterns, which is crucial for ensuring the safety and security of industrial applications. The primary challenge in this domain is to develop representations capable of discerning anomalies effectively. The prevalent methods for anomaly detection in the literature are predominantly reconstruction-based and predictive in nature. However, they typically concentrate on a single-dimensional instance level, thereby not fully harnessing the complex associations inherent in industrial MTS. To address this issue, we propose a novel self-supervised hierarchical contrastive consistency learning method for detecting anomalies in MTS, named HCL-MTSAD. It innovatively leverages data consistency at multiple levels inherent in industrial MTS, systematically capturing consistent associations across four latent levels-measurement, sample, channel, and process. By developing a multi-layer contrastive loss, HCL-MTSAD can extensively mine data consistency and spatio-temporal association, resulting in more informative representations. Subsequently, an anomaly discrimination module, grounded in self-supervised hierarchical contrastive learning, is designed to detect timestamp-level anomalies by calculating multi-scale data consistency. Extensive experiments conducted on six diverse MTS datasets retrieved from real cyber-physical systems and server machines, in comparison with 20 baselines, indicate that HCL-MTSAD's anomaly detection capability outperforms the state-of-the-art benchmark models by an average of 1.8\% in terms of F1 score.
Authors: Khadija Zanna, Akane Sano
Abstract: This paper considers the need for generalizable bias mitigation techniques in machine learning due to the growing concerns of fairness and discrimination in data-driven decision-making procedures across a range of industries. While many existing methods for mitigating bias in machine learning have succeeded in specific cases, they often lack generalizability and cannot be easily applied to different data types or models. Additionally, the trade-off between accuracy and fairness remains a fundamental tension in the field. To address these issues, we propose a bias mitigation method based on multi-task learning, utilizing the concept of Monte-Carlo dropout and Pareto optimality from multi-objective optimization. This method optimizes accuracy and fairness while improving the model's explainability without using sensitive information. We test this method on three datasets from different domains and show how it can deliver the most desired trade-off between model fairness and performance. This allows for tuning in specific domains where one metric may be more important than another. With the framework we introduce in this paper, we aim to enhance the fairness-performance trade-off and offer a solution to bias mitigation methods' generalizability issues in machine learning.
Authors: Hui Bai, Ran Cheng
Abstract: Hyperparameter optimization plays a key role in the machine learning domain. Its significance is especially pronounced in reinforcement learning (RL), where agents continuously interact with and adapt to their environments, requiring dynamic adjustments in their learning trajectories. To cater to this dynamicity, the Population-Based Training (PBT) was introduced, leveraging the collective intelligence of a population of agents learning simultaneously. However, PBT tends to favor high-performing agents, potentially neglecting the explorative potential of agents on the brink of significant advancements. To mitigate the limitations of PBT, we present the Generalized Population-Based Training (GPBT), a refined framework designed for enhanced granularity and flexibility in hyperparameter adaptation. Complementing GPBT, we further introduce Pairwise Learning (PL). Instead of merely focusing on elite agents, PL employs a comprehensive pairwise strategy to identify performance differentials and provide holistic guidance to underperforming agents. By integrating the capabilities of GPBT and PL, our approach significantly improves upon traditional PBT in terms of adaptability and computational efficiency. Rigorous empirical evaluations across a range of RL benchmarks confirm that our approach consistently outperforms not only the conventional PBT but also its Bayesian-optimized variant.
Authors: Zeyu Yang, Peikun Guo, Khadija Zanna, Akane Sano
Abstract: Diffusion models have emerged as a robust framework for various generative tasks, such as image and audio synthesis, and have also demonstrated a remarkable ability to generate mixed-type tabular data comprising both continuous and discrete variables. However, current approaches to training diffusion models on mixed-type tabular data tend to inherit the imbalanced distributions of features present in the training dataset, which can result in biased sampling. In this research, we introduce a fair diffusion model designed to generate balanced data on sensitive attributes. We present empirical evidence demonstrating that our method effectively mitigates the class imbalance in training data while maintaining the quality of the generated samples. Furthermore, we provide evidence that our approach outperforms existing methods for synthesizing tabular data in terms of performance and fairness.
Authors: Lars Ullrich, Alex McMaster, Knut Graichen
Abstract: Trajectory planning in autonomous driving is highly dependent on predicting the emergent behavior of other road users. Learning-based methods are currently showing impressive results in simulation-based challenges, with transformer-based architectures technologically leading the way. Ultimately, however, predictions are needed in the real world. In addition to the shifts from simulation to the real world, many vehicle- and country-specific shifts, i.e. differences in sensor systems, fusion and perception algorithms as well as traffic rules and laws, are on the agenda. Since models that can cover all system setups and design domains at once are not yet foreseeable, model adaptation plays a central role. Therefore, a simulation-based study on transfer learning techniques is conducted on basis of a transformer-based model. Furthermore, the study aims to provide insights into possible trade-offs between computational time and performance to support effective transfers into the real world.
Authors: Andrea Ponti
Abstract: Graphs are ubiquitous in various fields, and deep learning methods have been successful applied in graph classification tasks. However, building large and diverse graph datasets for training can be expensive. While augmentation techniques exist for structured data like images or numerical data, the augmentation of graph data remains challenging. This is primarily due to the complex and non-Euclidean nature of graph data. In this paper, it has been proposed a novel augmentation strategy for graphs that operates in a non-Euclidean space. This approach leverages graphon estimation, which models the generative mechanism of networks sequences. Computational results demonstrate the effectiveness of the proposed augmentation framework in improving the performance of graph classification models. Additionally, using a non-Euclidean distance, specifically the Gromow-Wasserstein distance, results in better approximations of the graphon. This framework also provides a means to validate different graphon estimation approaches, particularly in real-world scenarios where the true graphon is unknown.
Authors: Rongguang Ye, Lei Chen, Weiduo Liao, Jinyuan Zhang, Hisao Ishibuchi
Abstract: Pareto front learning is a technique that introduces preference vectors in a neural network to approximate the Pareto front. Previous Pareto front learning methods have demonstrated high performance in approximating simple Pareto fronts. These methods often sample preference vectors from a fixed Dirichlet distribution. However, no fixed sampling distribution can be adapted to diverse Pareto fronts. Efficiently sampling preference vectors and accurately estimating the Pareto front is a challenge. To address this challenge, we propose a data-driven preference vector sampling framework for Pareto front learning. We utilize the posterior information of the objective functions to adjust the parameters of the sampling distribution flexibly. In this manner, the proposed method can sample preference vectors from the location of the Pareto front with a high probability. Moreover, we design the distribution of the preference vector as a mixture of Dirichlet distributions to improve the performance of the model in disconnected Pareto fronts. Extensive experiments validate the superiority of the proposed method compared with state-of-the-art algorithms.
Authors: Hongtao Wang, Li Long, Jiangshe Zhang, Xiaoli Wei, Chunxia Zhang, Zhenbo Guo
Abstract: Contemporary automatic first break (FB) picking methods typically analyze 1D signals, 2D source gathers, or 3D source-receiver gathers. Utilizing higher-dimensional data, such as 2D or 3D, incorporates global features, improving the stability of local picking. Despite the benefits, high-dimensional data requires structured input and increases computational demands. Addressing this, we propose a novel approach using deep graph learning called DGL-FB, constructing a large graph to efficiently extract information. In this graph, each seismic trace is represented as a node, connected by edges that reflect similarities. To manage the size of the graph, we develop a subgraph sampling technique to streamline model training and inference. Our proposed framework, DGL-FB, leverages deep graph learning for FB picking. It encodes subgraphs into global features using a deep graph encoder. Subsequently, the encoded global features are combined with local node signals and fed into a ResUNet-based 1D segmentation network for FB detection. Field survey evaluations of DGL-FB show superior accuracy and stability compared to a 2D U-Net-based benchmark method.
Authors: William Fleshman, Aleem Khan, Marc Marone, Benjamin Van Durme
Abstract: Large language models (LLMs) are increasingly capable of completing knowledge intensive tasks by recalling information from a static pretraining corpus. Here we are concerned with LLMs in the context of evolving data requirements. For instance: batches of new data that are introduced periodically; subsets of data with user-based access controls; or requirements on dynamic removal of documents with guarantees that associated knowledge cannot be recalled. We wish to satisfy these requirements while at the same time ensuring a model does not forget old information when new data becomes available. To address these issues, we introduce AdapterSwap, a training and inference scheme that organizes knowledge from a data collection into a set of low-rank adapters, which are dynamically composed during inference. Our experiments demonstrate AdapterSwap's ability to support efficient continual learning, while also enabling organizations to have fine-grained control over data access and deletion.
Authors: Maeghal Jain, Ziya Uddin, Wubshet Ibrahim
Abstract: The outbreak of COVID-19 has highlighted the intricate interplay between public health and economic stability on a global scale. This study proposes a novel reinforcement learning framework designed to optimize health and economic outcomes during pandemics. The framework leverages the SIR model, integrating both lockdown measures (via a stringency index) and vaccination strategies to simulate disease dynamics. The stringency index, indicative of the severity of lockdown measures, influences both the spread of the disease and the economic health of a country. Developing nations, which bear a disproportionate economic burden under stringent lockdowns, are the primary focus of our study. By implementing reinforcement learning, we aim to optimize governmental responses and strike a balance between the competing costs associated with public health and economic stability. This approach also enhances transparency in governmental decision-making by establishing a well-defined reward function for the reinforcement learning agent. In essence, this study introduces an innovative and ethical strategy to navigate the challenge of balancing public health and economic stability amidst infectious disease outbreaks.
Authors: Patricia A. Apell\'aniz, Juan Parras, Santiago Zazo
Abstract: The rising use of machine learning in various fields requires robust methods to create synthetic tabular data. Data should preserve key characteristics while addressing data scarcity challenges. Current approaches based on Generative Adversarial Networks, such as the state-of-the-art CTGAN model, struggle with the complex structures inherent in tabular data. These data often contain both continuous and discrete features with non-Gaussian distributions. Therefore, we propose a novel Variational Autoencoder (VAE)-based model that addresses these limitations. Inspired by the TVAE model, our approach incorporates a Bayesian Gaussian Mixture model (BGM) within the VAE architecture. This avoids the limitations imposed by assuming a strictly Gaussian latent space, allowing for a more accurate representation of the underlying data distribution during data generation. Furthermore, our model offers enhanced flexibility by allowing the use of various differentiable distributions for individual features, making it possible to handle both continuous and discrete data types. We thoroughly validate our model on three real-world datasets with mixed data types, including two medically relevant ones, based on their resemblance and utility. This evaluation demonstrates significant outperformance against CTGAN and TVAE, establishing its potential as a valuable tool for generating synthetic tabular data in various domains, particularly in healthcare.
Authors: Cui Zhang, Xiao Xu, Qiong Wu, Pingyi Fan, Qiang Fan, Huiling Zhu, Jiangzhou Wang
Abstract: In vehicle edge computing (VEC), asynchronous federated learning (AFL) is used, where the edge receives a local model and updates the global model, effectively reducing the global aggregation latency.Due to different amounts of local data,computing capabilities and locations of the vehicles, renewing the global model with same weight is inappropriate.The above factors will affect the local calculation time and upload time of the local model, and the vehicle may also be affected by Byzantine attacks, leading to the deterioration of the vehicle data. However, based on deep reinforcement learning (DRL), we can consider these factors comprehensively to eliminate vehicles with poor performance as much as possible and exclude vehicles that have suffered Byzantine attacks before AFL. At the same time, when aggregating AFL, we can focus on those vehicles with better performance to improve the accuracy and safety of the system. In this paper, we proposed a vehicle selection scheme based on DRL in VEC. In this scheme, vehicle s mobility, channel conditions with temporal variations, computational resources with temporal variations, different data amount, transmission channel status of vehicles as well as Byzantine attacks were taken into account.Simulation results show that the proposed scheme effectively improves the safety and accuracy of the global model.
Authors: Xiaowen Jiang, Anton Rodomanov, Sebastian U. Stich
Abstract: Federated learning is a distributed optimization paradigm that allows training machine learning models across decentralized devices while keeping the data localized. The standard method, FedAvg, suffers from client drift which can hamper performance and increase communication costs over centralized methods. Previous works proposed various strategies to mitigate drift, yet none have shown uniformly improved communication-computation trade-offs over vanilla gradient descent. In this work, we revisit DANE, an established method in distributed optimization. We show that (i) DANE can achieve the desired communication reduction under Hessian similarity constraints. Furthermore, (ii) we present an extension, DANE+, which supports arbitrary inexact local solvers and has more freedom to choose how to aggregate the local updates. We propose (iii) a novel method, FedRed, which has improved local computational complexity and retains the same communication complexity compared to DANE/DANE+. This is achieved by using doubly regularized drift correction.
Authors: Mulugeta Weldezgina Asres, Christian Walter Omlin, Jay Dittmann, Pavel Parygin, Joshua Hiltbrand, Seth I. Cooper, Grace Cummings, David Yu
Abstract: Identifying outlier behavior among sensors and subsystems is essential for discovering faults and facilitating diagnostics in large systems. At the same time, exploring large systems with numerous multivariate data sets is challenging. This study presents a lightweight interconnection and divergence discovery mechanism (LIDD) to identify abnormal behavior in multi-system environments. The approach employs a multivariate analysis technique that first estimates the similarity heatmaps among the sensors for each system and then applies information retrieval algorithms to provide relevant multi-level interconnection and discrepancy details. Our experiment on the readout systems of the Hadron Calorimeter of the Compact Muon Solenoid (CMS) experiment at CERN demonstrates the effectiveness of the proposed method. Our approach clusters readout systems and their sensors consistent with the expected calorimeter interconnection configurations, while capturing unusual behavior in divergent clusters and estimating their root causes.
Authors: Changho Shin, Jitian Zhao, Sonia Cromp, Harit Vishwakarma, Frederic Sala
Abstract: Popular zero-shot models suffer due to artifacts inherited from pretraining. A particularly detrimental artifact, caused by unbalanced web-scale pretraining data, is mismatched label distribution. Existing approaches that seek to repair the label distribution are not suitable in zero-shot settings, as they have incompatible requirements such as access to labeled downstream task data or knowledge of the true label balance in the pretraining distribution. We sidestep these challenges and introduce a simple and lightweight approach to adjust pretrained model predictions via optimal transport. Our technique requires only an estimate of the label distribution of a downstream task. Theoretically, we characterize the improvement produced by our procedure under certain mild conditions and provide bounds on the error caused by misspecification. Empirically, we validate our method in a wide array of zero-shot image and text classification tasks, improving accuracy by 4.8% and 15.9% on average, and beating baselines like Prior Matching -- often by significant margins -- in 17 out of 21 datasets.
Authors: Emadeldeen Eldele, Mohamed Ragab, Zhenghua Chen, Min Wu, Xiaoli Li
Abstract: Time series data, characterized by its intrinsic long and short-range dependencies, poses a unique challenge across analytical applications. While Transformer-based models excel at capturing long-range dependencies, they face limitations in noise sensitivity, computational efficiency, and overfitting with smaller datasets. In response, we introduce a novel Time Series Lightweight Adaptive Network (TSLANet), as a universal convolutional model for diverse time series tasks. Specifically, we propose an Adaptive Spectral Block, harnessing Fourier analysis to enhance feature representation and to capture both long-term and short-term interactions while mitigating noise via adaptive thresholding. Additionally, we introduce an Interactive Convolution Block and leverage self-supervised learning to refine the capacity of TSLANet for decoding complex temporal patterns and improve its robustness on different datasets. Our comprehensive experiments demonstrate that TSLANet outperforms state-of-the-art models in various tasks spanning classification, forecasting, and anomaly detection, showcasing its resilience and adaptability across a spectrum of noise levels and data sizes. The code is available at \url{https://github.com/emadeldeen24/TSLANet}
Authors: Ozan Evkaya, Miguel de Carvalho
Abstract: As a result of recent advancements in generative AI, the field of Data Science is prone to various changes. This review critically examines the Data Analysis (DA) capabilities of ChatGPT assessing its performance across a wide range of tasks. While DA provides researchers and practitioners with unprecedented analytical capabilities, it is far from being perfect, and it is important to recognize and address its limitations.
Authors: Jonathan D. Chang, Wenhao Shan, Owen Oertell, Kiant\'e Brantley, Dipendra Misra, Jason D. Lee, Wen Sun
Abstract: Reinforcement Learning (RL) from Human Preference-based feedback is a popular paradigm for fine-tuning generative models, which has produced impressive models such as GPT-4 and Claude3 Opus. This framework often consists of two steps: learning a reward model from an offline preference dataset followed by running online RL to optimize the learned reward model. In this work, leveraging the idea of reset, we propose a new RLHF algorithm with provable guarantees. Motivated by the fact that offline preference dataset provides informative states (i.e., data that is preferred by the labelers), our new algorithm, Dataset Reset Policy Optimization (DR-PO), integrates the existing offline preference dataset into the online policy training procedure via dataset reset: it directly resets the policy optimizer to the states in the offline dataset, instead of always starting from the initial state distribution. In theory, we show that DR-PO learns to perform at least as good as any policy that is covered by the offline dataset under general function approximation with finite sample complexity. In experiments, we demonstrate that on both the TL;DR summarization and the Anthropic Helpful Harmful (HH) dataset, the generation from DR-PO is better than that from Proximal Policy Optimization (PPO) and Direction Preference Optimization (DPO), under the metric of GPT4 win-rate. Code for this work can be found at https://github.com/Cornell-RL/drpo.
Authors: Jonathan D. Chang, Dhruv Sreenivas, Yingbing Huang, Kiant\'e Brantley, Wen Sun
Abstract: Adversarial imitation learning (AIL) has stood out as a dominant framework across various imitation learning (IL) applications, with Discriminator Actor Critic (DAC) (Kostrikov et al.,, 2019) demonstrating the effectiveness of off-policy learning algorithms in improving sample efficiency and scalability to higher-dimensional observations. Despite DAC's empirical success, the original AIL objective is on-policy and DAC's ad-hoc application of off-policy training does not guarantee successful imitation (Kostrikov et al., 2019; 2020). Follow-up work such as ValueDICE (Kostrikov et al., 2020) tackles this issue by deriving a fully off-policy AIL objective. Instead in this work, we develop a novel and principled AIL algorithm via the framework of boosting. Like boosting, our new algorithm, AILBoost, maintains an ensemble of properly weighted weak learners (i.e., policies) and trains a discriminator that witnesses the maximum discrepancy between the distributions of the ensemble and the expert policy. We maintain a weighted replay buffer to represent the state-action distribution induced by the ensemble, allowing us to train discriminators using the entire data collected so far. In the weighted replay buffer, the contribution of the data from older policies are properly discounted with the weight computed based on the boosting framework. Empirically, we evaluate our algorithm on both controller state-based and pixel-based environments from the DeepMind Control Suite. AILBoost outperforms DAC on both types of environments, demonstrating the benefit of properly weighting replay buffer data for off-policy training. On state-based environments, DAC outperforms ValueDICE and IQ-Learn (Gary et al., 2021), achieving competitive performance with as little as one expert trajectory.
Authors: Xiaoze Xu, Xiuyu Sun, Wei Han, Xiaohui Zhong, Lei Chen, Hao Li
Abstract: Data assimilation (DA), as an indispensable component within contemporary Numerical Weather Prediction (NWP) systems, plays a crucial role in generating the analysis that significantly impacts forecast performance. Nevertheless, the development of an efficient DA system poses significant challenges, particularly in establishing intricate relationships between the background data and the vast amount of multi-source observation data within limited time windows in operational settings. To address these challenges, researchers design complex pre-processing methods for each observation type, leveraging approximate modeling and the power of super-computing clusters to expedite solutions. The emergence of deep learning (DL) models has been a game-changer, offering unified multi-modal modeling, enhanced nonlinear representation capabilities, and superior parallelization. These advantages have spurred efforts to integrate DL models into various domains of weather modeling. Remarkably, DL models have shown promise in matching, even surpassing, the forecast accuracy of leading operational NWP models worldwide. This success motivates the exploration of DL-based DA frameworks tailored for weather forecasting models. In this study, we introduces FuxiDA, a generalized DL-based DA framework for assimilating satellite observations. By assimilating data from Advanced Geosynchronous Radiation Imager (AGRI) aboard Fengyun-4B, FuXi-DA consistently mitigates analysis errors and significantly improves forecast performance. Furthermore, through a series of single-observation experiments, Fuxi-DA has been validated against established atmospheric physics, demonstrating its consistency and reliability.
Authors: Lucas Murray, Tatiana Castillo, Jaime Carrasco, Andr\'es Weintraub, Richard Weber, Isaac Mart\'in de Diego, Jos\'e Ram\'on Gonz\'alez, Jordi Garc\'ia-Gonzalo
Abstract: Over the past decades, the increase in both frequency and intensity of large-scale wildfires due to climate change has emerged as a significant natural threat. The pressing need to design resilient landscapes capable of withstanding such disasters has become paramount, requiring the development of advanced decision-support tools. Existing methodologies, including Mixed Integer Programming, Stochastic Optimization, and Network Theory, have proven effective but are hindered by computational demands, limiting their applicability. In response to this challenge, we propose using artificial intelligence techniques, specifically Deep Reinforcement Learning, to address the complex problem of firebreak placement in the landscape. We employ value-function based approaches like Deep Q-Learning, Double Deep Q-Learning, and Dueling Double Deep Q-Learning. Utilizing the Cell2Fire fire spread simulator combined with Convolutional Neural Networks, we have successfully implemented a computational agent capable of learning firebreak locations within a forest environment, achieving good results. Furthermore, we incorporate a pre-training loop, initially teaching our agent to mimic a heuristic-based algorithm and observe that it consistently exceeds the performance of these solutions. Our findings underscore the immense potential of Deep Reinforcement Learning for operational research challenges, especially in fire prevention. Our approach demonstrates convergence with highly favorable results in problem instances as large as 40 x 40 cells, marking a significant milestone in applying Reinforcement Learning to this critical issue. To the best of our knowledge, this study represents a pioneering effort in using Reinforcement Learning to address the aforementioned problem, offering promising perspectives in fire prevention and landscape management
Authors: Shreyas Chaudhari, Pranjal Aggarwal, Vishvak Murahari, Tanmay Rajpurohit, Ashwin Kalyan, Karthik Narasimhan, Ameet Deshpande, Bruno Castro da Silva
Abstract: State-of-the-art large language models (LLMs) have become indispensable tools for various tasks. However, training LLMs to serve as effective assistants for humans requires careful consideration. A promising approach is reinforcement learning from human feedback (RLHF), which leverages human feedback to update the model in accordance with human preferences and mitigate issues like toxicity and hallucinations. Yet, an understanding of RLHF for LLMs is largely entangled with initial design choices that popularized the method and current research focuses on augmenting those choices rather than fundamentally improving the framework. In this paper, we analyze RLHF through the lens of reinforcement learning principles to develop an understanding of its fundamentals, dedicating substantial focus to the core component of RLHF -- the reward model. Our study investigates modeling choices, caveats of function approximation, and their implications on RLHF training algorithms, highlighting the underlying assumptions made about the expressivity of reward. Our analysis improves the understanding of the role of reward models and methods for their training, concurrently revealing limitations of the current methodology. We characterize these limitations, including incorrect generalization, model misspecification, and the sparsity of feedback, along with their impact on the performance of a language model. The discussion and analysis are substantiated by a categorical review of current literature, serving as a reference for researchers and practitioners to understand the challenges of RLHF and build upon existing efforts.
Authors: Lin Li, Jianping Gou, Baosheng Yu, Lan Du, Zhang Yiand Dacheng Tao
Abstract: Federated Learning (FL) seeks to train a model collaboratively without sharing private training data from individual clients. Despite its promise, FL encounters challenges such as high communication costs for large-scale models and the necessity for uniform model architectures across all clients and the server. These challenges severely restrict the practical applications of FL. To address these limitations, the integration of knowledge distillation (KD) into FL has been proposed, forming what is known as Federated Distillation (FD). FD enables more flexible knowledge transfer between clients and the server, surpassing the mere sharing of model parameters. By eliminating the need for identical model architectures across clients and the server, FD mitigates the communication costs associated with training large-scale models. This paper aims to offer a comprehensive overview of FD, highlighting its latest advancements. It delves into the fundamental principles underlying the design of FD frameworks, delineates FD approaches for tackling various challenges, and provides insights into the diverse applications of FD across different scenarios.
Authors: Ege Aktemur, Ege Zorlutuna, Kaan Bilgili, Tacettin Emre Bok, Berrin Yanikoglu, Suha Orhun Mutluergil
Abstract: This paper introduces a new approach in distributed deep learning, utilizing Geoffrey Hinton's Forward-Forward (FF) algorithm to enhance the training of neural networks in distributed computing environments. Unlike traditional methods that rely on forward and backward passes, the FF algorithm employs a dual forward pass strategy, significantly diverging from the conventional backpropagation process. This novel method aligns more closely with the human brain's processing mechanisms, potentially offering a more efficient and biologically plausible approach to neural network training. Our research explores the implementation of the FF algorithm in distributed settings, focusing on its capability to facilitate parallel training of neural network layers. This parallelism aims to reduce training times and resource consumption, thereby addressing some of the inherent challenges in current distributed deep learning systems. By analyzing the effectiveness of the FF algorithm in distributed computing, we aim to demonstrate its potential as a transformative tool in distributed deep learning systems, offering improvements in training efficiency. The integration of the FF algorithm into distributed deep learning represents a significant step forward in the field, potentially revolutionizing the way neural networks are trained in distributed environments.
Authors: Alexander Sommers, Somayeh Bakhtiari Ramezani, Logan Cummins, Sudip Mittal, Shahram Rahimi, Maria Seale, Joseph Jaboure
Abstract: Data augmentation is an important facilitator of deep learning applications in the time series domain. A gap is identified in the literature, demonstrating sparse exploration of the transformer, the dominant sequence model, for data augmentation in time series. A architecture hybridizing several successful priors is put forth and tested using a powerful time domain similarity metric. Results suggest the challenge of this domain, and several valuable directions for future work.
Authors: Aniss Aiman Medbouhi, Giovanni Luca Marchetti, Vladislav Polianskii, Alexander Kravberg, Petra Poklukar, Anastasia Varava, Danica Kragic
Abstract: Hyperbolic machine learning is an emerging field aimed at representing data with a hierarchical structure. However, there is a lack of tools for evaluation and analysis of the resulting hyperbolic data representations. To this end, we propose Hyperbolic Delaunay Geometric Alignment (HyperDGA) -- a similarity score for comparing datasets in a hyperbolic space. The core idea is counting the edges of the hyperbolic Delaunay graph connecting datapoints across the given sets. We provide an empirical investigation on synthetic and real-life biological data and demonstrate that HyperDGA outperforms the hyperbolic version of classical distances between sets. Furthermore, we showcase the potential of HyperDGA for evaluating latent representations inferred by a Hyperbolic Variational Auto-Encoder.
Authors: Matteo Tucat, Anirbit Mukherjee
Abstract: In this work, we instantiate a regularized form of the gradient clipping algorithm and prove that it can converge to the global minima of deep neural network loss functions provided that the net is of sufficient width. We present empirical evidence that our theoretically founded regularized gradient clipping algorithm is also competitive with the state-of-the-art deep-learning heuristics. Hence the algorithm presented here constitutes a new approach to rigorous deep learning. The modification we do to standard gradient clipping is designed to leverage the PL* condition, a variant of the Polyak-Lojasiewicz inequality which was recently proven to be true for various neural networks for any depth within a neighborhood of the initialisation.
Authors: Xincan Feng, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe
Abstract: Subsampling is effective in Knowledge Graph Embedding (KGE) for reducing overfitting caused by the sparsity in Knowledge Graph (KG) datasets. However, current subsampling approaches consider only frequencies of queries that consist of entities and their relations. Thus, the existing subsampling potentially underestimates the appearance probabilities of infrequent queries even if the frequencies of their entities or relations are high. To address this problem, we propose Model-based Subsampling (MBS) and Mixed Subsampling (MIX) to estimate their appearance probabilities through predictions of KGE models. Evaluation results on datasets FB15k-237, WN18RR, and YAGO3-10 showed that our proposed subsampling methods actually improved the KG completion performances for popular KGE models, RotatE, TransE, HAKE, ComplEx, and DistMult.
Authors: Zhengde Zhang, Yiyu Zhang, Haodong Yao, Jianwen Luo, Rui Zhao, Bo Huang, Jiameng Zhao, Yipu Liao, Ke Li, Lina Zhao, Jun Cao, Fazhi Qi, Changzheng Yuan
Abstract: Large Language Models (LLMs) are undergoing a period of rapid updates and changes, with state-of-the-art (SOTA) model frequently being replaced. When applying LLMs to a specific scientific field, it's challenging to acquire unique domain knowledge while keeping the model itself advanced. To address this challenge, a sophisticated large language model system named as Xiwu has been developed, allowing you switch between the most advanced foundation models and quickly teach the model domain knowledge. In this work, we will report on the best practices for applying LLMs in the field of high-energy physics (HEP), including: a seed fission technology is proposed and some data collection and cleaning tools are developed to quickly obtain domain AI-Ready dataset; a just-in-time learning system is implemented based on the vector store technology; an on-the-fly fine-tuning system has been developed to facilitate rapid training under a specified foundation model. The results show that Xiwu can smoothly switch between foundation models such as LLaMA, Vicuna, ChatGLM and Grok-1. The trained Xiwu model is significantly outperformed the benchmark model on the HEP knowledge question-and-answering and code generation. This strategy significantly enhances the potential for growth of our model's performance, with the hope of surpassing GPT-4 as it evolves with the development of open-source models. This work provides a customized LLM for the field of HEP, while also offering references for applying LLM to other fields, the corresponding codes are available on Github.
Authors: Igor G. Smit, Zaharah Bukhsh, Mykola Pechenizkiy, Kostas Alogariastos, Kasper Hendriks, Yingqian Zhang
Abstract: In collaborative human-robot order picking systems, human pickers and Autonomous Mobile Robots (AMRs) travel independently through a warehouse and meet at pick locations where pickers load items onto the AMRs. In this paper, we consider an optimization problem in such systems where we allocate pickers to AMRs in a stochastic environment. We propose a novel multi-objective Deep Reinforcement Learning (DRL) approach to learn effective allocation policies to maximize pick efficiency while also aiming to improve workload fairness amongst human pickers. In our approach, we model the warehouse states using a graph, and define a neural network architecture that captures regional information and effectively extracts representations related to efficiency and workload. We develop a discrete-event simulation model, which we use to train and evaluate the proposed DRL approach. In the experiments, we demonstrate that our approach can find non-dominated policy sets that outline good trade-offs between fairness and efficiency objectives. The trained policies outperform the benchmarks in terms of both efficiency and fairness. Moreover, they show good transferability properties when tested on scenarios with different warehouse sizes. The implementation of the simulation model, proposed approach, and experiments are published.
Authors: Sukhdeep Singh, Sudhir Rohilla, Anuj Sharma
Abstract: Deep learning expresses a category of machine learning algorithms that have the capability to combine raw inputs into intermediate features layers. These deep learning algorithms have demonstrated great results in different fields. Deep learning has particularly witnessed for a great achievement of human level performance across a number of domains in computer vision and pattern recognition. For the achievement of state-of-the-art performances in diverse domains, the deep learning used different architectures and these architectures used activation functions to perform various computations between hidden and output layers of any architecture. This paper presents a survey on the existing studies of deep learning in handwriting recognition field. Even though the recent progress indicates that the deep learning methods has provided valuable means for speeding up or proving accurate results in handwriting recognition, but following from the extensive literature survey, the present study finds that the deep learning has yet to revolutionize more and has to resolve many of the most pressing challenges in this field, but promising advances have been made on the prior state of the art. Additionally, an inadequate availability of labelled data to train presents problems in this domain. Nevertheless, the present handwriting recognition survey foresees deep learning enabling changes at both bench and bedside with the potential to transform several domains as image processing, speech recognition, computer vision, machine translation, robotics and control, medical imaging, medical information processing, bio-informatics, natural language processing, cyber security, and many others.
Authors: Ahmad Sarlak, Hazim Alzorgan, Sayed Pedram Haeri Boroujeni, Abolfazl Razi, Rahul Amin
Abstract: Sharing and joint processing of camera feeds and sensor measurements, known as Cooperative Perception (CP), has emerged as a new technique to achieve higher perception qualities. CP can enhance the safety of Autonomous Vehicles (AVs) where their individual visual perception quality is compromised by adverse weather conditions (haze as foggy weather), low illumination, winding roads, and crowded traffic. To cover the limitations of former methods, in this paper, we propose a novel approach to realize an optimized CP under constrained communications. At the core of our approach is recruiting the best helper from the available list of front vehicles to augment the visual range and enhance the Object Detection (OD) accuracy of the ego vehicle. In this two-step process, we first select the helper vehicles that contribute the most to CP based on their visual range and lowest motion blur. Next, we implement a radio block optimization among the candidate vehicles to further improve communication efficiency. We specifically focus on pedestrian detection as an exemplary scenario. To validate our approach, we used the CARLA simulator to create a dataset of annotated videos for different driving scenarios where pedestrian detection is challenging for an AV with compromised vision. Our results demonstrate the efficacy of our two-step optimization process in improving the overall performance of cooperative perception in challenging scenarios, substantially improving driving safety under adverse conditions. Finally, we note that the networking assumptions are adopted from LTE Release 14 Mode 4 side-link communication, commonly used for Vehicle-to-Vehicle (V2V) communication. Nonetheless, our method is flexible and applicable to arbitrary V2V communications.
Authors: Lena Podina, Ali Ghodsi, Mohammad Kohandel
Abstract: Quantitative systems pharmacology (QSP) is widely used to assess drug effects and toxicity before the drug goes to clinical trial. However, significant manual distillation of the literature is needed in order to construct a QSP model. Parameters may need to be fit, and simplifying assumptions of the model need to be made. In this work, we apply Universal Physics-Informed Neural Networks (UPINNs) to learn unknown components of various differential equations that model chemotherapy pharmacodynamics. We learn three commonly employed chemotherapeutic drug actions (log-kill, Norton-Simon, and E_max) from synthetic data. Then, we use the UPINN method to fit the parameters for several synthetic datasets simultaneously. Finally, we learn the net proliferation rate in a model of doxorubicin (a chemotherapeutic) pharmacodynamics. As these are only toy examples, we highlight the usefulness of UPINNs in learning unknown terms in pharmacodynamic and pharmacokinetic models.
Authors: Sanat Sharma, Mayank Poddar, Jayant Kumar, Kosta Blank, Tracy King
Abstract: Knowledge graphs are useful tools to organize, recommend and sort data. Hierarchies in knowledge graphs provide significant benefit in improving understanding and compartmentalization of the data within a knowledge graph. This work leverages large language models to generate and augment hierarchies in an existing knowledge graph. For small (<100,000 node) domain-specific KGs, we find that a combination of few-shot prompting with one-shot generation works well, while larger KG may require cyclical generation. We present techniques for augmenting hierarchies, which led to coverage increase by 98% for intents and 99% for colors in our knowledge graph.
Authors: Zeyu Zhang, Yuanshen Zhao, Jingxian Duan, Yaou Liu, Hairong Zheng, Dong Liang, Zhenyu Zhang, Zhi-Cheng Li
Abstract: The diagnosis and prognosis of cancer are typically based on multi-modal clinical data, including histology images and genomic data, due to the complex pathogenesis and high heterogeneity. Despite the advancements in digital pathology and high-throughput genome sequencing, establishing effective multi-modal fusion models for survival prediction and revealing the potential association between histopathology and transcriptomics remains challenging. In this paper, we propose Pathology-Genome Heterogeneous Graph (PGHG) that integrates whole slide images (WSI) and bulk RNA-Seq expression data with heterogeneous graph neural network for cancer survival analysis. The PGHG consists of biological knowledge-guided representation learning network and pathology-genome heterogeneous graph. The representation learning network utilizes the biological prior knowledge of intra-modal and inter-modal data associations to guide the feature extraction. The node features of each modality are updated through attention-based graph learning strategy. Unimodal features and bi-modal fused features are extracted via attention pooling module and then used for survival prediction. We evaluate the model on low-grade gliomas, glioblastoma, and kidney renal papillary cell carcinoma datasets from the Cancer Genome Atlas (TCGA) and the First Affiliated Hospital of Zhengzhou University (FAHZU). Extensive experimental results demonstrate that the proposed method outperforms both unimodal and other multi-modal fusion models. For demonstrating the model interpretability, we also visualize the attention heatmap of pathological images and utilize integrated gradient algorithm to identify important tissue structure, biological pathways and key genes.
Authors: Ying Chen, Jiajing Xie, Yuxiang Lin, Yuhang Song, Wenxian Yang, Rongshan Yu
Abstract: Multi-modal learning that combines pathological images with genomic data has significantly enhanced the accuracy of survival prediction. Nevertheless, existing methods have not fully utilized the inherent hierarchical structure within both whole slide images (WSIs) and transcriptomic data, from which better intra-modal representations and inter-modal integration could be derived. Moreover, many existing studies attempt to improve multi-modal representations through attention mechanisms, which inevitably lead to high complexity when processing high-dimensional WSIs and transcriptomic data. Recently, a structured state space model named Mamba emerged as a promising approach for its superior performance in modeling long sequences with low complexity. In this study, we propose Mamba with multi-grained multi-modal interaction (SurvMamba) for survival prediction. SurvMamba is implemented with a Hierarchical Interaction Mamba (HIM) module that facilitates efficient intra-modal interactions at different granularities, thereby capturing more detailed local features as well as rich global representations. In addition, an Interaction Fusion Mamba (IFM) module is used for cascaded inter-modal interactive fusion, yielding more comprehensive features for survival prediction. Comprehensive evaluations on five TCGA datasets demonstrate that SurvMamba outperforms other existing methods in terms of performance and computational cost.
Authors: Runtao Liu, Ashkan Khakzar, Jindong Gu, Qifeng Chen, Philip Torr, Fabio Pizzati
Abstract: With the ability to generate high-quality images, text-to-image (T2I) models can be exploited for creating inappropriate content. To prevent misuse, existing safety measures are either based on text blacklists, which can be easily circumvented, or harmful content classification, requiring large datasets for training and offering low flexibility. Hence, we propose Latent Guard, a framework designed to improve safety measures in text-to-image generation. Inspired by blacklist-based approaches, Latent Guard learns a latent space on top of the T2I model's text encoder, where it is possible to check the presence of harmful concepts in the input text embeddings. Our proposed framework is composed of a data generation pipeline specific to the task using large language models, ad-hoc architectural components, and a contrastive learning strategy to benefit from the generated data. The effectiveness of our method is verified on three datasets and against four baselines. Code and data will be shared at https://github.com/rt219/LatentGuard.
Authors: Soroosh Tayebi Arasteh, Tomas Arias-Vergara, Paula Andrea Perez-Toro, Tobias Weise, Kai Packhaeuser, Maria Schuster, Elmar Noeth, Andreas Maier, Seung Hee Yang
Abstract: Integration of speech into healthcare has intensified privacy concerns due to its potential as a non-invasive biomarker containing individual biometric information. In response, speaker anonymization aims to conceal personally identifiable information while retaining crucial linguistic content. However, the application of anonymization techniques to pathological speech, a critical area where privacy is especially vital, has not been extensively examined. This study investigates anonymization's impact on pathological speech across over 2,700 speakers from multiple German institutions, focusing on privacy, pathological utility, and demographic fairness. We explore both training-based and signal processing-based anonymization methods, and document substantial privacy improvements across disorders-evidenced by equal error rate increases up to 1933%, with minimal overall impact on utility. Specific disorders such as Dysarthria, Dysphonia, and Cleft Lip and Palate experienced minimal utility changes, while Dysglossia showed slight improvements. Our findings underscore that the impact of anonymization varies substantially across different disorders. This necessitates disorder-specific anonymization strategies to optimally balance privacy with diagnostic utility. Additionally, our fairness analysis revealed consistent anonymization effects across most of the demographics. This study demonstrates the effectiveness of anonymization in pathological speech for enhancing privacy, while also highlighting the importance of customized approaches to account for inversion attacks.
Authors: He Chen, Jiajin Li, Anthony Man-Cho So
Abstract: Despite the considerable success of Bregman proximal-type algorithms, such as mirror descent, in machine learning, a critical question remains: Can existing stationarity measures, often based on Bregman divergence, reliably distinguish between stationary and non-stationary points? In this paper, we present a groundbreaking finding: All existing stationarity measures necessarily imply the existence of spurious stationary points. We further establish an algorithmic independent hardness result: Bregman proximal-type algorithms are unable to escape from a spurious stationary point in finite steps when the initial point is unfavorable, even for convex problems. Our hardness result points out the inherent distinction between Euclidean and Bregman geometries, and introduces both fundamental theoretical and numerical challenges to both machine learning and optimization communities.
Authors: Stefan Sylvius Wagner, Maike Behrendt, Marc Ziegele, Stefan Harmeling
Abstract: Stance detection is an important task for many applications that analyse or support online political discussions. Common approaches include fine-tuning transformer based models. However, these models require a large amount of labelled data, which might not be available. In this work, we present two different ways to leverage LLM-generated synthetic data to train and improve stance detection agents for online political discussions: first, we show that augmenting a small fine-tuning dataset with synthetic data can improve the performance of the stance detection model. Second, we propose a new active learning method called SQBC based on the "Query-by-Comittee" approach. The key idea is to use LLM-generated synthetic data as an oracle to identify the most informative unlabelled samples, that are selected for manual labelling. Comprehensive experiments show that both ideas can improve the stance detection performance. Curiously, we observed that fine-tuning on actively selected samples can exceed the performance of using the full dataset.
Authors: Mohannad Alhakami, Dylan R. Ashley, Joel Dunham, Francesco Faccio, Eric Feron, J\"urgen Schmidhuber
Abstract: Artificial intelligence has made great strides in many areas lately, yet it has had comparatively little success in general-use robotics. We believe one of the reasons for this is the disconnect between traditional robotic design and the properties needed for open-ended, creativity-based AI systems. To that end, we, taking selective inspiration from nature, build a robust, partially soft robotic limb with a large action space, rich sensory data stream from multiple cameras, and the ability to connect with others to enhance the action space and data stream. As a proof of concept, we train two contemporary machine learning algorithms to perform a simple target-finding task. Altogether, we believe that this design serves as a first step to building a robot tailor-made for achieving artificial general intelligence.
Authors: Haoyuan Sun, Ali Jadbabaie
Abstract: The focus of this paper is on linear system identification in the setting where it is known that the underlying partially-observed linear dynamical system lies within a finite collection of known candidate models. We first consider the problem of identification from a given trajectory, which in this setting reduces to identifying the index of the true model with high probability. We characterize the finite-time sample complexity of this problem by leveraging recent advances in the non-asymptotic analysis of linear least-square methods in the literature. In comparison to the earlier results that assume no prior knowledge of the system, our approach takes advantage of the smaller hypothesis class and leads to the design of a learner with a dimension-free sample complexity bound. Next, we consider the switching control of linear systems, where there is a candidate controller for each of the candidate models and data is collected through interaction of the system with a collection of potentially destabilizing controllers. We develop a dimension-dependent criterion that can detect those destabilizing controllers in finite time. By leveraging these results, we propose a data-driven switching strategy that identifies the unknown parameters of the underlying system. We then provide a non-asymptotic analysis of its performance and discuss its implications on the classical method of estimator-based supervisory control.
Authors: Markus R. Ernst, Francisco M. L\'opez, Arthur Aubret, Roland W. Fleming, Jochen Triesch
Abstract: Color constancy (CC) describes the ability of the visual system to perceive an object as having a relatively constant color despite changes in lighting conditions. While CC and its limitations have been carefully characterized in humans, it is still unclear how the visual system acquires this ability during development. Here, we present a first study showing that CC develops in a neural network trained in a self-supervised manner through an invariance learning objective. During learning, objects are presented under changing illuminations, while the network aims to map subsequent views of the same object onto close-by latent representations. This gives rise to representations that are largely invariant to the illumination conditions, offering a plausible example of how CC could emerge during human cognitive development via a form of self-supervised learning.
Authors: Tom Gur, Mohammad Mahdi Jahanara, Mohammad Mahdi Khodabandeh, Ninad Rajgopal, Bahar Salamatian, Igor Shinkar
Abstract: We continue the study of doubly-efficient proof systems for verifying agnostic PAC learning, for which we obtain the following results. - We construct an interactive protocol for learning the $t$ largest Fourier characters of a given function $f \colon \{0,1\}^n \to \{0,1\}$ up to an arbitrarily small error, wherein the verifier uses $\mathsf{poly}(t)$ random examples. This improves upon the Interactive Goldreich-Levin protocol of Goldwasser, Rothblum, Shafer, and Yehudayoff (ITCS 2021) whose sample complexity is $\mathsf{poly}(t,n)$. - For agnostically learning the class $\mathsf{AC}^0[2]$ under the uniform distribution, we build on the work of Carmosino, Impagliazzo, Kabanets, and Kolokolova (APPROX/RANDOM 2017) and design an interactive protocol, where given a function $f \colon \{0,1\}^n \to \{0,1\}$, the verifier learns the closest hypothesis up to $\mathsf{polylog}(n)$ multiplicative factor, using quasi-polynomially many random examples. In contrast, this class has been notoriously resistant even for constructing realisable learners (without a prover) using random examples. - For agnostically learning $k$-juntas under the uniform distribution, we obtain an interactive protocol, where the verifier uses $O(2^k)$ random examples to a given function $f \colon \{0,1\}^n \to \{0,1\}$. Crucially, the sample complexity of the verifier is independent of $n$. We also show that if we do not insist on doubly-efficient proof systems, then the model becomes trivial. Specifically, we show a protocol for an arbitrary class $\mathcal{C}$ of Boolean functions in the distribution-free setting, where the verifier uses $O(1)$ labeled examples to learn $f$.
Authors: Haoting Zhang, Jinghai He, Rhonda Righter, Zeyu Zheng
Abstract: With the advancement in generative language models, the selection of prompts has gained significant attention in recent years. A prompt is an instruction or description provided by the user, serving as a guide for the generative language model in content generation. Despite existing methods for prompt selection that are based on human labor, we consider facilitating this selection through simulation optimization, aiming to maximize a pre-defined score for the selected prompt. Specifically, we propose a two-stage framework. In the first stage, we determine a feasible set of prompts in sufficient numbers, where each prompt is represented by a moderate-dimensional vector. In the subsequent stage for evaluation and selection, we construct a surrogate model of the score regarding the moderate-dimensional vectors that represent the prompts. We propose sequentially selecting the prompt for evaluation based on this constructed surrogate model. We prove the consistency of the sequential evaluation procedure in our framework. We also conduct numerical experiments to demonstrate the efficacy of our proposed framework, providing practical instructions for implementation.
Authors: Farhad Farokhi
Abstract: Optimal encoding of classical data for statistical inference using quantum computing is investigated. A universal encoder is sought that is optimal for a wide array of statistical inference tasks. Accuracy of any statistical inference is shown to be upper bounded by a term that is proportional to maximal quantum leakage from the classical data, i.e., the input to the inference model, through its quantum encoding. This demonstrates that the maximal quantum leakage is a universal measure of the quality of the encoding strategy for statistical inference as it only depends on the quantum encoding of the data and not the inference task itself. The optimal universal encoding strategy, i.e., the encoding strategy that maximizes the maximal quantum leakage, is proved to be attained by pure states. When there are enough qubits, basis encoding is proved to be universally optimal. An iterative method for numerically computing the optimal universal encoding strategy is presented.
Authors: Masako Kishida, Shunsuke Ono
Abstract: This extended abstract introduces a class of graph learning applicable to cases where the underlying graph has polytopic uncertainty, i.e., the graph is not exactly known, but its parameters or properties vary within a known range. By incorporating this assumption that the graph lies in a polytopic set into two established graph learning frameworks, we find that our approach yields better results with less computation.
Authors: Jiayi Li, Linqi Ye, Yi Cheng, Houde Liu, Bin Liang
Abstract: The remarkable athletic intelligence displayed by humans in complex dynamic movements such as dancing and gymnastics suggests that the balance mechanism in biological beings is decoupled from specific movement patterns. This decoupling allows for the execution of both learned and unlearned movements under certain constraints while maintaining balance through minor whole-body coordination. To replicate this balance ability and body agility, this paper proposes a versatile controller for bipedal robots. This controller achieves ankle and body trajectory tracking across a wide range of gaits using a single small-scale neural network, which is based on a model-based IK solver and reinforcement learning. We consider a single step as the smallest control unit and design a universally applicable control input form suitable for any single-step variation. Highly flexible gait control can be achieved by combining these minimal control units with high-level policy through our extensible control interface. To enhance the trajectory-tracking capability of our controller, we utilize a three-stage training curriculum. After training, the robot can move freely between target footholds at varying distances and heights. The robot can also maintain static balance without repeated stepping to adjust posture. Finally, we evaluate the tracking accuracy of our controller on various bipedal tasks, and the effectiveness of our control framework is verified in the simulation environment.
Authors: Pu Li, Xiaoyan Yu, Hao Peng, Yantuan Xian, Linqin Wang, Li Sun, Jingyun Zhang, Philip S. Yu
Abstract: Social Event Detection (SED) aims to identify significant events from social streams, and has a wide application ranging from public opinion analysis to risk management. In recent years, Graph Neural Network (GNN) based solutions have achieved state-of-the-art performance. However, GNN-based methods often struggle with noisy and missing edges between messages, affecting the quality of learned message embedding. Moreover, these methods statically initialize node embedding before training, which, in turn, limits the ability to learn from message texts and relations simultaneously. In this paper, we approach social event detection from a new perspective based on Pre-trained Language Models (PLMs), and present RPLM_SED (Relational prompt-based Pre-trained Language Models for Social Event Detection). We first propose a new pairwise message modeling strategy to construct social messages into message pairs with multi-relational sequences. Secondly, a new multi-relational prompt-based pairwise message learning mechanism is proposed to learn more comprehensive message representation from message pairs with multi-relational prompts using PLMs. Thirdly, we design a new clustering constraint to optimize the encoding process by enhancing intra-cluster compactness and inter-cluster dispersion, making the message representation more distinguishable. We evaluate the RPLM_SED on three real-world datasets, demonstrating that the RPLM_SED model achieves state-of-the-art performance in offline, online, low-resource, and long-tail distribution scenarios for social event detection tasks.
Authors: MingXuan Xiao, Yufeng Li, Xu Yan, Min Gao, Weimin Wang
Abstract: Breast cancer is a relatively common cancer among gynecological cancers. Its diagnosis often relies on the pathology of cells in the lesion. The pathological diagnosis of breast cancer not only requires professionals and time, but also sometimes involves subjective judgment. To address the challenges of dependence on pathologists expertise and the time-consuming nature of achieving accurate breast pathological image classification, this paper introduces an approach utilizing convolutional neural networks (CNNs) for the rapid categorization of pathological images, aiming to enhance the efficiency of breast pathological image detection. And the approach enables the rapid and automatic classification of pathological images into benign and malignant groups. The methodology involves utilizing a convolutional neural network (CNN) model leveraging the Inceptionv3 architecture and transfer learning algorithm for extracting features from pathological images. Utilizing a neural network with fully connected layers and employing the SoftMax function for image classification. Additionally, the concept of image partitioning is introduced to handle high-resolution images. To achieve the ultimate classification outcome, the classification probabilities of each image block are aggregated using three algorithms: summation, product, and maximum. Experimental validation was conducted on the BreaKHis public dataset, resulting in accuracy rates surpassing 0.92 across all four magnification coefficients (40X, 100X, 200X, and 400X). It demonstrates that the proposed method effectively enhances the accuracy in classifying pathological images of breast cancer.
Authors: Kazuki Tsurumaki, Chie Hieida, Kazuki Miyazawa
Abstract: How are emotions formed? Through extensive debate and the promulgation of diverse theories , the theory of constructed emotion has become prevalent in recent research on emotions. According to this theory, an emotion concept refers to a category formed by interoceptive and exteroceptive information associated with a specific emotion. An emotion concept stores past experiences as knowledge and can predict unobserved information from acquired information. Therefore, in this study, we attempted to model the formation of emotion concepts using a constructionist approach from the perspective of the constructed emotion theory. Particularly, we constructed a model using multilayered multimodal latent Dirichlet allocation , which is a probabilistic generative model. We then trained the model for each subject using vision, physiology, and word information obtained from multiple people who experienced different visual emotion-evoking stimuli. To evaluate the model, we verified whether the formed categories matched human subjectivity and determined whether unobserved information could be predicted via categories. The verification results exceeded chance level, suggesting that emotion concept formation can be explained by the proposed model.
Authors: Peijie Sun, Yifan Wang, Min Zhang, Chuhan Wu, Yan Fang, Hong Zhu, Yuan Fang, Meng Wang
Abstract: With the surge in mobile gaming, accurately predicting user spending on newly downloaded games has become paramount for maximizing revenue. However, the inherently unpredictable nature of user behavior poses significant challenges in this endeavor. To address this, we propose a robust model training and evaluation framework aimed at standardizing spending data to mitigate label variance and extremes, ensuring stability in the modeling process. Within this framework, we introduce a collaborative-enhanced model designed to predict user game spending without relying on user IDs, thus ensuring user privacy and enabling seamless online training. Our model adopts a unique approach by separately representing user preferences and game features before merging them as input to the spending prediction module. Through rigorous experimentation, our approach demonstrates notable improvements over production models, achieving a remarkable \textbf{17.11}\% enhancement on offline data and an impressive \textbf{50.65}\% boost in an online A/B test. In summary, our contributions underscore the importance of stable model training frameworks and the efficacy of collaborative-enhanced models in predicting user spending behavior in mobile gaming.
Authors: Idan Amit, Dror G. Feitelson
Abstract: Context: Motivation is known to improve performance. In software development in particular, there has been considerable interest in the motivation of contributors to open source. Objective: We identify 11 motivators from the literature (enjoying programming, ownership of code, learning, self use, etc.), and evaluate their relative effect on motivation. Since motivation is an internal subjective feeling, we also analyze the validity of the answers. Method: We conducted a survey with 66 questions on motivation which was completed by 521 developers. Most of the questions used an 11 point scale. We evaluated the validity of the answers validity by comparing related questions, comparing to actual behavior on GitHub, and comparison with the same developer in a follow up survey. Results: Validity problems include moderate correlations between answers to related questions, as well as self promotion and mistakes in the answers. Despite these problems, predictive analysis, investigating how diverse motivators influence the probability of high motivation, provided valuable insights. The correlations between the different motivators are low, implying their independence. High values in all 11 motivators predict increased probability of high motivation. In addition, improvement analysis shows that an increase in most motivators predicts an increase in general motivation.
Authors: Hafsa Maryam, Tania Panayiotou, Georgios Ellinas
Abstract: A multi-period planning framework is proposed that exploits multi-step ahead traffic predictions to address service overprovisioning and improve adaptability to traffic changes, while ensuring the necessary quality-of-service (QoS) levels. An encoder-decoder deep learning model is initially leveraged for multi-step ahead prediction by analyzing real-traffic traces. This information is then exploited by multi-period planning heuristics to efficiently utilize available network resources while minimizing undesired service disruptions (caused due to lightpath re-allocations), with these heuristics outperforming a single-step ahead prediction approach.
Authors: Nils Lehmann, Nina Maria Gottschling, Stefan Depeweg, Eric Nalisnick
Abstract: Deep neural networks (DNNs) have been successfully applied to earth observation (EO) data and opened new research avenues. Despite the theoretical and practical advances of these techniques, DNNs are still considered black box tools and by default are designed to give point predictions. However, the majority of EO applications demand reliable uncertainty estimates that can support practitioners in critical decision making tasks. This work provides a theoretical and quantitative comparison of existing uncertainty quantification methods for DNNs applied to the task of wind speed estimation in satellite imagery of tropical cyclones. We provide a detailed evaluation of predictive uncertainty estimates from state-of-the-art uncertainty quantification (UQ) methods for DNNs. We find that predictive uncertainties can be utilized to further improve accuracy and analyze the predictive uncertainties of different methods across storm categories.
Authors: Nived Rajaraman, Jiantao Jiao, Kannan Ramchandran
Abstract: While there has been a large body of research attempting to circumvent tokenization for language modeling (Clark et al., 2022; Xue et al., 2022), the current consensus is that it is a necessary initial step for designing state-of-the-art performant language models. In this paper, we investigate tokenization from a theoretical point of view by studying the behavior of transformers on simple data generating processes. When trained on data drawn from certain simple $k^{\text{th}}$-order Markov processes for $k > 1$, transformers exhibit a surprising phenomenon - in the absence of tokenization, they empirically fail to learn the right distribution and predict characters according to a unigram model (Makkuva et al., 2024). With the addition of tokenization, however, we empirically observe that transformers break through this barrier and are able to model the probabilities of sequences drawn from the source near-optimally, achieving small cross-entropy loss. With this observation as starting point, we study the end-to-end cross-entropy loss achieved by transformers with and without tokenization. With the appropriate tokenization, we show that even the simplest unigram models (over tokens) learnt by transformers are able to model the probability of sequences drawn from $k^{\text{th}}$-order Markov sources near optimally. Our analysis provides a justification for the use of tokenization in practice through studying the behavior of transformers on Markovian data.
Authors: Yang Yang, Hongpeng Pan, Qing-Yuan Jiang, Yi Xu, Jinghui Tang
Abstract: Multi-modal learning aims to enhance performance by unifying models from various modalities but often faces the "modality imbalance" problem in real data, leading to a bias towards dominant modalities and neglecting others, thereby limiting its overall effectiveness. To address this challenge, the core idea is to balance the optimization of each modality to achieve a joint optimum. Existing approaches often employ a modal-level control mechanism for adjusting the update of each modal parameter. However, such a global-wise updating mechanism ignores the different importance of each parameter. Inspired by subnetwork optimization, we explore a uniform sampling-based optimization strategy and find it more effective than global-wise updating. According to the findings, we further propose a novel importance sampling-based, element-wise joint optimization method, called Adaptively Mask Subnetworks Considering Modal Significance(AMSS). Specifically, we incorporate mutual information rates to determine the modal significance and employ non-uniform adaptive sampling to select foreground subnetworks from each modality for parameter updates, thereby rebalancing multi-modal learning. Additionally, we demonstrate the reliability of the AMSS strategy through convergence analysis. Building upon theoretical insights, we further enhance the multi-modal mask subnetwork strategy using unbiased estimation, referred to as AMSS+. Extensive experiments reveal the superiority of our approach over comparison methods.
Authors: Veronika Spieker, Hannah Eichhorn, Jonathan K. Stelter, Wenqi Huang, Rickmer F. Braren, Daniel R\"uckert, Francisco Sahli Costabal, Kerstin Hammernik, Claudia Prieto, Dimitrios C. Karampinos, Julia A. Schnabel
Abstract: Neural implicit k-space representations have shown promising results for dynamic MRI at high temporal resolutions. Yet, their exclusive training in k-space limits the application of common image regularization methods to improve the final reconstruction. In this work, we introduce the concept of parallel imaging-inspired self-consistency (PISCO), which we incorporate as novel self-supervised k-space regularization enforcing a consistent neighborhood relationship. At no additional data cost, the proposed regularization significantly improves neural implicit k-space reconstructions on simulated data. Abdominal in-vivo reconstructions using PISCO result in enhanced spatio-temporal image quality compared to state-of-the-art methods. Code is available at https://github.com/vjspi/PISCO-NIK.
Authors: David Osowiechi, Gustavo A. Vargas Hakim, Mehrdad Noori, Milad Cheraghalikhani, Ali Bahri, Moslem Yazdanpanah, Ismail Ben Ayed, Christian Desrosiers
Abstract: Despite their exceptional performance in vision tasks, deep learning models often struggle when faced with domain shifts during testing. Test-Time Training (TTT) methods have recently gained popularity by their ability to enhance the robustness of models through the addition of an auxiliary objective that is jointly optimized with the main task. Being strictly unsupervised, this auxiliary objective is used at test time to adapt the model without any access to labels. In this work, we propose Noise-Contrastive Test-Time Training (NC-TTT), a novel unsupervised TTT technique based on the discrimination of noisy feature maps. By learning to classify noisy views of projected feature maps, and then adapting the model accordingly on new domains, classification performance can be recovered by an important margin. Experiments on several popular test-time adaptation baselines demonstrate the advantages of our method compared to recent approaches for this task. The code can be found at:https://github.com/GustavoVargasHakim/NCTTT.git
Authors: Rita Gonz\'alez-M\'arquez, Dmitry Kobak
Abstract: The ICLR conference is unique among the top machine learning conferences in that all submitted papers are openly available. Here we present the ICLR dataset consisting of abstracts of all 24 thousand ICLR submissions from 2017-2024 with meta-data, decision scores, and custom keyword-based labels. We find that on this dataset, bag-of-words representation outperforms most dedicated sentence transformer models in terms of $k$NN classification accuracy, and the top performing language models barely outperform TF-IDF. We see this as a challenge for the NLP community. Furthermore, we use the ICLR dataset to study how the field of machine learning has changed over the last seven years, finding some improvement in gender balance. Using a 2D embedding of the abstracts' texts, we describe a shift in research topics from 2017 to 2024 and identify hedgehogs and foxes among the authors with the highest number of ICLR submissions.
Authors: Arthur Ledaguenel, C\'eline Hudelot, Mostepha Khouadjia
Abstract: Neurosymbolic artificial intelligence is a growing field of research aiming to combine neural network learning capabilities with the reasoning abilities of symbolic systems. Informed multi-label classification is a sub-field of neurosymbolic AI which studies how to leverage prior knowledge to improve neural classification systems. A well known family of neurosymbolic techniques for informed classification use probabilistic reasoning to integrate this knowledge during learning, inference or both. Therefore, the asymptotic complexity of probabilistic reasoning is of cardinal importance to assess the scalability of such techniques. However, this topic is rarely tackled in the neurosymbolic literature, which can lead to a poor understanding of the limits of probabilistic neurosymbolic techniques. In this paper, we introduce a formalism for informed supervised classification tasks and techniques. We then build upon this formalism to define three abstract neurosymbolic techniques based on probabilistic reasoning. Finally, we show computational complexity results on several representation languages for prior knowledge commonly found in the neurosymbolic literature.
Authors: Lorenc Kapllani, Long Teng
Abstract: In this work, we propose a novel backward differential deep learning-based algorithm for solving high-dimensional nonlinear backward stochastic differential equations (BSDEs), where the deep neural network (DNN) models are trained not only on the inputs and labels but also the differentials of the corresponding labels. This is motivated by the fact that differential deep learning can provide an efficient approximation of the labels and their derivatives with respect to inputs. The BSDEs are reformulated as differential deep learning problems by using Malliavin calculus. The Malliavin derivatives of solution to a BSDE satisfy themselves another BSDE, resulting thus in a system of BSDEs. Such formulation requires the estimation of the solution, its gradient, and the Hessian matrix, represented by the triple of processes $\left(Y, Z, \Gamma\right).$ All the integrals within this system are discretized by using the Euler-Maruyama method. Subsequently, DNNs are employed to approximate the triple of these unknown processes. The DNN parameters are backwardly optimized at each time step by minimizing a differential learning type loss function, which is defined as a weighted sum of the dynamics of the discretized BSDE system, with the first term providing the dynamics of the process $Y$ and the other the process $Z$. An error analysis is carried out to show the convergence of the proposed algorithm. Various numerical experiments up to $50$ dimensions are provided to demonstrate the high efficiency. Both theoretically and numerically, it is demonstrated that our proposed scheme is more efficient compared to other contemporary deep learning-based methodologies, especially in the computation of the process $\Gamma$.
Authors: Emile van Krieken, Pasquale Minervini, Edoardo M. Ponti, Antonio Vergari
Abstract: State-of-the-art neurosymbolic learning systems use probabilistic reasoning to guide neural networks towards predictions that conform to logical constraints over symbols. Many such systems assume that the probabilities of the considered symbols are conditionally independent given the input to simplify learning and reasoning. We study and criticise this assumption, highlighting how it can hinder optimisation and prevent uncertainty quantification. We prove that loss functions bias conditionally independent neural networks to become overconfident in their predictions. As a result, they are unable to represent uncertainty over multiple valid options. Furthermore, we prove that these loss functions are difficult to optimise: they are non-convex, and their minima are usually highly disconnected. Our theoretical analysis gives the foundation for replacing the conditional independence assumption and designing more expressive neurosymbolic probabilistic models.
Authors: Adrien Bardes, Quentin Garrido, Jean Ponce, Xinlei Chen, Michael Rabbat, Yann LeCun, Mahmoud Assran, Nicolas Ballas
Abstract: This paper explores feature prediction as a stand-alone objective for unsupervised learning from video and introduces V-JEPA, a collection of vision models trained solely using a feature prediction objective, without the use of pretrained image encoders, text, negative examples, reconstruction, or other sources of supervision. The models are trained on 2 million videos collected from public datasets and are evaluated on downstream image and video tasks. Our results show that learning by predicting video features leads to versatile visual representations that perform well on both motion and appearance-based tasks, without adaption of the model's parameters; e.g., using a frozen backbone. Our largest model, a ViT-H/16 trained only on videos, obtains 81.9% on Kinetics-400, 72.2% on Something-Something-v2, and 77.9% on ImageNet1K.
Authors: Hai-Vy Nguyen, Fabrice Gamboa, Reda Chhaibi, Sixin Zhang, Serge Gratton, Thierry Giaccone
Abstract: We measure the Out-of-domain uncertainty in the prediction of Neural Networks using a statistical notion called ``Lens Depth'' (LD) combined with Fermat Distance, which is able to capture precisely the ``depth'' of a point with respect to a distribution in feature space, without any assumption about the form of distribution. Our method has no trainable parameter. The method is applicable to any classification model as it is applied directly in feature space at test time and does not intervene in training process. As such, it does not impact the performance of the original model. The proposed method gives excellent qualitative result on toy datasets and can give competitive or better uncertainty estimation on standard deep learning datasets compared to strong baseline methods.
Authors: Ahmad Halimi Razlighi, Carsten Bockelmann, Armin Dekorsy
Abstract: In this paper, we have expanded the current status of semantic communication limited to processing one task to a more general system that can handle multiple tasks concurrently. In pursuit of this, we first introduced our definition of the "semantic source", enabling the interpretation of multiple semantics based on a single observation. A semantic encoder design is then introduced, featuring the division of the encoder into a common unit and multiple specific units enabling cooperative multi-task processing. Simulation results demonstrate the effectiveness of the proposed semantic source and the system design. Our approach employs information maximization (infomax) and end-to-end design principles.
Authors: Haoran Qiu, Weichao Mao, Archit Patke, Shengkun Cui, Saurabh Jha, Chen Wang, Hubertus Franke, Zbigniew T. Kalbarczyk, Tamer Ba\c{s}ar, Ravishankar K. Iyer
Abstract: Large language models (LLMs) have been driving a new wave of interactive AI applications across numerous domains. However, efficiently serving LLM inference requests is challenging due to their unpredictable execution times originating from the autoregressive nature of generative models. Existing LLM serving systems exploit first-come-first-serve (FCFS) scheduling, suffering from head-of-line blocking issues. To address the non-deterministic nature of LLMs and enable efficient interactive LLM serving, we present a speculative shortest-job-first (SSJF) scheduler that uses a light proxy model to predict LLM output sequence lengths. Our open-source SSJF implementation does not require changes to memory management or batching strategies. Evaluations on real-world datasets and production workload traces show that SSJF reduces average job completion times by 30.5-39.6% and increases throughput by 2.2-3.6x compared to FCFS schedulers, across no batching, dynamic batching, and continuous batching settings.
Authors: Xuan Xie, Jiayang Song, Zhehua Zhou, Yuheng Huang, Da Song, Lei Ma
Abstract: While Large Language Models (LLMs) have seen widespread applications across numerous fields, their limited interpretability poses concerns regarding their safe operations from multiple aspects, e.g., truthfulness, robustness, and fairness. Recent research has started developing quality assurance methods for LLMs, introducing techniques such as offline detector-based or uncertainty estimation methods. However, these approaches predominantly concentrate on post-generation analysis, leaving the online safety analysis for LLMs during the generation phase an unexplored area. To bridge this gap, we conduct in this work a comprehensive evaluation of the effectiveness of existing online safety analysis methods on LLMs. We begin with a pilot study that validates the feasibility of detecting unsafe outputs in the early generation process. Following this, we establish the first publicly available benchmark of online safety analysis for LLMs, including a broad spectrum of methods, models, tasks, datasets, and evaluation metrics. Utilizing this benchmark, we extensively analyze the performance of state-of-the-art online safety analysis methods on both open-source and closed-source LLMs. This analysis reveals the strengths and weaknesses of individual methods and offers valuable insights into selecting the most appropriate method based on specific application scenarios and task requirements. Furthermore, we also explore the potential of using hybridization methods, i.e., combining multiple methods to derive a collective safety conclusion, to enhance the efficacy of online safety analysis for LLMs. Our findings indicate a promising direction for the development of innovative and trustworthy quality assurance methodologies for LLMs, facilitating their reliable deployments across diverse domains.
Authors: Tianyu Zhu, Myong Chol Jung, Jesse Clark
Abstract: Contrastive learning has gained widespread adoption for retrieval tasks due to its minimal requirement for manual annotations. However, popular contrastive frameworks typically learn from binary relevance, making them ineffective at incorporating direct fine-grained rankings. In this paper, we curate a large-scale dataset featuring detailed relevance scores for each query-document pair to facilitate future research and evaluation. Subsequently, we propose Generalized Contrastive Learning for Multi-Modal Retrieval and Ranking (GCL), which is designed to learn from fine-grained rankings beyond binary relevance scores. Our results show that GCL achieves a 94.5% increase in NDCG@10 for in-domain and 26.3 to 48.8% increases for cold-start evaluations, all relative to the CLIP baseline and involving ground truth rankings.
Authors: Josie Harrison, Alexander Hollberg, Yinan Yu
Abstract: Computer vision models trained on Google Street View images can create material cadastres. However, current approaches need manually annotated datasets that are difficult to obtain and often have class imbalance. To address these challenges, this paper fine-tuned a Swin Transformer model on a synthetic dataset generated with DALL-E and compared the performance to a similar manually annotated dataset. Although manual annotation remains the gold standard, the synthetic dataset performance demonstrates a reasonable alternative. The findings will ease annotation needed to develop material cadastres, offering architects insights into opportunities for material reuse, thus contributing to the reduction of demolition waste.
Authors: Litao Li, Steven H. H. Ding, Andrew Walenstein, Philippe Charland, Benjamin C. M. Fung
Abstract: Software vulnerabilities are a challenge in cybersecurity. Manual security patches are often difficult and slow to be deployed, while new vulnerabilities are created. Binary code vulnerability detection is less studied and more complex compared to source code, and this has important practical implications. Deep learning has become an efficient and powerful tool in the security domain, where it provides end-to-end and accurate prediction. Modern deep learning approaches learn the program semantics through sequence and graph neural networks, using various intermediate representation of programs, such as abstract syntax trees (AST) or control flow graphs (CFG). Due to the complex nature of program execution, the output of an execution depends on the many program states and inputs. Also, a CFG generated from static analysis can be an overestimation of the true program flow. Moreover, the size of programs often does not allow a graph neural network with fixed layers to aggregate global information. To address these issues, we propose DeepEXE, an agent-based implicit neural network that mimics the execution path of a program. We use reinforcement learning to enhance the branching decision at every program state transition and create a dynamic environment to learn the dependency between a vulnerability and certain program states. An implicitly defined neural network enables nearly infinite state transitions until convergence, which captures the structural information at a higher level. The experiments are conducted on two semi-synthetic and two real-world datasets. We show that DeepEXE is an accurate and efficient method and outperforms the state-of-the-art vulnerability detection methods.
Authors: Liu Yang, Qiang Li, Xiaoyang Ren, Yi Fang, Shafei Wang
Abstract: Radio Frequency Fingerprint Identification (RFFI), which exploits non-ideal hardware-induced unique distortion resident in the transmit signals to identify an emitter, is emerging as a means to enhance the security of communication systems. Recently, machine learning has achieved great success in developing state-of-the-art RFFI models. However, few works consider cross-receiver RFFI problems, where the RFFI model is trained and deployed on different receivers. Due to altered receiver characteristics, direct deployment of RFFI model on a new receiver leads to significant performance degradation. To address this issue, we formulate the cross-receiver RFFI as a model adaptation problem, which adapts the trained model to unlabeled signals from a new receiver. We first develop a theoretical generalization error bound for the adaptation model. Motivated by the bound, we propose a novel method to solve the cross-receiver RFFI problem, which includes domain alignment and adaptive pseudo-labeling. The former aims at finding a feature space where both domains exhibit similar distributions, effectively reducing the domain discrepancy. Meanwhile, the latter employs a dynamic pseudo-labeling scheme to implicitly transfer the label information from the labeled receiver to the new receiver. Experimental results indicate that the proposed method can effectively mitigate the receiver impact and improve the cross-receiver RFFI performance.
Authors: Hanlin Tian, Kethan Reddy, Yuxiang Feng, Mohammed Quddus, Yiannis Demiris, Panagiotis Angeloudis
Abstract: This paper introduces CRITICAL, a novel closed-loop framework for autonomous vehicle (AV) training and testing. CRITICAL stands out for its ability to generate diverse scenarios, focusing on critical driving situations that target specific learning and performance gaps identified in the Reinforcement Learning (RL) agent. The framework achieves this by integrating real-world traffic dynamics, driving behavior analysis, surrogate safety measures, and an optional Large Language Model (LLM) component. It is proven that the establishment of a closed feedback loop between the data generation pipeline and the training process can enhance the learning rate during training, elevate overall system performance, and augment safety resilience. Our evaluations, conducted using the Proximal Policy Optimization (PPO) and the HighwayEnv simulation environment, demonstrate noticeable performance improvements with the integration of critical case generation and LLM analysis, indicating CRITICAL's potential to improve the robustness of AV systems and streamline the generation of critical scenarios. This ultimately serves to hasten the development of AV agents, expand the general scope of RL training, and ameliorate validation efforts for AV safety.
Authors: William Gantt, Aaron Steven White
Abstract: Effective ontology transfer has been a major goal of recent work on event argument extraction (EAE). Two methods in particular -- question answering (QA) and template infilling (TI) -- have emerged as promising approaches to this problem. However, detailed explorations of these techniques' ability to actually enable this transfer are lacking. In this work, we provide such a study, exploring zero-shot transfer using both techniques on six major EAE datasets at both the sentence and document levels. Further, we challenge the growing reliance on LLMs for zero-shot extraction, showing that vastly smaller models trained on an appropriate source ontology can yield zero-shot performance superior to that of GPT-3.5 or GPT-4.
Authors: Lorenzo Bardone, Sebastian Goldt
Abstract: Neural networks extract features from data using stochastic gradient descent (SGD). In particular, higher-order input cumulants (HOCs) are crucial for their performance. However, extracting information from the $p$th cumulant of $d$-dimensional inputs is computationally hard: the number of samples required to recover a single direction from an order-$p$ tensor (tensor PCA) using online SGD grows as $d^{p-1}$, which is prohibitive for high-dimensional inputs. This result raises the question of how neural networks extract relevant directions from the HOCs of their inputs efficiently. Here, we show that correlations between latent variables along the directions encoded in different input cumulants speed up learning from higher-order correlations. We show this effect analytically by deriving nearly sharp thresholds for the number of samples required by a single neuron to weakly-recover these directions using online SGD from a random start in high dimensions. Our analytical results are confirmed in simulations of two-layer neural networks and unveil a new mechanism for hierarchical learning in neural networks.
Authors: Mingmeng Geng, Roberto Trotta
Abstract: Based on one million arXiv papers submitted from May 2018 to January 2024, we assess the textual density of ChatGPT's writing style in their abstracts by means of a statistical analysis of word frequency changes. Our model is calibrated and validated on a mixture of real abstracts and ChatGPT-modified abstracts (simulated data) after a careful noise analysis. We find that ChatGPT is having an increasing impact on arXiv abstracts, especially in the field of computer science, where the fraction of ChatGPT-revised abstracts is estimated to be approximately 35%, if we take the output of one of the simplest prompts, "revise the following sentences", as a baseline. We conclude with an analysis of both positive and negative aspects of the penetration of ChatGPT into academics' writing style.
Authors: Sunny Sanyal, Sujay Sanghavi, Alexandros G. Dimakis
Abstract: We study the effectiveness of a simple approach to develop a small base language model (LM) starting from an existing large base LM: first inherit a few transformer blocks from the larger LM, and then train this smaller model on a very small subset (0.1\%) of the raw pretraining data of the larger model. We call our simple recipe Inheritune and first demonstrate it for building a small base LM with 1.5B parameters using 1B tokens (and a starting few layers of larger LM of 3B parameters); we do this using a single A6000 GPU for less than half a day. Across 9 diverse evaluation datasets as well as the MMLU benchmark, the resulting model compares favorably to publicly available base models of 1B-2B size, some of which have been trained using 50-1000 times more tokens. We investigate Inheritune in a slightly different setting where we train small LMs utilizing larger LMs and their full pre-training dataset. Here we show that smaller LMs trained utilizing some of the layers of GPT2-medium (355M) and GPT-2-large (770M) can effectively match the val loss of their bigger counterparts when trained from scratch for the same number of training steps on OpenWebText dataset with 9B tokens. We analyze our recipe with extensive experiments and demonstrate it efficacy on diverse settings. Our code is available at https://github.com/sanyalsunny111/LLM-Inheritune.
Authors: Robin Winter, Marco Bertolini, Tuan Le, Frank No\'e, Djork-Arn\'e Clevert
Abstract: Equivariant neural networks, whose hidden features transform according to representations of a group G acting on the data, exhibit training efficiency and an improved generalisation performance. In this work, we extend group invariant and equivariant representation learning to the field of unsupervised deep learning. We propose a general learning strategy based on an encoder-decoder framework in which the latent representation is separated in an invariant term and an equivariant group action component. The key idea is that the network learns to encode and decode data to and from a group-invariant representation by additionally learning to predict the appropriate group action to align input and output pose to solve the reconstruction task. We derive the necessary conditions on the equivariant encoder, and we present a construction valid for any G, both discrete and continuous. We describe explicitly our construction for rotations, translations and permutations. We test the validity and the robustness of our approach in a variety of experiments with diverse data types employing different network architectures.
Authors: Gangshan Jing, He Bai, Jemin George, Aranya Chakrabortty, Piyush K. Sharma
Abstract: Achieving distributed reinforcement learning (RL) for large-scale cooperative multi-agent systems (MASs) is challenging because: (i) each agent has access to only limited information; (ii) issues on convergence or computational complexity emerge due to the curse of dimensionality. In this paper, we propose a general computationally efficient distributed framework for cooperative multi-agent reinforcement learning (MARL) by utilizing the structures of graphs involved in this problem. We introduce three coupling graphs describing three types of inter-agent couplings in MARL, namely, the state graph, the observation graph and the reward graph. By further considering a communication graph, we propose two distributed RL approaches based on local value-functions derived from the coupling graphs. The first approach is able to reduce sample complexity significantly under specific conditions on the aforementioned four graphs. The second approach provides an approximate solution and can be efficient even for problems with dense coupling graphs. Here there is a trade-off between minimizing the approximation error and reducing the computational complexity. Simulations show that our RL algorithms have a significantly improved scalability to large-scale MASs compared with centralized and consensus-based distributed RL algorithms.
Authors: Neville K Kitson, Anthony C Constantinou
Abstract: Causal Bayesian Networks provide an important tool for reasoning under uncertainty with potential application to many complex causal systems. Structure learning algorithms that can tell us something about the causal structure of these systems are becoming increasingly important. In the literature, the validity of these algorithms is often tested for sensitivity over varying sample sizes, hyper-parameters, and occasionally objective functions. In this paper, we show that the order in which the variables are read from data can have much greater impact on the accuracy of the algorithm than these factors. Because the variable ordering is arbitrary, any significant effect it has on learnt graph accuracy is concerning, and this raises questions about the validity of the results produced by algorithms that are sensitive to, but have not been assessed against, different variable orderings.
Authors: Yakov Medvedovsky, Eran Treister, Tirza Routtenberg
Abstract: The Laplacian-constrained Gaussian Markov Random Field (LGMRF) is a common multivariate statistical model for learning a weighted sparse dependency graph from given data. This graph learning problem can be formulated as a maximum likelihood estimation (MLE) of the precision matrix, subject to Laplacian structural constraints, with a sparsity-inducing penalty term. This paper aims to solve this learning problem accurately and efficiently. First, since the commonly used $\ell_1$-norm penalty is inappropriate in this setting and may lead to a complete graph, we employ the nonconvex minimax concave penalty (MCP), which promotes sparse solutions with lower estimation bias. Second, as opposed to existing first-order methods for this problem, we develop a second-order proximal Newton approach to obtain an efficient solver, utilizing several algorithmic features, such as using Conjugate Gradients, preconditioning, and splitting to active/free sets. Numerical experiments demonstrate the advantages of the proposed method in terms of both computational complexity and graph learning accuracy compared to existing methods.
Authors: Wenhao Yuan, Xuehe Wang
Abstract: Federated Learning (FL) has emerged as a pivotal paradigm within distributed model training, facilitating collaboration among multiple devices to refine a shared model, harnessing their respective datasets as orchestrated by a central server, while ensuring the localization of private data. Nonetheless, the non-independent-and-identically-distributed (Non-IID) data generated on heterogeneous clients and the incessant information exchange among participants may markedly impede training efficacy and retard the convergence rate. In this paper, we refine the conventional stochastic gradient descent (SGD) methodology by introducing aggregated gradients at each local training epoch and propose an adaptive learning rate iterative algorithm that concerns the divergence between local and average parameters. To surmount the obstacle that acquiring other clients' local information, we introduce the mean-field approach by leveraging two mean-field terms to approximately estimate the average local parameters and gradients over time in a manner that precludes the need for local information exchange among clients and design the decentralized adaptive learning rate for each client. Through meticulous theoretical analysis, we provide a robust convergence guarantee for our proposed algorithm and ensure its wide applicability. Our numerical experiments substantiate the superiority of our framework in comparison with existing state-of-the-art FL strategies for enhancing model performance and accelerating convergence rate under IID and Non-IID data distributions.
Authors: Hao Qin, Kwang-Sung Jun, Chicheng Zhang
Abstract: We study $K$-armed bandit problems where the reward distributions of the arms are all supported on the $[0,1]$ interval. It has been a challenge to design regret-efficient randomized exploration algorithms in this setting. Maillard sampling \cite{maillard13apprentissage}, an attractive alternative to Thompson sampling, has recently been shown to achieve competitive regret guarantees in the sub-Gaussian reward setting \cite{bian2022maillard} while maintaining closed-form action probabilities, which is useful for offline policy evaluation. In this work, we propose the Kullback-Leibler Maillard Sampling (KL-MS) algorithm, a natural extension of Maillard sampling for achieving KL-style gap-dependent regret bound. We show that KL-MS enjoys the asymptotic optimality when the rewards are Bernoulli and has a worst-case regret bound of the form $O(\sqrt{\mu^*(1-\mu^*) K T \ln K} + K \ln T)$, where $\mu^*$ is the expected reward of the optimal arm, and $T$ is the time horizon length.
Authors: Jiayi Huang, Sangwoo Park, Osvaldo Simeone
Abstract: Deep learning models, including modern systems like large language models, are well known to offer unreliable estimates of the uncertainty of their decisions. In order to improve the quality of the confidence levels, also known as calibration, of a model, common approaches entail the addition of either data-dependent or data-independent regularization terms to the training loss. Data-dependent regularizers have been recently introduced in the context of conventional frequentist learning to penalize deviations between confidence and accuracy. In contrast, data-independent regularizers are at the core of Bayesian learning, enforcing adherence of the variational distribution in the model parameter space to a prior density. The former approach is unable to quantify epistemic uncertainty, while the latter is severely affected by model misspecification. In light of the limitations of both methods, this paper proposes an integrated framework, referred to as calibration-aware Bayesian neural networks (CA-BNNs), that applies both regularizers while optimizing over a variational distribution as in Bayesian learning. Numerical results validate the advantages of the proposed approach in terms of expected calibration error (ECE) and reliability diagrams.
Authors: Laixi Shi, Gen Li, Yuting Wei, Yuxin Chen, Matthieu Geist, Yuejie Chi
Abstract: This paper investigates model robustness in reinforcement learning (RL) to reduce the sim-to-real gap in practice. We adopt the framework of distributionally robust Markov decision processes (RMDPs), aimed at learning a policy that optimizes the worst-case performance when the deployed environment falls within a prescribed uncertainty set around the nominal MDP. Despite recent efforts, the sample complexity of RMDPs remained mostly unsettled regardless of the uncertainty set in use. It was unclear if distributional robustness bears any statistical consequences when benchmarked against standard RL. Assuming access to a generative model that draws samples based on the nominal MDP, we characterize the sample complexity of RMDPs when the uncertainty set is specified via either the total variation (TV) distance or $\chi^2$ divergence. The algorithm studied here is a model-based method called {\em distributionally robust value iteration}, which is shown to be near-optimal for the full range of uncertainty levels. Somewhat surprisingly, our results uncover that RMDPs are not necessarily easier or harder to learn than standard MDPs. The statistical consequence incurred by the robustness requirement depends heavily on the size and shape of the uncertainty set: in the case w.r.t.~the TV distance, the minimax sample complexity of RMDPs is always smaller than that of standard MDPs; in the case w.r.t.~the $\chi^2$ divergence, the sample complexity of RMDPs can often far exceed the standard MDP counterpart.
Authors: Steven Braun, Martin Mundt, Kristian Kersting
Abstract: Access to pre-trained models has recently emerged as a standard across numerous machine learning domains. Unfortunately, access to the original data the models were trained on may not equally be granted. This makes it tremendously challenging to fine-tune, compress models, adapt continually, or to do any other type of data-driven update. We posit that original data access may however not be required. Specifically, we propose Contrastive Abductive Knowledge Extraction (CAKE), a model-agnostic knowledge distillation procedure that mimics deep classifiers without access to the original data. To this end, CAKE generates pairs of noisy synthetic samples and diffuses them contrastively toward a model's decision boundary. We empirically corroborate CAKE's effectiveness using several benchmark datasets and various architectural choices, paving the way for broad application.
Authors: Wei Cui, Wei Yu
Abstract: In reinforcement learning, the objective is almost always defined as a \emph{cumulative} function over the rewards along the process. However, there are many optimal control and reinforcement learning problems in various application fields, especially in communications and networking, where the objectives are not naturally expressed as summations of the rewards. In this paper, we recognize the prevalence of non-cumulative objectives in various problems, and propose a modification to existing algorithms for optimizing such objectives. Specifically, we dive into the fundamental building block for many optimal control and reinforcement learning algorithms: the Bellman optimality equation. To optimize a non-cumulative objective, we replace the original summation operation in the Bellman update rule with a generalized operation corresponding to the objective. Furthermore, we provide sufficient conditions on the form of the generalized operation as well as assumptions on the Markov decision process under which the globally optimal convergence of the generalized Bellman updates can be guaranteed. We demonstrate the idea experimentally with the bottleneck objective, i.e., the objectives determined by the minimum reward along the process, on classical optimal control and reinforcement learning tasks, as well as on two network routing problems on maximizing the flow rates.
Authors: Albert Yu Sun, Eliott Zemour, Arushi Saxena, Udith Vaidyanathan, Eric Lin, Christian Lau, Vaikkunth Mugunthan
Abstract: Machine learning practitioners often fine-tune generative pre-trained models like GPT-3 to improve model performance at specific tasks. Previous works, however, suggest that fine-tuned machine learning models memorize and emit sensitive information from the original fine-tuning dataset. Companies such as OpenAI offer fine-tuning services for their models, but no prior work has conducted a memorization attack on any closed-source models. In this work, we simulate a privacy attack on GPT-3 using OpenAI's fine-tuning API. Our objective is to determine if personally identifiable information (PII) can be extracted from this model. We (1) explore the use of naive prompting methods on a GPT-3 fine-tuned classification model, and (2) we design a practical word generation task called Autocomplete to investigate the extent of PII memorization in fine-tuned GPT-3 within a real-world context. Our findings reveal that fine-tuning GPT3 for both tasks led to the model memorizing and disclosing critical personally identifiable information (PII) obtained from the underlying fine-tuning dataset. To encourage further research, we have made our codes and datasets publicly available on GitHub at: https://github.com/albertsun1/gpt3-pii-attacks
Authors: Hwan Kim, Junghoon Kim, Byung Suk Lee, Sungsu Lim
Abstract: Graph anomaly detection has attracted considerable attention from various domain ranging from network security to finance in recent years. Due to the fact that labeling is very costly, existing methods are predominately developed in an unsupervised manner. However, the detected anomalies may be found out uninteresting instances due to the absence of prior knowledge regarding the anomalies looking for. This issue may be solved by using few labeled anomalies as prior knowledge. In real-world scenarios, we can easily obtain few labeled anomalies. Efficiently leveraging labelled anomalies as prior knowledge is crucial for graph anomaly detection; however, this process remains challenging due to the inherently limited number of anomalies available. To address the problem, we propose a novel approach that leverages metapath to embed actual connectivity patterns between anomalous and normal nodes. To further efficiently exploit context information from metapath-based anomaly subgraph, we present a new framework, Metapath-based Graph Anomaly Detection (MGAD), incorporating GCN layers in both the dual-encoders and decoders to efficiently propagate context information between abnormal and normal nodes. Specifically, MGAD employs GNN-based graph autoencoder as its backbone network. Moreover, dual encoders capture the complex interactions and metapath-based context information between labeled and unlabeled nodes both globally and locally. Through a comprehensive set of experiments conducted on seven real-world networks, this paper demonstrates the superiority of the MGAD method compared to state-of-the-art techniques. The code is available at https://github.com/missinghwan/MGAD.
Authors: Mingyuan Zhang, Ambuj Tewari
Abstract: In online ranking, a learning algorithm sequentially ranks a set of items and receives feedback on its ranking in the form of relevance scores. Since obtaining relevance scores typically involves human annotation, it is of great interest to consider a partial feedback setting where feedback is restricted to the top-$k$ items in the rankings. Chaudhuri and Tewari [2017] developed a framework to analyze online ranking algorithms with top $k$ feedback. A key element in their work was the use of techniques from partial monitoring. In this paper, we further investigate online ranking with top $k$ feedback and solve some open problems posed by Chaudhuri and Tewari [2017]. We provide a full characterization of minimax regret rates with the top $k$ feedback model for all $k$ and for the following ranking performance measures: Pairwise Loss, Discounted Cumulative Gain, and Precision@n. In addition, we give an efficient algorithm that achieves the minimax regret rate for Precision@n.
Authors: Vincent Lemaire, Nathan Le Boudec, Victor Guyomard, Fran\c{c}oise Fessant
Abstract: There are now many explainable AI methods for understanding the decisions of a machine learning model. Among these are those based on counterfactual reasoning, which involve simulating features changes and observing the impact on the prediction. This article proposes to view this simulation process as a source of creating a certain amount of knowledge that can be stored to be used, later, in different ways. This process is illustrated in the additive model and, more specifically, in the case of the naive Bayes classifier, whose interesting properties for this purpose are shown.
Authors: Dong Bok Lee, Seanie Lee, Joonho Ko, Kenji Kawaguchi, Juho Lee, Sung Ju Hwang
Abstract: Dataset distillation methods have achieved remarkable success in distilling a large dataset into a small set of representative samples. However, they are not designed to produce a distilled dataset that can be effectively used for facilitating self-supervised pre-training. To this end, we propose a novel problem of distilling an unlabeled dataset into a set of small synthetic samples for efficient self-supervised learning (SSL). We first prove that a gradient of synthetic samples with respect to a SSL objective in naive bilevel optimization is \textit{biased} due to the randomness originating from data augmentations or masking. To address this issue, we propose to minimize the mean squared error (MSE) between a model's representations of the synthetic examples and their corresponding learnable target feature representations for the inner objective, which does not introduce any randomness. Our primary motivation is that the model obtained by the proposed inner optimization can mimic the \textit{self-supervised target model}. To achieve this, we also introduce the MSE between representations of the inner model and the self-supervised target model on the original full dataset for outer optimization. Lastly, assuming that a feature extractor is fixed, we only optimize a linear head on top of the feature extractor, which allows us to reduce the computational cost and obtain a closed-form solution of the head with kernel ridge regression. We empirically validate the effectiveness of our method on various applications involving transfer learning.
Authors: William Merrill, Ashish Sabharwal
Abstract: Recent theoretical work has identified surprisingly simple reasoning problems, such as checking if two nodes in a graph are connected or simulating finite-state machines, that are provably unsolvable by standard transformers that answer immediately after reading their input. However, in practice, transformers' reasoning can be improved by allowing them to use a "chain of thought" or "scratchpad", i.e., generate and condition on a sequence of intermediate tokens before answering. Motivated by this, we ask: Does such intermediate generation fundamentally extend the computational power of a decoder-only transformer? We show that the answer is yes, but the amount of increase depends crucially on the amount of intermediate generation. For instance, we find that transformer decoders with a logarithmic number of decoding steps (w.r.t. the input length) push the limits of standard transformers only slightly, while a linear number of decoding steps, assuming projected pre-norm (a slight generalization of standard pre-norm), adds a clear new ability (under standard complexity conjectures): recognizing all regular languages. Our results also imply that linear steps keep transformer decoders within context-sensitive languages, and polynomial steps with generalized pre-norm make them recognize exactly the class of polynomial-time solvable problems -- the first exact characterization of a type of transformers in terms of standard complexity classes. Together, this provides a nuanced framework for understanding how the length of a transformer's chain of thought or scratchpad impacts its reasoning power.
Authors: Runqi Lin, Chaojian Yu, Bo Han, Tongliang Liu
Abstract: Overfitting negatively impacts the generalization ability of deep neural networks (DNNs) in both natural and adversarial training. Existing methods struggle to consistently address different types of overfitting, typically designing strategies that focus separately on either natural or adversarial patterns. In this work, we adopt a unified perspective by solely focusing on natural patterns to explore different types of overfitting. Specifically, we examine the memorization effect in DNNs and reveal a shared behaviour termed over-memorization, which impairs their generalization capacity. This behaviour manifests as DNNs suddenly becoming high-confidence in predicting certain training patterns and retaining a persistent memory for them. Furthermore, when DNNs over-memorize an adversarial pattern, they tend to simultaneously exhibit high-confidence prediction for the corresponding natural pattern. These findings motivate us to holistically mitigate different types of overfitting by hindering the DNNs from over-memorization training patterns. To this end, we propose a general framework, Distraction Over-Memorization (DOM), which explicitly prevents over-memorization by either removing or augmenting the high-confidence natural patterns. Extensive experiments demonstrate the effectiveness of our proposed method in mitigating overfitting across various training paradigms.
Authors: Shiyu Shen, Bin Pan, Tianyang Shi, Tao Li, Zhenwei Shi
Abstract: Bayesian Neural Networks (BNNs) have become one of the promising approaches for uncertainty estimation due to the solid theorical foundations. However, the performance of BNNs is affected by the ability of catching uncertainty. Instead of only seeking the distribution of neural network weights by in-distribution (ID) data, in this paper, we propose a new Bayesian Neural Network with an Attached structure (ABNN) to catch more uncertainty from out-of-distribution (OOD) data. We first construct a mathematical description for the uncertainty of OOD data according to the prior distribution, and then develop an attached Bayesian structure to integrate the uncertainty of OOD data into the backbone network. ABNN is composed of an expectation module and several distribution modules. The expectation module is a backbone deep network which focuses on the original task, and the distribution modules are mini Bayesian structures which serve as attachments of the backbone. In particular, the distribution modules aim at extracting the uncertainty from both ID and OOD data. We further provide theoretical analysis for the convergence of ABNN, and experimentally validate its superiority by comparing with some state-of-the-art uncertainty estimation methods Code will be made available.
Authors: Xinran Gu, Kaifeng Lyu, Sanjeev Arora, Jingzhao Zhang, Longbo Huang
Abstract: In distributed deep learning with data parallelism, synchronizing gradients at each training step can cause a huge communication overhead, especially when many nodes work together to train large models. Local gradient methods, such as Local SGD, address this issue by allowing workers to compute locally for $H$ steps without synchronizing with others, hence reducing communication frequency. While $H$ has been viewed as a hyperparameter to trade optimization efficiency for communication cost, recent research indicates that setting a proper $H$ value can lead to generalization improvement. Yet, selecting a proper $H$ is elusive. This work proposes a theory-grounded method for determining $H$, named the Quadratic Synchronization Rule (QSR), which recommends dynamically setting $H$ in proportion to $\frac{1}{\eta^2}$ as the learning rate $\eta$ decays over time. Extensive ImageNet experiments on ResNet and ViT show that local gradient methods with QSR consistently improve the test accuracy over other synchronization strategies. Compared with the standard data parallel training, QSR enables Local AdamW on ViT-B to cut the training time on 16 or 64 GPUs down from 26.7 to 20.2 hours or from 8.6 to 5.5 hours and, at the same time, achieves $1.16\%$ or $0.84\%$ higher top-1 validation accuracy.
Authors: Tim Reichelt, Luke Ong, Tom Rainforth
Abstract: The posterior in probabilistic programs with stochastic support decomposes as a weighted sum of the local posterior distributions associated with each possible program path. We show that making predictions with this full posterior implicitly performs a Bayesian model averaging (BMA) over paths. This is potentially problematic, as BMA weights can be unstable due to model misspecification or inference approximations, leading to sub-optimal predictions in turn. To remedy this issue, we propose alternative mechanisms for path weighting: one based on stacking and one based on ideas from PAC-Bayes. We show how both can be implemented as a cheap post-processing step on top of existing inference engines. In our experiments, we find them to be more robust and lead to better predictions compared to the default BMA weights.
Authors: Xiaomin Ouyang, Xian Shuai, Yang Li, Li Pan, Xifan Zhang, Heming Fu, Sitong Cheng, Xinyan Wang, Shihua Cao, Jiang Xin, Hazel Mok, Zhenyu Yan, Doris Sau Fung Yu, Timothy Kwok, Guoliang Xing
Abstract: Alzheimer's Disease (AD) and related dementia are a growing global health challenge due to the aging population. In this paper, we present ADMarker, the first end-to-end system that integrates multi-modal sensors and new federated learning algorithms for detecting multidimensional AD digital biomarkers in natural living environments. ADMarker features a novel three-stage multi-modal federated learning architecture that can accurately detect digital biomarkers in a privacy-preserving manner. Our approach collectively addresses several major real-world challenges, such as limited data labels, data heterogeneity, and limited computing resources. We built a compact multi-modality hardware system and deployed it in a four-week clinical trial involving 91 elderly participants. The results indicate that ADMarker can accurately detect a comprehensive set of digital biomarkers with up to 93.8% accuracy and identify early AD with an average of 88.9% accuracy. ADMarker offers a new platform that can allow AD clinicians to characterize and track the complex correlation between multidimensional interpretable digital biomarkers, demographic factors of patients, and AD diagnosis in a longitudinal manner.
Authors: Viggo Moro, Charlotte Loh, Rumen Dangovski, Ali Ghorashi, Andrew Ma, Zhuo Chen, Samuel Kim, Peter Y. Lu, Thomas Christensen, Marin Solja\v{c}i\'c
Abstract: Artificial intelligence is transforming computational materials science, improving the prediction of material properties, and accelerating the discovery of novel materials. Recently, publicly available material data repositories have grown rapidly. This growth encompasses not only more materials, but also a greater variety and quantity of their associated properties. Existing machine learning efforts in materials science focus primarily on single-modality tasks, i.e., relationships between materials and a single physical property, thus not taking advantage of the rich and multimodal set of material properties. Here, we introduce Multimodal Learning for Materials (MultiMat), which enables self-supervised multi-modality training of foundation models for materials. We demonstrate our framework's potential using data from the Materials Project database on multiple axes: (i) MultiMat achieves state-of-the-art performance for challenging material property prediction tasks; (ii) MultiMat enables novel and accurate material discovery via latent space similarity, enabling screening for stable materials with desired properties; and (iii) MultiMat encodes interpretable emergent features that may provide novel scientific insights.
Authors: Boris N. Slautin, Yongtao Liu, Hiroshi Funakubo, Sergei V. Kalinin
Abstract: The current focus in Autonomous Experimentation (AE) is on developing robust workflows to conduct the AE effectively. This entails the need for well-defined approaches to guide the AE process, including strategies for hyperparameter tuning and high-level human interventions within the workflow loop. This paper presents a comprehensive analysis of the influence of initial experimental conditions and in-loop interventions on the learning dynamics of Deep Kernel Learning (DKL) within the realm of AE in Scanning Probe Microscopy. We explore the concept of 'seed effect', where the initial experiment setup has a substantial impact on the subsequent learning trajectory. Additionally, we introduce an approach of the seed point interventions in AE allowing the operator to influence the exploration process. Using a dataset from Piezoresponse Force Microscopy (PFM) on PbTiO3 thin films, we illustrate the impact of the 'seed effect' and in-loop seed interventions on the effectiveness of DKL in predicting material properties. The study highlights the importance of initial choices and adaptive interventions in optimizing learning rates and enhancing the efficiency of automated material characterization. This work offers valuable insights into designing more robust and effective AE workflows in microscopy with potential applications across various characterization techniques. The analysis code that supports the funding is publicly available at https://github.com/Slautin/2024_Seed_effect_DKL_BO.
Authors: Philip Quirke, Clement Neo, Fazl Barez
Abstract: Language Models (LMs) are increasingly used for a wide range of prediction tasks, but their training can often neglect rare edge cases, reducing their reliability. Here, we define a stringent standard of trustworthiness whereby the task algorithm and circuit implementation must be verified, accounting for edge cases, with no known failure modes. We show that a transformer model can be trained to meet this standard if built using mathematically and logically specified frameworks. In this paper, we fully verify a model for n-digit integer addition. To exhibit the reusability of verified modules, we insert the trained integer addition model into an untrained model and train the combined model to perform both addition and subtraction. We find extensive reuse of the addition circuits for both tasks, easing verification of the more complex subtractor model. We discuss how inserting verified task modules into LMs can leverage model reuse to improve verifiability and trustworthiness of language models built using them. The reuse of verified circuits reduces the effort to verify more complex composite models which we believe to be a significant step towards safety of language models.
Authors: Fei Liu, Xi Lin, Zhenkun Wang, Qingfu Zhang, Xialiang Tong, Mingxuan Yuan
Abstract: Vehicle routing problems (VRPs), which can be found in numerous real-world applications, have been an important research topic for several decades. Recently, the neural combinatorial optimization (NCO) approach that leverages a learning-based model to solve VRPs without manual algorithm design has gained substantial attention. However, current NCO methods typically require building one model for each routing problem, which significantly hinders their practical application for real-world industry problems with diverse attributes. In this work, we make the first attempt to tackle the crucial challenge of cross-problem generalization. In particular, we formulate VRPs as different combinations of a set of shared underlying attributes and solve them simultaneously via a single model through attribute composition. In this way, our proposed model can successfully solve VRPs with unseen attribute combinations in a zero-shot generalization manner. Extensive experiments are conducted on eleven VRP variants, benchmark datasets, and industry logistic scenarios. The results show that the unified model demonstrates superior performance in the eleven VRPs, reducing the average gap to around 5% from over 20% in the existing approach and achieving a significant performance boost on benchmark datasets as well as a real-world logistics application. The source code is included in https://github.com/FeiLiu36/MTNCO.
Authors: Sayak Ray Chowdhury, Anush Kini, Nagarajan Natarajan
Abstract: Learning from preference-based feedback has recently gained traction as a promising approach to align language models with human interests. While these aligned generative models have demonstrated impressive capabilities across various tasks, their dependence on high-quality human preference data poses a bottleneck in practical applications. Specifically, noisy (incorrect and ambiguous) preference pairs in the dataset might restrict the language models from capturing human intent accurately. While practitioners have recently proposed heuristics to mitigate the effect of noisy preferences, a complete theoretical understanding of their workings remain elusive. In this work, we aim to bridge this gap by by introducing a general framework for policy optimization in the presence of random preference flips. We focus on the direct preference optimization (DPO) algorithm in particular since it assumes that preferences adhere to the Bradley-Terry-Luce (BTL) model, raising concerns about the impact of noisy data on the learned policy. We design a novel loss function, which de-bias the effect of noise on average, making a policy trained by minimizing that loss robust to the noise. Under log-linear parameterization of the policy class and assuming good feature coverage of the SFT policy, we prove that the sub-optimality gap of the proposed robust DPO (rDPO) policy compared to the optimal policy is of the order $O(\frac{1}{1-2\epsilon}\sqrt{\frac{d}{n}})$, where $\epsilon < 1/2$ is flip rate of labels, $d$ is policy parameter dimension and $n$ is size of dataset. Our experiments on IMDb sentiment generation and Anthropic's helpful-harmless dataset show that rDPO is robust to noise in preference labels compared to vanilla DPO and other heuristics proposed by practitioners.
Authors: Abhishek Ghose, Emma Nguyen
Abstract: Active learning (AL) techniques aim to maximally utilize a labeling budget by iteratively selecting instances that are most likely to improve prediction accuracy. However, their benefit compared to random sampling has not been consistent across various setups, e.g., different datasets, classifiers. In this empirical study, we examine how a combination of different factors might obscure any gains from an AL technique. Focusing on text classification, we rigorously evaluate AL techniques over around 1000 experiments that vary wrt the dataset, batch size, text representation and the classifier. We show that AL is only effective in a narrow set of circumstances. We also address the problem of using metrics that are better aligned with real world expectations. The impact of this study is in its insights for a practitioner: (a) the choice of text representation and classifier is as important as that of an AL technique, (b) choice of the right metric is critical in assessment of the latter, and, finally, (c) reported AL results must be holistically interpreted, accounting for variables other than just the query strategy.
Authors: Wei Cui, Wei Yu
Abstract: In most applications of utilizing neural networks for mathematical optimization, a dedicated model is trained for each specific optimization objective. However, in many scenarios, several distinct yet correlated objectives or tasks often need to be optimized on the same set of problem inputs. Instead of independently training a different neural network for each problem separately, it would be more efficient to exploit the correlations between these objectives and to train multiple neural network models with shared model parameters and feature representations. To achieve this, this paper first establishes the concept of common information: the shared knowledge required for solving the correlated tasks, then proposes a novel approach for model training by adding into the model an additional reconstruction stage associated with a new reconstruction loss. This loss is for reconstructing the common information starting from a selected hidden layer in the model. The proposed approach encourages the learned features to be general and transferable, and therefore can be readily used for efficient transfer learning. For numerical simulations, three applications are studied: transfer learning on classifying MNIST handwritten digits, the device-to-device wireless network power allocation, and the multiple-input-single-output network downlink beamforming and localization. Simulation results suggest that the proposed approach is highly efficient in data and model complexity, is resilient to over-fitting, and has competitive performances.
Authors: Zhenyu Qian, Yiming Qian, Yuting Song, Fei Gao, Hai Jin, Chen Yu, Xia Xie
Abstract: Handling graph data is one of the most difficult tasks. Traditional techniques, such as those based on geometry and matrix factorization, rely on assumptions about the data relations that become inadequate when handling large and complex graph data. On the other hand, deep learning approaches demonstrate promising results in handling large graph data, but they often fall short of providing interpretable explanations. To equip the graph processing with both high accuracy and explainability, we introduce a novel approach that harnesses the power of a large language model (LLM), enhanced by an uncertainty-aware module to provide a confidence score on the generated answer. We experiment with our approach on two graph processing tasks: few-shot knowledge graph completion and graph classification. Our results demonstrate that through parameter efficient fine-tuning, the LLM surpasses state-of-the-art algorithms by a substantial margin across ten diverse benchmark datasets. Moreover, to address the challenge of explainability, we propose an uncertainty estimation based on perturbation, along with a calibration scheme to quantify the confidence scores of the generated answers. Our confidence measure achieves an AUC of 0.8 or higher on seven out of the ten datasets in predicting the correctness of the answer generated by LLM.
Authors: Kleanthis Malialis, Jin Li, Christos G. Panayiotou, Marios M. Polycarpou
Abstract: Data stream mining aims at extracting meaningful knowledge from continually evolving data streams, addressing the challenges posed by nonstationary environments, particularly, concept drift which refers to a change in the underlying data distribution over time. Graph structures offer a powerful modelling tool to represent complex systems, such as, critical infrastructure systems and social networks. Learning from graph streams becomes a necessity to understand the dynamics of graph structures and to facilitate informed decision-making. This work introduces a novel method for graph stream classification which operates under the general setting where a data generating process produces graphs with varying nodes and edges over time. The method uses incremental learning for continual model adaptation, selecting representative graphs (prototypes) for each class, and creating graph embeddings. Additionally, it incorporates a loss-based concept drift detection mechanism to recalculate graph prototypes when drift is detected.
Authors: Christian Marius Lillelund, Martin Magris, Christian Fischer Pedersen
Abstract: Predicting future events always comes with uncertainty, but traditional non-probabilistic methods cannot distinguish certain from uncertain predictions. In survival analysis, probabilistic methods applied to state-of-the-art solutions in the healthcare and biomedical field are still novel, and their implications have not been fully evaluated. In this paper, we study the benefits of modeling uncertainty in deep neural networks for survival analysis with a focus on prediction and calibration performance. For this, we present a Bayesian deep learning framework that consists of three probabilistic network architectures, which we train by optimizing the Cox partial likelihood and combining input-dependent aleatoric uncertainty together with epistemic uncertainty. This enables us to provide uncertainty estimates as credible intervals when predicting the survival curve or as a probability density function over the predicted median survival times. For our empirical analyses, we evaluated our proposed method on four benchmark datasets and found that our method demonstrates prediction performance comparable to the state-of-the-art based on the concordance index and outperforms all other Cox-based approaches in terms of the mean absolute error. Our work explicitly compares the extent to which different Bayesian approximation techniques differ from each other and improves the prediction over traditional non-probabilistic alternatives.
Authors: Lanpei Li, Elia Piccoli, Andrea Cossu, Davide Bacciu, Vincenzo Lomonaco
Abstract: Continual Learning (CL) focuses on maximizing the predictive performance of a model across a non-stationary stream of data. Unfortunately, CL models tend to forget previous knowledge, thus often underperforming when compared with an offline model trained jointly on the entire data stream. Given that any CL model will eventually make mistakes, it is of crucial importance to build calibrated CL models: models that can reliably tell their confidence when making a prediction. Model calibration is an active research topic in machine learning, yet to be properly investigated in CL. We provide the first empirical study of the behavior of calibration approaches in CL, showing that CL strategies do not inherently learn calibrated models. To mitigate this issue, we design a continual calibration approach that improves the performance of post-processing calibration methods over a wide range of different benchmarks and CL strategies. CL does not necessarily need perfect predictive models, but rather it can benefit from reliable predictive models. We believe our study on continual calibration represents a first step towards this direction.
Authors: J. Warner, A. Devaraj, R. Miikkulainen
Abstract: Lifelong development allows animals and machines to adapt to changes in the environment as well as in their own systems, such as wear and tear in sensors and actuators. An important use case of such adaptation is industrial odor-sensing. Metal-oxide-based sensors can be used to detect gaseous compounds in the air; however, the gases interact with the sensors, causing their responses to change over time in a process called sensor drift. Sensor drift is irreversible and requires frequent recalibration with additional data. This paper demonstrates that an adaptive system that represents the drift as context for the skill of odor sensing achieves the same goal automatically. After it is trained on the history of changes, a neural network predicts future contexts, allowing the context+skill sensing system to adapt to sensor drift. Evaluated on an industrial dataset of gas-sensor drift, the approach performed better than standard drift-naive and ensembling methods. In this way, the context+skill system emulates the natural ability of animal olfaction systems to adapt to a changing world, and demonstrates how it can be effective in real-world applications.
Authors: Michael O'Connell, Guanya Shi, Xichen Shi, Kamyar Azizzadenesheli, Anima Anandkumar, Yisong Yue, Soon-Jo Chung
Abstract: Executing safe and precise flight maneuvers in dynamic high-speed winds is important for the ongoing commoditization of uninhabited aerial vehicles (UAVs). However, because the relationship between various wind conditions and its effect on aircraft maneuverability is not well understood, it is challenging to design effective robot controllers using traditional control design methods. We present Neural-Fly, a learning-based approach that allows rapid online adaptation by incorporating pretrained representations through deep learning. Neural-Fly builds on two key observations that aerodynamics in different wind conditions share a common representation and that the wind-specific part lies in a low-dimensional space. To that end, Neural-Fly uses a proposed learning algorithm, domain adversarially invariant meta-learning (DAIML), to learn the shared representation, only using 12 minutes of flight data. With the learned representation as a basis, Neural-Fly then uses a composite adaptation law to update a set of linear coefficients for mixing the basis elements. When evaluated under challenging wind conditions generated with the Caltech Real Weather Wind Tunnel, with wind speeds up to 43.6 kilometers/hour (12.1 meters/second), Neural-Fly achieves precise flight control with substantially smaller tracking error than state-of-the-art nonlinear and adaptive controllers. In addition to strong empirical performance, the exponential stability of Neural-Fly results in robustness guarantees. Last, our control design extrapolates to unseen wind conditions, is shown to be effective for outdoor flights with only onboard sensors, and can transfer across drones with minimal performance degradation.
Authors: Cheng Guo
Abstract: Utilizing an abstract information processing model based on minimal yet realistic assumptions inspired by biological systems, we study how to achieve the early visual system's two ultimate objectives: efficient information transmission and accurate sensor probability distribution modeling. We prove that optimizing for information transmission does not guarantee optimal probability distribution modeling in general. We illustrate, using a two-pixel (2D) system and image patches, that an efficient representation can be realized through a nonlinear population code driven by two types of biologically plausible loss functions that depend solely on output. After unsupervised learning, our abstract information processing model bears remarkable resemblances to biological systems, despite not mimicking many features of real neurons, such as spiking activity. A preliminary comparison with a contemporary deep learning model suggests that our model offers a significant efficiency advantage. Our model provides novel insights into the computational theory of early visual systems as well as a potential new approach to enhance the efficiency of deep learning models.
Authors: Francesco Saverio Pezzicoli, Guillaume Charpiat, Fran\c{c}ois P. Landes
Abstract: The difficult problem of relating the static structure of glassy liquids and their dynamics is a good target for Machine Learning, an approach which excels at finding complex patterns hidden in data. Indeed, this approach is currently a hot topic in the glassy liquids community, where the state of the art consists in Graph Neural Networks (GNNs), which have great expressive power but are heavy models and lack interpretability. Inspired by recent advances in the field of Machine Learning group-equivariant representations, we build a GNN that learns a robust representation of the glass' static structure by constraining it to preserve the roto-translation (SE(3)) equivariance. We show that this constraint significantly improves the predictive power at comparable or reduced number of parameters but most importantly, improves the ability to generalize to unseen temperatures. While remaining a Deep network, our model has improved interpretability compared to other GNNs, as the action of our basic convolution layer relates directly to well-known rotation-invariant expert features. Through transfer-learning experiments displaying unprecedented performance, we demonstrate that our network learns a robust representation, which allows us to push forward the idea of a learned structural order parameter for glasses.
Authors: Hainan Xu, Fei Jia, Somshubra Majumdar, Shinji Watanabe, Boris Ginsburg
Abstract: This paper proposes a modification to RNN-Transducer (RNN-T) models for automatic speech recognition (ASR). In standard RNN-T, the emission of a blank symbol consumes exactly one input frame; in our proposed method, we introduce additional blank symbols, which consume two or more input frames when emitted. We refer to the added symbols as big blanks, and the method multi-blank RNN-T. For training multi-blank RNN-Ts, we propose a novel logit under-normalization method in order to prioritize emissions of big blanks. With experiments on multiple languages and datasets, we show that multi-blank RNN-T methods could bring relative speedups of over +90%/+139% to model inference for English Librispeech and German Multilingual Librispeech datasets, respectively. The multi-blank RNN-T method also improves ASR accuracy consistently. We will release our implementation of the method in the NeMo (https://github.com/NVIDIA/NeMo) toolkit.
Authors: Mateus P. Otto, Rafael Izbicki
Abstract: Kernel methods provide a flexible and theoretically grounded approach to nonlinear and nonparametric learning. While memory and run-time requirements hinder their applicability to large datasets, many low-rank kernel approximations, such as random Fourier features, were recently developed to scale up such kernel methods. However, these scalable approaches are based on approximations of isotropic kernels, which cannot remove the influence of irrelevant features. In this work, we design random Fourier features for a family of automatic relevance determination (ARD) kernels, and introduce RFFNet, a new large-scale kernel method that learns the kernel relevances' on the fly via first-order stochastic optimization. We present an effective initialization scheme for the method's non-convex objective function, evaluate if hard-thresholding RFFNet's learned relevances yield a sensible rule for variable selection, and perform an extensive ablation study of RFFNet's components. Numerical validation on simulated and real-world data shows that our approach has a small memory footprint and run-time, achieves low prediction error, and effectively identifies relevant features, thus leading to more interpretable solutions. We supply users with an efficient, PyTorch-based library, that adheres to the scikit-learn standard API and code for fully reproducing our results.
Authors: Boyi Li, Rodolfo Corona, Karttikeya Mangalam, Catherine Chen, Daniel Flaherty, Serge Belongie, Kilian Q. Weinberger, Jitendra Malik, Trevor Darrell, Dan Klein
Abstract: Are multimodal inputs necessary for grammar induction? Recent work has shown that multimodal training inputs can improve grammar induction. However, these improvements are based on comparisons to weak text-only baselines that were trained on relatively little textual data. To determine whether multimodal inputs are needed in regimes with large amounts of textual training data, we design a stronger text-only baseline, which we refer to as LC-PCFG. LC-PCFG is a C-PFCG that incorporates em-beddings from text-only large language models (LLMs). We use a fixed grammar family to directly compare LC-PCFG to various multi-modal grammar induction methods. We compare performance on four benchmark datasets. LC-PCFG provides an up to 17% relative improvement in Corpus-F1 compared to state-of-the-art multimodal grammar induction methods. LC-PCFG is also more computationally efficient, providing an up to 85% reduction in parameter count and 8.8x reduction in training time compared to multimodal approaches. These results suggest that multimodal inputs may not be necessary for grammar induction, and emphasize the importance of strong vision-free baselines for evaluating the benefit of multimodal approaches.
Authors: Henry Senior, Gregory Slabaugh, Shanxin Yuan, Luca Rossi
Abstract: 2D image understanding is a complex problem within computer vision, but it holds the key to providing human-level scene comprehension. It goes further than identifying the objects in an image, and instead, it attempts to understand the scene. Solutions to this problem form the underpinning of a range of tasks, including image captioning, visual question answering (VQA), and image retrieval. Graphs provide a natural way to represent the relational arrangement between objects in an image, and thus, in recent years graph neural networks (GNNs) have become a standard component of many 2D image understanding pipelines, becoming a core architectural component, especially in the VQA group of tasks. In this survey, we review this rapidly evolving field and we provide a taxonomy of graph types used in 2D image understanding approaches, a comprehensive list of the GNN models used in this domain, and a roadmap of future potential developments. To the best of our knowledge, this is the first comprehensive survey that covers image captioning, visual question answering, and image retrieval techniques that focus on using GNNs as the main part of their architecture.
Authors: Manon Flageat, Bryan Lim, Antoine Cully
Abstract: With the development of fast and massively parallel evaluations in many domains, Quality-Diversity (QD) algorithms, that already proved promising in a large range of applications, have seen their potential multiplied. However, we have yet to understand how to best use a large number of evaluations as using them for random variations alone is not always effective. High-dimensional search spaces are a typical situation where random variations struggle to effectively search. Another situation is uncertain settings where solutions can appear better than they truly are and naively evaluating more solutions might mislead QD algorithms. In this work, we propose MAP-Elites-Multi-ES (MEMES), a novel QD algorithm based on Evolution Strategies (ES) designed to exploit fast parallel evaluations more effectively. MEMES maintains multiple (up to 100) simultaneous ES processes, each with its own independent objective and reset mechanism designed for QD optimisation, all on just a single GPU. We show that MEMES outperforms both gradient-based and mutation-based QD algorithms on black-box optimisation and QD-Reinforcement-Learning tasks, demonstrating its benefit across domains. Additionally, our approach outperforms sampling-based QD methods in uncertain domains when given the same evaluation budget. Overall, MEMES generates reproducible solutions that are high-performing and diverse through large-scale ES optimisation on easily accessible hardware.
Authors: Shensheng Zheng, Wenhao Yuan, Xuehe Wang, Lingjie Duan
Abstract: Federated Learning (FL) has emerged as a prominent distributed machine learning framework that enables geographically discrete clients to train a global model collaboratively while preserving their privacy-sensitive data. However, due to the non-independent-and-identically-distributed (Non-IID) data generated by heterogeneous clients, the performances of the conventional federated optimization schemes such as FedAvg and its variants deteriorate, requiring the design to adaptively adjust specific model parameters to alleviate the negative influence of heterogeneity. In this paper, by leveraging entropy as a new metric for assessing the degree of system disorder, we propose an adaptive FEDerated learning algorithm based on ENTropy theory (FedEnt) to alleviate the parameter deviation among heterogeneous clients and achieve fast convergence. Nevertheless, given the data disparity and parameter deviation of heterogeneous clients, determining the optimal dynamic learning rate for each client becomes a challenging task as there is no communication among participating clients during the local training epochs. To enable a decentralized learning rate for each participating client, we first introduce the mean-field terms to estimate the components associated with other clients' local parameters. Furthermore, we provide rigorous theoretical analysis on the existence and determination of the mean-field estimators. Based on the mean-field estimators, the closed-form adaptive learning rate for each client is derived by constructing the Hamilton equation. Moreover, the convergence rate of our proposed FedEnt is proved. The extensive experimental results on the real-world datasets (i.e., MNIST, EMNIST-L, CIFAR10, and CIFAR100) show that our FedEnt algorithm surpasses FedAvg and its variants (i.e., FedAdam, FedProx, and FedDyn) under Non-IID settings and achieves a faster convergence rate.
Authors: Adam Spannaus, Heidi A. Hanson, Lynne Penberthy, Georgia Tourassi
Abstract: With the growing adoption of AI-based systems across everyday life, the need to understand their decision-making mechanisms is correspondingly increasing. The level at which we can trust the statistical inferences made from AI-based decision systems is an increasing concern, especially in high-risk systems such as criminal justice or medical diagnosis, where incorrect inferences may have tragic consequences. Despite their successes in providing solutions to problems involving real-world data, deep learning (DL) models cannot quantify the certainty of their predictions. These models are frequently quite confident, even when their solutions are incorrect. This work presents a method to infer prominent features in two DL classification models trained on clinical and non-clinical text by employing techniques from topological and geometric data analysis. We create a graph of a model's feature space and cluster the inputs into the graph's vertices by the similarity of features and prediction statistics. We then extract subgraphs demonstrating high-predictive accuracy for a given label. These subgraphs contain a wealth of information about features that the DL model has recognized as relevant to its decisions. We infer these features for a given label using a distance metric between probability measures, and demonstrate the stability of our method compared to the LIME and SHAP interpretability methods. This work establishes that we may gain insights into the decision mechanism of a DL model. This method allows us to ascertain if the model is making its decisions based on information germane to the problem or identifies extraneous patterns within the data.
Authors: Daniel J. Williams, Song Liu
Abstract: Estimating truncated density models is difficult, as these models have intractable normalising constants and hard to satisfy boundary conditions. Score matching can be adapted to solve the truncated density estimation problem, but requires a continuous weighting function which takes zero at the boundary and is positive elsewhere. Evaluation of such a weighting function (and its gradient) often requires a closed-form expression of the truncation boundary and finding a solution to a complicated optimisation problem. In this paper, we propose approximate Stein classes, which in turn leads to a relaxed Stein identity for truncated density estimation. We develop a novel discrepancy measure, truncated kernelised Stein discrepancy (TKSD), which does not require fixing a weighting function in advance, and can be evaluated using only samples on the boundary. We estimate a truncated density model by minimising the Lagrangian dual of TKSD. Finally, experiments show the accuracy of our method to be an improvement over previous works even without the explicit functional form of the boundary.
Authors: Matthias Freiberger, Peter Kun, Christian Igel, Anders Sundnes L{\o}vlie, Sebastian Risi
Abstract: Models leveraging both visual and textual data such as Contrastive Language-Image Pre-training (CLIP), are the backbone of many recent advances in artificial intelligence. In this work, we show that despite their versatility, such models are vulnerable to what we refer to as fooling master images. Fooling master images are capable of maximizing the confidence score of a CLIP model for a significant number of widely varying prompts, while being either unrecognizable or unrelated to the attacked prompts for humans. The existence of such images is problematic as it could be used by bad actors to maliciously interfere with CLIP-trained image retrieval models in production with comparably small effort as a single image can attack many different prompts. We demonstrate how fooling master images for CLIP (CLIPMasterPrints) can be mined using stochastic gradient descent, projected gradient descent, or blackbox optimization. Contrary to many common adversarial attacks, the blackbox optimization approach allows us to mine CLIPMasterPrints even when the weights of the model are not accessible. We investigate the properties of the mined images, and find that images trained on a small number of image captions generalize to a much larger number of semantically related captions. We evaluate possible mitigation strategies, where we increase the robustness of the model and introduce an approach to automatically detect CLIPMasterPrints to sanitize the input of vulnerable models. Finally, we find that vulnerability to CLIPMasterPrints is related to a modality gap in contrastive pre-trained multi-modal networks. Code available at https://github.com/matfrei/CLIPMasterPrints.
Authors: Anthony Ozier-Lafontaine, Camille Fourneaux, Ghislain Durif, Polina Arsenteva, C\'eline Vallot, Olivier Gandrillon, Sandrine Giraud, Bertrand Michel, Franck Picard
Abstract: Single-cell technologies offer insights into molecular feature distributions, but comparing them poses challenges. We propose a kernel-testing framework for non-linear cell-wise distribution comparison, analyzing gene expression and epigenomic modifications. Our method allows feature-wise and global transcriptome/epigenome comparisons, revealing cell population heterogeneities. Using a classifier based on embedding variability, we identify transitions in cell states, overcoming limitations of traditional single-cell analysis. Applied to single-cell ChIP-Seq data, our approach identifies untreated breast cancer cells with an epigenomic profile resembling persister cells. This demonstrates the effectiveness of kernel testing in uncovering subtle population variations that might be missed by other methods.
Authors: Eloi Tanguy, R\'emi Flamary, Julie Delon
Abstract: The Sliced Wasserstein (SW) distance has become a popular alternative to the Wasserstein distance for comparing probability measures. Widespread applications include image processing, domain adaptation and generative modelling, where it is common to optimise some parameters in order to minimise SW, which serves as a loss function between discrete probability measures (since measures admitting densities are numerically unattainable). All these optimisation problems bear the same sub-problem, which is minimising the Sliced Wasserstein energy. In this paper we study the properties of $\mathcal{E}: Y \longmapsto \mathrm{SW}_2^2(\gamma_Y, \gamma_Z)$, i.e. the SW distance between two uniform discrete measures with the same amount of points as a function of the support $Y \in \mathbb{R}^{n \times d}$ of one of the measures. We investigate the regularity and optimisation properties of this energy, as well as its Monte-Carlo approximation $\mathcal{E}_p$ (estimating the expectation in SW using only $p$ samples) and show convergence results on the critical points of $\mathcal{E}_p$ to those of $\mathcal{E}$, as well as an almost-sure uniform convergence and a uniform Central Limit result on the process $\mathcal{E}_p(Y)$. Finally, we show that in a certain sense, Stochastic Gradient Descent methods minimising $\mathcal{E}$ and $\mathcal{E}_p$ converge towards (Clarke) critical points of these energies.
Authors: Jiaxing Xu, Qingtian Bian, Xinhang Li, Aihu Zhang, Yiping Ke, Miao Qiao, Wei Zhang, Wei Khang Jeremy Sim, Bal\'azs Guly\'as
Abstract: Functional magnetic resonance imaging (fMRI) is a commonly used technique to measure neural activation. Its application has been particularly important in identifying underlying neurodegenerative conditions such as Parkinson's, Alzheimer's, and Autism. Recent analysis of fMRI data models the brain as a graph and extracts features by graph neural networks (GNNs). However, the unique characteristics of fMRI data require a special design of GNN. Tailoring GNN to generate effective and domain-explainable features remains challenging. In this paper, we propose a contrastive dual-attention block and a differentiable graph pooling method called ContrastPool to better utilize GNN for brain networks, meeting fMRI-specific requirements. We apply our method to 5 resting-state fMRI brain network datasets of 3 diseases and demonstrate its superiority over state-of-the-art baselines. Our case study confirms that the patterns extracted by our method match the domain knowledge in neuroscience literature, and disclose direct and interesting insights. Our contributions underscore the potential of ContrastPool for advancing the understanding of brain networks and neurodegenerative conditions. The source code is available at https://github.com/AngusMonroe/ContrastPool.
Authors: Tobias Christian Nauen, Sebastian Palacio, Andreas Dengel
Abstract: Transformers come with a high computational cost, yet their effectiveness in addressing problems in language and vision has sparked extensive research aimed at enhancing their efficiency. However, diverse experimental conditions, spanning multiple input domains, prevent a fair comparison based solely on reported results, posing challenges for model selection. To address this gap in comparability, we design a comprehensive benchmark of more than 30 models for image classification, evaluating key efficiency aspects, including accuracy, speed, and memory usage. This benchmark provides a standardized baseline across the landscape of efficiency-oriented transformers and our framework of analysis, based on Pareto optimality, reveals surprising insights. Despite claims of other models being more efficient, ViT remains Pareto optimal across multiple metrics. We observe that hybrid attention-CNN models exhibit remarkable inference memory- and parameter-efficiency. Moreover, our benchmark shows that using a larger model in general is more efficient than using higher resolution images. Thanks to our holistic evaluation, we provide a centralized resource for practitioners and researchers, facilitating informed decisions when selecting transformers or measuring progress of the development of efficient transformers.
Authors: Talay M Cheema, Carl Edward Rasmussen
Abstract: Sparse variational approximations are popular methods for scaling up inference and learning in Gaussian processes to larger datasets. For $N$ training points, exact inference has $O(N^3)$ cost; with $M \ll N$ features, state of the art sparse variational methods have $O(NM^2)$ cost. Recently, methods have been proposed using more sophisticated features; these promise $O(M^3)$ cost, with good performance in low dimensional tasks such as spatial modelling, but they only work with a very limited class of kernels, excluding some of the most commonly used. In this work, we propose integrated Fourier features, which extends these performance benefits to a very broad class of stationary covariance functions. We motivate the method and choice of parameters from a convergence analysis and empirical exploration, and show practical speedup in synthetic and real world spatial regression tasks.
Authors: Zahra Kadkhodaie, Florentin Guth, Eero P. Simoncelli, St\'ephane Mallat
Abstract: Deep neural networks (DNNs) trained for image denoising are able to generate high-quality samples with score-based reverse diffusion algorithms. These impressive capabilities seem to imply an escape from the curse of dimensionality, but recent reports of memorization of the training set raise the question of whether these networks are learning the "true" continuous density of the data. Here, we show that two DNNs trained on non-overlapping subsets of a dataset learn nearly the same score function, and thus the same density, when the number of training images is large enough. In this regime of strong generalization, diffusion-generated images are distinct from the training set, and are of high visual quality, suggesting that the inductive biases of the DNNs are well-aligned with the data density. We analyze the learned denoising functions and show that the inductive biases give rise to a shrinkage operation in a basis adapted to the underlying image. Examination of these bases reveals oscillating harmonic structures along contours and in homogeneous regions. We demonstrate that trained denoisers are inductively biased towards these geometry-adaptive harmonic bases since they arise not only when the network is trained on photographic images, but also when it is trained on image classes supported on low-dimensional manifolds for which the harmonic basis is suboptimal. Finally, we show that when trained on regular image classes for which the optimal basis is known to be geometry-adaptive and harmonic, the denoising performance of the networks is near-optimal.
Authors: Luke O'Loughlin, John Maclean, Andrew Black
Abstract: Stochastic processes defined on integer valued state spaces are popular within the physical and biological sciences. These models are necessary for capturing the dynamics of small systems where the individual nature of the populations cannot be ignored and stochastic effects are important. The inference of the parameters of such models, from time series data, is challenging due to intractability of the likelihood. To work at all, current simulation based inference methods require the generation of realisations of the model conditional on the data, which can be both tricky to implement and computationally expensive. In this paper we instead construct a neural likelihood approximation that can be trained using unconditional simulation of the underlying model, which is much simpler. We demonstrate our method by performing inference on a number of ecological and epidemiological models, showing that we can accurately approximate the true posterior while achieving significant computational speed ups compared to current best methods.
Authors: Ozan \"Ozdenizci, Robert Legenstein
Abstract: Spiking neural networks (SNNs) provide an energy-efficient alternative to a variety of artificial neural network (ANN) based AI applications. As the progress in neuromorphic computing with SNNs expands their use in applications, the problem of adversarial robustness of SNNs becomes more pronounced. To the contrary of the widely explored end-to-end adversarial training based solutions, we address the limited progress in scalable robust SNN training methods by proposing an adversarially robust ANN-to-SNN conversion algorithm. Our method provides an efficient approach to embrace various computationally demanding robust learning objectives that have been proposed for ANNs. During a post-conversion robust finetuning phase, our method adversarially optimizes both layer-wise firing thresholds and synaptic connectivity weights of the SNN to maintain transferred robustness gains from the pre-trained ANN. We perform experimental evaluations in a novel setting proposed to rigorously assess the robustness of SNNs, where numerous adaptive adversarial attacks that account for the spike-based operation dynamics are considered. Results show that our approach yields a scalable state-of-the-art solution for adversarially robust deep SNNs with low-latency.
Authors: Chuhao Qin, Evangelos Pournaras
Abstract: Swarms of autonomous interactive drones, with the support of recharging technology, can provide compelling sensing capabilities in Smart Cities, such as traffic monitoring and disaster response. This paper aims to deliver a novel coordination solution for the cost-effective navigation, sensing, and recharging of drones. Existing approaches, such as deep reinforcement learning (DRL), offer long-term adaptability, but lack energy efficiency, resilience, and flexibility in dynamic environments. Therefore, this paper proposes a novel approach where each drone independently determines its flying direction and recharging place using DRL, while adapting navigation and sensing through distributed optimization, which improves energy-efficiency during sensing tasks. Furthermore, drones efficiently exchange information while retaining decision-making autonomy via a structured tree communication model. Extensive experimentation with datasets generated from realistic urban mobility underscores an outstanding performance of the proposed solution compared to state-of-the-art methods. Significant new insights show that long-term methods optimize scarce drone resource for traffic management, while the integration of short-term methods is crucial for advising on charging policies and maintaining battery safety.
Authors: Valentyn Melnychuk, Dennis Frauen, Stefan Feuerriegel
Abstract: State-of-the-art methods for conditional average treatment effect (CATE) estimation make widespread use of representation learning. Here, the idea is to reduce the variance of the low-sample CATE estimation by a (potentially constrained) low-dimensional representation. However, low-dimensional representations can lose information about the observed confounders and thus lead to bias, because of which the validity of representation learning for CATE estimation is typically violated. In this paper, we propose a new, representation-agnostic refutation framework for estimating bounds on the representation-induced confounding bias that comes from dimensionality reduction (or other constraints on the representations) in CATE estimation. First, we establish theoretically under which conditions CATE is non-identifiable given low-dimensional (constrained) representations. Second, as our remedy, we propose a neural refutation framework which performs partial identification of CATE or, equivalently, aims at estimating lower and upper bounds of the representation-induced confounding bias. We demonstrate the effectiveness of our bounds in a series of experiments. In sum, our refutation framework is of direct relevance in practice where the validity of CATE estimation is of importance.
Authors: Ahmad Sajedi, Samir Khaki, Yuri A. Lawryshyn, Konstantinos N. Plataniotis
Abstract: Multi-label image classification presents a challenging task in many domains, including computer vision and medical imaging. Recent advancements have introduced graph-based and transformer-based methods to improve performance and capture label dependencies. However, these methods often include complex modules that entail heavy computation and lack interpretability. In this paper, we propose Probabilistic Multi-label Contrastive Learning (ProbMCL), a novel framework to address these challenges in multi-label image classification tasks. Our simple yet effective approach employs supervised contrastive learning, in which samples that share enough labels with an anchor image based on a decision threshold are introduced as a positive set. This structure captures label dependencies by pulling positive pair embeddings together and pushing away negative samples that fall below the threshold. We enhance representation learning by incorporating a mixture density network into contrastive learning and generating Gaussian mixture distributions to explore the epistemic uncertainty of the feature encoder. We validate the effectiveness of our framework through experimentation with datasets from the computer vision and medical imaging domains. Our method outperforms the existing state-of-the-art methods while achieving a low computational footprint on both datasets. Visualization analyses also demonstrate that ProbMCL-learned classifiers maintain a meaningful semantic topology.
Authors: Kosuke Sumiyasu, Kazuhiko Kawamoto, Hiroshi Kera
Abstract: To better understand the behavior of image classifiers, it is useful to visualize the contribution of individual pixels to the model prediction. In this study, we propose a method, MoXI ($\textbf{Mo}$del e$\textbf{X}$planation by $\textbf{I}$nteractions), that efficiently and accurately identifies a group of pixels with high prediction confidence. The proposed method employs game-theoretic concepts, Shapley values and interactions, taking into account the effects of individual pixels and the cooperative influence of pixels on model confidence. Theoretical analysis and experiments demonstrate that our method better identifies the pixels that are highly contributing to the model outputs than widely-used visualization by Grad-CAM, Attention rollout, and Shapley value. While prior studies have suffered from the exponential computational cost in the computation of Shapley value and interactions, we show that this can be reduced to quadratic cost for our task. The code is available at https://github.com/KosukeSumiyasu/MoXI.
Authors: Somnath Basu Roy Chowdhury, Nicholas Monath, Avinava Dubey, Manzil Zaheer, Andrew McCallum, Amr Ahmed, Snigdha Chaturvedi
Abstract: Extractive opinion summarization involves automatically producing a summary of text about an entity (e.g., a product's reviews) by extracting representative sentences that capture prevalent opinions in the review set. Typically, in online marketplaces user reviews accumulate over time, and opinion summaries need to be updated periodically to provide customers with up-to-date information. In this work, we study the task of extractive opinion summarization in an incremental setting, where the underlying review set evolves over time. Many of the state-of-the-art extractive opinion summarization approaches are centrality-based, such as CentroidRank (Radev et al., 2004; Chowdhury et al., 2022). CentroidRank performs extractive summarization by selecting a subset of review sentences closest to the centroid in the representation space as the summary. However, these methods are not capable of operating efficiently in an incremental setting, where reviews arrive one at a time. In this paper, we present an efficient algorithm for accurately computing the CentroidRank summaries in an incremental setting. Our approach, CoverSumm, relies on indexing review representations in a cover tree and maintaining a reservoir of candidate summary review sentences. CoverSumm's efficacy is supported by a theoretical and empirical analysis of running time. Empirically, on a diverse collection of data (both real and synthetically created to illustrate scaling considerations), we demonstrate that CoverSumm is up to 36x faster than baseline methods, and capable of adapting to nuanced changes in data distribution. We also conduct human evaluations of the generated summaries and find that CoverSumm is capable of producing informative summaries consistent with the underlying review set.
Authors: Mohammed Elnawawy, Mohammadreza Hallajiyan, Gargi Mitra, Shahrear Iqbal, Karthik Pattabiraman
Abstract: The adoption of machine-learning-enabled systems in the healthcare domain is on the rise. While the use of ML in healthcare has several benefits, it also expands the threat surface of medical systems. We show that the use of ML in medical systems, particularly connected systems that involve interfacing the ML engine with multiple peripheral devices, has security risks that might cause life-threatening damage to a patient's health in case of adversarial interventions. These new risks arise due to security vulnerabilities in the peripheral devices and communication channels. We present a case study where we demonstrate an attack on an ML-enabled blood glucose monitoring system by introducing adversarial data points during inference. We show that an adversary can achieve this by exploiting a known vulnerability in the Bluetooth communication channel connecting the glucose meter with the ML-enabled app. We further show that state-of-the-art risk assessment techniques are not adequate for identifying and assessing these new risks. Our study highlights the need for novel risk analysis methods for analyzing the security of AI-enabled connected health devices.
Authors: Blake Bordelon, Alexander Atanasov, Cengiz Pehlevan
Abstract: On a variety of tasks, the performance of neural networks predictably improves with training time, dataset size and model size across many orders of magnitude. This phenomenon is known as a neural scaling law. Of fundamental importance is the compute-optimal scaling law, which reports the performance as a function of units of compute when choosing model sizes optimally. We analyze a random feature model trained with gradient descent as a solvable model of network training and generalization. This reproduces many observations about neural scaling laws. First, our model makes a prediction about why the scaling of performance with training time and with model size have different power law exponents. Consequently, the theory predicts an asymmetric compute-optimal scaling rule where the number of training steps are increased faster than model parameters, consistent with recent empirical observations. Second, it has been observed that early in training, networks converge to their infinite-width dynamics at a rate $1/\textit{width}$ but at late time exhibit a rate $\textit{width}^{-c}$, where $c$ depends on the structure of the architecture and task. We show that our model exhibits this behavior. Lastly, our theory shows how the gap between training and test loss can gradually build up over time due to repeated reuse of data.
Authors: Isaac Corley, Caleb Robinson, Anthony Ortiz
Abstract: In recent years, there has been an explosion of proposed change detection deep learning architectures in the remote sensing literature. These approaches claim to offer state-of-the-art performance on different standard benchmark datasets. However, has the field truly made significant progress? In this paper we perform experiments which conclude a simple U-Net segmentation baseline without training tricks or complicated architectural changes is still a top performer for the task of change detection.
Authors: Roberto C. Alamino
Abstract: As powerful as machine learning (ML) techniques are in solving problems involving data with large dimensionality, explaining the results from the fitted parameters remains a challenging task of utmost importance, especially in physics applications. This work shows how this can be accomplished for the ferromagnetic Ising model, the main target of several ML studies in statistical physics. Here it is demonstrated that the successful unsupervised identification of the phases and order parameter by principal component analysis, a common method in those studies, detects that the magnetization per spin has its greatest variation with the temperature, the actual control parameter of the phase transition. Then, by using a neural network (NN) without hidden layers (the simplest possible) and informed by the symmetry of the Hamiltonian, an explanation is provided for the strategy used in finding the supervised learning solution for the critical temperature of the model's continuous phase transition. This allows the prediction of the minimal extension of the NN to solve the problem when the symmetry is not known, which becomes also explainable. These results pave the way to a physics-informed explainable generalized framework, enabling the extraction of physical laws and principles from the parameters of the models.
Authors: Shubhashis Roy Dipta, Sai Vallurupalli
Abstract: The aim of SemEval-2024 Task 1, "Semantic Textual Relatedness for African and Asian Languages" is to develop models for identifying semantic textual relatedness (STR) between two sentences using multiple languages (14 African and Asian languages) and settings (supervised, unsupervised, and cross-lingual). Large language models (LLMs) have shown impressive performance on several natural language understanding tasks such as multilingual machine translation (MMT), semantic similarity (STS), and encoding sentence embeddings. Using a combination of LLMs that perform well on these tasks, we developed two STR models, $\textit{TranSem}$ and $\textit{FineSem}$, for the supervised and cross-lingual settings. We explore the effectiveness of several training methods and the usefulness of machine translation. We find that direct fine-tuning on the task is comparable to using sentence embeddings and translating to English leads to better performance for some languages. In the supervised setting, our model performance is better than the official baseline for 3 languages with the remaining 4 performing on par. In the cross-lingual setting, our model performance is better than the baseline for 3 languages (leading to $1^{st}$ place for Africaans and $2^{nd}$ place for Indonesian), is on par for 2 languages and performs poorly on the remaining 7 languages. Our code is publicly available at https://github.com/dipta007/SemEval24-Task8.
Authors: Lucas Fabian Naumann, Jannik Irmai, Shengxian Zhao, Bjoern Andres
Abstract: The lifted multicut problem is a combinatorial optimization problem whose feasible solutions relate one-to-one to the decompositions of a graph $G = (V, E)$. Given an augmentation $\widehat{G} = (V, E \cup F)$ of $G$ and given costs $c \in \mathbb{R}^{E \cup F}$, the objective is to minimize the sum of those $c_{uw}$ with $uw \in E \cup F$ for which $u$ and $w$ are in distinct components. For $F = \emptyset$, the problem specializes to the multicut problem, and for $E = \tbinom{V}{2}$ to the clique partitioning problem. We study a binary linear program formulation of the lifted multicut problem. More specifically, we contribute to the analysis of the associated lifted multicut polytopes: Firstly, we establish a necessary, sufficient and efficiently decidable condition for a lower box inequality to define a facet. Secondly, we show that deciding whether a cut inequality of the binary linear program defines a facet is NP-hard.
Authors: Martin Willbo, Aleksis Pirinen, John Martinsson, Edvin Listo Zec, Olof Mogren, Mikael Nilsson
Abstract: Land cover classification and change detection are two important applications of remote sensing and Earth observation (EO) that have benefited greatly from the advances of deep learning. Convolutional and transformer-based U-net models are the state-of-the-art architectures for these tasks, and their performances have been boosted by an increased availability of large-scale annotated EO datasets. However, the influence of different visual characteristics of the input EO data on a model's predictions is not well understood. In this work we systematically examine model sensitivities with respect to several color- and texture-based distortions on the input EO data during inference, given models that have been trained without such distortions. We conduct experiments with multiple state-of-the-art segmentation networks for land cover classification and show that they are in general more sensitive to texture than to color distortions. Beyond revealing intriguing characteristics of widely used land cover classification models, our results can also be used to guide the development of more robust models within the EO domain.
Authors: Antonia Calvi, Th\'eophile Gaudin, Dominik Miketa, Dominique Sydow, Liam Wilbraham
Abstract: Assessing whether a molecule can be synthesised is a primary task in drug discovery. It enables computational chemists to filter for viable compounds or bias molecular generative models. The notion of synthesisability is dynamic as it evolves depending on the availability of key compounds. A common approach in drug discovery involves exploring the chemical space surrounding synthetically-accessible intermediates. This strategy improves the synthesisability of the derived molecules due to the availability of key intermediates. Existing synthesisability scoring methods such as SAScore, SCScore and RAScore, cannot condition on intermediates dynamically. Our approach, Leap, is a GPT-2 model trained on the depth, or longest linear path, of predicted synthesis routes that allows information on the availability of key intermediates to be included at inference time. We show that Leap surpasses all other scoring methods by at least 5% on AUC score when identifying synthesisable molecules, and can successfully adapt predicted scores when presented with a relevant intermediate compound.
Authors: Yuqing Wang, Mika V. M\"antyl\"a, Serge Demeyer, Mutlu Beyazit, Joanna Kisaakye, Jesse Nyyss\"ol\"a
Abstract: Microservice-based systems (MSS) may experience failures in various fault categories due to their complex and dynamic nature. To effectively handle failures, AIOps tools utilize trace-based anomaly detection and root cause analysis. In this paper, we propose a novel framework for few-shot abnormal trace classification for MSS. Our framework comprises two main components: (1) Multi-Head Attention Autoencoder for constructing system-specific trace representations, which enables (2) Transformer Encoder-based Model-Agnostic Meta-Learning to perform effective and efficient few-shot learning for abnormal trace classification. The proposed framework is evaluated on two representative MSS, Trainticket and OnlineBoutique, with open datasets. The results show that our framework can adapt the learned knowledge to classify new, unseen abnormal traces of novel fault categories both within the same system it was initially trained on and even in the different MSS. Within the same MSS, our framework achieves an average accuracy of 93.26\% and 85.2\% across 50 meta-testing tasks for Trainticket and OnlineBoutique, respectively, when provided with 10 instances for each task. In a cross-system context, our framework gets an average accuracy of 92.19\% and 84.77\% for the same meta-testing tasks of the respective system, also with 10 instances provided for each task. Our work demonstrates the applicability of achieving few-shot abnormal trace classification for MSS and shows how it can enable cross-system adaptability. This opens an avenue for building more generalized AIOps tools that require less system-specific data labeling for anomaly detection and root cause analysis.
Authors: Zhiyuan Peng, Xuyang Wu, Qifan Wang, Sravanthi Rajanala, Yi Fang
Abstract: Parameter Efficient Fine-Tuning (PEFT) methods have been extensively utilized in Large Language Models (LLMs) to improve the down-streaming tasks without the cost of fine-tuing the whole LLMs. Recent studies have shown how to effectively use PEFT for fine-tuning LLMs in ranking tasks with convincing performance; there are some limitations, including the learned prompt being fixed for different documents, overfitting to specific tasks, and low adaptation ability. In this paper, we introduce a query-dependent parameter efficient fine-tuning (Q-PEFT) approach for text reranking to leak the information of the true queries to LLMs and then make the generation of true queries from input documents much easier. Specifically, we utilize the query to extract the top-$k$ tokens from concatenated documents, serving as contextual clues. We further augment Q-PEFT by substituting the retrieval mechanism with a multi-head attention layer to achieve end-to-end training and cover all the tokens in the documents, guiding the LLMs to generate more document-specific synthetic queries, thereby further improving the reranking performance. Extensive experiments are conducted on four public datasets, demonstrating the effectiveness of our proposed approach.
Authors: Hongyu Cai, Arjun Arunasalam, Leo Y. Lin, Antonio Bianchi, Z. Berkay Celik
Abstract: Large language models (LLMs) have become increasingly integrated with various applications. To ensure that LLMs do not generate unsafe responses, they are aligned with safeguards that specify what content is restricted. However, such alignment can be bypassed to produce prohibited content using a technique commonly referred to as jailbreak. Different systems have been proposed to perform the jailbreak automatically. These systems rely on evaluation methods to determine whether a jailbreak attempt is successful. However, our analysis reveals that current jailbreak evaluation methods have two limitations. (1) Their objectives lack clarity and do not align with the goal of identifying unsafe responses. (2) They oversimplify the jailbreak result as a binary outcome, successful or not. In this paper, we propose three metrics, safeguard violation, informativeness, and relative truthfulness, to evaluate language model jailbreak. Additionally, we demonstrate how these metrics correlate with the goal of different malicious actors. To compute these metrics, we introduce a multifaceted approach that extends the natural language generation evaluation method after preprocessing the response. We evaluate our metrics on a benchmark dataset produced from three malicious intent datasets and three jailbreak systems. The benchmark dataset is labeled by three annotators. We compare our multifaceted approach with three existing jailbreak evaluation methods. Experiments demonstrate that our multifaceted evaluation outperforms existing methods, with F1 scores improving on average by 17% compared to existing baselines. Our findings motivate the need to move away from the binary view of the jailbreak problem and incorporate a more comprehensive evaluation to ensure the safety of the language model.
Authors: Guanhang Lei, Zhen Lei, Lei Shi, Chenyu Zeng
Abstract: We propose the POD-DNN, a novel algorithm leveraging deep neural networks (DNNs) along with radial basis functions (RBFs) in the context of the proper orthogonal decomposition (POD) reduced basis method (RBM), aimed at approximating the parametric mapping of parametric partial differential equations on irregular domains. The POD-DNN algorithm capitalizes on the low-dimensional characteristics of the solution manifold for parametric equations, alongside the inherent offline-online computational strategy of RBM and DNNs. In numerical experiments, POD-DNN demonstrates significantly accelerated computation speeds during the online phase. Compared to other algorithms that utilize RBF without integrating DNNs, POD-DNN substantially improves the computational speed in the online inference process. Furthermore, under reasonable assumptions, we have rigorously derived upper bounds on the complexity of approximating parametric mappings with POD-DNN, thereby providing a theoretical analysis of the algorithm's empirical performance.
Authors: Sheng Gong, Yumin Zhang, Zhenliang Mu, Zhichen Pu, Hongyi Wang, Zhiao Yu, Mengyi Chen, Tianze Zheng, Zhi Wang, Lifei Chen, Xiaojie Wu, Shaochen Shi, Weihao Gao, Wen Yan, Liang Xiang
Abstract: Despite the widespread applications of machine learning force field (MLFF) on solids and small molecules, there is a notable gap in applying MLFF to complex liquid electrolytes. In this work, we introduce BAMBOO (ByteDance AI Molecular Simulation Booster), a novel framework for molecular dynamics (MD) simulations, with a demonstration of its capabilities in the context of liquid electrolytes for lithium batteries. We design a physics-inspired graph equivariant transformer architecture as the backbone of BAMBOO to learn from quantum mechanical simulations. Additionally, we pioneer an ensemble knowledge distillation approach and apply it on MLFFs to improve the stability of MD simulations. Finally, we propose the density alignment algorithm to align BAMBOO with experimental measurements. BAMBOO demonstrates state-of-the-art accuracy in predicting key electrolyte properties such as density, viscosity, and ionic conductivity across various solvents and salt combinations. Our current model, trained on more than 15 chemical species, achieves the average density error of 0.01 g/cm$^3$ on various compositions compared with experimental data. Moreover, our model demonstrates transferability to molecules not included in the quantum mechanical dataset. We envision this work as paving the way to a "universal MLFF" capable of simulating properties of common organic liquids.
Authors: Hou-I Liu, Marco Galindo, Hongxia Xie, Lai-Kuan Wong, Hong-Han Shuai, Yung-Hui Li, Wen-Huang Cheng
Abstract: Over the past decade, the dominance of deep learning has prevailed across various domains of artificial intelligence, including natural language processing, computer vision, and biomedical signal processing. While there have been remarkable improvements in model accuracy, deploying these models on lightweight devices, such as mobile phones and microcontrollers, is constrained by limited resources. In this survey, we provide comprehensive design guidance tailored for these devices, detailing the meticulous design of lightweight models, compression methods, and hardware acceleration strategies. The principal goal of this work is to explore methods and concepts for getting around hardware constraints without compromising the model's accuracy. Additionally, we explore two notable paths for lightweight deep learning in the future: deployment techniques for TinyML and Large Language Models. Although these paths undoubtedly have potential, they also present significant challenges, encouraging research into unexplored areas.
Authors: Xiangpeng Li, Ali Mostafavi
Abstract: There is a limitation in the literature of data-driven analyses for the ex-post evaluation of community risk and resilience, particularly using features related to the performance of coupled human-infrastructure systems. To address this gap, in this study we created a machine learning-based method for the ex-post assessment of community risk and resilience and their interplay based on features related to the coupled human-infrastructure systems performance. Utilizing feature groups related to population protective actions, infrastructure/building performance features, and recovery features, we examined the risk and resilience performance of communities in the context of the 2017 Hurricane Harvey in Harris County, Texas. These features related to the coupled human-infrastructure systems performance were processed using the K-means clustering method to classify census block groups into four distinct clusters then, based on feature analysis, these clusters were labeled and designated into four quadrants of risk-resilience archetypes. Finally, we analyzed the disparities in risk-resilience status of spatial areas across different clusters as well as different income groups. The findings unveil the risk-resilience status of spatial areas shaped by their coupled human-infrastructure systems performance and their interactions. The results also inform about features that contribute to high resilience in high-risk areas. For example, the results indicate that in high-risk areas, evacuation rates contributed to a greater resilience, while in low-risk areas, preparedness contributed to greater resilience.
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 any audio system 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 available and provide the trained audio effect and synth models in a VST plugin at https://christhetree.github.io/all_pole_filters/.