Authors: Mario Guevara
Abstract: Development of a spatial-temporal and data-driven model of soil respiration at the global scale based on soil temperature, yearly soil moisture, and soil organic carbon (C) estimates. Prediction of soil respiration on an annual basis (1991-2018) with relatively high accuracy (NSE 0.69, CCC 0.82). Lower soil respiration trends, higher soil respiration magnitudes, and higher soil organic C stocks across areas experiencing the presence of sustainable soil management practices.
Authors: Georgy Tyukin
Abstract: Large Language Models are growing in size, and we expect them to continue to do so, as larger models train quicker. However, this increase in size will severely impact inference costs. Therefore model compression is important, to retain the performance of larger models, but with a reduced cost of running them. In this thesis we explore the methods of model compression, and we empirically demonstrate that the simple method of skipping latter attention sublayers in Transformer LLMs is an effective method of model compression, as these layers prove to be redundant, whilst also being incredibly computationally expensive. We observed a 21% speed increase in one-token generation for Llama 2 7B, whilst surprisingly and unexpectedly improving performance over several common benchmarks.
Authors: Yixuan Sun, Ololade Sowunmi, Romain Egele, Sri Hari Krishna Narayanan, Luke Van Roekel, Prasanna Balaprakash
Abstract: Training an effective deep learning model to learn ocean processes involves careful choices of various hyperparameters. We leverage DeepHyper's advanced search algorithms for multiobjective optimization, streamlining the development of neural networks tailored for ocean modeling. The focus is on optimizing Fourier neural operators (FNOs), a data-driven model capable of simulating complex ocean behaviors. Selecting the correct model and tuning the hyperparameters are challenging tasks, requiring much effort to ensure model accuracy. DeepHyper allows efficient exploration of hyperparameters associated with data preprocessing, FNO architecture-related hyperparameters, and various model training strategies. We aim to obtain an optimal set of hyperparameters leading to the most performant model. Moreover, on top of the commonly used mean squared error for model training, we propose adopting the negative anomaly correlation coefficient as the additional loss term to improve model performance and investigate the potential trade-off between the two terms. The experimental results show that the optimal set of hyperparameters enhanced model performance in single timestepping forecasting and greatly exceeded the baseline configuration in the autoregressive rollout for long-horizon forecasting up to 30 days. Utilizing DeepHyper, we demonstrate an approach to enhance the use of FNOs in ocean dynamics forecasting, offering a scalable solution with improved precision.
Authors: Zhengyang Zhao, Haitao Yuan, Nan Jiang, Minxiao Chen, Ning Liu, Zengxiang Li
Abstract: Accurate Traffic Prediction is a challenging task in intelligent transportation due to the spatial-temporal aspects of road networks. The traffic of a road network can be affected by long-distance or long-term dependencies where existing methods fall short in modeling them. In this paper, we introduce a novel framework known as Spatial-Temporal Multi-Granularity Framework (STMGF) to enhance the capture of long-distance and long-term information of the road networks. STMGF makes full use of different granularity information of road networks and models the long-distance and long-term information by gathering information in a hierarchical interactive way. Further, it leverages the inherent periodicity in traffic sequences to refine prediction results by matching with recent traffic data. We conduct experiments on two real-world datasets, and the results demonstrate that STMGF outperforms all baseline models and achieves state-of-the-art performance.
Authors: Kaveen Hiniduma, Suren Byna, Jean Luca Bez
Abstract: Data are the critical fuel for Artificial Intelligence (AI) models. Poor quality data produces inaccurate and ineffective AI models that may lead to incorrect or unsafe use. Checking for data readiness is a crucial step in improving data quality. Numerous R&D efforts have been spent on improving data quality. However, standardized metrics for evaluating data readiness for use in AI training are still evolving. In this study, we perform a comprehensive survey of metrics used for verifying AI's data readiness. This survey examines more than 120 papers that are published by ACM Digital Library, IEEE Xplore, other reputable journals, and articles published on the web by prominent AI experts. This survey aims to propose a taxonomy of data readiness for AI (DRAI) metrics for structured and unstructured datasets. We anticipate that this taxonomy can lead to new standards for DRAI metrics that would be used for enhancing the quality and accuracy of AI training and inference.
Authors: Kaloyan Danovski, Miguel C. Soriano, Lucas Lacasa
Abstract: The process of training an artificial neural network involves iteratively adapting its parameters so as to minimize the error of the network's prediction, when confronted with a learning task. This iterative change can be naturally interpreted as a trajectory in network space -- a time series of networks -- and thus the training algorithm (e.g. gradient descent optimization of a suitable loss function) can be interpreted as a dynamical system in graph space. In order to illustrate this interpretation, here we study the dynamical properties of this process by analyzing through this lens the network trajectories of a shallow neural network, and its evolution through learning a simple classification task. We systematically consider different ranges of the learning rate and explore both the dynamical and orbital stability of the resulting network trajectories, finding hints of regular and chaotic behavior depending on the learning rate regime. Our findings are put in contrast to common wisdom on convergence properties of neural networks and dynamical systems theory. This work also contributes to the cross-fertilization of ideas between dynamical systems theory, network theory and machine learning
Authors: Yutian Ren, Aaron Haohua Yen, G. P. Li
Abstract: Adaptive machine learning (ML) aims to allow ML models to adapt to ever-changing environments with potential concept drift after model deployment. Traditionally, adaptive ML requires a new dataset to be manually labeled to tailor deployed models to altered data distributions. Recently, an interactive causality based self-labeling method was proposed to autonomously associate causally related data streams for domain adaptation, showing promising results compared to traditional feature similarity-based semi-supervised learning. Several unanswered research questions remain, including self-labeling's compatibility with multivariate causality and the quantitative analysis of the auxiliary models used in the self-labeling. The auxiliary models, the interaction time model (ITM) and the effect state detector (ESD), are vital to the success of self-labeling. This paper further develops the self-labeling framework and its theoretical foundations to address these research questions. A framework for the application of self-labeling to multivariate causal graphs is proposed using four basic causal relationships, and the impact of non-ideal ITM and ESD performance is analyzed. A simulated experiment is conducted based on a multivariate causal graph, validating the proposed theory.
Authors: Ming Zhong, Dehao Liu, Raymundo Arroyave, Ulisses Braga-Neto
Abstract: This paper proposes a semi-supervised methodology for training physics-informed machine learning methods. This includes self-training of physics-informed neural networks and physics-informed Gaussian processes in isolation, and the integration of the two via co-training. We demonstrate via extensive numerical experiments how these methods can ameliorate the issue of propagating information forward in time, which is a common failure mode of physics-informed machine learning.
Authors: Andre R Kuroswiski, Annie S Wu, Angelo Passaro
Abstract: In this paper, we introduce an alternative approach to enhancing Multi-Agent Reinforcement Learning (MARL) through the integration of domain knowledge and attention-based policy mechanisms. Our methodology focuses on the incorporation of domain-specific expertise into the learning process, which simplifies the development of collaborative behaviors. This approach aims to reduce the complexity and learning overhead typically associated with MARL by enabling agents to concentrate on essential aspects of complex tasks, thus optimizing the learning curve. The utilization of attention mechanisms plays a key role in our model. It allows for the effective processing of dynamic context data and nuanced agent interactions, leading to more refined decision-making. Applied in standard MARL scenarios, such as the Stanford Intelligent Systems Laboratory (SISL) Pursuit and Multi-Particle Environments (MPE) Simple Spread, our method has been shown to improve both learning efficiency and the effectiveness of collaborative behaviors. The results indicate that our attention-based approach can be a viable approach for improving the efficiency of MARL training process, integrating domain-specific knowledge at the action level.
Authors: Franz A. Heinsen
Abstract: We propose a simple modification to the conventional attention mechanism applied by Transformers: Instead of quantifying pairwise query-key similarity with scaled dot-products, we quantify it with the logarithms of scaled dot-products of exponentials. Attention becomes expressible as a composition of log-sums of exponentials that is linearizable, with a latent space of constant size, enabling sequential application with constant time and space complexity per token. We implement our modification, verify that it works in practice, and conclude that it is a promising alternative to conventional attention.
Authors: Ruiqi Zhang, Licong Lin, Yu Bai, Song Mei
Abstract: Large Language Models (LLMs) often memorize sensitive, private, or copyrighted data during pre-training. LLM unlearning aims to eliminate the influence of undesirable data from the pre-trained model while preserving the model's utilities on other tasks. Several practical methods have recently been proposed for LLM unlearning, mostly based on gradient ascent (GA) on the loss of undesirable data. However, on certain unlearning tasks, these methods either fail to effectively unlearn the target data or suffer from catastrophic collapse -- a drastic degradation of the model's utilities. In this paper, we propose Negative Preference Optimization (NPO), a simple alignment-inspired method that could efficiently and effectively unlearn a target dataset. We theoretically show that the progression toward catastrophic collapse by minimizing the NPO loss is exponentially slower than GA. Through experiments on synthetic data and the benchmark TOFU dataset, we demonstrate that NPO-based methods achieve a better balance between unlearning the undesirable data and maintaining the model's utilities. We also observe that NPO-based methods generate more sensible outputs than GA-based methods, whose outputs are often gibberish. Remarkably, on TOFU, NPO-based methods are the first to achieve reasonable unlearning results in forgetting 50% (or more) of the training data, whereas existing methods already struggle with forgetting 10% of training data.
Authors: Yu Qin, Brittany Terese Fasy, Carola Wenk, Brian Summa
Abstract: Merge trees are a valuable tool in scientific visualization of scalar fields; however, current methods for merge tree comparisons are computationally expensive, primarily due to the exhaustive matching between tree nodes. To address this challenge, we introduce the merge tree neural networks (MTNN), a learned neural network model designed for merge tree comparison. The MTNN enables rapid and high-quality similarity computation. We first demonstrate how graph neural networks (GNNs), which emerged as an effective encoder for graphs, can be trained to produce embeddings of merge trees in vector spaces that enable efficient similarity comparison. Next, we formulate the novel MTNN model that further improves the similarity comparisons by integrating the tree and node embeddings with a new topological attention mechanism. We demonstrate the effectiveness of our model on real-world data in different domains and examine our model's generalizability across various datasets. Our experimental analysis demonstrates our approach's superiority in accuracy and efficiency. In particular, we speed up the prior state-of-the-art by more than 100x on the benchmark datasets while maintaining an error rate below 0.1%.
Authors: Andrew Holliday, Ahmed El-Geneidy, Gregory Dudek
Abstract: Transit agencies world-wide face tightening budgets. To maintain quality of service while cutting costs, efficient transit network design is essential. But planning a network of public transit routes is a challenging optimization problem. The most successful approaches to date use metaheuristic algorithms to search through the space of solutions by applying low-level heuristics that randomly alter routes in a network. The design of these low-level heuristics has a major impact on the quality of the result. In this paper we use deep reinforcement learning with graph neural nets to learn low-level heuristics for an evolutionary algorithm, instead of designing them manually. These learned heuristics improve the algorithm's results on benchmark synthetic cities with 70 nodes or more, and obtain state-of-the-art results when optimizing operating costs. They also improve upon a simulation of the real transit network in the city of Laval, Canada, by as much as 54% and 18% on two key metrics, and offer cost savings of up to 12% over the city's existing transit network.
Authors: Hadi Fanaee-T
Abstract: We introduce Natural Learning (NL), a novel algorithm that elevates the explainability and interpretability of machine learning to an extreme level. NL simplifies decisions into intuitive rules, like "We rejected your loan because your income, employment status, and age collectively resemble a rejected prototype more than an accepted prototype." When applied to real-life datasets, NL produces impressive results. For example, in a colon cancer dataset with 1545 patients and 10935 genes, NL achieves 98.1% accuracy, comparable to DNNs and RF, by analyzing just 3 genes of test samples against 2 discovered prototypes. Similarly, in the UCI's WDBC dataset, NL achieves 98.3% accuracy using only 7 features and 2 prototypes. Even on the MNIST dataset (0 vs. 1), NL achieves 99.5% accuracy with only 3 pixels from 2 prototype images. NL is inspired by prototype theory, an old concept in cognitive psychology suggesting that people learn single sparse prototypes to categorize objects. Leveraging this relaxed assumption, we redesign Support Vector Machines (SVM), replacing its mathematical formulation with a fully nearest-neighbor-based solution, and to address the curse of dimensionality, we utilize locality-sensitive hashing. Following theory's generalizability principle, we propose a recursive method to prune non-core features. As a result, NL efficiently discovers the sparsest prototypes in O(n^2pL) with high parallelization capacity in terms of n. Evaluation of NL with 17 benchmark datasets shows its significant outperformance compared to decision trees and logistic regression, two methods widely favored in healthcare for their interpretability. Moreover, NL achieves performance comparable to finetuned black-box models such as deep neural networks and random forests in 40% of cases, with only a 1-2% lower average accuracy. The code is available via http://natural-learning.cc.
Authors: Guilherme Seidyo Imai Aldeia (Federal University of ABC), Fabricio Olivetti de Franca (Federal University of ABC)
Abstract: In some situations, the interpretability of the machine learning models plays a role as important as the model accuracy. Interpretability comes from the need to trust the prediction model, verify some of its properties, or even enforce them to improve fairness. Many model-agnostic explanatory methods exists to provide explanations for black-box models. In the regression task, the practitioner can use white-boxes or gray-boxes models to achieve more interpretable results, which is the case of symbolic regression. When using an explanatory method, and since interpretability lacks a rigorous definition, there is a need to evaluate and compare the quality and different explainers. This paper proposes a benchmark scheme to evaluate explanatory methods to explain regression models, mainly symbolic regression models. Experiments were performed using 100 physics equations with different interpretable and non-interpretable regression methods and popular explanation methods, evaluating the performance of the explainers performance with several explanation measures. In addition, we further analyzed four benchmarks from the GP community. The results have shown that Symbolic Regression models can be an interesting alternative to white-box and black-box models that is capable of returning accurate models with appropriate explanations. Regarding the explainers, we observed that Partial Effects and SHAP were the most robust explanation models, with Integrated Gradients being unstable only with tree-based models. This benchmark is publicly available for further experiments.
Authors: Lillian Muyama, Antoine Neuraz, Adrien Coulet
Abstract: Background: Clinical diagnosis is typically reached by following a series of steps recommended by guidelines authored by colleges of experts. Accordingly, guidelines play a crucial role in rationalizing clinical decisions but suffer from limitations as they are built to cover the majority of the population and fail at covering patients with uncommon conditions. Moreover, their updates are long and expensive, making them unsuitable for emerging diseases and practices. Methods: Inspired by guidelines, we formulate the task of diagnosis as a sequential decision-making problem and study the use of Deep Reinforcement Learning (DRL) algorithms to learn the optimal sequence of actions to perform in order to obtain a correct diagnosis from Electronic Health Records (EHRs). We apply DRL on synthetic, but realistic EHRs and develop two clinical use cases: Anemia diagnosis, where the decision pathways follow the schema of a decision tree; and Systemic Lupus Erythematosus (SLE) diagnosis, which follows a weighted criteria score. We particularly evaluate the robustness of our approaches to noisy and missing data since these frequently occur in EHRs. Results: In both use cases, and in the presence of imperfect data, our best DRL algorithms exhibit competitive performance when compared to the traditional classifiers, with the added advantage that they enable the progressive generation of a pathway to the suggested diagnosis which can both guide and explain the decision-making process. Conclusion: DRL offers the opportunity to learn personalized decision pathways to diagnosis. We illustrate with our two use cases their advantages: they generate step-by-step pathways that are self-explanatory; and their correctness is competitive when compared to state-of-the-art approaches.
Authors: Sai Aparna Aketi, Abolfazl Hashemi, Kaushik Roy
Abstract: Decentralized learning is crucial in supporting on-device learning over large distributed datasets, eliminating the need for a central server. However, the communication overhead remains a major bottleneck for the practical realization of such decentralized setups. To tackle this issue, several algorithms for decentralized training with compressed communication have been proposed in the literature. Most of these algorithms introduce an additional hyper-parameter referred to as consensus step-size which is tuned based on the compression ratio at the beginning of the training. In this work, we propose AdaGossip, a novel technique that adaptively adjusts the consensus step-size based on the compressed model differences between neighboring agents. We demonstrate the effectiveness of the proposed method through an exhaustive set of experiments on various Computer Vision datasets (CIFAR-10, CIFAR-100, Fashion MNIST, Imagenette, and ImageNet), model architectures, and network topologies. Our experiments show that the proposed method achieves superior performance ($0-2\%$ improvement in test accuracy) compared to the current state-of-the-art method for decentralized learning with communication compression.
Authors: Anshuman Sinha, Spencer H. Bryngelson
Abstract: We demonstrate that neural networks can be FLOP-efficient integrators of one-dimensional oscillatory integrands. We train a feed-forward neural network to compute integrals of highly oscillatory 1D functions. The training set is a parametric combination of functions with varying characters and oscillatory behavior degrees. Numerical examples show that these networks are FLOP-efficient for sufficiently oscillatory integrands with an average FLOP gain of 1000 FLOPs. The network calculates oscillatory integrals better than traditional quadrature methods under the same computational budget or number of floating point operations. We find that feed-forward networks of 5 hidden layers are satisfactory for a relative accuracy of 0.001. The computational burden of inference of the neural network is relatively small, even compared to inner-product pattern quadrature rules. We postulate that our result follows from learning latent patterns in the oscillatory integrands that are otherwise opaque to traditional numerical integrators.
Authors: Jinyuan Feng, Min Chen, Zhiqiang Pu, Tenghai Qiu, Jianqiang Yi
Abstract: Multi-task reinforcement learning (MTRL) demonstrate potential for enhancing the generalization of a robot, enabling it to perform multiple tasks concurrently. However, the performance of MTRL may still be susceptible to conflicts between tasks and negative interference. To facilitate efficient MTRL, we propose Task-Specific Action Correction (TSAC), a general and complementary approach designed for simultaneous learning of multiple tasks. TSAC decomposes policy learning into two separate policies: a shared policy (SP) and an action correction policy (ACP). To alleviate conflicts resulting from excessive focus on specific tasks' details in SP, ACP incorporates goal-oriented sparse rewards, enabling an agent to adopt a long-term perspective and achieve generalization across tasks. Additional rewards transform the original problem into a multi-objective MTRL problem. Furthermore, to convert the multi-objective MTRL into a single-objective formulation, TSAC assigns a virtual expected budget to the sparse rewards and employs Lagrangian method to transform a constrained single-objective optimization into an unconstrained one. Experimental evaluations conducted on Meta-World's MT10 and MT50 benchmarks demonstrate that TSAC outperforms existing state-of-the-art methods, achieving significant improvements in both sample efficiency and effective action execution.
Authors: Gon\c{c}alo Paulo, Thomas Marshall, Nora Belrose
Abstract: Recent advances in recurrent neural network architectures, such as Mamba and RWKV, have enabled RNNs to match or exceed the performance of equal-size transformers in terms of language modeling perplexity and downstream evaluations, suggesting that future systems may be built on completely new architectures. In this paper, we examine if selected interpretability methods originally designed for transformer language models will transfer to these up-and-coming recurrent architectures. Specifically, we focus on steering model outputs via contrastive activation addition, on eliciting latent predictions via the tuned lens, and eliciting latent knowledge from models fine-tuned to produce false outputs under certain conditions. Our results show that most of these techniques are effective when applied to RNNs, and we show that it is possible to improve some of them by taking advantage of RNNs' compressed state.
Authors: Yutian Ren, Yuqi He, Xuyin Zhang, Aaron Yen, G. P. Li
Abstract: Machine Learning (ML) has been demonstrated to improve productivity in many manufacturing applications. To host these ML applications, several software and Industrial Internet of Things (IIoT) systems have been proposed for manufacturing applications to deploy ML applications and provide real-time intelligence. Recently, an interactive causality enabled self-labeling method has been proposed to advance adaptive ML applications in cyber-physical systems, especially manufacturing, by automatically adapting and personalizing ML models after deployment to counter data distribution shifts. The unique features of the self-labeling method require a novel software system to support dynamism at various levels. This paper proposes the AdaptIoT system, comprised of an end-to-end data streaming pipeline, ML service integration, and an automated self-labeling service. The self-labeling service consists of causal knowledge bases and automated full-cycle self-labeling workflows to adapt multiple ML models simultaneously. AdaptIoT employs a containerized microservice architecture to deliver a scalable and portable solution for small and medium-sized manufacturers. A field demonstration of a self-labeling adaptive ML application is conducted with a makerspace and shows reliable performance.
Authors: Bryan Bo Cao, Abhinav Sharma, Lawrence O'Gorman, Michael Coss, Shubham Jain
Abstract: Despite accuracy and computation benchmarks being widely available to help choose among neural network models, these are usually trained on datasets with many classes, and do not give a precise idea of performance for applications of few (< 10) classes. The conventional procedure to predict performance is to train and test repeatedly on the different models and dataset variations of interest. However, this is computationally expensive. We propose an efficient classification difficulty measure that is calculated from the number of classes and intra- and inter-class similarity metrics of the dataset. After a single stage of training and testing per model family, relative performance for different datasets and models of the same family can be predicted by comparing difficulty measures - without further training and testing. We show how this measure can help a practitioner select a computationally efficient model for a small dataset 6 to 29x faster than through repeated training and testing. We give an example of use of the measure for an industrial application in which options are identified to select a model 42% smaller than the baseline YOLOv5-nano model, and if class merging from 3 to 2 classes meets requirements, 85% smaller.
Authors: Shaona Ghosh, Prasoon Varshney, Erick Galinkin, Christopher Parisien
Abstract: As Large Language Models (LLMs) and generative AI become more widespread, the content safety risks associated with their use also increase. We find a notable deficiency in high-quality content safety datasets and benchmarks that comprehensively cover a wide range of critical safety areas. To address this, we define a broad content safety risk taxonomy, comprising 13 critical risk and 9 sparse risk categories. Additionally, we curate AEGISSAFETYDATASET, a new dataset of approximately 26, 000 human-LLM interaction instances, complete with human annotations adhering to the taxonomy. We plan to release this dataset to the community to further research and to help benchmark LLM models for safety. To demonstrate the effectiveness of the dataset, we instruction-tune multiple LLM-based safety models. We show that our models (named AEGISSAFETYEXPERTS), not only surpass or perform competitively with the state-of-the-art LLM-based safety models and general purpose LLMs, but also exhibit robustness across multiple jail-break attack categories. We also show how using AEGISSAFETYDATASET during the LLM alignment phase does not negatively impact the performance of the aligned models on MT Bench scores. Furthermore, we propose AEGIS, a novel application of a no-regret online adaptation framework with strong theoretical guarantees, to perform content moderation with an ensemble of LLM content safety experts in deployment
Authors: Xuheng Li, Heyang Zhao, Quanquan Gu
Abstract: Contextual dueling bandits, where a learner compares two options based on context and receives feedback indicating which was preferred, extends classic dueling bandits by incorporating contextual information for decision-making and preference learning. Several algorithms based on the upper confidence bound (UCB) have been proposed for linear contextual dueling bandits. However, no algorithm based on posterior sampling has been developed in this setting, despite the empirical success observed in traditional contextual bandits. In this paper, we propose a Thompson sampling algorithm, named FGTS.CDB, for linear contextual dueling bandits. At the core of our algorithm is a new Feel-Good exploration term specifically tailored for dueling bandits. This term leverages the independence of the two selected arms, thereby avoiding a cross term in the analysis. We show that our algorithm achieves nearly minimax-optimal regret, i.e., $\tilde{\mathcal{O}}(d\sqrt T)$, where $d$ is the model dimension and $T$ is the time horizon. Finally, we evaluate our algorithm on synthetic data and observe that FGTS.CDB outperforms existing algorithms by a large margin.
Authors: Mahdi Tavassoli Kejani (UT3), Fadi Dornaika (IMT), Jean-Michel Loubes (IMT)
Abstract: In recent years, Graph Neural Networks (GNNs) have made significant advancements, particularly in tasks such as node classification, link prediction, and graph representation. However, challenges arise from biases that can be hidden not only in the node attributes but also in the connections between entities. Therefore, ensuring fairness in graph neural network learning has become a critical problem. To address this issue, we propose a novel model for training fairness-aware GNN, which enhances the Counterfactual Augmented Fair Graph Neural Network Framework (CAF). Our approach integrates Supervised Contrastive Loss and Environmental Loss to enhance both accuracy and fairness. Experimental validation on three real datasets demonstrates the superiority of our proposed model over CAF and several other existing graph-based learning methods.
Authors: Connall Garrod, Jonathan P. Keating
Abstract: Modern deep neural networks have achieved high performance across various tasks. Recently, researchers have noted occurrences of low-dimensional structure in the weights, Hessian's, gradients, and feature vectors of these networks, spanning different datasets and architectures when trained to convergence. In this analysis, we theoretically demonstrate these observations arising, and show how they can be unified within a generalized unconstrained feature model that can be considered analytically. Specifically, we consider a previously described structure called Neural Collapse, and its multi-layer counterpart, Deep Neural Collapse, which emerges when the network approaches global optima. This phenomenon explains the other observed low-dimensional behaviours on a layer-wise level, such as the bulk and outlier structure seen in Hessian spectra, and the alignment of gradient descent with the outlier eigenspace of the Hessian. Empirical results in both the deep linear unconstrained feature model and its non-linear equivalent support these predicted observations.
Authors: Fatima Ezzeddine, Mirna Saad, Omran Ayoub, Davide Andreoletti, Martin Gjoreski, Ihab Sbeity, Marc Langheinrich, Silvia Giordano
Abstract: Anomaly detection (AD), also referred to as outlier detection, is a statistical process aimed at identifying observations within a dataset that significantly deviate from the expected pattern of the majority of the data. Such a process finds wide application in various fields, such as finance and healthcare. While the primary objective of AD is to yield high detection accuracy, the requirements of explainability and privacy are also paramount. The first ensures the transparency of the AD process, while the second guarantees that no sensitive information is leaked to untrusted parties. In this work, we exploit the trade-off of applying Explainable AI (XAI) through SHapley Additive exPlanations (SHAP) and differential privacy (DP). We perform AD with different models and on various datasets, and we thoroughly evaluate the cost of privacy in terms of decreased accuracy and explainability. Our results show that the enforcement of privacy through DP has a significant impact on detection accuracy and explainability, which depends on both the dataset and the considered AD model. We further show that the visual interpretation of explanations is also influenced by the choice of the AD algorithm.
Authors: Shengze Dong, Zhuorui Cui, Ding Liu, Jinzhi Lei
Abstract: Motivation: Single-cell RNA sequencing (scRNA-seq) is a groundbreaking technology extensively utilized in biological research, facilitating the examination of gene expression at the individual cell level within a given tissue sample. While numerous tools have been developed for scRNA-seq data analysis, the challenge persists in capturing the distinct features of such data and replicating virtual datasets that share analogous statistical properties. Results: Our study introduces a generative approach termed scRNA-seq Diffusion Transformer (scRDiT). This method generates virtual scRNA-seq data by leveraging a real dataset. The method is a neural network constructed based on Denoising Diffusion Probabilistic Models (DDPMs) and Diffusion Transformers (DiTs). This involves subjecting Gaussian noises to the real dataset through iterative noise-adding steps and ultimately restoring the noises to form scRNA-seq samples. This scheme allows us to learn data features from actual scRNA-seq samples during model training. Our experiments, conducted on two distinct scRNA-seq datasets, demonstrate superior performance. Additionally, the model sampling process is expedited by incorporating Denoising Diffusion Implicit Models (DDIM). scRDiT presents a unified methodology empowering users to train neural network models with their unique scRNA-seq datasets, enabling the generation of numerous high-quality scRNA-seq samples. Availability and implementation: https://github.com/DongShengze/scRDiT
Authors: Ping Xu, Zhiyuan Ning, Meng Xiao, Guihai Feng, Xin Li, Yuanchun Zhou, Pengfei Wang
Abstract: Single-cell RNA sequencing (scRNA-seq) is essential for unraveling cellular heterogeneity and diversity, offering invaluable insights for bioinformatics advancements. Despite its potential, traditional clustering methods in scRNA-seq data analysis often neglect the structural information embedded in gene expression profiles, crucial for understanding cellular correlations and dependencies. Existing strategies, including graph neural networks, face challenges in handling the inefficiency due to scRNA-seq data's intrinsic high-dimension and high-sparsity. Addressing these limitations, we introduce scCDCG (single-cell RNA-seq Clustering via Deep Cut-informed Graph), a novel framework designed for efficient and accurate clustering of scRNA-seq data that simultaneously utilizes intercellular high-order structural information. scCDCG comprises three main components: (i) A graph embedding module utilizing deep cut-informed techniques, which effectively captures intercellular high-order structural information, overcoming the over-smoothing and inefficiency issues prevalent in prior graph neural network methods. (ii) A self-supervised learning module guided by optimal transport, tailored to accommodate the unique complexities of scRNA-seq data, specifically its high-dimension and high-sparsity. (iii) An autoencoder-based feature learning module that simplifies model complexity through effective dimension reduction and feature extraction. Our extensive experiments on 6 datasets demonstrate scCDCG's superior performance and efficiency compared to 7 established models, underscoring scCDCG's potential as a transformative tool in scRNA-seq data analysis. Our code is available at: https://github.com/XPgogogo/scCDCG.
Authors: Lakshmi Nair
Abstract: Contrastive Language-Image Pre-training (CLIP) has been shown to improve zero-shot generalization capabilities of language and vision models. In this paper, we extend CLIP for efficient knowledge distillation, by utilizing embeddings as teachers. Typical knowledge distillation frameworks require running forward passes through a teacher model, which is often prohibitive in the case of billion or trillion parameter teachers. In these cases, using only the embeddings of the teacher models to guide the distillation can yield significant computational savings. Our preliminary findings show that CLIP-based knowledge distillation with embeddings can outperform full scale knowledge distillation using $9\times$ less memory and $8\times$ less training time. Code available at: https://github.com/lnairGT/CLIP-Distillation/
Authors: Xudong Yu, Chenjia Bai, Hongyi Guo, Changhong Wang, Zhen Wang
Abstract: Offline Reinforcement Learning (RL) faces distributional shift and unreliable value estimation, especially for out-of-distribution (OOD) actions. To address this, existing uncertainty-based methods penalize the value function with uncertainty quantification and demand numerous ensemble networks, posing computational challenges and suboptimal outcomes. In this paper, we introduce a novel strategy employing diverse randomized value functions to estimate the posterior distribution of $Q$-values. It provides robust uncertainty quantification and estimates lower confidence bounds (LCB) of $Q$-values. By applying moderate value penalties for OOD actions, our method fosters a provably pessimistic approach. We also emphasize on diversity within randomized value functions and enhance efficiency by introducing a diversity regularization method, reducing the requisite number of networks. These modules lead to reliable value estimation and efficient policy learning from offline data. Theoretical analysis shows that our method recovers the provably efficient LCB-penalty under linear MDP assumptions. Extensive empirical results also demonstrate that our proposed method significantly outperforms baseline methods in terms of performance and parametric efficiency.
Authors: Claudia Ehrig, Catherine Cleophas, Germain Forestier
Abstract: Models, pre-trained on a similar or diverse source data set, have become pivotal in enhancing the efficiency and accuracy of time series forecasting on target data sets by leveraging transfer learning. While benchmarks validate the performance of model generalization on various target data sets, there is no structured research providing similarity and diversity measures explaining which characteristics of source and target data lead to transfer learning success. Our study pioneers in systematically evaluating the impact of source-target similarity and source diversity on zero-shot and fine-tuned forecasting outcomes in terms of accuracy, bias, and uncertainty estimation. We investigate these dynamics using pre-trained neural networks across five public source datasets, applied in forecasting five target data sets, including real-world wholesales data. We identify two feature-based similarity and diversity measures showing: Source-target similarity enhances forecasting accuracy and reduces bias, while source diversity enhances forecasting accuracy and uncertainty estimation and increases the bias.
Authors: Sebastian Bordt, Harsha Nori, Vanessa Rodrigues, Besmira Nushi, Rich Caruana
Abstract: While many have shown how Large Language Models (LLMs) can be applied to a diverse set of tasks, the critical issues of data contamination and memorization are often glossed over. In this work, we address this concern for tabular data. Specifically, we introduce a variety of different techniques to assess whether a language model has seen a tabular dataset during training. This investigation reveals that LLMs have memorized many popular tabular datasets verbatim. We then compare the few-shot learning performance of LLMs on datasets that were seen during training to the performance on datasets released after training. We find that LLMs perform better on datasets seen during training, indicating that memorization leads to overfitting. At the same time, LLMs show non-trivial performance on novel datasets and are surprisingly robust to data transformations. We then investigate the in-context statistical learning abilities of LLMs. Without fine-tuning, we find them to be limited. This suggests that much of the few-shot performance on novel datasets is due to the LLM's world knowledge. Overall, our results highlight the importance of testing whether an LLM has seen an evaluation dataset during pre-training. We make the exposure tests we developed available as the tabmemcheck Python package at https://github.com/interpretml/LLM-Tabular-Memorization-Checker
URLs: https://github.com/interpretml/LLM-Tabular-Memorization-Checker
Authors: Yuka Hashimoto, Ryuichiro Hataya
Abstract: This paper introduces quantum circuit $C^*$-algebra net, which provides a connection between $C^*$-algebra nets proposed in classical machine learning and quantum circuits. Using $C^*$-algebra, a generalization of the space of complex numbers, we can represent quantum gates as weight parameters of a neural network. By introducing additional parameters, we can induce interaction among multiple circuits constructed by quantum gates. This interaction enables the circuits to share information among them, which contributes to improved generalization performance in machine learning tasks. As an application, we propose to use the quantum circuit $C^*$-algebra net to encode classical data into quantum states, which enables us to integrate classical data into quantum algorithms. Numerical results demonstrate that the interaction among circuits improves performance significantly in image classification, and encoded data by the quantum circuit $C^*$-algebra net are useful for downstream quantum machine learning tasks.
Authors: Rui Cai, Shichao Pei, Xiangliang Zhang
Abstract: Relational learning is an essential task in the domain of knowledge representation, particularly in knowledge graph completion (KGC).While relational learning in traditional single-modal settings has been extensively studied, exploring it within a multimodal KGC context presents distinct challenges and opportunities. One of the major challenges is inference on newly discovered relations without any associated training data. This zero-shot relational learning scenario poses unique requirements for multimodal KGC, i.e., utilizing multimodality to facilitate relational learning. However, existing works fail to support the leverage of multimodal information and leave the problem unexplored. In this paper, we propose a novel end-to-end framework, consisting of three components, i.e., multimodal learner, structure consolidator, and relation embedding generator, to integrate diverse multimodal information and knowledge graph structures to facilitate the zero-shot relational learning. Evaluation results on two multimodal knowledge graphs demonstrate the superior performance of our proposed method.
Authors: Emre Ozfatura, Kerem Ozfatura, Alptekin Kupcu, Deniz Gunduz
Abstract: Federated learning (FL) has been introduced to enable a large number of clients, possibly mobile devices, to collaborate on generating a generalized machine learning model thanks to utilizing a larger number of local samples without sharing to offer certain privacy to collaborating clients. However, due to the participation of a large number of clients, it is often difficult to profile and verify each client, which leads to a security threat that malicious participants may hamper the accuracy of the trained model by conveying poisoned models during the training. Hence, the aggregation framework at the parameter server also needs to minimize the detrimental effects of these malicious clients. A plethora of attack and defence strategies have been analyzed in the literature. However, often the Byzantine problem is analyzed solely from the outlier detection perspective, being oblivious to the topology of neural networks (NNs). In the scope of this work, we argue that by extracting certain side information specific to the NN topology, one can design stronger attacks. Hence, inspired by the sparse neural networks, we introduce a hybrid sparse Byzantine attack that is composed of two parts: one exhibiting a sparse nature and attacking only certain NN locations with higher sensitivity, and the other being more silent but accumulating over time, where each ideally targets a different type of defence mechanism, and together they form a strong but imperceptible attack. Finally, we show through extensive simulations that the proposed hybrid Byzantine attack is effective against 8 different defence methods.
Authors: Keyvan Amiri Elyasi, Han van der Aa, Heiner Stuckenschmidt
Abstract: We present PGTNet, an approach that transforms event logs into graph datasets and leverages graph-oriented data for training Process Graph Transformer Networks to predict the remaining time of business process instances. PGTNet consistently outperforms state-of-the-art deep learning approaches across a diverse range of 20 publicly available real-world event logs. Notably, our approach is most promising for highly complex processes, where existing deep learning approaches encounter difficulties stemming from their limited ability to learn control-flow relationships among process activities and capture long-range dependencies. PGTNet addresses these challenges, while also being able to consider multiple process perspectives during the learning process.
Authors: Karim Abdel Sadek, Marek Elias
Abstract: ML-augmented algorithms utilize predictions to achieve performance beyond their worst-case bounds. Producing these predictions might be a costly operation -- this motivated Im et al. '22 to introduce the study of algorithms which use predictions parsimoniously. We design parsimonious algorithms for caching and MTS with action predictions, proposed by Antoniadis et al. '20, focusing on the parameters of consistency (performance with perfect predictions) and smoothness (dependence of their performance on the prediction error). Our algorithm for caching is 1-consistent, robust, and its smoothness deteriorates with the decreasing number of available predictions. We propose an algorithm for general MTS whose consistency and smoothness both scale linearly with the decreasing number of predictions. Without the restriction on the number of available predictions, both algorithms match the earlier guarantees achieved by Antoniadis et al. '20.
Authors: Amir Hagai, Yair Weiss
Abstract: The ability to fool deep learning classifiers with tiny perturbations of the input has lead to the development of adversarial training in which the loss with respect to adversarial examples is minimized in addition to the training examples. While adversarial training improves the robustness of the learned classifiers, the procedure is computationally expensive, sensitive to hyperparameters and may still leave the classifier vulnerable to other types of small perturbations. In this paper we analyze the adversarial robustness of the 1 Nearest Neighbor (1NN) classifier and compare its performance to adversarial training. We prove that under reasonable assumptions, the 1 NN classifier will be robust to {\em any} small image perturbation of the training images and will give high adversarial accuracy on test images as the number of training examples goes to infinity. In experiments with 45 different binary image classification problems taken from CIFAR10, we find that 1NN outperform TRADES (a powerful adversarial training algorithm) in terms of average adversarial accuracy. In additional experiments with 69 pretrained robust models for CIFAR10, we find that 1NN outperforms almost all of them in terms of robustness to perturbations that are only slightly different from those seen during training. Taken together, our results suggest that modern adversarial training methods still fall short of the robustness of the simple 1NN classifier. our code can be found at https://github.com/amirhagai/On-Adversarial-Training-And-The-1-Nearest-Neighbor-Classifier
URLs: https://github.com/amirhagai/On-Adversarial-Training-And-The-1-Nearest-Neighbor-Classifier
Authors: Tom Hanika, Tobias Hille
Abstract: Dimensionality is an important aspect for analyzing and understanding (high-dimensional) data. In their 2006 ICDM paper Tatti et al. answered the question for a (interpretable) dimension of binary data tables by introducing a normalized correlation dimension. In the present work we revisit their results and contrast them with a concept based notion of intrinsic dimension (ID) recently introduced for geometric data sets. To do this, we present a novel approximation for this ID that is based on computing concepts only up to a certain support value. We demonstrate and evaluate our approximation using all available datasets from Tatti et al., which have between 469 and 41271 extrinsic dimensions.
Authors: Yanjie Li, Weijun Li, Lina Yu, Min Wu, Jingyi Liu, Wenqiang Li, Meilan Hao, Shu Wei, Yusong Deng
Abstract: The mathematical formula is the human language to describe nature and is the essence of scientific research. Finding mathematical formulas from observational data is a major demand of scientific research and a major challenge of artificial intelligence. This area is called symbolic regression. Originally symbolic regression was often formulated as a combinatorial optimization problem and solved using GP or reinforcement learning algorithms. These two kinds of algorithms have strong noise robustness ability and good Versatility. However, inference time usually takes a long time, so the search efficiency is relatively low. Later, based on large-scale pre-training data proposed, such methods use a large number of synthetic data points and expression pairs to train a Generative Pre-Trained Transformer(GPT). Then this GPT can only need to perform one forward propagation to obtain the results, the advantage is that the inference speed is very fast. However, its performance is very dependent on the training data and performs poorly on data outside the training set, which leads to poor noise robustness and Versatility of such methods. So, can we combine the advantages of the above two categories of SR algorithms? In this paper, we propose \textbf{FormulaGPT}, which trains a GPT using massive sparse reward learning histories of reinforcement learning-based SR algorithms as training data. After training, the SR algorithm based on reinforcement learning is distilled into a Transformer. When new test data comes, FormulaGPT can directly generate a "reinforcement learning process" and automatically update the learning policy in context. Tested on more than ten datasets including SRBench, formulaGPT achieves the state-of-the-art performance in fitting ability compared with four baselines. In addition, it achieves satisfactory results in noise robustness, versatility, and inference efficiency.
Authors: Yu Zhou, Xingyu Wu, Beicheng Huang, Jibin Wu, Liang Feng, Kay Chen Tan
Abstract: Causality reveals fundamental principles behind data distributions in real-world scenarios, and the capability of large language models (LLMs) to understand causality directly impacts their efficacy across explaining outputs, adapting to new evidence, and generating counterfactuals. With the proliferation of LLMs, the evaluation of this capacity is increasingly garnering attention. However, the absence of a comprehensive benchmark has rendered existing evaluation studies being straightforward, undiversified, and homogeneous. To address these challenges, this paper proposes a comprehensive benchmark, namely CausalBench, to evaluate the causality understanding capabilities of LLMs. Originating from the causal research community, CausalBench encompasses three causal learning-related tasks, which facilitate a convenient comparison of LLMs' performance with classic causal learning algorithms. Meanwhile, causal networks of varying scales and densities are integrated in CausalBench, to explore the upper limits of LLMs' capabilities across task scenarios of varying difficulty. Notably, background knowledge and structured data are also incorporated into CausalBench to thoroughly unlock the underlying potential of LLMs for long-text comprehension and prior information utilization. Based on CausalBench, this paper evaluates nineteen leading LLMs and unveils insightful conclusions in diverse aspects. Firstly, we present the strengths and weaknesses of LLMs and quantitatively explore the upper limits of their capabilities across various scenarios. Meanwhile, we further discern the adaptability and abilities of LLMs to specific structural networks and complex chain of thought structures. Moreover, this paper quantitatively presents the differences across diverse information sources and uncovers the gap between LLMs' capabilities in causal understanding within textual contexts and numerical domains.
Authors: Mahmut S. Gokmen, Cody Bumgardner, Jie Zhang, Ge Wang, Jin Chen
Abstract: Consistency models possess high capabilities for image generation, advancing sampling steps to a single step through their advanced techniques. Current advancements move one step forward consistency training techniques and eliminates the limitation of distillation training. Even though the proposed curriculum and noise scheduling in improved training techniques yield better results than basic consistency models, it lacks well balanced noise distribution and its consistency between curriculum. In this study, it is investigated the balance between high and low noise levels in noise distribution and offered polynomial noise distribution to maintain the stability. This proposed polynomial noise distribution is also supported with a predefined Karras noises to prevent unique noise levels arises with Karras noise generation algorithm. Furthermore, by elimination of learned noisy steps with a curriculum based on sinusoidal function increase the performance of the model in denoising. To make a fair comparison with the latest released consistency model training techniques, experiments are conducted with same hyper-parameters except curriculum and noise distribution. The models utilized during experiments are determined with low depth to prove the robustness of our proposed technique. The results show that the polynomial noise distribution outperforms the model trained with log-normal noise distribution, yielding a 33.54 FID score after 100,000 training steps with constant discretization steps. Additionally, the implementation of a sinusoidal-based curriculum enhances denoising performance, resulting in a FID score of 30.48.
Authors: Matthew Thomas Jackson, Michael Tryfan Matthews, Cong Lu, Benjamin Ellis, Shimon Whiteson, Jakob Foerster
Abstract: In many real-world settings, agents must learn from an offline dataset gathered by some prior behavior policy. Such a setting naturally leads to distribution shift between the behavior policy and the target policy being trained - requiring policy conservatism to avoid instability and overestimation bias. Autoregressive world models offer a different solution to this by generating synthetic, on-policy experience. However, in practice, model rollouts must be severely truncated to avoid compounding error. As an alternative, we propose policy-guided diffusion. Our method uses diffusion models to generate entire trajectories under the behavior distribution, applying guidance from the target policy to move synthetic experience further on-policy. We show that policy-guided diffusion models a regularized form of the target distribution that balances action likelihood under both the target and behavior policies, leading to plausible trajectories with high target policy probability, while retaining a lower dynamics error than an offline world model baseline. Using synthetic experience from policy-guided diffusion as a drop-in substitute for real data, we demonstrate significant improvements in performance across a range of standard offline reinforcement learning algorithms and environments. Our approach provides an effective alternative to autoregressive offline world models, opening the door to the controllable generation of synthetic training data.
Authors: Zhanran Lin, Puheng Li, Lei Wu
Abstract: One of the most intriguing findings in the structure of neural network landscape is the phenomenon of mode connectivity: For two typical global minima, there exists a path connecting them without barrier. This concept of mode connectivity has played a crucial role in understanding important phenomena in deep learning. In this paper, we conduct a fine-grained analysis of this connectivity phenomenon. First, we demonstrate that in the overparameterized case, the connecting path can be as simple as a two-piece linear path, and the path length can be nearly equal to the Euclidean distance. This finding suggests that the landscape should be nearly convex in a certain sense. Second, we uncover a surprising star-shaped connectivity: For a finite number of typical minima, there exists a center on minima manifold that connects all of them simultaneously via linear paths. These results are provably valid for linear networks and two-layer ReLU networks under a teacher-student setup, and are empirically supported by models trained on MNIST and CIFAR-10.
Authors: Maximilian Witte, Fabricio Rodrigues Lapolli, Philip Freese, Sebastian G\"otschel, Daniel Ruprecht, Peter Korn, Christopher Kadow
Abstract: Using the nonlinear shallow water equations as benchmark, we demonstrate that a simulation with the ICON-O ocean model with a 20km resolution that is frequently corrected by a U-net-type neural network can achieve discretization errors of a simulation with 10km resolution. The network, originally developed for image-based super-resolution in post-processing, is trained to compute the difference between solutions on both meshes and is used to correct the coarse mesh every 12h. Our setup is the Galewsky test case, modeling transition of a barotropic instability into turbulent flow. We show that the ML-corrected coarse resolution run correctly maintains a balance flow and captures the transition to turbulence in line with the higher resolution simulation. After 8 day of simulation, the $L_2$-error of the corrected run is similar to a simulation run on the finer mesh. While mass is conserved in the corrected runs, we observe some spurious generation of kinetic energy.
Authors: Ayman Chaouki, Jesse Read, Albert Bifet
Abstract: Decision Trees are prominent prediction models for interpretable Machine Learning. They have been thoroughly researched, mostly in the batch setting with a fixed labelled dataset, leading to popular algorithms such as C4.5, ID3 and CART. Unfortunately, these methods are of heuristic nature, they rely on greedy splits offering no guarantees of global optimality and often leading to unnecessarily complex and hard-to-interpret Decision Trees. Recent breakthroughs addressed this suboptimality issue in the batch setting, but no such work has considered the online setting with data arriving in a stream. To this end, we devise a new Monte Carlo Tree Search algorithm, Thompson Sampling Decision Trees (TSDT), able to produce optimal Decision Trees in an online setting. We analyse our algorithm and prove its almost sure convergence to the optimal tree. Furthermore, we conduct extensive experiments to validate our findings empirically. The proposed TSDT outperforms existing algorithms on several benchmarks, all while presenting the practical advantage of being tailored to the online setting.
Authors: Wei Xu, Derek Freeman DeSantis, Xihaier Luo, Avish Parmar, Klaus Tan, Balu Nadiga, Yihui Ren, Shinjae Yoo
Abstract: Learning a continuous and reliable representation of physical fields from sparse sampling is challenging and it affects diverse scientific disciplines. In a recent work, we present a novel model called MMGN (Multiplicative and Modulated Gabor Network) with implicit neural networks. In this work, we design additional studies leveraging explainability methods to complement the previous experiments and further enhance the understanding of latent representations generated by the model. The adopted methods are general enough to be leveraged for any latent space inspection. Preliminary results demonstrate the contextual information incorporated in the latent representations and their impact on the model performance. As a work in progress, we will continue to verify our findings and develop novel explainability approaches.
Authors: Christian Marius Lillelund, Martin Magris, Christian Fischer Pedersen
Abstract: Predicting future events always comes with uncertainty, but traditional non-Bayesian methods cannot distinguish certain from uncertain predictions or explain the confidence in their predictions. In survival analysis, Bayesian 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 Bayesian network architectures, which we train by optimizing the Cox partial likelihood and combining input-dependent aleatoric uncertainty with model-specific 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-Bayesian alternatives.
Authors: Filip Granqvist, Congzheng Song, \'Aine Cahill, Rogier van Dalen, Martin Pelikan, Yi Sheng Chan, Xiaojun Feng, Natarajan Krishnaswami, Vojta Jina, Mona Chitnis
Abstract: Federated learning (FL) is an emerging machine learning (ML) training paradigm where clients own their data and collaborate to train a global model, without revealing any data to the server and other participants. Researchers commonly perform experiments in a simulation environment to quickly iterate on ideas. However, existing open-source tools do not offer the efficiency required to simulate FL on larger and more realistic FL datasets. We introduce pfl-research, a fast, modular, and easy-to-use Python framework for simulating FL. It supports TensorFlow, PyTorch, and non-neural network models, and is tightly integrated with state-of-the-art privacy algorithms. We study the speed of open-source FL frameworks and show that pfl-research is 7-72$\times$ faster than alternative open-source frameworks on common cross-device setups. Such speedup will significantly boost the productivity of the FL research community and enable testing hypotheses on realistic FL datasets that were previously too resource intensive. We release a suite of benchmarks that evaluates an algorithm's overall performance on a diverse set of realistic scenarios. The code is available on GitHub at https://github.com/apple/pfl-research.
Authors: Zihan Fang, Zheng Lin, Zhe Chen, Xianhao Chen, Yue Gao, Yuguang Fang
Abstract: Recently, there has been a surge in the development of advanced intelligent generative content (AIGC), especially large language models (LLMs). However, for many downstream tasks, it is necessary to fine-tune LLMs using private data. While federated learning offers a promising privacy-preserving solution to LLM fine-tuning, the substantial size of an LLM, combined with high computational and communication demands, makes it hard to apply to downstream tasks. More importantly, private edge servers often possess varying computing and network resources in real-world scenarios, introducing additional complexities to LLM fine-tuning. To tackle these problems, we design and implement an automated federated pipeline, named FedPipe, to fine-tune LLMs with minimal training cost but without adding any inference latency. FedPipe firstly identifies the weights to be fine-tuned based on their contributions to the LLM training. It then configures a low-rank adapter for each selected weight to train local low-rank adapters on an edge server, and aggregate local adapters of all edge servers to fine-tune the whole LLM. Finally, it appropriately quantizes the parameters of LLM to reduce memory space according to the requirements of edge servers. Extensive experiments demonstrate that FedPipe expedites the model training and achieves higher accuracy than state-of-the-art benchmarks.
Authors: Thomas L. Lee, Sigrid Passano Hellan, Linus Ericsson, Elliot J. Crowley, Amos Storkey
Abstract: In continual learning (CL) -- where a learner trains on a stream of data -- standard hyperparameter optimisation (HPO) cannot be applied, as a learner does not have access to all of the data at the same time. This has prompted the development of CL-specific HPO frameworks. The most popular way to tune hyperparameters in CL is to repeatedly train over the whole data stream with different hyperparameter settings. However, this end-of-training HPO is unrealistic as in practice a learner can only see the stream once. Hence, there is an open question: what HPO framework should a practitioner use for a CL problem in reality? This paper answers this question by evaluating several realistic HPO frameworks. We find that all the HPO frameworks considered, including end-of-training HPO, perform similarly. We therefore advocate using the realistic and most computationally efficient method: fitting the hyperparameters on the first task and then fixing them throughout training.
Authors: Jiayi Shen, Cheems Wang, Zehao Xiao, Nanne Van Noord, Marcel Worring
Abstract: This paper proposes \textit{GO4Align}, a multi-task optimization approach that tackles task imbalance by explicitly aligning the optimization across tasks. To achieve this, we design an adaptive group risk minimization strategy, compromising two crucial techniques in implementation: (i) dynamical group assignment, which clusters similar tasks based on task interactions; (ii) risk-guided group indicators, which exploit consistent task correlations with risk information from previous iterations. Comprehensive experimental results on diverse typical benchmarks demonstrate our method's performance superiority with even lower computational costs.
Authors: Victor-Alexandru Darvariu, Stephen Hailes, Mirco Musolesi
Abstract: Graphs are a natural representation for systems based on relations between connected entities. Combinatorial optimization problems, which arise when considering an objective function related to a process of interest on discrete structures, are often challenging due to the rapid growth of the solution space. The trial-and-error paradigm of Reinforcement Learning has recently emerged as a promising alternative to traditional methods, such as exact algorithms and (meta)heuristics, for discovering better decision-making strategies in a variety of disciplines including chemistry, computer science, and statistics. Despite the fact that they arose in markedly different fields, these techniques share significant commonalities. Therefore, we set out to synthesize this work in a unifying perspective that we term Graph Reinforcement Learning, interpreting it as a constructive decision-making method for graph problems. After covering the relevant technical background, we review works along the dividing line of whether the goal is to optimize graph structure given a process of interest, or to optimize the outcome of the process itself under fixed graph structure. Finally, we discuss the common challenges facing the field and open research questions. In contrast with other surveys, the present work focuses on non-canonical graph problems for which performant algorithms are typically not known and Reinforcement Learning is able to provide efficient and effective solutions.
Authors: Ekansh Sharma, Devin Kwok, Tom Denton, Daniel M. Roy, David Rolnick, Gintare Karolina Dziugaite
Abstract: Neural networks typically exhibit permutation symmetries which contribute to the non-convexity of the networks' loss landscapes, since linearly interpolating between two permuted versions of a trained network tends to encounter a high loss barrier. Recent work has argued that permutation symmetries are the only sources of non-convexity, meaning there are essentially no such barriers between trained networks if they are permuted appropriately. In this work, we refine these arguments into three distinct claims of increasing strength. We show that existing evidence only supports "weak linear connectivity"-that for each pair of networks belonging to a set of SGD solutions, there exist (multiple) permutations that linearly connect it with the other networks. In contrast, the claim "strong linear connectivity"-that for each network, there exists one permutation that simultaneously connects it with the other networks-is both intuitively and practically more desirable. This stronger claim would imply that the loss landscape is convex after accounting for permutation, and enable linear interpolation between three or more independently trained models without increased loss. In this work, we introduce an intermediate claim-that for certain sequences of networks, there exists one permutation that simultaneously aligns matching pairs of networks from these sequences. Specifically, we discover that a single permutation aligns sequences of iteratively trained as well as iteratively pruned networks, meaning that two networks exhibit low loss barriers at each step of their optimization and sparsification trajectories respectively. Finally, we provide the first evidence that strong linear connectivity may be possible under certain conditions, by showing that barriers decrease with increasing network width when interpolating among three networks.
Authors: Sayantan Kumara, Thomas Earnest, Braden Yang, Deydeep Kothapalli, Tammie L. S. Benzinger, Brian A. Gordon, Philip Payne, Aristeidis Sotiras
Abstract: Alzheimer Disease (AD) is a multi-faceted disorder, with each modality providing unique and complementary info about AD. In this study, we used a deep-learning based multimodal normative model to assess the heterogeneity in regional brain patterns for ATN (amyloid-tau-neurodegeneration) biomarkers. We selected discovery (n = 665) and replication (n = 430) cohorts with simultaneous availability of ATN biomarkers: Florbetapir amyloid, Flortaucipir tau and T1-weighted MRI (magnetic resonance imaging) imaging. A multimodal variational autoencoder (conditioned on age and sex) was used as a normative model to learn the multimodal regional brain patterns of a cognitively unimpaired (CU) control group. The trained model was applied on individuals on the ADS (AD Spectrum) to estimate their deviations (Z-scores) from the normative distribution, resulting in a Z-score regional deviation map per ADS individual per modality. ADS individuals with moderate or severe dementia showed higher proportion of regional outliers for each modality as well as more dissimilarity in modality-specific regional outlier patterns compared to ADS individuals with early or mild dementia. DSI was associated with the progressive stages of dementia, (ii) showed significant associations with neuropsychological composite scores and (iii) related to the longitudinal risk of CDR progression. Findings were reproducible in both discovery and replication cohorts. Our is the first study to examine the heterogeneity in AD through the lens of multiple neuroimaging modalities (ATN), based on distinct or overlapping patterns of regional outlier deviations. Regional MRI and tau outliers were more heterogenous than regional amyloid outliers. DSI has the potential to be an individual patient metric of neurodegeneration that can help in clinical decision making and monitoring patient response for anti-amyloid treatments.
Authors: Cristiano Fanelli, James Giroux, Patrick Moran, Hemalata Nayak, Karthik Suresh, Eric Walter
Abstract: The 2023 AI4EIC hackathon was the culmination of the third annual AI4EIC workshop at The Catholic University of America. This workshop brought together researchers from physics, data science and computer science to discuss the latest developments in Artificial Intelligence (AI) and Machine Learning (ML) for the Electron Ion Collider (EIC), including applications for detectors, accelerators, and experimental control. The hackathon, held on the final day of the workshop, involved using a chatbot powered by a Large Language Model, ChatGPT-3.5, to train a binary classifier neutrons and photons in simulated data from the \textsc{GlueX} Barrel Calorimeter. In total, six teams of up to four participants from all over the world took part in this intense educational and research event. This article highlights the hackathon challenge, the resources and methodology used, and the results and insights gained from analyzing physics data using the most cutting-edge tools in AI/ML.
Authors: Patrick Ebel, Brandon Victor, Peter Naylor, Gabriele Meoni, Federico Serva, Rochelle Schneider
Abstract: Hurricanes and coastal floods are among the most disastrous natural hazards. Both are intimately related to storm surges, as their causes and effects, respectively. However, the short-term forecasting of storm surges has proven challenging, especially when targeting previously unseen locations or sites without tidal gauges. Furthermore, recent work improved short and medium-term weather forecasting but the handling of raw unassimilated data remains non-trivial. In this paper, we tackle both challenges and demonstrate that neural networks can implicitly assimilate sparse in situ tide gauge data with coarse ocean state reanalysis in order to forecast storm surges. We curate a global dataset to learn and validate the dense prediction of storm surges, building on preceding efforts. Other than prior work limited to known gauges, our approach extends to ungauged sites, paving the way for global storm surge forecasting.
Authors: Fatma Zahra Abdeldjouad, Menaouer Brahami, Mohammed Sabri
Abstract: Adverse drug reactions considerably impact patient outcomes and healthcare costs in cancer therapy. Using artificial intelligence to predict adverse drug reactions in real time could revolutionize oncology treatment. This study aims to assess the performance of artificial intelligence models in predicting adverse drug reactions in patients with cancer. This is the first systematic review and meta-analysis. Scopus, PubMed, IEEE Xplore, and ACM Digital Library databases were searched for studies in English, French, and Arabic from January 1, 2018, to August 20, 2023. The inclusion criteria were: (1) peer-reviewed research articles; (2) use of artificial intelligence algorithms (machine learning, deep learning, knowledge graphs); (3) study aimed to predict adverse drug reactions (cardiotoxicity, neutropenia, nephrotoxicity, hepatotoxicity); (4) study was on cancer patients. The data were extracted and evaluated by three reviewers for study quality. Of the 332 screened articles, 17 studies (5%) involving 93,248 oncology patients from 17 countries were included in the systematic review, of which ten studies synthesized the meta-analysis. A random-effects model was created to pool the sensitivity, specificity, and AUC of the included studies. The pooled results were 0.82 (95% CI:0.69, 0.9), 0.84 (95% CI:0.75, 0.9), and 0.83 (95% CI:0.77, 0.87) for sensitivity, specificity, and AUC, respectively, of ADR predictive models. Biomarkers proved their effectiveness in predicting ADRs, yet they were adopted by only half of the reviewed studies. The use of AI in cancer treatment shows great potential, with models demonstrating high specificity and sensitivity in predicting ADRs. However, standardized research and multicenter studies are needed to improve the quality of evidence. AI can enhance cancer patient care by bridging the gap between data-driven insights and clinical expertise.
Authors: Shuo Zhou, Junhao Luo, Yaya Jiang, Haolin Wang, Haiping Lu, Gaolang Gong
Abstract: Lateralization is a fundamental feature of the human brain, where sex differences have been observed. Conventional studies in neuroscience on sex-specific lateralization are typically conducted on univariate statistical comparisons between male and female groups. However, these analyses often lack effective validation of group specificity. Here, we formulate modeling sex differences in lateralization of functional networks as a dual-classification problem, consisting of first-order classification for left vs. right functional networks and second-order classification for male vs. female models. To capture sex-specific patterns, we develop the Group-Specific Discriminant Analysis (GSDA) for first-order classification. The evaluation on two public neuroimaging datasets demonstrates the efficacy of GSDA in learning sex-specific models from functional networks, achieving a significant improvement in group specificity over baseline methods. The major sex differences are in the strength of lateralization and the interactions within and between lobes. The GSDA-based method is generic in nature and can be adapted to other group-specific analyses such as handedness-specific or disease-specific analyses.
Authors: Djemel Ziou
Abstract: In this report, we explore the data selection leading to a family of estimators maximizing a centrality. The family allows a nice properties leading to accurate and robust probability density function fitting according to some criteria we define. We establish a link between the centrality estimator and the maximum likelihood, showing that the latter is a particular case. Therefore, a new probability interpretation of Fisher maximum likelihood is provided. We will introduce and study two specific centralities that we have named H\"older and Lehmer estimators. A numerical simulation is provided showing the effectiveness of the proposed families of estimators opening the door to development of new concepts and algorithms in machine learning, data mining, statistics, and data analysis.
Authors: Ashwin Pananjady, Vidya Muthukumar, Andrew Thangaraj
Abstract: We study the problem of estimating the stationary mass -- also called the unigram mass -- that is missing from a single trajectory of a discrete-time, ergodic Markov chain. This problem has several applications -- for example, estimating the stationary missing mass is critical for accurately smoothing probability estimates in sequence models. While the classical Good--Turing estimator from the 1950s has appealing properties for i.i.d. data, it is known to be biased in the Markov setting, and other heuristic estimators do not come equipped with guarantees. Operating in the general setting in which the size of the state space may be much larger than the length $n$ of the trajectory, we develop a linear-runtime estimator called \emph{Windowed Good--Turing} (\textsc{WingIt}) and show that its risk decays as $\widetilde{\mathcal{O}}(\mathsf{T_{mix}}/n)$, where $\mathsf{T_{mix}}$ denotes the mixing time of the chain in total variation distance. Notably, this rate is independent of the size of the state space and minimax-optimal up to a logarithmic factor in $n / \mathsf{T_{mix}}$. We also present a bound on the variance of the missing mass random variable, which may be of independent interest. We extend our estimator to approximate the stationary mass placed on elements occurring with small frequency in $X^n$. Finally, we demonstrate the efficacy of our estimators both in simulations on canonical chains and on sequences constructed from a popular natural language corpus.
Authors: Giuseppe Montalbano, Leonardo Banchi
Abstract: We show that hybrid quantum classifiers based on quantum kernel methods and support vector machines are vulnerable against adversarial attacks, namely small engineered perturbations of the input data can deceive the classifier into predicting the wrong result. Nonetheless, we also show that simple defence strategies based on data augmentation with a few crafted perturbations can make the classifier robust against new attacks. Our results find applications in security-critical learning problems and in mitigating the effect of some forms of quantum noise, since the attacker can also be understood as part of the surrounding environment.
Authors: Zoltan Csaki, Bo Li, Jonathan Li, Qiantong Xu, Pian Pawakapan, Leon Zhang, Yun Du, Hengyu Zhao, Changran Hu, Urmish Thakker
Abstract: Despite the widespread availability of LLMs, there remains a substantial gap in their capabilities and availability across diverse languages. One approach to address these issues has been to take an existing pre-trained LLM and continue to train it on new languages. While prior works have experimented with language adaptation, many questions around best practices and methodology have not been covered. In this paper, we present a comprehensive investigation into the adaptation of LLMs to new languages. Our study covers the key components in this process, including vocabulary extension, direct preference optimization and the data scarcity problem for human alignment in low-resource languages. We scale these experiments across 9 languages and 2 parameter scales (7B and 70B). We compare our models against Llama 2, Aya-101, XGLM, BLOOM and existing language experts, outperforming all prior published baselines. Additionally, all evaluation code and checkpoints are made public to facilitate future research.
Authors: Henrik Hose, Alexander Gr\"afe, Sebastian Trimpe
Abstract: Model Predictive Control (MPC) is a method to control nonlinear systems with guaranteed stability and constraint satisfaction but suffers from high computation times. Approximate MPC (AMPC) with neural networks (NNs) has emerged to address this limitation, enabling deployment on resource-constrained embedded systems. However, when tuning AMPCs for real-world systems, large datasets need to be regenerated and the NN needs to be retrained at every tuning step. This work introduces a novel, parameter-adaptive AMPC architecture capable of online tuning without recomputing large datasets and retraining. By incorporating local sensitivities of nonlinear programs, the proposed method not only mimics optimal MPC inputs but also adjusts to changes in physical parameters of the model using linear predictions while still guaranteeing stability. We showcase the effectiveness of parameter-adaptive AMPC by controlling the swing-ups of two different real cartpole systems with a severely resource-constrained microcontroller (MCU). We use the same NN across both system instances that have different parameters. This work not only represents the first experimental demonstration of AMPC for fast-moving systems on low-cost MCUs to the best of our knowledge, but also showcases generalization across system instances and variations through our parameter-adaptation method. Taken together, these contributions represent a marked step toward the practical application of AMPC in real-world systems.
Authors: Halil Ismail Helvaci, Sen-ching Samson Cheung, Chen-Nee Chuah, Sally Ozonoff
Abstract: Autism Spectrum Disorder (ASD) presents significant challenges in early diagnosis and intervention, impacting children and their families. With prevalence rates rising, there is a critical need for accessible and efficient screening tools. Leveraging machine learning (ML) techniques, in particular Temporal Action Localization (TAL), holds promise for automating ASD screening. This paper introduces a self-attention based TAL model designed to identify ASD-related behaviors in infant videos. Unlike existing methods, our approach simplifies complex modeling and emphasizes efficiency, which is essential for practical deployment in real-world scenarios. Importantly, this work underscores the importance of developing computer vision methods capable of operating in naturilistic environments with little equipment control, addressing key challenges in ASD screening. This study is the first to conduct end-to-end temporal action localization in untrimmed videos of infants with ASD, offering promising avenues for early intervention and support. We report baseline results of behavior detection using our TAL model. We achieve 70% accuracy for look face, 79% accuracy for look object, 72% for smile and 65% for vocalization.
Authors: Ahmed Faisal Abdelrahman, Matias Valdenegro-Toro, Maren Bennewitz, Paul G. Pl\"oger
Abstract: Neuromorphic computing mimics computational principles of the brain in $\textit{silico}$ and motivates research into event-based vision and spiking neural networks (SNNs). Event cameras (ECs) exclusively capture local intensity changes and offer superior power consumption, response latencies, and dynamic ranges. SNNs replicate biological neuronal dynamics and have demonstrated potential as alternatives to conventional artificial neural networks (ANNs), such as in reducing energy expenditure and inference time in visual classification. Nevertheless, these novel paradigms remain scarcely explored outside the domain of aerial robots. To investigate the utility of brain-inspired sensing and data processing, we developed a neuromorphic approach to obstacle avoidance on a camera-equipped manipulator. Our approach adapts high-level trajectory plans with reactive maneuvers by processing emulated event data in a convolutional SNN, decoding neural activations into avoidance motions, and adjusting plans using a dynamic motion primitive. We conducted experiments with a Kinova Gen3 arm performing simple reaching tasks that involve obstacles in sets of distinct task scenarios and in comparison to a non-adaptive baseline. Our neuromorphic approach facilitated reliable avoidance of imminent collisions in simulated and real-world experiments, where the baseline consistently failed. Trajectory adaptations had low impacts on safety and predictability criteria. Among the notable SNN properties were the correlation of computations with the magnitude of perceived motions and a robustness to different event emulation methods. Tests with a DAVIS346 EC showed similar performance, validating our experimental event emulation. Our results motivate incorporating SNN learning, utilizing neuromorphic processors, and further exploring the potential of neuromorphic methods.
Authors: Neelesh Gupta, Narayanan Kannan, Pengmiao Zhang, Viktor Prasanna
Abstract: Convolutional Neural Networks (CNNs) have demonstrated remarkable ability throughout the field of computer vision. However, CNN inference requires a large number of arithmetic operations, making them expensive to deploy in hardware. Current approaches alleviate this issue by developing hardware-supported, algorithmic processes to simplify spatial convolution functions. However, these methods still heavily rely on matrix multiplication, leading to significant computational overhead. To bridge the gap between hardware, algorithmic acceleration, and approximate matrix multiplication, we propose TabConv, a novel, table-based approximation for convolution to significantly reduce arithmetic operations during inference. Additionally, we introduce a priority masking technique based on cosine similarity to select layers for table-based approximation, thereby maintaining the model performance. We evaluate our approach on popular CNNs: ResNet-18, ResNet-34, and NetworkInNetwork (NIN). TabConv preserves over 93% of the original model's performance while reducing arithmetic operations by 36.5%, 25.8%, and 99.4% for ResNet-18 on CIFAR-10, CIFAR-100, and MNIST, respectively, 35.6% and 99.3% for ResNet-34 on CIFAR-10 and MNIST, and 98.9% for NIN on MNIST, achieving low-computation inference.
Authors: Zifeng Wang, Chun-Liang Li, Vincent Perot, Long T. Le, Jin Miao, Zizhao Zhang, Chen-Yu Lee, Tomas Pfister
Abstract: Instruction tuning has emerged as the key in aligning large language models (LLMs) with specific task instructions, thereby mitigating the discrepancy between the next-token prediction objective and users' actual goals. To reduce the labor and time cost to collect or annotate data by humans, researchers start to explore the use of LLMs to generate instruction-aligned synthetic data. Recent works focus on generating diverse instructions and applying LLM to increase instruction complexity, often neglecting downstream use cases. It remains unclear how to tailor high-quality data to elicit better instruction-following abilities in different target instruction distributions and LLMs. To this end, we introduce CodecLM, a general framework for adaptively generating high-quality synthetic data for LLM alignment with different downstream instruction distributions and LLMs. Drawing on the Encode-Decode principles, we use LLMs as codecs to guide the data generation process. We first encode seed instructions into metadata, which are concise keywords generated on-the-fly to capture the target instruction distribution, and then decode metadata to create tailored instructions. We also introduce Self-Rubrics and Contrastive Filtering during decoding to tailor data-efficient samples. Extensive experiments on four open-domain instruction following benchmarks validate the effectiveness of CodecLM over the current state-of-the-arts.
Authors: Maryam Ahang, Mostafa Abbasi, Todd Charter, Homayoun Najjaran
Abstract: Condition monitoring of industrial systems is crucial for ensuring safety and maintenance planning, yet notable challenges arise in real-world settings due to the limited or non-existent availability of fault samples. This paper introduces an innovative solution to this problem by proposing a new method for fault detection and condition monitoring for unseen data. Adopting an approach inspired by zero-shot learning, our method can identify faults and assign a relative health index to various operational conditions. Typically, we have plenty of data on normal operations, some data on compromised conditions, and very few (if any) samples of severe faults. We use a variational autoencoder to capture the probabilistic distribution of previously seen and new unseen conditions. The health status is determined by comparing each sample's deviation from a normal operation reference distribution in the latent space. Faults are detected by establishing a threshold for the health indexes, allowing the model to identify severe, unseen faults with high accuracy, even amidst noise. We validate our approach using the run-to-failure IMS-bearing dataset and compare it with other methods. The health indexes generated by our model closely match the established descriptive model of bearing wear, attesting to the robustness and reliability of our method. These findings highlight the potential of our methodology in augmenting fault detection capabilities within industrial domains, thereby contributing to heightened safety protocols and optimized maintenance practices.
Authors: Guilherme Seidyo Imai Aldeia (Federal University of ABC), Fabricio Olivetti de Franca (Federal University of ABC), William G. La Cava (Boston Children's Hospital, Harvard Medical School)
Abstract: Symbolic regression (SR) searches for parametric models that accurately fit a dataset, prioritizing simplicity and interpretability. Despite this secondary objective, studies point out that the models are often overly complex due to redundant operations, introns, and bloat that arise during the iterative process, and can hinder the search with repeated exploration of bloated segments. Applying a fast heuristic algebraic simplification may not fully simplify the expression and exact methods can be infeasible depending on size or complexity of the expressions. We propose a novel agnostic simplification and bloat control for SR employing an efficient memoization with locality-sensitive hashing (LHS). The idea is that expressions and their sub-expressions traversed during the iterative simplification process are stored in a dictionary using LHS, enabling efficient retrieval of similar structures. We iterate through the expression, replacing subtrees with others of same hash if they result in a smaller expression. Empirical results shows that applying this simplification during evolution performs equal or better than without simplification in minimization of error, significantly reducing the number of nonlinear functions. This technique can learn simplification rules that work in general or for a specific problem, and improves convergence while reducing model complexity.
Authors: Bo Lin, Yangzheng Zhong, Weiqing Ren
Abstract: Understanding the transition events between metastable states in complex systems is an important subject in the fields of computational physics, chemistry and biology. The transition pathway plays an important role in characterizing the mechanism underlying the transition, for example, in the study of conformational changes of bio-molecules. In fact, computing the transition pathway is a challenging task for complex and high-dimensional systems. In this work, we formulate the path-finding task as a cost minimization problem over a particular path space. The cost function is adapted from the Freidlin-Wentzell action functional so that it is able to deal with rough potential landscapes. The path-finding problem is then solved using a actor-critic method based on the deep deterministic policy gradient algorithm (DDPG). The method incorporates the potential force of the system in the policy for generating episodes and combines physical properties of the system with the learning process for molecular systems. The exploitation and exploration nature of reinforcement learning enables the method to efficiently sample the transition events and compute the globally optimal transition pathway. We illustrate the effectiveness of the proposed method using three benchmark systems including an extended Mueller system and the Lennard-Jones system of seven particles.
Authors: Masato Fujitake
Abstract: In this paper, we present a method for enhancing the accuracy of scene text recognition tasks by judging whether the image and text match each other. While previous studies focused on generating the recognition results from input images, our approach also considers the model's misrecognition results to understand its error tendencies, thus improving the text recognition pipeline. This method boosts text recognition accuracy by providing explicit feedback on the data that the model is likely to misrecognize by predicting correct or incorrect between the image and text. The experimental results on publicly available datasets demonstrate that our proposed method outperforms the baseline and state-of-the-art methods in scene text recognition.
Authors: Seunghoi Kim, Chen Jin, Tom Diethe, Matteo Figini, Henry F. J. Tregidgo, Asher Mullokandov, Philip Teare, Daniel C. Alexander
Abstract: Recent developments in diffusion models have advanced conditioned image generation, yet they struggle with reconstructing out-of-distribution (OOD) images, such as unseen tumors in medical images, causing ``image hallucination'' and risking misdiagnosis. We hypothesize such hallucinations result from local OOD regions in the conditional images. We verify that partitioning the OOD region and conducting separate image generations alleviates hallucinations in several applications. From this, we propose a training-free diffusion framework that reduces hallucination with multiple Local Diffusion processes. Our approach involves OOD estimation followed by two modules: a ``branching'' module generates locally both within and outside OOD regions, and a ``fusion'' module integrates these predictions into one. Our evaluation shows our method mitigates hallucination over baseline models quantitatively and qualitatively, reducing misdiagnosis by 40% and 25% in the real-world medical and natural image datasets, respectively. It also demonstrates compatibility with various pre-trained diffusion models.
Authors: Anamitra Maiti, Subham Laha, Rishav Upadhaya, Soumyajit Biswas, Vikas Choudhary, Biplab Kar, Nikhil Kumar, Jaydip Sen
Abstract: In today's digital age, the internet is essential for communication and the sharing of information, creating a critical need for sophisticated data security measures to prevent unauthorized access and exploitation. Cryptography encrypts messages into a cipher text that is incomprehensible to unauthorized readers, thus safeguarding data during its transmission. Steganography, on the other hand, originates from the Greek term for "covered writing" and involves the art of hiding data within another medium, thereby facilitating covert communication by making the message invisible. This proposed approach takes advantage of the latest advancements in Artificial Intelligence (AI) and Deep Learning (DL), especially through the application of Generative Adversarial Networks (GANs), to improve upon traditional steganographic methods. By embedding encrypted data within another medium, our method ensures that the communication remains hidden from prying eyes. The application of GANs enables a smart, secure system that utilizes the inherent sensitivity of neural networks to slight alterations in data, enhancing the protection against detection. By merging the encryption techniques of cryptography with the hiding capabilities of steganography, and augmenting these with the strengths of AI, we introduce a comprehensive security system designed to maintain both the privacy and integrity of information. This system is crafted not just to prevent unauthorized access or modification of data, but also to keep the existence of the data hidden. This fusion of technologies tackles the core challenges of data security in the current era of open digital communication, presenting an advanced solution with the potential to transform the landscape of information security.
Authors: Pengfei Zhang, Dingzhu Wen, Guangxu Zhu, Qimei Chen, Kaifeng Han, Yuanming Shi
Abstract: In this paper, a cloud radio access network (Cloud-RAN) based collaborative edge AI inference architecture is proposed. Specifically, geographically distributed devices capture real-time noise-corrupted sensory data samples and extract the noisy local feature vectors, which are then aggregated at each remote radio head (RRH) to suppress sensing noise. To realize efficient uplink feature aggregation, we allow each RRH receives local feature vectors from all devices over the same resource blocks simultaneously by leveraging an over-the-air computation (AirComp) technique. Thereafter, these aggregated feature vectors are quantized and transmitted to a central processor (CP) for further aggregation and downstream inference tasks. Our aim in this work is to maximize the inference accuracy via a surrogate accuracy metric called discriminant gain, which measures the discernibility of different classes in the feature space. The key challenges lie on simultaneously suppressing the coupled sensing noise, AirComp distortion caused by hostile wireless channels, and the quantization error resulting from the limited capacity of fronthaul links. To address these challenges, this work proposes a joint transmit precoding, receive beamforming, and quantization error control scheme to enhance the inference accuracy. Extensive numerical experiments demonstrate the effectiveness and superiority of our proposed optimization algorithm compared to various baselines.
Authors: Yixuan Zhang, Dongyan Huo, Yudong Chen, Qiaomin Xie
Abstract: Motivated by Q-learning, we study nonsmooth contractive stochastic approximation (SA) with constant stepsize. We focus on two important classes of dynamics: 1) nonsmooth contractive SA with additive noise, and 2) synchronous and asynchronous Q-learning, which features both additive and multiplicative noise. For both dynamics, we establish weak convergence of the iterates to a stationary limit distribution in Wasserstein distance. Furthermore, we propose a prelimit coupling technique for establishing steady-state convergence and characterize the limit of the stationary distribution as the stepsize goes to zero. Using this result, we derive that the asymptotic bias of nonsmooth SA is proportional to the square root of the stepsize, which stands in sharp contrast to smooth SA. This bias characterization allows for the use of Richardson-Romberg extrapolation for bias reduction in nonsmooth SA.
Authors: Baoxing Jiang
Abstract: Aspect-Based Sentiment Analysis (ABSA) is an indispensable and highly challenging task in natural language processing. Current efforts have focused on specific sub-tasks, making it difficult to comprehensively cover all sub-tasks within the ABSA domain. With the development of Generative Pre-trained Transformers (GPTs), there came inspiration for a one-stop solution to sentiment analysis. In this study, we used GPTs for all sub-tasks of few-shot ABSA while defining a general learning paradigm for this application. We propose the All in One (AiO) model, a simple yet effective two-stage model for all ABSA sub-tasks. In the first stage, a specific backbone network learns the semantic information of the review and generates heuristically enhanced candidates. In the second stage, AiO leverages GPT contextual learning capabilities to generate predictions. The study conducted comprehensive comparative and ablation experiments on five benchmark datasets, and the results show that AiO can effectively handle all ABSA sub-tasks, even with few-shot data.
Authors: Alessandro Benfenati, Alessio Marta
Abstract: Neural networks are playing a crucial role in everyday life, with the most modern generative models able to achieve impressive results. Nonetheless, their functioning is still not very clear, and several strategies have been adopted to study how and why these model reach their outputs. A common approach is to consider the data in an Euclidean settings: recent years has witnessed instead a shift from this paradigm, moving thus to more general framework, namely Riemannian Geometry. Two recent works introduced a geometric framework to study neural networks making use of singular Riemannian metrics. In this paper we extend these results to convolutional, residual and recursive neural networks, studying also the case of non-differentiable activation functions, such as ReLU. We illustrate our findings with some numerical experiments on classification of images and thermodynamic problems.
Authors: Sebastian Hirt, Andreas H\"ohl, Joachim Schaeffer, Johannes Pohlodek, Richard D. Braatz, Rolf Findeisen
Abstract: Tuning parameters in model predictive control (MPC) presents significant challenges, particularly when there is a notable discrepancy between the controller's predictions and the actual behavior of the closed-loop plant. This mismatch may stem from factors like substantial model-plant differences, limited prediction horizons that do not cover the entire time of interest, or unforeseen system disturbances. Such mismatches can jeopardize both performance and safety, including constraint satisfaction. Traditional methods address this issue by modifying the finite horizon cost function to better reflect the overall operational cost, learning parts of the prediction model from data, or implementing robust MPC strategies, which might be either computationally intensive or overly cautious. As an alternative, directly optimizing or learning the controller parameters to enhance closed-loop performance has been proposed. We apply Bayesian optimization for efficient learning of unknown model parameters and parameterized constraint backoff terms, aiming to improve closed-loop performance of battery fast charging. This approach establishes a hierarchical control framework where Bayesian optimization directly fine-tunes closed-loop behavior towards a global and long-term objective, while MPC handles lower-level, short-term control tasks. For lithium-ion battery fast charging, we show that the learning approach not only ensures safe operation but also maximizes closed-loop performance. This includes maintaining the battery's operation below its maximum terminal voltage and reducing charging times, all achieved using a standard nominal MPC model with a short horizon and notable initial model-plant mismatch.
Authors: Faseeh Ahmad, Matthias Mayr, Sulthan Suresh-Fazeela, Volker Kreuger
Abstract: In dynamic operational environments, particularly in collaborative robotics, the inevitability of failures necessitates robust and adaptable recovery strategies. Traditional automated recovery strategies, while effective for predefined scenarios, often lack the flexibility required for on-the-fly task management and adaptation to expected failures. Addressing this gap, we propose a novel approach that models recovery behaviors as adaptable robotic skills, leveraging the Behavior Trees and Motion Generators~(BTMG) framework for policy representation. This approach distinguishes itself by employing reinforcement learning~(RL) to dynamically refine recovery behavior parameters, enabling a tailored response to a wide array of failure scenarios with minimal human intervention. We assess our methodology through a series of progressively challenging scenarios within a peg-in-a-hole task, demonstrating the approach's effectiveness in enhancing operational efficiency and task success rates in collaborative robotics settings. We validate our approach using a dual-arm KUKA robot.
Authors: Tianyu Cao, Natraj Raman, Danial Dervovic, Chenhao Tan
Abstract: As large language models (LLMs) expand the power of natural language processing to handle long inputs, rigorous and systematic analyses are necessary to understand their abilities and behavior. A salient application is summarization, due to its ubiquity and controversy (e.g., researchers have declared the death of summarization). In this paper, we use financial report summarization as a case study because financial reports not only are long but also use numbers and tables extensively. We propose a computational framework for characterizing multimodal long-form summarization and investigate the behavior of Claude 2.0/2.1, GPT-4/3.5, and Command. We find that GPT-3.5 and Command fail to perform this summarization task meaningfully. For Claude 2 and GPT-4, we analyze the extractiveness of the summary and identify a position bias in LLMs. This position bias disappears after shuffling the input for Claude, which suggests that Claude has the ability to recognize important information. We also conduct a comprehensive investigation on the use of numeric data in LLM-generated summaries and offer a taxonomy of numeric hallucination. We employ prompt engineering to improve GPT-4's use of numbers with limited success. Overall, our analyses highlight the strong capability of Claude 2 in handling long multimodal inputs compared to GPT-4.
Authors: Bo Lin, Weiqing Ren
Abstract: The committor function is a central object for quantifying the transitions between metastable states of dynamical systems. Recently, a number of computational methods based on deep neural networks have been developed for computing the high-dimensional committor function. The success of the methods relies on sampling adequate data for the transition, which still is a challenging task for complex systems at low temperatures. In this work, we propose a deep learning method with two novel adaptive sampling schemes (I and II). In the two schemes, the data are generated actively with a modified potential where the bias potential is constructed from the learned committor function. We theoretically demonstrate the advantages of the sampling schemes and show that the data in sampling scheme II are uniformly distributed along the transition tube. This makes a promising method for studying the transition of complex systems. The efficiency of the method is illustrated in high-dimensional systems including the alanine dipeptide and a solvated dimer system.
Authors: Elizaveta Goncharova, Anton Razzhigaev, Matvey Mikhalchuk, Maxim Kurkin, Irina Abdullaeva, Matvey Skripkin, Ivan Oseledets, Denis Dimitrov, Andrey Kuznetsov
Abstract: Last year, multimodal architectures served up a revolution in AI-based approaches and solutions, extending the capabilities of large language models (LLM). We propose an \textit{OmniFusion} model based on a pretrained LLM and adapters for visual modality. We evaluated and compared several architecture design principles for better text and visual data coupling: MLP and transformer adapters, various CLIP ViT-based encoders (SigLIP, InternVIT, etc.), and their fusing approach, image encoding method (whole image or tiles encoding) and two 7B LLMs (the proprietary one and open-source Mistral). Experiments on 8 visual-language benchmarks show the top score for the best OmniFusion setup in terms of different VQA tasks in comparison with open-source LLaVA-like solutions: VizWiz, Pope, MM-Vet, ScienceQA, MMBench, TextVQA, VQAv2, MMMU. We also propose a variety of situations, where OmniFusion provides highly-detailed answers in different domains: housekeeping, sightseeing, culture, medicine, handwritten and scanned equations recognition, etc. Mistral-based OmniFusion model is an open-source solution with weights, training and inference scripts available at https://github.com/AIRI-Institute/OmniFusion.
Authors: Bill Cai, Clarence Boon Liang Ng, Daniel Tan, Shelvia Hotama
Abstract: Dictionary example sentences play an important role in illustrating word definitions and usage, but manually creating quality sentences is challenging. Prior works have demonstrated that language models can be trained to generate example sentences. However, they relied on costly customized models and word sense datasets for generation and evaluation of their work. Rapid advancements in foundational models present the opportunity to create low-cost, zero-shot methods for the generation and evaluation of dictionary example sentences. We introduce a new automatic evaluation metric called OxfordEval that measures the win-rate of generated sentences against existing Oxford Dictionary sentences. OxfordEval shows high alignment with human judgments, enabling large-scale automated quality evaluation. We experiment with various LLMs and configurations to generate dictionary sentences across word classes. We complement this with a novel approach of using masked language models to identify and select sentences that best exemplify word meaning. The eventual model, FM-MLM, achieves over 85.1% win rate against Oxford baseline sentences according to OxfordEval, compared to 39.8% win rate for prior model-generated sentences.
Authors: Qunlong Ma, Zhi Ma, Jinlong Xu, Hairui Zhang, Ming Gao
Abstract: Many deep neural networks have been used to solve Ising models, including autoregressive neural networks, convolutional neural networks, recurrent neural networks, and graph neural networks. Learning a probability distribution of energy configuration or finding the ground states of a disordered, fully connected Ising model is essential for statistical mechanics and NP-hard problems. Despite tremendous efforts, a neural network architecture with the ability to high-accurately solve these fully connected and extremely intractable problems on larger systems is still lacking. Here we propose a variational autoregressive architecture with a message passing mechanism, which can effectively utilize the interactions between spin variables. The new network trained under an annealing framework outperforms existing methods in solving several prototypical Ising spin Hamiltonians, especially for larger spin systems at low temperatures. The advantages also come from the great mitigation of mode collapse during the training process of deep neural networks. Considering these extremely difficult problems to be solved, our method extends the current computational limits of unsupervised neural networks to solve combinatorial optimization problems.
Authors: Arthur Drichel, Marc Meyer, Ulrike Meyer
Abstract: In this work, we conduct a comprehensive study on the robustness of domain generation algorithm (DGA) classifiers. We implement 32 white-box attacks, 19 of which are very effective and induce a false-negative rate (FNR) of $\approx$ 100\% on unhardened classifiers. To defend the classifiers, we evaluate different hardening approaches and propose a novel training scheme that leverages adversarial latent space vectors and discretized adversarial domains to significantly improve robustness. In our study, we highlight a pitfall to avoid when hardening classifiers and uncover training biases that can be easily exploited by attackers to bypass detection, but which can be mitigated by adversarial training (AT). In our study, we do not observe any trade-off between robustness and performance, on the contrary, hardening improves a classifier's detection performance for known and unknown DGAs. We implement all attacks and defenses discussed in this paper as a standalone library, which we make publicly available to facilitate hardening of DGA classifiers: https://gitlab.com/rwth-itsec/robust-dga-detection
Authors: Sharana Dharshikgan Suresh Dass, Hrishav Bakul Barua, Ganesh Krishnasamy, Raveendran Paramesran, Raphael C. -W. Phan
Abstract: Human action or activity recognition in videos is a fundamental task in computer vision with applications in surveillance and monitoring, self-driving cars, sports analytics, human-robot interaction and many more. Traditional supervised methods require large annotated datasets for training, which are expensive and time-consuming to acquire. This work proposes a novel approach using Cross-Architecture Pseudo-Labeling with contrastive learning for semi-supervised action recognition. Our framework leverages both labeled and unlabelled data to robustly learn action representations in videos, combining pseudo-labeling with contrastive learning for effective learning from both types of samples. We introduce a novel cross-architecture approach where 3D Convolutional Neural Networks (3D CNNs) and video transformers (VIT) are utilised to capture different aspects of action representations; hence we call it ActNetFormer. The 3D CNNs excel at capturing spatial features and local dependencies in the temporal domain, while VIT excels at capturing long-range dependencies across frames. By integrating these complementary architectures within the ActNetFormer framework, our approach can effectively capture both local and global contextual information of an action. This comprehensive representation learning enables the model to achieve better performance in semi-supervised action recognition tasks by leveraging the strengths of each of these architectures. Experimental results on standard action recognition datasets demonstrate that our approach performs better than the existing methods, achieving state-of-the-art performance with only a fraction of labeled data. The official website of this work is available at: https://github.com/rana2149/ActNetFormer.
Authors: Vitaly Bulgakov, Alec Segal
Abstract: Dimensionality reduction in vector databases is pivotal for streamlining AI data management, enabling efficient storage, faster computation, and improved model performance. This paper explores the benefits of reducing vector database dimensions, with a focus on computational efficiency and overcoming the curse of dimensionality. We introduce a novel application of Fast Fourier Transform (FFT) to dimensionality reduction, a method previously underexploited in this context. By demonstrating its utility across various AI domains, including Retrieval-Augmented Generation (RAG) models and image processing, this FFT-based approach promises to improve data retrieval processes and enhance the efficiency and scalability of AI solutions. The incorporation of FFT may not only optimize operations in real-time processing and recommendation systems but also extend to advanced image processing techniques, where dimensionality reduction can significantly improve performance and analysis efficiency. This paper advocates for the broader adoption of FFT in vector database management, marking a significant stride towards addressing the challenges of data volume and complexity in AI research and applications. Unlike many existing approaches, we directly handle the embedding vectors produced by the model after processing a test input.
Authors: Francisco Escudero Guti\'errez
Abstract: We consider the problems of testing and learning an $n$-qubit $k$-local Hamiltonian from queries to its evolution operator with respect the 2-norm of the Pauli spectrum, or equivalently, the normalized Frobenius norm. For testing whether a Hamiltonian is $\epsilon_1$-close to $k$-local or $\epsilon_2$-far from $k$-local, we show that $O(1/(\epsilon_2-\epsilon_1)^{8})$ queries suffice. This solves two questions posed in a recent work by Bluhm, Caro and Oufkir. For learning up to error $\epsilon$, we show that $\exp(O(k^2+k\log(1/\epsilon)))$ queries suffice. Our proofs are simple, concise and based on Pauli-analytic techniques.
Authors: Ming-Kun Xie, Jia-Hao Xiao, Pei Peng, Gang Niu, Masashi Sugiyama, Sheng-Jun Huang
Abstract: The key to multi-label image classification (MLC) is to improve model performance by leveraging label correlations. Unfortunately, it has been shown that overemphasizing co-occurrence relationships can cause the overfitting issue of the model, ultimately leading to performance degradation. In this paper, we provide a causal inference framework to show that the correlative features caused by the target object and its co-occurring objects can be regarded as a mediator, which has both positive and negative impacts on model predictions. On the positive side, the mediator enhances the recognition performance of the model by capturing co-occurrence relationships; on the negative side, it has the harmful causal effect that causes the model to make an incorrect prediction for the target object, even when only co-occurring objects are present in an image. To address this problem, we propose a counterfactual reasoning method to measure the total direct effect, achieved by enhancing the direct effect caused only by the target object. Due to the unknown location of the target object, we propose patching-based training and inference to accomplish this goal, which divides an image into multiple patches and identifies the pivot patch that contains the target object. Experimental results on multiple benchmark datasets with diverse configurations validate that the proposed method can achieve state-of-the-art performance.
Authors: Arkaprabha Basu, Kushal Bose, Sankha Subhra Mullick, Anish Chakrabarty, Swagatam Das
Abstract: Super-Resolution (SR) is a time-hallowed image processing problem that aims to improve the quality of a Low-Resolution (LR) sample up to the standard of its High-Resolution (HR) counterpart. We aim to address this by introducing Super-Resolution Generator (SuRGe), a fully-convolutional Generative Adversarial Network (GAN)-based architecture for SR. We show that distinct convolutional features obtained at increasing depths of a GAN generator can be optimally combined by a set of learnable convex weights to improve the quality of generated SR samples. In the process, we employ the Jensen-Shannon and the Gromov-Wasserstein losses respectively between the SR-HR and LR-SR pairs of distributions to further aid the generator of SuRGe to better exploit the available information in an attempt to improve SR. Moreover, we train the discriminator of SuRGe with the Wasserstein loss with gradient penalty, to primarily prevent mode collapse. The proposed SuRGe, as an end-to-end GAN workflow tailor-made for super-resolution, offers improved performance while maintaining low inference time. The efficacy of SuRGe is substantiated by its superior performance compared to 18 state-of-the-art contenders on 10 benchmark datasets.
Authors: Nico Meyer, Christian Ufrecht, Maniraman Periyasamy, Axel Plinge, Christopher Mutschler, Daniel D. Scherer, Andreas Maier
Abstract: Quantum computer simulation software is an integral tool for the research efforts in the quantum computing community. An important aspect is the efficiency of respective frameworks, especially for training variational quantum algorithms. Focusing on the widely used Qiskit software environment, we develop the qiskit-torch-module. It improves runtime performance by two orders of magnitude over comparable libraries, while facilitating low-overhead integration with existing codebases. Moreover, the framework provides advanced tools for integrating quantum neural networks with PyTorch. The pipeline is tailored for single-machine compute systems, which constitute a widely employed setup in day-to-day research efforts.
Authors: Payam Abdisarabshali, Kwang Taik Kim, Michael Langberg, Weifeng Su, Seyyedali Hosseinalipour
Abstract: Existing studies on federated learning (FL) are mostly focused on system orchestration for static snapshots of the network and making static control decisions (e.g., spectrum allocation). However, real-world wireless networks are susceptible to temporal variations of wireless channel capacity and users' datasets. In this paper, we incorporate multi-granular system dynamics (MSDs) into FL, including (M1) dynamic wireless channel capacity, captured by a set of discrete-time events, called $\mathscr{D}$-Events, and (M2) dynamic datasets of users. The latter is characterized by (M2-a) modeling the dynamics of user's dataset size via an ordinary differential equation and (M2-b) introducing dynamic model drift}, formulated via a partial differential inequality} drawing concrete analytical connections between the dynamics of users' datasets and FL accuracy. We then conduct FL orchestration under MSDs by introducing dynamic cooperative FL with dedicated MAC schedulers (DCLM), exploiting the unique features of open radio access network (O-RAN). DCLM proposes (i) a hierarchical device-to-device (D2D)-assisted model training, (ii) dynamic control decisions through dedicated O-RAN MAC schedulers, and (iii) asymmetric user selection. We provide extensive theoretical analysis to study the convergence of DCLM. We then optimize the degrees of freedom (e.g., user selection and spectrum allocation) in DCLM through a highly non-convex optimization problem. We develop a systematic approach to obtain the solution for this problem, opening the door to solving a broad variety of network-aware FL optimization problems. We show the efficiency of DCLM via numerical simulations and provide a series of future directions.
Authors: Yuchen Zhu, Tianrong Chen, Evangelos A. Theodorou, Xie Chen, Molei Tao
Abstract: This article considers the generative modeling of the states of quantum systems, and an approach based on denoising diffusion model is proposed. The key contribution is an algorithmic innovation that respects the physical nature of quantum states. More precisely, the commonly used density matrix representation of mixed-state has to be complex-valued Hermitian, positive semi-definite, and trace one. Generic diffusion models, or other generative methods, may not be able to generate data that strictly satisfy these structural constraints, even if all training data do. To develop a machine learning algorithm that has physics hard-wired in, we leverage the recent development of Mirror Diffusion Model and design a previously unconsidered mirror map, to enable strict structure-preserving generation. Both unconditional generation and conditional generation via classifier-free guidance are experimentally demonstrated efficacious, the latter even enabling the design of new quantum states when generated on unseen labels.
Authors: Mathivanan Periasamy, Rohith Mahadevan, Bagiya Lakshmi S, Raja CSP Raman, Hasan Kumar S, Jasper Jessiman
Abstract: Sentiment analysis, a vital component in natural language processing, plays a crucial role in understanding the underlying emotions and opinions expressed in textual data. In this paper, we propose an innovative ensemble approach for sentiment analysis for finding fake reviews that amalgamate the predictive capabilities of Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Decision Tree classifiers. Our ensemble architecture strategically combines these diverse models to capitalize on their strengths while mitigating inherent weaknesses, thereby achieving superior accuracy and robustness in fake review prediction. By combining all the models of our classifiers, the predictive performance is boosted and it also fosters adaptability to varied linguistic patterns and nuances present in real-world datasets. The metrics accounted for on fake reviews demonstrate the efficacy and competitiveness of the proposed ensemble method against traditional single-model approaches. Our findings underscore the potential of ensemble techniques in advancing the state-of-the-art in finding fake reviews using hybrid algorithms, with implications for various applications in different social media and e-platforms to find the best reviews and neglect the fake ones, eliminating puffery and bluffs.
Authors: Alessio Ferrari, Sallam Abualhaija, Chetan Arora
Abstract: Complementing natural language (NL) requirements with graphical models can improve stakeholders' communication and provide directions for system design. However, creating models from requirements involves manual effort. The advent of generative large language models (LLMs), ChatGPT being a notable example, offers promising avenues for automated assistance in model generation. This paper investigates the capability of ChatGPT to generate a specific type of model, i.e., UML sequence diagrams, from NL requirements. We conduct a qualitative study in which we examine the sequence diagrams generated by ChatGPT for 28 requirements documents of various types and from different domains. Observations from the analysis of the generated diagrams have systematically been captured through evaluation logs, and categorized through thematic analysis. Our results indicate that, although the models generally conform to the standard and exhibit a reasonable level of understandability, their completeness and correctness with respect to the specified requirements often present challenges. This issue is particularly pronounced in the presence of requirements smells, such as ambiguity and inconsistency. The insights derived from this study can influence the practical utilization of LLMs in the RE process, and open the door to novel RE-specific prompting strategies targeting effective model generation.
Authors: Shengding Hu, Yuge Tu, Xu Han, Chaoqun He, Ganqu Cui, Xiang Long, Zhi Zheng, Yewei Fang, Yuxiang Huang, Weilin Zhao, Xinrong Zhang, Zheng Leng Thai, Kaihuo Zhang, Chongyi Wang, Yuan Yao, Chenyang Zhao, Jie Zhou, Jie Cai, Zhongwu Zhai, Ning Ding, Chao Jia, Guoyang Zeng, Dahai Li, Zhiyuan Liu, Maosong Sun
Abstract: The burgeoning interest in developing Large Language Models (LLMs) with up to trillion parameters has been met with concerns regarding resource efficiency and practical expense, particularly given the immense cost of experimentation. This scenario underscores the importance of exploring the potential of Small Language Models (SLMs) as a resource-efficient alternative. In this context, we introduce MiniCPM, specifically the 1.2B and 2.4B non-embedding parameter variants, not only excel in their respective categories but also demonstrate capabilities on par with 7B-13B LLMs. While focusing on SLMs, our approach exhibits scalability in both model and data dimensions for future LLM research. Regarding model scaling, we employ extensive model wind tunnel experiments for stable and optimal scaling. For data scaling, we introduce a Warmup-Stable-Decay (WSD) learning rate scheduler (LRS), conducive to continuous training and domain adaptation. We present an in-depth analysis of the intriguing training dynamics that occurred in the WSD LRS. With WSD LRS, we are now able to efficiently study data-model scaling law without extensive retraining experiments on both axes of model and data, from which we derive the much higher compute optimal data-model ratio than Chinchilla Optimal. Additionally, we introduce MiniCPM family, including MiniCPM-DPO, MiniCPM-MoE and MiniCPM-128K, whose excellent performance further cementing MiniCPM's foundation in diverse SLM applications. MiniCPM models are available publicly at https://github.com/OpenBMB/MiniCPM .
Authors: M. Namvarpour, A. Razi
Abstract: Large Language Models (LLMs) have emerged as powerful tools in various research domains. This article examines their potential through a literature review and firsthand experimentation. While LLMs offer benefits like cost-effectiveness and efficiency, challenges such as prompt tuning, biases, and subjectivity must be addressed. The study presents insights from experiments utilizing LLMs for qualitative analysis, highlighting successes and limitations. Additionally, it discusses strategies for mitigating challenges, such as prompt optimization techniques and leveraging human expertise. This study aligns with the 'LLMs as Research Tools' workshop's focus on integrating LLMs into HCI data work critically and ethically. By addressing both opportunities and challenges, our work contributes to the ongoing dialogue on their responsible application in research.
Authors: Shiven Sinha, Ameya Prabhu, Ponnurangam Kumaraguru, Siddharth Bhat, Matthias Bethge
Abstract: Proving geometric theorems constitutes a hallmark of visual reasoning combining both intuitive and logical skills. Therefore, automated theorem proving of Olympiad-level geometry problems is considered a notable milestone in human-level automated reasoning. The introduction of AlphaGeometry, a neuro-symbolic model trained with 100 million synthetic samples, marked a major breakthrough. It solved 25 of 30 International Mathematical Olympiad (IMO) problems whereas the reported baseline based on Wu's method solved only ten. In this note, we revisit the IMO-AG-30 Challenge introduced with AlphaGeometry, and find that Wu's method is surprisingly strong. Wu's method alone can solve 15 problems, and some of them are not solved by any of the other methods. This leads to two key findings: (i) Combining Wu's method with the classic synthetic methods of deductive databases and angle, ratio, and distance chasing solves 21 out of 30 methods by just using a CPU-only laptop with a time limit of 5 minutes per problem. Essentially, this classic method solves just 4 problems less than AlphaGeometry and establishes the first fully symbolic baseline strong enough to rival the performance of an IMO silver medalist. (ii) Wu's method even solves 2 of the 5 problems that AlphaGeometry failed to solve. Thus, by combining AlphaGeometry with Wu's method we set a new state-of-the-art for automated theorem proving on IMO-AG-30, solving 27 out of 30 problems, the first AI method which outperforms an IMO gold medalist.
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: Hritik Bana, Manav Mishra, Saswata Sarkar, Sujeevraja Sanjeevi, Sujit PB, Kaarthik Sundar
Abstract: This article presents a deep reinforcement learning-based approach to tackle a persistent surveillance mission requiring a single unmanned aerial vehicle initially stationed at a depot with fuel or time-of-flight constraints to repeatedly visit a set of targets with equal priority. Owing to the vehicle's fuel or time-of-flight constraints, the vehicle must be regularly refueled, or its battery must be recharged at the depot. The objective of the problem is to determine an optimal sequence of visits to the targets that minimizes the maximum time elapsed between successive visits to any target while ensuring that the vehicle never runs out of fuel or charge. We present a deep reinforcement learning algorithm to solve this problem and present the results of numerical experiments that corroborate the effectiveness of this approach in comparison with common-sense greedy heuristics.
Authors: Dimitrios Michail, Lefki-Ioanna Panagiotou, Charalampos Davalas, Ioannis Prapas, Spyros Kondylatos, Nikolaos Ioannis Bountos, Ioannis Papoutsis
Abstract: With climate change expected to exacerbate fire weather conditions, the accurate anticipation of wildfires on a global scale becomes increasingly crucial for disaster mitigation. In this study, we utilize SeasFire, a comprehensive global wildfire dataset with climate, vegetation, oceanic indices, and human-related variables, to enable seasonal wildfire forecasting with machine learning. For the predictive analysis, we train deep learning models with different architectures that capture the spatio-temporal context leading to wildfires. Our investigation focuses on assessing the effectiveness of these models in predicting the presence of burned areas at varying forecasting time horizons globally, extending up to six months into the future, and on how different spatial or/and temporal context affects the performance of the models. Our findings demonstrate the great potential of deep learning models in seasonal fire forecasting; longer input time-series leads to more robust predictions across varying forecasting horizons, while integrating spatial information to capture wildfire spatio-temporal dynamics boosts performance. Finally, our results hint that in order to enhance performance at longer forecasting horizons, a larger receptive field spatially needs to be considered.
Authors: Maximilian Dreyer, Erblina Purelku, Johanna Vielhaben, Wojciech Samek, Sebastian Lapuschkin
Abstract: The field of mechanistic interpretability aims to study the role of individual neurons in Deep Neural Networks. Single neurons, however, have the capability to act polysemantically and encode for multiple (unrelated) features, which renders their interpretation difficult. We present a method for disentangling polysemanticity of any Deep Neural Network by decomposing a polysemantic neuron into multiple monosemantic "virtual" neurons. This is achieved by identifying the relevant sub-graph ("circuit") for each "pure" feature. We demonstrate how our approach allows us to find and disentangle various polysemantic units of ResNet models trained on ImageNet. While evaluating feature visualizations using CLIP, our method effectively disentangles representations, improving upon methods based on neuron activations. Our code is available at https://github.com/maxdreyer/PURE.
Authors: Weronika Hryniewska-Guzik, Jakub Bilski, Bartosz Chrostowski, Jakub Drak Sbahi, Przemys{\l}aw Biecek
Abstract: Robust and highly accurate lung segmentation in X-rays is crucial in medical imaging. This study evaluates deep learning solutions for this task, ranking existing methods and analyzing their performance under diverse image modifications. Out of 61 analyzed papers, only nine offered implementation or pre-trained models, enabling assessment of three prominent methods: Lung VAE, TransResUNet, and CE-Net. The analysis revealed that CE-Net performs best, demonstrating the highest values in dice similarity coefficient and intersection over union metric.
Authors: Beomseok Kang, Harshit Kumar, Minah Lee, Biswadeep Chakraborty, Saibal Mukhopadhyay
Abstract: Locally interacting dynamical systems, such as epidemic spread, rumor propagation through crowd, and forest fire, exhibit complex global dynamics originated from local, relatively simple, and often stochastic interactions between dynamic elements. Their temporal evolution is often driven by transitions between a finite number of discrete states. Despite significant advancements in predictive modeling through deep learning, such interactions among many elements have rarely explored as a specific domain for predictive modeling. We present Attentive Recurrent Neural Cellular Automata (AR-NCA), to effectively discover unknown local state transition rules by associating the temporal information between neighboring cells in a permutation-invariant manner. AR-NCA exhibits the superior generalizability across various system configurations (i.e., spatial distribution of states), data efficiency and robustness in extremely data-limited scenarios even in the presence of stochastic interactions, and scalability through spatial dimension-independent prediction.
Authors: Rohan Sarkar, Avinash Kak
Abstract: We add one more invariance - state invariance - to the more commonly used other invariances for learning object representations for recognition and retrieval. By state invariance, we mean robust with respect to changes in the structural form of the object, such as when an umbrella is folded, or when an item of clothing is tossed on the floor. Since humans generally have no difficulty in recognizing objects despite such state changes, we are naturally faced with the question of whether it is possible to devise a neural architecture with similar abilities. To that end, we present a novel dataset, ObjectsWithStateChange, that captures state and pose variations in the object images recorded from arbitrary viewpoints. We believe that this dataset will facilitate research in fine-grained object recognition and retrieval of objects that are capable of state changes. The goal of such research would be to train models capable of generating object embeddings that remain invariant to state changes while also staying invariant to transformations induced by changes in viewpoint, pose, illumination, etc. To demonstrate the usefulness of the ObjectsWithStateChange dataset, we also propose a curriculum learning strategy that uses the similarity relationships in the learned embedding space after each epoch to guide the training process. The model learns discriminative features by comparing visually similar objects within and across different categories, encouraging it to differentiate between objects that may be challenging to distinguish due to changes in their state. We believe that this strategy enhances the model's ability to capture discriminative features for fine-grained tasks that may involve objects with state changes, leading to performance improvements on object-level tasks not only on our new dataset, but also on two other challenging multi-view datasets such as ModelNet40 and ObjectPI.
Authors: Ra\'ul Mi\~n\'an, Javier Gallardo, \'Alvaro Ciudad, Alexis Molina
Abstract: This work introduces GeoDirDock (GDD), a novel approach to molecular docking that enhances the accuracy and physical plausibility of ligand docking predictions. GDD guides the denoising process of a diffusion model along geodesic paths within multiple spaces representing translational, rotational, and torsional degrees of freedom. Our method leverages expert knowledge to direct the generative modeling process, specifically targeting desired protein-ligand interaction regions. We demonstrate that GDD significantly outperforms existing blind docking methods in terms of RMSD accuracy and physicochemical pose realism. Our results indicate that incorporating domain expertise into the diffusion process leads to more biologically relevant docking predictions. Additionally, we explore the potential of GDD for lead optimization in drug discovery through angle transfer in maximal common substructure (MCS) docking, showcasing its capability to predict ligand orientations for chemically similar compounds accurately.
Authors: Cailean Osborne
Abstract: Governments are increasingly allocating funding for open source software (OSS) development in order to address concerns related to software security, digital sovereignty, and the competitiveness of domestic software markets, amongst others. While such funding is generally welcomed by OSS practitioners, how OSS developers perceive the relative benefits and drawbacks of governmental funding remains an open question. This paper explores this question through a case study on scikit-learn, a Python library for machine learning, whose funding model combines research grants, commercial sponsorship, community donations, and a 32 million EUR grant from the French government's artificial intelligence strategy. Through 25 interviews with scikit-learn maintainers and funders, this study makes two key contributions with implications for research and practice. First, it provides novel insights into the role of a public-private funding model in a successful, community-led OSS project and how maintainers evaluate their funding model. Furthermore, it highlights the governance mechanisms employed by maintainers to safeguard the community ethos of the project. Second, it offers practical implications for OSS developer communities, companies, and governments. For OSS communities, the study illustrates the benefits of a diversified funding model in balancing the merits and drawbacks of different funding sources. For companies, it serves as a reminder that sponsoring developers or directly funding OSS projects can significantly support OSS maintainers, who often struggle with limited resources and towering workloads. For governments, the findings emphasise the importance of funding the maintenance of existing OSS projects in addition to or exclusively funding new innovations. The paper concludes with suggestions for future research on OSS funding models.
Authors: Anton Sch\"afer, Thomas Hofmann, Imanol Schlag, Tiago Pimentel
Abstract: Tokenisation is a core part of language models (LMs). It involves splitting a character sequence into subwords which are assigned arbitrary indices before being served to the LM. While typically lossless, however, this process may lead to less sample efficient LM training: as it removes character-level information, it could make it harder for LMs to generalise across similar subwords, such as now and Now. We refer to such subwords as near duplicates. In this paper, we study the impact of near duplicate subwords on LM training efficiency. First, we design an experiment that gives us an upper bound to how much we should expect a model to improve if we could perfectly generalise across near duplicates. We do this by duplicating each subword in our LM's vocabulary, creating perfectly equivalent classes of subwords. Experimentally, we find that LMs need roughly 17% more data when trained in a fully duplicated setting. Second, we investigate the impact of naturally occurring near duplicates on LMs. Here, we see that merging them considerably hurts LM performance. Therefore, although subword duplication negatively impacts LM training efficiency, naturally occurring near duplicates may not be as similar as anticipated, limiting the potential for performance improvements.
Authors: Juhong Min, Shyamal Buch, Arsha Nagrani, Minsu Cho, Cordelia Schmid
Abstract: This paper addresses the task of video question answering (videoQA) via a decomposed multi-stage, modular reasoning framework. Previous modular methods have shown promise with a single planning stage ungrounded in visual content. However, through a simple and effective baseline, we find that such systems can lead to brittle behavior in practice for challenging videoQA settings. Thus, unlike traditional single-stage planning methods, we propose a multi-stage system consisting of an event parser, a grounding stage, and a final reasoning stage in conjunction with an external memory. All stages are training-free, and performed using few-shot prompting of large models, creating interpretable intermediate outputs at each stage. By decomposing the underlying planning and task complexity, our method, MoReVQA, improves over prior work on standard videoQA benchmarks (NExT-QA, iVQA, EgoSchema, ActivityNet-QA) with state-of-the-art results, and extensions to related tasks (grounded videoQA, paragraph captioning).
Authors: Shubhomoy Das, Md Rakibul Islam, Nitthilan Kannappan Jayakodi, Janardhan Rao Doppa
Abstract: In many real-world AD applications including computer security and fraud prevention, the anomaly detector must be configurable by the human analyst to minimize the effort on false positives. One important way to configure the detector is by providing true labels (nominal or anomaly) for a few instances. Recent work on active anomaly discovery has shown that greedily querying the top-scoring instance and tuning the weights of ensemble detectors based on label feedback allows us to quickly discover true anomalies. This paper makes four main contributions to improve the state-of-the-art in anomaly discovery using tree-based ensembles. First, we provide an important insight that explains the practical successes of unsupervised tree-based ensembles and active learning based on greedy query selection strategy. We also present empirical results on real-world data to support our insights and theoretical analysis to support active learning. Second, we develop a novel batch active learning algorithm to improve the diversity of discovered anomalies based on a formalism called compact description to describe the discovered anomalies. Third, we develop a novel active learning algorithm to handle streaming data setting. We present a data drift detection algorithm that not only detects the drift robustly, but also allows us to take corrective actions to adapt the anomaly detector in a principled manner. Fourth, we present extensive experiments to evaluate our insights and our tree-based active anomaly discovery algorithms in both batch and streaming data settings. Our results show that active learning allows us to discover significantly more anomalies than state-of-the-art unsupervised baselines, our batch active learning algorithm discovers diverse anomalies, and our algorithms under the streaming-data setup are competitive with the batch setup.
Authors: Yatong Bai, Brendon G. Anderson, Aerin Kim, Somayeh Sojoudi
Abstract: While prior research has proposed a plethora of methods that build neural classifiers robust against adversarial robustness, practitioners are still reluctant to adopt them due to their unacceptably severe clean accuracy penalties. This paper significantly alleviates this accuracy-robustness trade-off by mixing the output probabilities of a standard classifier and a robust classifier, where the standard network is optimized for clean accuracy and is not robust in general. We show that the robust base classifier's confidence difference for correct and incorrect examples is the key to this improvement. In addition to providing intuitions and empirical evidence, we theoretically certify the robustness of the mixed classifier under realistic assumptions. Furthermore, we adapt an adversarial input detector into a mixing network that adaptively adjusts the mixture of the two base models, further reducing the accuracy penalty of achieving robustness. The proposed flexible method, termed "adaptive smoothing", can work in conjunction with existing or even future methods that improve clean accuracy, robustness, or adversary detection. Our empirical evaluation considers strong attack methods, including AutoAttack and adaptive attack. On the CIFAR-100 dataset, our method achieves an 85.21% clean accuracy while maintaining a 38.72% $\ell_\infty$-AutoAttacked ($\epsilon = 8/255$) accuracy, becoming the second most robust method on the RobustBench CIFAR-100 benchmark as of submission, while improving the clean accuracy by ten percentage points compared with all listed models. The code that implements our method is available at https://github.com/Bai-YT/AdaptiveSmoothing.
Authors: Snir Hordan, Tal Amir, Steven J. Gortler, Nadav Dym
Abstract: Neural networks for point clouds, which respect their natural invariance to permutation and rigid motion, have enjoyed recent success in modeling geometric phenomena, from molecular dynamics to recommender systems. Yet, to date, no model with polynomial complexity is known to be complete, that is, able to distinguish between any pair of non-isomorphic point clouds. We fill this theoretical gap by showing that point clouds can be completely determined, up to permutation and rigid motion, by applying the 3-WL graph isomorphism test to the point cloud's centralized Gram matrix. Moreover, we formulate an Euclidean variant of the 2-WL test and show that it is also sufficient to achieve completeness. We then show how our complete Euclidean WL tests can be simulated by an Euclidean graph neural network of moderate size and demonstrate their separation capability on highly symmetrical point clouds.
Authors: Xu Tan, Jiawei Yang, Junqi Chen, Sylwan Rahardja, Susanto Rahardja
Abstract: AutoEncoders (AEs) are commonly used for machine learning tasks due to their intrinsic learning ability. This unique characteristic can be capitalized for Outlier Detection (OD). However conventional AE-based methods face the issue of overconfident decisions and unexpected reconstruction results of outliers, limiting their performance in OD. To mitigate these issues, the Mean Squared Error (MSE) and Negative Logarithmic Likelihood (NLL) were first analyzed, and the importance of incorporating aleatoric uncertainty to AE-based OD was elucidated. Then the Weighted Negative Logarithmic Likelihood (WNLL) was proposed to adjust for the effect of uncertainty for different OD scenarios. Moreover, the Mean-Shift Scoring (MSS) method was proposed to utilize the local relationship of data to reduce the issue of false inliers caused by AE. Experiments on 32 real-world OD datasets proved the effectiveness of the proposed methods. The combination of WNLL and MSS achieved 41% relative performance improvement compared to the best baseline. In addition, MSS improved the performance of multiple AE-based outlier detectors by an average of 20%. The proposed methods have the potential to advance AE's development in OD. The code is available on www.OutlierNet.com for reproducibility.
Authors: Tao Yu, Toni J. B. Liu, Albert Tseng, Christopher De Sa
Abstract: Hyperbolic space has proven to be well-suited for capturing hierarchical relations in data, such as trees and directed acyclic graphs. Prior work introduced the concept of entailment cones, which uses partial orders defined by nested cones in the Poincar\'e ball to model hierarchies. Here, we introduce the ``shadow cones" framework, a physics-inspired entailment cone construction. Specifically, we model partial orders as subset relations between shadows formed by a light source and opaque objects in hyperbolic space. The shadow cones framework generalizes entailment cones to a broad class of formulations and hyperbolic space models beyond the Poincar\'e ball. This results in clear advantages over existing constructions: for example, shadow cones possess better optimization properties over constructions limited to the Poincar\'e ball. Our experiments on datasets of various sizes and hierarchical structures show that shadow cones consistently and significantly outperform existing entailment cone constructions. These results indicate that shadow cones are an effective way to model partial orders in hyperbolic space, offering physically intuitive and novel insights about the nature of such structures.
Authors: Miguel Lerma, Mirtha Lucas
Abstract: We discuss a vulnerability involving a category of attribution methods used to provide explanations for the outputs of convolutional neural networks working as classifiers. It is known that this type of networks are vulnerable to adversarial attacks, in which imperceptible perturbations of the input may alter the outputs of the model. In contrast, here we focus on effects that small modifications in the model may cause on the attribution method without altering the model outputs.
Authors: Alessio Gravina, Davide Bacciu
Abstract: Recent progress in research on Deep Graph Networks (DGNs) has led to a maturation of the domain of learning on graphs. Despite the growth of this research field, there are still important challenges that are yet unsolved. Specifically, there is an urge of making DGNs suitable for predictive tasks on realworld systems of interconnected entities, which evolve over time. With the aim of fostering research in the domain of dynamic graphs, at first, we survey recent advantages in learning both temporal and spatial information, providing a comprehensive overview of the current state-of-the-art in the domain of representation learning for dynamic graphs. Secondly, we conduct a fair performance comparison among the most popular proposed approaches on node and edge-level tasks, leveraging rigorous model selection and assessment for all the methods, thus establishing a sound baseline for evaluating new architectures and approaches
Authors: Yongyuan Liang, Yanchao Sun, Ruijie Zheng, Xiangyu Liu, Benjamin Eysenbach, Tuomas Sandholm, Furong Huang, Stephen McAleer
Abstract: Deploying reinforcement learning (RL) systems requires robustness to uncertainty and model misspecification, yet prior robust RL methods typically only study noise introduced independently across time. However, practical sources of uncertainty are usually coupled across time. We formally introduce temporally-coupled perturbations, presenting a novel challenge for existing robust RL methods. To tackle this challenge, we propose GRAD, a novel game-theoretic approach that treats the temporally-coupled robust RL problem as a partially observable two-player zero-sum game. By finding an approximate equilibrium within this game, GRAD optimizes for general robustness against temporally-coupled perturbations. Experiments on continuous control tasks demonstrate that, compared with prior methods, our approach achieves a higher degree of robustness to various types of attacks on different attack domains, both in settings with temporally-coupled perturbations and decoupled perturbations.
Authors: David Steinmann, Wolfgang Stammer, Felix Friedrich, Kristian Kersting
Abstract: While traditional deep learning models often lack interpretability, concept bottleneck models (CBMs) provide inherent explanations via their concept representations. Specifically, they allow users to perform interventional interactions on these concepts by updating the concept values and thus correcting the predictive output of the model. Traditionally, however, these interventions are applied to the model only once and discarded afterward. To rectify this, we present concept bottleneck memory models (CB2M), an extension to CBMs. Specifically, a CB2M learns to generalize interventions to appropriate novel situations via a two-fold memory with which it can learn to detect mistakes and to reapply previous interventions. In this way, a CB2M learns to automatically improve model performance from a few initially obtained interventions. If no prior human interventions are available, a CB2M can detect potential mistakes of the CBM bottleneck and request targeted interventions. In our experimental evaluations on challenging scenarios like handling distribution shifts and confounded training data, we illustrate that CB2M are able to successfully generalize interventions to unseen data and can indeed identify wrongly inferred concepts. Overall, our results show that CB2M is a great tool for users to provide interactive feedback on CBMs, e.g., by guiding a user's interaction and requiring fewer interventions.
Authors: Gaotang Li, Jiarui Liu, Wei Hu
Abstract: Neural networks produced by standard training are known to suffer from poor accuracy on rare subgroups despite achieving high accuracy on average, due to the correlations between certain spurious features and labels. Previous approaches based on worst-group loss minimization (e.g. Group-DRO) are effective in improving worse-group accuracy but require expensive group annotations for all the training samples. In this paper, we focus on the more challenging and realistic setting where group annotations are only available on a small validation set or are not available at all. We propose BAM, a novel two-stage training algorithm: in the first stage, the model is trained using a bias amplification scheme via introducing a learnable auxiliary variable for each training sample; in the second stage, we upweight the samples that the bias-amplified model misclassifies, and then continue training the same model on the reweighted dataset. Empirically, BAM achieves competitive performance compared with existing methods evaluated on spurious correlation benchmarks in computer vision and natural language processing. Moreover, we find a simple stopping criterion based on minimum class accuracy difference that can remove the need for group annotations, with little or no loss in worst-group accuracy. We perform extensive analyses and ablations to verify the effectiveness and robustness of our algorithm in varying class and group imbalance ratios.
Authors: Philip M. Long, Peter L. Bartlett
Abstract: Recent experiments have shown that, often, when training a neural network with gradient descent (GD) with a step size $\eta$, the operator norm of the Hessian of the loss grows until it approximately reaches $2/\eta$, after which it fluctuates around this value. The quantity $2/\eta$ has been called the "edge of stability" based on consideration of a local quadratic approximation of the loss. We perform a similar calculation to arrive at an "edge of stability" for Sharpness-Aware Minimization (SAM), a variant of GD which has been shown to improve its generalization. Unlike the case for GD, the resulting SAM-edge depends on the norm of the gradient. Using three deep learning training tasks, we see empirically that SAM operates on the edge of stability identified by this analysis.
Authors: Zijun Gao, Lingbo Li
Abstract: Data Augmentation (DA) has emerged as an indispensable strategy in Time Series Classification (TSC), primarily due to its capacity to amplify training samples, thereby bolstering model robustness, diversifying datasets, and curtailing overfitting. However, the current landscape of DA in TSC is plagued with fragmented literature reviews, nebulous methodological taxonomies, inadequate evaluative measures, and a dearth of accessible, user-oriented tools. In light of these challenges, this study embarks on an exhaustive dissection of DA methodologies within the TSC realm. Our initial approach involved an extensive literature review spanning a decade, revealing that contemporary surveys scarcely capture the breadth of advancements in DA for TSC, prompting us to meticulously analyze over 100 scholarly articles to distill more than 60 unique DA techniques. This rigorous analysis precipitated the formulation of a novel taxonomy, purpose-built for the intricacies of DA in TSC, categorizing techniques into five principal echelons: Transformation-Based, Pattern-Based, Generative, Decomposition-Based, and Automated Data Augmentation. Our taxonomy promises to serve as a robust navigational aid for scholars, offering clarity and direction in method selection. Addressing the conspicuous absence of holistic evaluations for prevalent DA techniques, we executed an all-encompassing empirical assessment, wherein upwards of 15 DA strategies were subjected to scrutiny across 8 UCR time-series datasets, employing ResNet and a multi-faceted evaluation paradigm encompassing Accuracy, Method Ranking, and Residual Analysis, yielding a benchmark accuracy of 88.94 +- 11.83%. Our investigation underscored the inconsistent efficacies of DA techniques, with....
Authors: Wei Yao, Zhanke Zhou, Zhicong Li, Bo Han, Yong Liu
Abstract: It has been observed that machine learning algorithms exhibit biased predictions against certain population groups. To mitigate such bias while achieving comparable accuracy, a promising approach is to introduce surrogate functions of the concerned fairness definition and solve a constrained optimization problem. However, it is intriguing in previous work that such fairness surrogate functions may yield unfair results and high instability. In this work, in order to deeply understand them, taking a widely used fairness definition--demographic parity as an example, we show that there is a surrogate-fairness gap between the fairness definition and the fairness surrogate function. Also, the theoretical analysis and experimental results about the gap motivate us that the fairness and stability will be affected by the points far from the decision boundary, which is the large margin points issue investigated in this paper. To address it, we propose the general sigmoid surrogate to simultaneously reduce both the surrogate-fairness gap and the variance, and offer a rigorous fairness and stability upper bound. Interestingly, the theory also provides insights into two important issues that deal with the large margin points as well as obtaining a more balanced dataset are beneficial to fairness and stability. Furthermore, we elaborate a novel and general algorithm called Balanced Surrogate, which iteratively reduces the gap to mitigate unfairness. Finally, we provide empirical evidence showing that our methods consistently improve fairness and stability while maintaining accuracy comparable to the baselines in three real-world datasets.
Authors: Aleksandar Petrov, Philip H. S. Torr, Adel Bibi
Abstract: Context-based fine-tuning methods, including prompting, in-context learning, soft prompting (also known as prompt tuning), and prefix-tuning, have gained popularity due to their ability to often match the performance of full fine-tuning with a fraction of the parameters. Despite their empirical successes, there is little theoretical understanding of how these techniques influence the internal computation of the model and their expressiveness limitations. We show that despite the continuous embedding space being more expressive than the discrete token space, soft-prompting and prefix-tuning are potentially less expressive than full fine-tuning, even with the same number of learnable parameters. Concretely, context-based fine-tuning cannot change the relative attention pattern over the content and can only bias the outputs of an attention layer in a fixed direction. This suggests that while techniques like prompting, in-context learning, soft prompting, and prefix-tuning can effectively elicit skills present in the pretrained model, they may not be able to learn novel tasks that require new attention patterns.
Authors: Matt Gorbett, Hossein Shirazi, Indrakshi Ray
Abstract: Learning from the collective knowledge of data dispersed across private sources can provide neural networks with enhanced generalization capabilities. Federated learning, a method for collaboratively training a machine learning model across remote clients, achieves this by combining client models via the orchestration of a central server. However, current approaches face two critical limitations: i) they struggle to converge when client domains are sufficiently different, and ii) current aggregation techniques produce an identical global model for each client. In this work, we address these issues by reformulating the typical federated learning setup: rather than learning a single global model, we learn N models each optimized for a common objective. To achieve this, we apply a weighted distance minimization to model parameters shared in a peer-to-peer topology. The resulting framework, Iterative Parameter Alignment, applies naturally to the cross-silo setting, and has the following properties: (i) a unique solution for each participant, with the option to globally converge each model in the federation, and (ii) an optional early-stopping mechanism to elicit fairness among peers in collaborative learning settings. These characteristics jointly provide a flexible new framework for iteratively learning from peer models trained on disparate datasets. We find that the technique achieves competitive results on a variety of data partitions compared to state-of-the-art approaches. Further, we show that the method is robust to divergent domains (i.e. disjoint classes across peers) where existing approaches struggle.
Authors: Haim Barad, Ekaterina Aidova, Yury Gorbachev
Abstract: Inference optimizations are critical for improving user experience and reducing infrastructure costs and power consumption. In this article, we illustrate a form of dynamic execution known as speculative sampling to reduce the overall latency of text generation and compare it with standard autoregressive sampling. This can be used together with model-based optimizations (e.g. quantization) to provide an optimized solution. Both sampling methods make use of KV caching. A Jupyter notebook and some sample executions are provided.
Authors: Han-Byul Kim, Joo Hyung Lee, Sungjoo Yoo, Hong-Seok Kim
Abstract: Mixed-precision quantization of efficient networks often suffer from activation instability encountered in the exploration of bit selections. To address this problem, we propose a novel method called MetaMix which consists of bit selection and weight training phases. The bit selection phase iterates two steps, (1) the mixed-precision-aware weight update, and (2) the bit-search training with the fixed mixed-precision-aware weights, both of which combined reduce activation instability in mixed-precision quantization and contribute to fast and high-quality bit selection. The weight training phase exploits the weights and step sizes trained in the bit selection phase and fine-tunes them thereby offering fast training. Our experiments with efficient and hard-to-quantize networks, i.e., MobileNet v2 and v3, and ResNet-18 on ImageNet show that our proposed method pushes the boundary of mixed-precision quantization, in terms of accuracy vs. operations, by outperforming both mixed- and single-precision SOTA methods.
Authors: Chentao Jia, Ming Hu, Zekai Chen, Yanxin Yang, Xiaofei Xie, Yang Liu, Mingsong Chen
Abstract: Although Federated Learning (FL) is promising to enable collaborative learning among Artificial Intelligence of Things (AIoT) devices, it suffers from the problem of low classification performance due to various heterogeneity factors (e.g., computing capacity, memory size) of devices and uncertain operating environments. To address these issues, this paper introduces an effective FL approach named AdaptiveFL based on a novel fine-grained width-wise model pruning strategy, which can generate various heterogeneous local models for heterogeneous AIoT devices. By using our proposed reinforcement learning-based device selection mechanism, AdaptiveFL can adaptively dispatch suitable heterogeneous models to corresponding AIoT devices on the fly based on their available resources for local training. Experimental results show that, compared to state-of-the-art methods, AdaptiveFL can achieve up to 16.83% inference improvements for both IID and non-IID scenarios.
Authors: Fahdi Kanavati, Lucy Katsnith, Masayuki Tsuneki
Abstract: Linear principal component analysis (PCA), nonlinear PCA, and linear independent component analysis (ICA) -- those are three methods with single-layer autoencoder formulations for learning special linear transformations from data. Linear PCA learns orthogonal transformations that orient axes to maximise variance, but it suffers from a subspace rotational indeterminacy: it fails to find a unique rotation for axes that share the same variance. Both nonlinear PCA and linear ICA reduce the subspace indeterminacy from rotational to permutational by maximising statistical independence under the assumption of unit variance. The main difference between them is that nonlinear PCA only learns rotations while linear ICA learns not just rotations but any linear transformation with unit variance. The relationship between all three can be understood by the singular value decomposition of the linear ICA transformation into a sequence of rotation, scale, rotation. Linear PCA learns the first rotation; nonlinear PCA learns the second. The scale is the inverse of the standard deviations. The problem is that, in contrast to linear PCA, conventional nonlinear PCA cannot be used directly on the data to learn the first rotation, the first being special as it reduces dimensionality and orders by variances. In this paper, as solution to this problem, we propose $\sigma$-PCA: a unified neural model for linear and nonlinear PCA as single-layer autoencoders. Essentially, we propose a modification that allows nonlinear PCA to learn not just the second, but also the first rotation -- by maximising both variance and statistical independence. And so, like linear PCA, nonlinear PCA can now learn a semi-orthogonal transformation that reduces dimensionality and orders by variances, but, unlike linear PCA, nonlinear PCA can also eliminate the subspace rotational indeterminacy.
Authors: Dennis Frauen, Fergus Imrie, Alicia Curth, Valentyn Melnychuk, Stefan Feuerriegel, Mihaela van der Schaar
Abstract: Unobserved confounding is common in many applications, making causal inference from observational data challenging. As a remedy, causal sensitivity analysis is an important tool to draw causal conclusions under unobserved confounding with mathematical guarantees. In this paper, we propose NeuralCSA, a neural framework for generalized causal sensitivity analysis. Unlike previous work, our framework is compatible with (i) a large class of sensitivity models, including the marginal sensitivity model, f-sensitivity models, and Rosenbaum's sensitivity model; (ii) different treatment types (i.e., binary and continuous); and (iii) different causal queries, including (conditional) average treatment effects and simultaneous effects on multiple outcomes. The generality of NeuralCSA is achieved by learning a latent distribution shift that corresponds to a treatment intervention using two conditional normalizing flows. We provide theoretical guarantees that NeuralCSA is able to infer valid bounds on the causal query of interest and also demonstrate this empirically using both simulated and real-world data.
Authors: Vijay Ekambaram, Arindam Jati, Nam H. Nguyen, Pankaj Dayama, Chandra Reddy, Wesley M. Gifford, Jayant Kalagnanam
Abstract: Large pre-trained models for zero/few-shot learning excel in language and vision domains but encounter challenges in multivariate time series (TS) due to the diverse nature and scarcity of publicly available pre-training data. Consequently, there has been a recent surge in utilizing pre-trained large language models (LLMs) with token adaptations for TS forecasting. These approaches employ cross-domain transfer learning and surprisingly yield impressive results. However, these models are typically very slow and large (~billion parameters) and do not consider cross-channel correlations. To address this, we present Tiny Time Mixers (TTM), a significantly small model based on the lightweight TSMixer architecture. TTM marks the first success in developing fast and tiny general pre-trained models (<1M parameters), exclusively trained on public TS datasets, with effective transfer learning capabilities for forecasting. To tackle the complexity of pre-training on multiple datasets with varied temporal resolutions, we introduce several novel enhancements such as adaptive patching, dataset augmentation via downsampling, and resolution prefix tuning. Moreover, we employ a multi-level modeling strategy to effectively model channel correlations and infuse exogenous signals during fine-tuning, a crucial capability lacking in existing benchmarks. TTM shows significant accuracy gains (12-38\%) over popular benchmarks in few/zero-shot forecasting. It also drastically reduces the compute needs as compared to LLM-TS methods, with a 14X cut in learnable parameters, 106X less total parameters, and substantial reductions in fine-tuning (65X) and inference time (54X). In fact, TTM's zero-shot often surpasses the few-shot results in many popular benchmarks, highlighting the efficacy of our approach. Models and source code are available at https://huggingface.co/ibm/TTM
Authors: Jianshu Zhang, Yankai Fu, Ziheng Peng, Dongyu Yao, Kun He
Abstract: This paper introduces a novel perspective to significantly mitigate catastrophic forgetting in continuous learning (CL), which emphasizes models' capacity to preserve existing knowledge and assimilate new information. Current replay-based methods treat every task and data sample equally and thus can not fully exploit the potential of the replay buffer. In response, we propose COgnitive REplay (CORE), which draws inspiration from human cognitive review processes. CORE includes two key strategies: Adaptive Quantity Allocation and Quality-Focused Data Selection. The former adaptively modulates the replay buffer allocation for each task based on its forgetting rate, while the latter guarantees the inclusion of representative data that best encapsulates the characteristics of each task within the buffer. Our approach achieves an average accuracy of 37.95% on split-CIFAR10, surpassing the best baseline method by 6.52%. Additionally, it significantly enhances the accuracy of the poorest-performing task by 6.30% compared to the top baseline. Code is available at https://github.com/sterzhang/CORE.
Authors: Dobrik Georgiev, Pietro Li\`o, Davide Buffelli
Abstract: Recent work on neural algorithmic reasoning has demonstrated that graph neural networks (GNNs) could learn to execute classical algorithms. Doing so, however, has always used a recurrent architecture, where each iteration of the GNN aligns with an algorithm's iteration. Since an algorithm's solution is often an equilibrium, we conjecture and empirically validate that one can train a network to solve algorithmic problems by directly finding the equilibrium. Note that this does not require matching each GNN iteration with a step of the algorithm.
Authors: Danial Yazdani, Juergen Branke, Mohammad Sadegh Khorshidi, Mohammad Nabi Omidvar, Xiaodong Li, Amir H. Gandomi, Xin Yao
Abstract: Clustering in dynamic environments is of increasing importance, with broad applications ranging from real-time data analysis and online unsupervised learning to dynamic facility location problems. While meta-heuristics have shown promising effectiveness in static clustering tasks, their application for tracking optimal clustering solutions or robust clustering over time in dynamic environments remains largely underexplored. This is partly due to a lack of dynamic datasets with diverse, controllable, and realistic dynamic characteristics, hindering systematic performance evaluations of clustering algorithms in various dynamic scenarios. This deficiency leads to a gap in our understanding and capability to effectively design algorithms for clustering in dynamic environments. To bridge this gap, this paper introduces the Dynamic Dataset Generator (DDG). DDG features multiple dynamic Gaussian components integrated with a range of heterogeneous, local, and global changes. These changes vary in spatial and temporal severity, patterns, and domain of influence, providing a comprehensive tool for simulating a wide range of dynamic scenarios.
Authors: Zhaolin Ren, Na Li
Abstract: This paper presents a new approach for batch Bayesian Optimization (BO) called Thompson Sampling-Regret to Sigma Ratio directed sampling (TS-RSR), where we sample a new batch of actions by minimizing a Thompson Sampling approximation of a regret to uncertainty ratio. Our sampling objective is able to coordinate the actions chosen in each batch in a way that minimizes redundancy between points whilst focusing on points with high predictive means or high uncertainty. We provide high-probability theoretical guarantees on the regret of our algorithm. Finally, numerically, we demonstrate that our method attains state-of-the-art performance on a range of challenging synthetic and realistic test functions, where it outperforms several competitive benchmark batch BO algorithms.
Authors: Jaewon Jung, Hongsun Jang, Jaeyong Song, Jinho Lee
Abstract: Adversarial robustness of the neural network is a significant concern when it is applied to security-critical domains. In this situation, adversarial distillation is a promising option which aims to distill the robustness of the teacher network to improve the robustness of a small student network. Previous works pretrain the teacher network to make it robust to the adversarial examples aimed at itself. However, the adversarial examples are dependent on the parameters of the target network. The fixed teacher network inevitably degrades its robustness against the unseen transferred adversarial examples which targets the parameters of the student network in the adversarial distillation process. We propose PeerAiD to make a peer network learn the adversarial examples of the student network instead of adversarial examples aimed at itself. PeerAiD is an adversarial distillation that trains the peer network and the student network simultaneously in order to make the peer network specialized for defending the student network. We observe that such peer networks surpass the robustness of pretrained robust teacher network against student-attacked adversarial samples. With this peer network and adversarial distillation, PeerAiD achieves significantly higher robustness of the student network with AutoAttack (AA) accuracy up to 1.66%p and improves the natural accuracy of the student network up to 4.72%p with ResNet-18 and TinyImageNet dataset.
Authors: Mengchu Li, Ye Tian, Yang Feng, Yi Yu
Abstract: Federated learning is gaining increasing popularity, with data heterogeneity and privacy being two prominent challenges. In this paper, we address both issues within a federated transfer learning framework, aiming to enhance learning on a target data set by leveraging information from multiple heterogeneous source data sets while adhering to privacy constraints. We rigorously formulate the notion of \textit{federated differential privacy}, which offers privacy guarantees for each data set without assuming a trusted central server. Under this privacy constraint, we study three classical statistical problems, namely univariate mean estimation, low-dimensional linear regression, and high-dimensional linear regression. By investigating the minimax rates and identifying the costs of privacy for these problems, we show that federated differential privacy is an intermediate privacy model between the well-established local and central models of differential privacy. Our analyses incorporate data heterogeneity and privacy, highlighting the fundamental costs of both in federated learning and underscoring the benefit of knowledge transfer across data sets.
Authors: Yunfei Yang, Han Feng, Ding-Xuan Zhou
Abstract: We study approximation and learning capacities of convolutional neural networks (CNNs) with one-side zero-padding and multiple channels. Our first result proves a new approximation bound for CNNs with certain constraint on the weights. Our second result gives new analysis on the covering number of feed-forward neural networks with CNNs as special cases. The analysis carefully takes into account the size of the weights and hence gives better bounds than the existing literature in some situations. Using these two results, we are able to derive rates of convergence for estimators based on CNNs in many learning problems. In particular, we establish minimax optimal convergence rates of the least squares based on CNNs for learning smooth functions in the nonparametric regression setting. For binary classification, we derive convergence rates for CNN classifiers with hinge loss and logistic loss. It is also shown that the obtained rates for classification are minimax optimal in some common settings.
Authors: Dimitris Bertsimas, Vassilis Digalakis Jr, Yu Ma, Phevos Paschalidis
Abstract: Retraining machine learning models remains an important task for real-world machine learning model deployment. Existing methods focus largely on greedy approaches to find the best-performing model without considering the stability of trained model structures across different retraining evolutions. In this study, we develop a mixed integer optimization algorithm that holistically considers the problem of retraining machine learning models across different data batch updates. Our method focuses on retaining consistent analytical insights - which is important to model interpretability, ease of implementation, and fostering trust with users - by using custom-defined distance metrics that can be directly incorporated into the optimization problem. Importantly, our method shows stronger stability than greedily trained models with a small, controllable sacrifice in model performance in a real-world production case study. Finally, important analytical insights, as demonstrated using SHAP feature importance, are shown to be consistent across retraining iterations.
Authors: Amit Dhurandhar, Tejaswini Pedapati, Ronny Luss, Soham Dan, Aurelie Lozano, Payel Das, Georgios Kollias
Abstract: Transformer-based Language Models have become ubiquitous in Natural Language Processing (NLP) due to their impressive performance on various tasks. However, expensive training as well as inference remains a significant impediment to their widespread applicability. While enforcing sparsity at various levels of the model architecture has found promise in addressing scaling and efficiency issues, there remains a disconnect between how sparsity affects network topology. Inspired by brain neuronal networks, we explore sparsity approaches through the lens of network topology. Specifically, we exploit mechanisms seen in biological networks, such as preferential attachment and redundant synapse pruning, and show that principled, model-agnostic sparsity approaches are performant and efficient across diverse NLP tasks, spanning both classification (such as natural language inference) and generation (summarization, machine translation), despite our sole objective not being optimizing performance. NeuroPrune is competitive with (or sometimes superior to) baselines on performance and can be up to $10$x faster in terms of training time for a given level of sparsity, simultaneously exhibiting measurable improvements in inference time in many cases.
Authors: J\k{e}drzej Kozal, Jan Wasilewski, Bartosz Krawczyk, Micha{\l} Wo\'zniak
Abstract: Continual learning poses a fundamental challenge for modern machine learning systems, requiring models to adapt to new tasks while retaining knowledge from previous ones. Addressing this challenge necessitates the development of efficient algorithms capable of learning from data streams and accumulating knowledge over time. This paper proposes a novel approach to continual learning utilizing the weight consolidation method. Our method, a simple yet powerful technique, enhances robustness against catastrophic forgetting by interpolating between old and new model weights after each novel task, effectively merging two models to facilitate exploration of local minima emerging after arrival of new concepts. Moreover, we demonstrate that our approach can complement existing rehearsal-based replay approaches, improving their accuracy and further mitigating the forgetting phenomenon. Additionally, our method provides an intuitive mechanism for controlling the stability-plasticity trade-off. Experimental results showcase the significant performance enhancement to state-of-the-art experience replay algorithms the proposed weight consolidation approach offers. Our algorithm can be downloaded from https://github.com/jedrzejkozal/weight-interpolation-cl.
URLs: https://github.com/jedrzejkozal/weight-interpolation-cl.
Authors: Tianze Wang, Maryam Honari-Jahromi, Styliani Katsarou, Olga Mikheeva, Theodoros Panagiotakopoulos, Sahar Asadi, Oleg Smirnov
Abstract: Methods for learning latent user representations from historical behavior logs have gained traction for recommendation tasks in e-commerce, content streaming, and other settings. However, this area still remains relatively underexplored in video and mobile gaming contexts. In this work, we present a novel method for overcoming this limitation by extending a long-range Transformer model from the natural language processing domain to player behavior data. We discuss specifics of behavior tracking in games and propose preprocessing and tokenization approaches by viewing in-game events in an analogous way to words in sentences, thus enabling learning player representations in a self-supervised manner in the absence of ground-truth annotations. We experimentally demonstrate the efficacy of the proposed approach in fitting the distribution of behavior events by evaluating intrinsic language modeling metrics. Furthermore, we qualitatively analyze the emerging structure of the learned embedding space and show its value for generating insights into behavior patterns to inform downstream applications.
Authors: Amin Aminifar, Baichuan Huang, Azra Abtahi, Amir Aminifar
Abstract: The human brain performs tasks with an outstanding energy-efficiency, i.e., with approximately 20 Watts. The state-of-the-art Artificial/Deep Neural Networks (ANN/DNN), on the other hand, have recently been shown to consume massive amounts of energy. The training of these ANNs/DNNs is done almost exclusively based on the back-propagation algorithm, which is known to be biologically implausible. This has led to a new generation of forward-only techniques, including the Forward-Forward algorithm. In this paper, we propose a lightweight inference scheme specifically designed for DNNs trained using the Forward-Forward algorithm. We have evaluated our proposed lightweight inference scheme in the case of the MNIST and CIFAR datasets, as well as two real-world applications, namely, epileptic seizure detection and cardiac arrhythmia classification using wearable technologies, where complexity overheads/energy consumption is a major constraint, and demonstrate its relevance.
Authors: Shuai Guo, Jielei Chu, Lei Zhu, Tianrui Li
Abstract: Generative Flow Networks (GFlowNets) are probabilistic models predicated on Markov flows, employing specific amortization algorithms to learn stochastic policies that generate compositional substances including biomolecules, chemical materials, and more. Demonstrating formidable prowess in generating high-performance biochemical molecules, GFlowNets accelerate the discovery of scientific substances, effectively circumventing the time-consuming, labor-intensive, and costly shortcomings intrinsic to conventional material discovery. However, previous work often struggles to accumulate exploratory experience and is prone to becoming disoriented within expansive sampling spaces. Attempts to address this issue, such as LS-GFN, are limited to local greedy searches and lack broader global adjustments. This paper introduces a novel GFlowNets variant, the Dynamic Backtracking GFN (DB-GFN), which enhances the adaptability of decision-making steps through a reward-based dynamic backtracking mechanism. DB-GFN permits backtracking during the network construction process according to the current state's reward value, thus correcting disadvantageous decisions and exploring alternative pathways during the exploration process. Applied to generative tasks of biochemical molecules and genetic material sequences, DB-GFN surpasses existing GFlowNets models and traditional reinforcement learning methods in terms of sample quality, exploration sample quantity, and training convergence speed. Furthermore, the orthogonal nature of DB-GFN suggests its potential as a powerful tool for future improvements in GFlowNets, with the promise of integrating with other strategies to achieve more efficient search performance.
Authors: Tu Nguyen, Cheng Li, Claudia Nieder\'ee
Abstract: Recently a lot of progress has been made in rumor modeling and rumor detection for micro-blogging streams. However, existing automated methods do not perform very well for early rumor detection, which is crucial in many settings, e.g., in crisis situations. One reason for this is that aggregated rumor features such as propagation features, which work well on the long run, are - due to their accumulating characteristic - not very helpful in the early phase of a rumor. In this work, we present an approach for early rumor detection, which leverages Convolutional Neural Networks for learning the hidden representations of individual rumor-related tweets to gain insights on the credibility of each tweets. We then aggregate the predictions from the very beginning of a rumor to obtain the overall event credits (so-called wisdom), and finally combine it with a time series based rumor classification model. Our extensive experiments show a clearly improved classification performance within the critical very first hours of a rumor. For a better understanding, we also conduct an extensive feature evaluation that emphasized on the early stage and shows that the low-level credibility has best predictability at all phases of the rumor lifetime.
Authors: Tu Nguyen
Abstract: Recent work have done a good job in modeling rumors and detecting them over microblog streams. However, the performance of their automatic approaches are not relatively high when looking early in the diffusion. A first intuition is that, at early stage, most of the aggregated rumor features (e.g., propagation features) are not mature and distinctive enough. The objective of rumor debunking in microblogs, however, are to detect these misinformation as early as possible. In this work, we leverage neural models in learning the hidden representations of individual rumor-related tweets at the very beginning of a rumor. Our extensive experiments show that the resulting signal improves our classification performance over time, significantly within the first 10 hours. To deepen the understanding of these low and high-level features in contributing to the model performance over time, we conduct an extensive study on a wide range of high impact rumor features for the 48 hours range. The end model that engages these features are shown to be competitive, reaches over 90% accuracy and out-performs strong baselines in our carefully cured dataset.
Authors: Tu Nguyen, Nattiya Kanhabua, Wolfgang Nejdl
Abstract: Entity aspect recommendation is an emerging task in semantic search that helps users discover serendipitous and prominent information with respect to an entity, of which salience (e.g., popularity) is the most important factor in previous work. However, entity aspects are temporally dynamic and often driven by events happening over time. For such cases, aspect suggestion based solely on salience features can give unsatisfactory results, for two reasons. First, salience is often accumulated over a long time period and does not account for recency. Second, many aspects related to an event entity are strongly time-dependent. In this paper, we study the task of temporal aspect recommendation for a given entity, which aims at recommending the most relevant aspects and takes into account time in order to improve search experience. We propose a novel event-centric ensemble ranking method that learns from multiple time and type-dependent models and dynamically trades off salience and recency characteristics. Through extensive experiments on real-world query logs, we demonstrate that our method is robust and achieves better effectiveness than competitive baselines.
Authors: Tu Nguyen, Markus Rokicki
Abstract: With continuous glucose monitoring (CGM), data-driven models on blood glucose prediction have been shown to be effective in related work. However, such (CGM) systems are not always available, e.g., for a patient at home. In this work, we conduct a study on 9 patients and examine the online predictability of data-driven (aka. machine learning) based models on patient-level blood glucose prediction; with measurements are taken only periodically (i.e., after several hours). To this end, we propose several post-prediction methods to account for the noise nature of these data, that marginally improves the performance of the end system.
Authors: Shams Mehdi, Pratyush Tiwary
Abstract: In recent years, predictive machine learning methods have gained prominence in various scientific domains. However, due to their black-box nature, it is essential to establish trust in these models before accepting them as accurate. One promising strategy for assigning trust involves employing explanation techniques that elucidate the rationale behind a black-box model's predictions in a manner that humans can understand. However, assessing the degree of human interpretability of the rationale generated by such methods is a nontrivial challenge. In this work, we introduce interpretation entropy as a universal solution for assessing the degree of human interpretability associated with any linear model. Using this concept and drawing inspiration from classical thermodynamics, we present Thermodynamics-inspired Explainable Representations of AI and other black-box Paradigms (TERP), a method for generating accurate, and human-interpretable explanations for black-box predictions in a model-agnostic manner. To demonstrate the wide-ranging applicability of TERP, we successfully employ it to explain various black-box model architectures, including deep learning Autoencoders, Recurrent Neural Networks, and Convolutional Neural Networks, across diverse domains such as molecular simulations, text, and image classification.
Authors: Kevin Zhang, Zhiqiang Shen
Abstract: Masked image modeling (MIM) has been recognized as a strong self-supervised pre-training approach in the vision domain. However, the mechanism and properties of the learned representations by such a scheme, as well as how to further enhance the representations are so far not well-explored. In this paper, we aim to explore an interactive Masked Autoencoders (i-MAE) framework to enhance the representation capability from two aspects: (1) employing a two-way image reconstruction and a latent feature reconstruction with distillation loss to learn better features; (2) proposing a semantics-enhanced sampling strategy to boost the learned semantics in MAE. Upon the proposed i-MAE architecture, we can address two critical questions to explore the behaviors of the learned representations in MAE: (1) Whether the separability of latent representations in Masked Autoencoders is helpful for model performance? We study it by forcing the input as a mixture of two images instead of one. (2) Whether we can enhance the representations in the latent feature space by controlling the degree of semantics during sampling on Masked Autoencoders? To this end, we propose a sampling strategy within a mini-batch based on the semantics of training samples to examine this aspect. Extensive experiments are conducted on CIFAR-10/100, Tiny-ImageNet and ImageNet-1K to verify the observations we discovered. Furthermore, in addition to qualitatively analyzing the characteristics of the latent representations, we examine the existence of linear separability and the degree of semantics in the latent space by proposing two evaluation schemes. The surprising and consistent results demonstrate that i-MAE is a superior framework design for understanding MAE frameworks, as well as achieving better representational ability. Code is available at https://github.com/vision-learning-acceleration-lab/i-mae.
URLs: https://github.com/vision-learning-acceleration-lab/i-mae.
Authors: Yoichi Ishibashi, Sho Yokoi, Katsuhito Sudoh, Satoshi Nakamura
Abstract: In the field of natural language processing (NLP), continuous vector representations are crucial for capturing the semantic meanings of individual words. Yet, when it comes to the representations of sets of words, the conventional vector-based approaches often struggle with expressiveness and lack the essential set operations such as union, intersection, and complement. Inspired by quantum logic, we realize the representation of word sets and corresponding set operations within pre-trained word embedding spaces. By grounding our approach in the linear subspaces, we enable efficient computation of various set operations and facilitate the soft computation of membership functions within continuous spaces. Moreover, we allow for the computation of the F-score directly within word vectors, thereby establishing a direct link to the assessment of sentence similarity. In experiments with widely-used pre-trained embeddings and benchmarks, we show that our subspace-based set operations consistently outperform vector-based ones in both sentence similarity and set retrieval tasks.
Authors: Ibrahim Batuhan Akkaya, Ugur Halici
Abstract: Unsupervised source-free domain adaptation methods aim to train a model for the target domain utilizing a pretrained source-domain model and unlabeled target-domain data, particularly when accessibility to source data is restricted due to intellectual property or privacy concerns. Traditional methods usually use self-training with pseudo-labeling, which is often subjected to thresholding based on prediction confidence. However, such thresholding limits the effectiveness of self-training due to insufficient supervision. This issue becomes more severe in a source-free setting, where supervision comes solely from the predictions of the pre-trained source model. In this study, we propose a novel approach by incorporating a mean-teacher model, wherein the student network is trained using all predictions from the teacher network. Instead of employing thresholding on predictions, we introduce a method to weight the gradients calculated from pseudo-labels based on the reliability of the teacher's predictions. To assess reliability, we introduce a novel approach using proxy-based metric learning. Our method is evaluated in synthetic-to-real and cross-city scenarios, demonstrating superior performance compared to existing state-of-the-art methods.
Authors: Shengling Shi, Anastasios Tsiamis, Bart De Schutter
Abstract: In this work, we aim to analyze how the trade-off between the modeling error, the terminal value function error, and the prediction horizon affects the performance of a nominal receding-horizon linear quadratic (LQ) controller. By developing a novel perturbation result of the Riccati difference equation, a novel performance upper bound is obtained and suggests that for many cases, the prediction horizon can be either one or infinity to improve the control performance, depending on the relative difference between the modeling error and the terminal value function error. The result also shows that when an infinite horizon is desired, a finite prediction horizon that is larger than the controllability index can be sufficient for achieving a near-optimal performance, revealing a close relation between the prediction horizon and controllability. The obtained suboptimality performance bound is also applied to provide novel sample complexity and regret guarantees for nominal receding-horizon LQ controllers in a learning-based setting.
Authors: Vidit Goel, Elia Peruzzo, Yifan Jiang, Dejia Xu, Xingqian Xu, Nicu Sebe, Trevor Darrell, Zhangyang Wang, Humphrey Shi
Abstract: Generative image editing has recently witnessed extremely fast-paced growth. Some works use high-level conditioning such as text, while others use low-level conditioning. Nevertheless, most of them lack fine-grained control over the properties of the different objects present in the image, i.e. object-level image editing. In this work, we tackle the task by perceiving the images as an amalgamation of various objects and aim to control the properties of each object in a fine-grained manner. Out of these properties, we identify structure and appearance as the most intuitive to understand and useful for editing purposes. We propose PAIR Diffusion, a generic framework that can enable a diffusion model to control the structure and appearance properties of each object in the image. We show that having control over the properties of each object in an image leads to comprehensive editing capabilities. Our framework allows for various object-level editing operations on real images such as reference image-based appearance editing, free-form shape editing, adding objects, and variations. Thanks to our design, we do not require any inversion step. Additionally, we propose multimodal classifier-free guidance which enables editing images using both reference images and text when using our approach with foundational diffusion models. We validate the above claims by extensively evaluating our framework on both unconditional and foundational diffusion models. Please refer to https://vidit98.github.io/publication/conference-paper/pair_diff.html for code and model release.
URLs: https://vidit98.github.io/publication/conference-paper/pair_diff.html
Authors: Inbar Huberman-Spiegelglas, Vladimir Kulikov, Tomer Michaeli
Abstract: Denoising diffusion probabilistic models (DDPMs) employ a sequence of white Gaussian noise samples to generate an image. In analogy with GANs, those noise maps could be considered as the latent code associated with the generated image. However, this native noise space does not possess a convenient structure, and is thus challenging to work with in editing tasks. Here, we propose an alternative latent noise space for DDPM that enables a wide range of editing operations via simple means, and present an inversion method for extracting these edit-friendly noise maps for any given image (real or synthetically generated). As opposed to the native DDPM noise space, the edit-friendly noise maps do not have a standard normal distribution and are not statistically independent across timesteps. However, they allow perfect reconstruction of any desired image, and simple transformations on them translate into meaningful manipulations of the output image (e.g. shifting, color edits). Moreover, in text-conditional models, fixing those noise maps while changing the text prompt, modifies semantics while retaining structure. We illustrate how this property enables text-based editing of real images via the diverse DDPM sampling scheme (in contrast to the popular non-diverse DDIM inversion). We also show how it can be used within existing diffusion-based editing methods to improve their quality and diversity. Webpage: https://inbarhub.github.io/DDPM_inversion
Authors: Konstantin Gasenzer (High Performance Computing and Analytics Lab, Universit\"at Bonn, Germany), Moritz Wolter (High Performance Computing and Analytics Lab, Universit\"at Bonn, Germany)
Abstract: Today's generative neural networks allow the creation of high-quality synthetic speech at scale. While we welcome the creative use of this new technology, we must also recognize the risks. As synthetic speech is abused for monetary and identity theft, we require a broad set of deepfake identification tools. Furthermore, previous work reported a limited ability of deep classifiers to generalize to unseen audio generators. We study the frequency domain fingerprints of current audio generators. Building on top of the discovered frequency footprints, we train excellent lightweight detectors that generalize. We report improved results on the WaveFake dataset and an extended version. To account for the rapid progress in the field, we extend the WaveFake dataset by additionally considering samples drawn from the novel Avocodo and BigVGAN networks. For illustration purposes, the supplementary material contains audio samples of generator artifacts.
Authors: Sanghyuk Chun
Abstract: Image-Text Matching (ITM) task, a fundamental vision-language (VL) task, suffers from the inherent ambiguity arising from multiplicity and imperfect annotations. Deterministic functions are not sufficiently powerful to capture ambiguity, prompting the exploration of probabilistic embeddings to tackle the challenge. However, the existing probabilistic ITM approach encounters two key shortcomings; the burden of heavy computations due to the Monte Carlo approximation, and the loss saturation issue in the face of abundant false negatives. To overcome the issues, this paper presents an improved Probabilistic Cross-Modal Embeddings (named PCME++) by introducing a new probabilistic distance with a closed-form solution. In addition, two optimization techniques are proposed to enhance PCME++ further: first, the incorporation of pseudo-positives to prevent the negative effect under massive false negatives; second, mixed sample data augmentation for probabilistic matching. Experimental results on MS-COCO Caption and two extended benchmarks, CxC and ECCV Caption, demonstrate the effectiveness of PCME++ compared to state-of-the-art ITM methods. The robustness of PCME++ is also evaluated under noisy image-text correspondences. In addition, the potential applicability of PCME++ in automatic prompt-filtering for zero-shot classification is shown. The code is available at https://github.com/naver-ai/pcmepp
Authors: Bowen Li, Bin Shi, Ya-xiang Yuan
Abstract: A significant milestone in modern gradient-based optimization was achieved with the development of Nesterov's accelerated gradient descent (NAG) method. This forward-backward technique has been further advanced with the introduction of its proximal generalization, commonly known as the fast iterative shrinkage-thresholding algorithm (FISTA), which enjoys widespread application in image science and engineering. Nonetheless, it remains unclear whether both NAG and FISTA exhibit linear convergence for strongly convex functions. Remarkably, these algorithms demonstrate convergence without requiring any prior knowledge of strongly convex modulus, and this intriguing characteristic has been acknowledged as an open problem in the comprehensive review [Chambolle and Pock, 2016, Appendix B]. In this paper, we address this question by utilizing the high-resolution ordinary differential equation (ODE) framework. Expanding upon the established phase-space representation, we emphasize the distinctive approach employed in crafting the Lyapunov function, which involves a dynamically adapting coefficient of kinetic energy that evolves throughout the iterations. Furthermore, we highlight that the linear convergence of both NAG and FISTA is independent of the parameter $r$. Additionally, we demonstrate that the square of the proximal subgradient norm likewise advances towards linear convergence.
Authors: Zhenting Wang, Chen Chen, Lingjuan Lyu, Dimitris N. Metaxas, Shiqing Ma
Abstract: Recent text-to-image diffusion models have shown surprising performance in generating high-quality images. However, concerns have arisen regarding the unauthorized data usage during the training or fine-tuning process. One example is when a model trainer collects a set of images created by a particular artist and attempts to train a model capable of generating similar images without obtaining permission and giving credit to the artist. To address this issue, we propose a method for detecting such unauthorized data usage by planting the injected memorization into the text-to-image diffusion models trained on the protected dataset. Specifically, we modify the protected images by adding unique contents on these images using stealthy image warping functions that are nearly imperceptible to humans but can be captured and memorized by diffusion models. By analyzing whether the model has memorized the injected content (i.e., whether the generated images are processed by the injected post-processing function), we can detect models that had illegally utilized the unauthorized data. Experiments on Stable Diffusion and VQ Diffusion with different model training or fine-tuning methods (i.e, LoRA, DreamBooth, and standard training) demonstrate the effectiveness of our proposed method in detecting unauthorized data usages. Code: https://github.com/ZhentingWang/DIAGNOSIS.
Authors: Xinmeng Huang, Ping Li, Xiaoyun Li
Abstract: Communication compression, a technique aiming to reduce the information volume to be transmitted over the air, has gained great interests in Federated Learning (FL) for the potential of alleviating its communication overhead. However, communication compression brings forth new challenges in FL due to the interplay of compression-incurred information distortion and inherent characteristics of FL such as partial participation and data heterogeneity. Despite the recent development, the performance of compressed FL approaches has not been fully exploited. The existing approaches either cannot accommodate arbitrary data heterogeneity or partial participation, or require stringent conditions on compression. In this paper, we revisit the seminal stochastic controlled averaging method by proposing an equivalent but more efficient/simplified formulation with halved uplink communication costs. Building upon this implementation, we propose two compressed FL algorithms, SCALLION and SCAFCOM, to support unbiased and biased compression, respectively. Both the proposed methods outperform the existing compressed FL methods in terms of communication and computation complexities. Moreover, SCALLION and SCAFCOM accommodates arbitrary data heterogeneity and do not make any additional assumptions on compression errors. Experiments show that SCALLION and SCAFCOM can match the performance of corresponding full-precision FL approaches with substantially reduced uplink communication, and outperform recent compressed FL methods under the same communication budget.
Authors: Vasisht Duddu, Anudeep Das, Nora Khayata, Hossein Yalame, Thomas Schneider, N. Asokan
Abstract: The success of machine learning (ML) has been accompanied by increased concerns about its trustworthiness. Several jurisdictions are preparing ML regulatory frameworks. One such concern is ensuring that model training data has desirable distributional properties for certain sensitive attributes. For example, draft regulations indicate that model trainers are required to show that training datasets have specific distributional properties, such as reflecting diversity of the population. We propose the notion of property attestation allowing a prover (e.g., model trainer) to demonstrate relevant distributional properties of training data to a verifier (e.g., a customer) without revealing the data. We present an effective hybrid property attestation combining property inference with cryptographic mechanisms.
Authors: Siyuan Song, Hanxun Jin
Abstract: Identifying constitutive parameters in engineering and biological materials, particularly those with intricate geometries and mechanical behaviors, remains a longstanding challenge. The recent advent of Physics-Informed Neural Networks (PINNs) offers promising solutions, but current frameworks are often limited to basic constitutive laws and encounter practical constraints when combined with experimental data. In this paper, we introduce a robust PINN-based framework designed to identify material parameters for soft materials, specifically those exhibiting complex constitutive behaviors, under large deformation in plane stress conditions. Distinctively, our model emphasizes training PINNs with multi-modal synthetic experimental datasets consisting of full-field deformation and loading history, ensuring algorithm robustness even with noisy data. Our results reveal that the PINNs framework can accurately identify constitutive parameters of the incompressible Arruda-Boyce model for samples with intricate geometries, maintaining an error below 5%, even with an experimental noise level of 5%. We believe our framework provides a robust modulus identification approach for complex solids, especially for those with geometrical and constitutive complexity.
Authors: Ting-Han Fan, Ta-Chung Chi, Alexander I. Rudnicky
Abstract: In recent studies, linear recurrent neural networks (LRNNs) have achieved Transformer-level performance in natural language and long-range modeling, while offering rapid parallel training and constant inference cost. With the resurgence of interest in LRNNs, we study whether they can learn the hidden rules in training sequences, such as the grammatical structures of regular language. We theoretically analyze some existing LRNNs and discover their limitations in modeling regular language. Motivated by this analysis, we propose a new LRNN equipped with a block-diagonal and input-dependent transition matrix. Experiments suggest that the proposed model is the only LRNN capable of performing length extrapolation on regular language tasks such as Sum, Even Pair, and Modular Arithmetic. The code is released at \url{https://github.com/tinghanf/RegluarLRNN}.
Authors: Yash Semlani, Mihir Relan, Krithik Ramesh
Abstract: Jet tagging is a classification problem in high-energy physics experiments that aims to identify the collimated sprays of subatomic particles, jets, from particle collisions and tag them to their emitter particle. Advances in jet tagging present opportunities for searches of new physics beyond the Standard Model. Current approaches use deep learning to uncover hidden patterns in complex collision data. However, the representation of jets as inputs to a deep learning model have been varied, and often, informative features are withheld from models. In this study, we propose a graph-based representation of a jet that encodes the most information possible. To learn best from this representation, we design Particle Chebyshev Network (PCN), a graph neural network (GNN) using Chebyshev graph convolutions (ChebConv). ChebConv has been demonstrated as an effective alternative to classical graph convolutions in GNNs and has yet to be explored in jet tagging. PCN achieves a substantial improvement in accuracy over existing taggers and opens the door to future studies into graph-based representations of jets and ChebConv layers in high-energy physics experiments. Code is available at https://github.com/YVSemlani/PCN-Jet-Tagging.
Authors: Humberto Reyes-Gonzalez, Riccardo Torre
Abstract: We propose the NFLikelihood, an unsupervised version, based on Normalizing Flows, of the DNNLikelihood proposed in Ref.[1]. We show, through realistic examples, how Autoregressive Flows, based on affine and rational quadratic spline bijectors, are able to learn complicated high-dimensional Likelihoods arising in High Energy Physics (HEP) analyses. We focus on a toy LHC analysis example already considered in the literature and on two Effective Field Theory fits of flavor and electroweak observables, whose samples have been obtained throught the HEPFit code. We discuss advantages and disadvantages of the unsupervised approach with respect to the supervised one and discuss possible interplays of the two.
Authors: Aryaman Gupta, Kaustav Chakraborty, Somil Bansal
Abstract: Autonomous systems, such as self-driving cars and drones, have made significant strides in recent years by leveraging visual inputs and machine learning for decision-making and control. Despite their impressive performance, these vision-based controllers can make erroneous predictions when faced with novel or out-of-distribution inputs. Such errors can cascade to catastrophic system failures and compromise system safety. In this work, we introduce a run-time anomaly monitor to detect and mitigate such closed-loop, system-level failures. Specifically, we leverage a reachability-based framework to stress-test the vision-based controller offline and mine its system-level failures. This data is then used to train a classifier that is leveraged online to flag inputs that might cause system breakdowns. The anomaly detector highlights issues that transcend individual modules and pertain to the safety of the overall system. We also design a fallback controller that robustly handles these detected anomalies to preserve system safety. We validate the proposed approach on an autonomous aircraft taxiing system that uses a vision-based controller for taxiing. Our results show the efficacy of the proposed approach in identifying and handling system-level anomalies, outperforming methods such as prediction error-based detection, and ensembling, thereby enhancing the overall safety and robustness of autonomous systems.
Authors: Philipp Quentin, Dino Knoll, Daniel Goehring
Abstract: Despite the advances in robotics a large proportion of the of parts handling tasks in the automotive industry's internal logistics are not automated but still performed by humans. A key component to competitively automate these processes is a 6D pose estimation that can handle a large number of different parts, is adaptable to new parts with little manual effort, and is sufficiently accurate and robust with respect to industry requirements. In this context, the question arises as to the current status quo with respect to these measures. To address this we built a representative 6D pose estimation pipeline with state-of-the-art components from economically scalable real to synthetic data generation to pose estimators and evaluated it on automotive parts with regards to a realistic sequencing process. We found that using the data generation approaches, the performance of the trained 6D pose estimators are promising, but do not meet industry requirements. We reveal that the reason for this is the inability of the estimators to provide reliable uncertainties for their poses, rather than the ability of to provide sufficiently accurate poses. In this context we further analyzed how RGB- and RGB-D-based approaches compare against this background and show that they are differently vulnerable to the domain gap induced by synthetic data.
Authors: Elies Gil-Fuster, Jens Eisert, Vedran Dunjko
Abstract: One of the most natural connections between quantum and classical machine learning has been established in the context of kernel methods. Kernel methods rely on kernels, which are inner products of feature vectors living in large feature spaces. Quantum kernels are typically evaluated by explicitly constructing quantum feature states and then taking their inner product, here called embedding quantum kernels. Since classical kernels are usually evaluated without using the feature vectors explicitly, we wonder how expressive embedding quantum kernels are. In this work, we raise the fundamental question: can all quantum kernels be expressed as the inner product of quantum feature states? Our first result is positive: Invoking computational universality, we find that for any kernel function there always exists a corresponding quantum feature map and an embedding quantum kernel. The more operational reading of the question is concerned with efficient constructions, however. In a second part, we formalize the question of universality of efficient embedding quantum kernels. For shift-invariant kernels, we use the technique of random Fourier features to show that they are universal within the broad class of all kernels which allow a variant of efficient Fourier sampling. We then extend this result to a new class of so-called composition kernels, which we show also contains projected quantum kernels introduced in recent works. After proving the universality of embedding quantum kernels for both shift-invariant and composition kernels, we identify the directions towards new, more exotic, and unexplored quantum kernel families, for which it still remains open whether they correspond to efficient embedding quantum kernels.
Authors: Alessio Arcudi, Davide Frizzo, Chiara Masiero, Gian Antonio Susto
Abstract: Anomaly Detection involves identifying unusual behaviors within complex datasets and systems. While Machine Learning algorithms and Decision Support Systems (DSSs) offer effective solutions for this task, simply pinpointing anomalies may prove insufficient in real-world applications. Users require insights into the rationale behind these predictions to facilitate root cause analysis and foster trust in the model. However, the unsupervised nature of AD presents a challenge in developing interpretable tools. This paper addresses this challenge by introducing ExIFFI, a novel interpretability approach specifically designed to explain the predictions made by Extended Isolation Forest. ExIFFI leverages feature importance to provide explanations at both global and local levels. This work also introduces EIF+, an enhanced variant of Extended Isolation Forest, conceived to improve its generalization capabilities through a different splitting hyperplanes design strategy. A comprehensive comparative analysis is conducted, employing both synthetic and real-world datasets to evaluate various unsupervised AD approaches. The analysis demonstrates the effectiveness of ExIFFI in providing explanations for AD predictions. Furthermore, the paper explores the utility of ExIFFI as a feature selection technique in unsupervised settings. Finally, this work contributes to the research community by providing open-source code, facilitating further investigation and reproducibility.
Authors: Qiyuan Ou, Siwei Wang, Pei Zhang, Sihang Zhou, En Zhu
Abstract: Multi-view clustering has attracted growing attention owing to its capabilities of aggregating information from various sources and its promising horizons in public affairs. Up till now, many advanced approaches have been proposed in recent literature. However, there are several ongoing difficulties to be tackled. One common dilemma occurs while attempting to align the features of different views. {Moreover, due to the fact that many existing multi-view clustering algorithms stem from spectral clustering, this results to cubic time complexity w.r.t. the number of dataset. However, we propose Anchor-based Multi-view Subspace Clustering with Hierarchical Feature Descent(MVSC-HFD) to tackle the discrepancy among views through hierarchical feature descent and project to a common subspace( STAGE 1), which reveals dependency of different views. We further reduce the computational complexity to linear time cost through a unified sampling strategy in the common subspace( STAGE 2), followed by anchor-based subspace clustering to learn the bipartite graph collectively( STAGE 3). }Extensive experimental results on public benchmark datasets demonstrate that our proposed model consistently outperforms the state-of-the-art techniques.
Authors: Jacopo Talpini, Fabio Sartori, Marco Savi
Abstract: The evolution of Internet and its related communication technologies have consistently increased the risk of cyber-attacks. In this context, a crucial role is played by Intrusion Detection Systems (IDSs), which are security devices designed to identify and mitigate attacks to modern networks. Data-driven approaches based on Machine Learning (ML) have gained more and more popularity for executing the classification tasks required by signature-based IDSs. However, typical ML models adopted for this purpose do not properly take into account the uncertainty associated with their prediction. This poses significant challenges, as they tend to produce misleadingly high classification scores for both misclassified inputs and inputs belonging to unknown classes (e.g. novel attacks), limiting the trustworthiness of existing ML-based solutions. In this paper, we argue that ML-based IDSs should always provide accurate uncertainty quantification to avoid overconfident predictions. In fact, an uncertainty-aware classification would be beneficial to enhance closed-set classification performance, would make it possible to carry out Active Learning, and would help recognize inputs of unknown classes as truly unknowns, unlocking open-set classification capabilities and Out-of-Distribution (OoD) detection. To verify it, we compare various ML-based methods for uncertainty quantification and for open-set classification, either specifically designed for or tailored to the domain of network intrusion detection. Moreover, we develop a custom model based on Bayesian Neural Networks to ensure reliable uncertainty estimates and improve the OoD detection capabilities, thus showing how proper uncertainty quantification can be exploited to significantly enhance the trustworthiness of ML-based IDSs.
Authors: Saad Zafar Khan, Nazeefa Muzammil, Salman Ghafoor, Haibat Khan, Syed Mohammad Hasan Zaidi, Abdulah Jeza Aljohani, Imran Aziz
Abstract: Accurate solar power forecasting is pivotal for the global transition towards sustainable energy systems. This study conducts a meticulous comparison between Quantum Long Short-Term Memory (QLSTM) and classical Long Short-Term Memory (LSTM) models for solar power production forecasting. The primary objective is to evaluate the potential advantages of QLSTMs, leveraging their exponential representational capabilities, in capturing the intricate spatiotemporal patterns inherent in renewable energy data. Through controlled experiments on real-world photovoltaic datasets, our findings reveal promising improvements offered by QLSTMs, including accelerated training convergence and substantially reduced test loss within the initial epoch compared to classical LSTMs. These empirical results demonstrate QLSTM's potential to swiftly assimilate complex time series relationships, enabled by quantum phenomena like superposition. However, realizing QLSTM's full capabilities necessitates further research into model validation across diverse conditions, systematic hyperparameter optimization, hardware noise resilience, and applications to correlated renewable forecasting problems. With continued progress, quantum machine learning can offer a paradigm shift in renewable energy time series prediction, potentially ushering in an era of unprecedented accuracy and reliability in solar power forecasting worldwide. This pioneering work provides initial evidence substantiating quantum advantages over classical LSTM models while acknowledging present limitations. Through rigorous benchmarking grounded in real-world data, our study illustrates a promising trajectory for quantum learning in renewable forecasting.
Authors: Gianluigi Lopardo, Frederic Precioso, Damien Garreau
Abstract: Interpretability is essential for machine learning models to be trusted and deployed in critical domains. However, existing methods for interpreting text models are often complex, lack mathematical foundations, and their performance is not guaranteed. In this paper, we propose FRED (Faithful and Robust Explainer for textual Documents), a novel method for interpreting predictions over text. FRED offers three key insights to explain a model prediction: (1) it identifies the minimal set of words in a document whose removal has the strongest influence on the prediction, (2) it assigns an importance score to each token, reflecting its influence on the model's output, and (3) it provides counterfactual explanations by generating examples similar to the original document, but leading to a different prediction. We establish the reliability of FRED through formal definitions and theoretical analyses on interpretable classifiers. Additionally, our empirical evaluation against state-of-the-art methods demonstrates the effectiveness of FRED in providing insights into text models.
Authors: Xuanwen Liang, Eric Wai Ming Lee
Abstract: Crowd simulations play a pivotal role in building design, influencing both user experience and public safety. While traditional knowledge-driven models have their merits, data-driven crowd simulation models promise to bring a new dimension of realism to these simulations. However, most of the existing data-driven models are designed for specific geometries, leading to poor adaptability and applicability. A promising strategy for enhancing the adaptability and realism of data-driven crowd simulation models is to incorporate visual information, including the scenario geometry and pedestrian locomotion. Consequently, this paper proposes a novel visual-information-driven (VID) crowd simulation model. The VID model predicts the pedestrian velocity at the next time step based on the prior social-visual information and motion data of an individual. A radar-geometry-locomotion method is established to extract the visual information of pedestrians. Moreover, a temporal convolutional network (TCN)-based deep learning model, named social-visual TCN, is developed for velocity prediction. The VID model is tested on three public pedestrian motion datasets with distinct geometries, i.e., corridor, corner, and T-junction. Both qualitative and quantitative metrics are employed to evaluate the VID model, and the results highlight the improved adaptability of the model across all three geometric scenarios. Overall, the proposed method demonstrates effectiveness in enhancing the adaptability of data-driven crowd models.
Authors: Hung Quoc To, Minh Huynh Nguyen, Nghi D. Q. Bui
Abstract: Code Large Language Models (CodeLLMs) have marked a new era in code generation advancements. However, selecting the best solutions from all possible CodeLLM solutions remains a challenge. Previous methods frequently overlooked the intricate functional similarities and interactions between clusters, resulting in suboptimal results. In this work, we introduce \textit{SRank}, a novel reranking strategy for selecting the best solution from code generation that focuses on modeling the relationship between clusters of solutions. By quantifying the functional overlap between clusters, our approach provides a better ranking strategy of code solutions. Empirical results show that our method achieves remarkable results on pass@1 score. For instance, on the Human-Eval benchmark, we achieve 69.66\% in pass@1 with Codex002, 75.31\% for WizardCoder, 53.99\% for StarCoder and 60.55\% for CodeGen, which surpass the state-of-the-arts solution ranking methods, such as CodeT and Coder-Reviewer on the same CodeLLM with significant margin ($\approx 6.1\%$ improvement on average). Even in scenarios with a limited number of sampled solutions and test cases, our approach demonstrates robustness and superiority, marking a new benchmark in code generation reranking.
Authors: Michaela Hardt, William R. Orchard, Patrick Bl\"obaum, Shiva Kasiviswanathan, Elke Kirschbaum
Abstract: Identifying root causes for unexpected or undesirable behavior in complex systems is a prevalent challenge. This issue becomes especially crucial in modern cloud applications that employ numerous microservices. Although the machine learning and systems research communities have proposed various techniques to tackle this problem, there is currently a lack of standardized datasets for quantitative benchmarking. Consequently, research groups are compelled to create their own datasets for experimentation. This paper introduces a dataset specifically designed for evaluating root cause analyses in microservice-based applications. The dataset encompasses latency, requests, and availability metrics emitted in 5-minute intervals from a distributed application. In addition to normal operation metrics, the dataset includes 68 injected performance issues, which increase latency and reduce availability throughout the system. We showcase how this dataset can be used to evaluate the accuracy of a variety of methods spanning different causal and non-causal characterisations of the root cause analysis problem. We hope the new dataset, available at https://github.com/amazon-science/petshop-root-cause-analysis/ enables further development of techniques in this important area.
URLs: https://github.com/amazon-science/petshop-root-cause-analysis/
Authors: Rocktim Jyoti Das, Mingjie Sun, Liqun Ma, Zhiqiang Shen
Abstract: Large Language Models (LLMs) with billions of parameters are prime targets for network pruning, removing some model weights without hurting performance. Prior approaches such as magnitude pruning, SparseGPT, and Wanda, either concentrated solely on weights or integrated weights with activations for sparsity. However, they overlooked the informative gradients derived from pretrained LLMs. In this paper, we present a novel sparsity-centric pruning method for pretrained LLMs, termed Gradient-based Language Model Pruner (GBLM-Pruner). GBLM-Pruner leverages the first-order term of the Taylor expansion, operating in a training-free manner by harnessing properly normalized gradients from a few calibration samples to determine the pruning metric, and substantially outperforms competitive counterparts like SparseGPT and Wanda in multiple benchmarks. Intriguingly, by incorporating gradients, unstructured pruning with our method tends to reveal some structural patterns, which mirrors the geometric interdependence inherent in the LLMs' parameter structure. Additionally, GBLM-Pruner functions without any subsequent retraining or weight updates to maintain its simplicity as other counterparts. Extensive evaluations on LLaMA-1 and LLaMA-2 across various benchmarks show that GBLM-Pruner surpasses magnitude pruning, Wanda and SparseGPT by significant margins. We further extend our approach on Vision Transformer. Our code and models are available at https://github.com/VILA-Lab/GBLM-Pruner.
Authors: Archiki Prasad, Alexander Koller, Mareike Hartmann, Peter Clark, Ashish Sabharwal, Mohit Bansal, Tushar Khot
Abstract: Large Language Models (LLMs) are increasingly being used for interactive decision-making tasks requiring planning and adapting to the environment. Recent works employ LLMs-as-agents in broadly two ways: iteratively determining the next action (iterative executors) or generating plans and executing sub-tasks using LLMs (plan-and-execute). However, these methods struggle with task complexity, as the inability to execute any sub-task may lead to task failure. To address these shortcomings, we introduce As-Needed Decomposition and Planning for complex Tasks (ADaPT), an approach that explicitly plans and decomposes complex sub-tasks as-needed, i.e., when the LLM is unable to execute them. ADaPT recursively decomposes sub-tasks to adapt to both task complexity and LLM capability. Our results demonstrate that ADaPT substantially outperforms established strong baselines, achieving success rates up to 28.3% higher in ALFWorld, 27% in WebShop, and 33% in TextCraft -- a novel compositional dataset that we introduce. Through extensive analysis, we illustrate the importance of multilevel decomposition and establish that ADaPT dynamically adjusts to the capabilities of the executor LLM as well as to task complexity.
Authors: Nicholas Lourie, Kyunghyun Cho, He He
Abstract: The choice of hyperparameters greatly impacts performance in natural language processing. Often, it is hard to tell if a method is better than another or just better tuned. Tuning curves fix this ambiguity by accounting for tuning effort. Specifically, they plot validation performance as a function of the number of hyperparameter choices tried so far. While several estimators exist for these curves, it is common to use point estimates, which we show fail silently and give contradictory results when given too little data. Beyond point estimates, confidence bands are necessary to rigorously establish the relationship between different approaches. We present the first method to construct valid confidence bands for tuning curves. The bands are exact, simultaneous, and distribution-free, thus they provide a robust basis for comparing methods. Empirical analysis shows that while bootstrap confidence bands, which serve as a baseline, fail to approximate their target confidence, ours achieve it exactly. We validate our design with ablations, analyze the effect of sample size, and provide guidance on comparing models with our method. To promote confident comparisons in future work, we release opda: an easy-to-use library that you can install with pip. https://github.com/nicholaslourie/opda
Authors: Frederikke Isa Marin, Felix Teufel, Marc Horlacher, Dennis Madsen, Dennis Pultz, Ole Winther, Wouter Boomsma
Abstract: The genome sequence contains the blueprint for governing cellular processes. While the availability of genomes has vastly increased over the last decades, experimental annotation of the various functional, non-coding and regulatory elements encoded in the DNA sequence remains both expensive and challenging. This has sparked interest in unsupervised language modeling of genomic DNA, a paradigm that has seen great success for protein sequence data. Although various DNA language models have been proposed, evaluation tasks often differ between individual works, and might not fully recapitulate the fundamental challenges of genome annotation, including the length, scale and sparsity of the data. In this study, we introduce BEND, a Benchmark for DNA language models, featuring a collection of realistic and biologically meaningful downstream tasks defined on the human genome. We find that embeddings from current DNA LMs can approach performance of expert methods on some tasks, but only capture limited information about long-range features. BEND is available at https://github.com/frederikkemarin/BEND.
Authors: Jonas Eschmann, Dario Albani, Giuseppe Loianno
Abstract: Learning-based methods, particularly Reinforcement Learning (RL), hold great promise for streamlining deployment, enhancing performance, and achieving generalization in the control of autonomous multirotor aerial vehicles. Deep RL has been able to control complex systems with impressive fidelity and agility in simulation but the simulation-to-reality transfer often brings a hard-to-bridge reality gap. Moreover, RL is commonly plagued by prohibitively long training times. In this work, we propose a novel asymmetric actor-critic-based architecture coupled with a highly reliable RL-based training paradigm for end-to-end quadrotor control. We show how curriculum learning and a highly optimized simulator enhance sample complexity and lead to fast training times. To precisely discuss the challenges related to low-level/end-to-end multirotor control, we also introduce a taxonomy that classifies the existing levels of control abstractions as well as non-linearities and domain parameters. Our framework enables Simulation-to-Reality (Sim2Real) transfer for direct RPM control after only 18 seconds of training on a consumer-grade laptop as well as its deployment on microcontrollers to control a multirotor under real-time guarantees. Finally, our solution exhibits competitive performance in trajectory tracking, as demonstrated through various experimental comparisons with existing state-of-the-art control solutions using a real Crazyflie nano quadrotor. We open source the code including a very fast multirotor dynamics simulator that can simulate about 5 months of flight per second on a laptop GPU. The fast training times and deployment to a cheap, off-the-shelf quadrotor lower the barriers to entry and help democratize the research and development of these systems.
Authors: Yiwen Lu, Zishuo Li, Yihan Zhou, Na Li, Yilin Mo
Abstract: In this paper, we introduce a new class of parameterized controllers, drawing inspiration from Model Predictive Control (MPC). The controller resembles a Quadratic Programming (QP) solver of a linear MPC problem, with the parameters of the controller being trained via Deep Reinforcement Learning (DRL) rather than derived from system models. This approach addresses the limitations of common controllers with Multi-Layer Perceptron (MLP) or other general neural network architecture used in DRL, in terms of verifiability and performance guarantees, and the learned controllers possess verifiable properties like persistent feasibility and asymptotic stability akin to MPC. On the other hand, numerical examples illustrate that the proposed controller empirically matches MPC and MLP controllers in terms of control performance and has superior robustness against modeling uncertainty and noises. Furthermore, the proposed controller is significantly more computationally efficient compared to MPC and requires fewer parameters to learn than MLP controllers. Real-world experiments on vehicle drift maneuvering task demonstrate the potential of these controllers for robotics and other demanding control tasks.
Authors: Pakkapon Phongthawee, Worameth Chinchuthakun, Nontaphat Sinsunthithet, Amit Raj, Varun Jampani, Pramook Khungurn, Supasorn Suwajanakorn
Abstract: We present a simple yet effective technique to estimate lighting in a single input image. Current techniques rely heavily on HDR panorama datasets to train neural networks to regress an input with limited field-of-view to a full environment map. However, these approaches often struggle with real-world, uncontrolled settings due to the limited diversity and size of their datasets. To address this problem, we leverage diffusion models trained on billions of standard images to render a chrome ball into the input image. Despite its simplicity, this task remains challenging: the diffusion models often insert incorrect or inconsistent objects and cannot readily generate images in HDR format. Our research uncovers a surprising relationship between the appearance of chrome balls and the initial diffusion noise map, which we utilize to consistently generate high-quality chrome balls. We further fine-tune an LDR diffusion model (Stable Diffusion XL) with LoRA, enabling it to perform exposure bracketing for HDR light estimation. Our method produces convincing light estimates across diverse settings and demonstrates superior generalization to in-the-wild scenarios.
Authors: Thomas W. Mitchel, Carlos Esteves, Ameesh Makadia
Abstract: We introduce a framework for intrinsic latent diffusion models operating directly on the surfaces of 3D shapes, with the goal of synthesizing high-quality textures. Our approach is underpinned by two contributions: field latents, a latent representation encoding textures as discrete vector fields on the mesh vertices, and field latent diffusion models, which learn to denoise a diffusion process in the learned latent space on the surface. We consider a single-textured-mesh paradigm, where our models are trained to generate variations of a given texture on a mesh. We show the synthesized textures are of superior fidelity compared those from existing single-textured-mesh generative models. Our models can also be adapted for user-controlled editing tasks such as inpainting and label-guided generation. The efficacy of our approach is due in part to the equivariance of our proposed framework under isometries, allowing our models to seamlessly reproduce details across locally similar regions and opening the door to a notion of generative texture transfer.
Authors: Jaehui Hwang, Junghyuk Lee, Jong-Seok Lee
Abstract: With the advancement of generative models, the assessment of generated images becomes more and more important. Previous methods measure distances between features of reference and generated images from trained vision models. In this paper, we conduct an extensive investigation into the relationship between the representation space and input space around generated images. We first propose two measures related to the presence of unnatural elements within images: complexity, which indicates how non-linear the representation space is, and vulnerability, which is related to how easily the extracted feature changes by adversarial input changes. Based on these, we introduce a new metric to evaluating image-generative models called anomaly score (AS). Moreover, we propose AS-i (anomaly score for individual images) that can effectively evaluate generated images individually. Experimental results demonstrate the validity of the proposed approach.
Authors: Tianyue Chu, Nikolaos Laoutaris
Abstract: Federated Learning (FL) permits different parties to collaboratively train a global model without disclosing their respective local labels. A crucial step of FL, that of aggregating local models to produce the global one, shares many similarities with public decision-making, and elections in particular. In that context, a major weakness of FL, namely its vulnerability to poisoning attacks, can be interpreted as a consequence of the one person one vote (henceforth 1p1v) principle underpinning most contemporary aggregation rules. In this paper, we propose FedQV, a novel aggregation algorithm built upon the quadratic voting scheme, recently proposed as a better alternative to 1p1v-based elections. Our theoretical analysis establishes that FedQV is a truthful mechanism in which bidding according to one's true valuation is a dominant strategy that achieves a convergence rate that matches those of state-of-the-art methods. Furthermore, our empirical analysis using multiple real-world datasets validates the superior performance of FedQV against poisoning attacks. It also shows that combining FedQV with unequal voting ``budgets'' according to a reputation score increases its performance benefits even further. Finally, we show that FedQV can be easily combined with Byzantine-robust privacy-preserving mechanisms to enhance its robustness against both poisoning and privacy attacks.
Authors: Nicholas Kluge Corr\^ea, Sophia Falk, Shiza Fatimah, Aniket Sen, Nythamar de Oliveira
Abstract: Large language models (LLMs) have significantly advanced natural language processing, but their progress has yet to be equal across languages. While most LLMs are trained in high-resource languages like English, multilingual models generally underperform monolingual ones. Additionally, aspects of their multilingual foundation sometimes restrict the byproducts they produce, like computational demands and licensing regimes. In this study, we document the development of open-foundation models tailored for use in low-resource settings, their limitations, and their benefits. This is the TeenyTinyLlama pair: two compact models for Brazilian Portuguese text generation. We release them under the permissive Apache 2.0 license on GitHub and Hugging Face for community use and further development. See https://github.com/Nkluge-correa/TeenyTinyLlama
Authors: Thomas D Swinburne, Danny Perez
Abstract: The expected loss is an upper bound to the model generalization error which admits robust PAC-Bayes bounds for learning. However, loss minimization is known to ignore misspecification, where models cannot exactly reproduce observations. This leads to significant underestimates of parameter uncertainties in the large data, or underparameterized, limit. We analyze the generalization error of near-deterministic, misspecified and underparametrized surrogate models, a regime of broad relevance in science and engineering. We show posterior distributions must cover every training point to avoid a divergent generalization error and derive an ensemble \textit{ansatz} that respects this constraint, which for linear models incurs minimal overhead. The efficient approach is demonstrated on model problems before application to high dimensional datasets in atomistic machine learning. Parameter uncertainties from misspecification survive in the underparametrized limit, giving accurate prediction and bounding of test errors.
Authors: Cristiano Capone, Paolo Muratore
Abstract: Reinforcement learning (RL) faces substantial challenges when applied to real-life problems, primarily stemming from the scarcity of available data due to limited interactions with the environment. This limitation is exacerbated by the fact that RL often demands a considerable volume of data for effective learning. The complexity escalates further when implementing RL in recurrent spiking networks, where inherent noise introduced by spikes adds a layer of difficulty. Life-long learning machines must inherently resolve the plasticity-stability paradox. Striking a balance between acquiring new knowledge and maintaining stability is crucial for artificial agents. To address this challenge, we draw inspiration from machine learning technology and introduce a biologically plausible implementation of proximal policy optimization, referred to as lf-cs (learning fast changing slow). Our approach results in two notable advancements: firstly, the capacity to assimilate new information into a new policy without requiring alterations to the current policy; and secondly, the capability to replay experiences without experiencing policy divergence. Furthermore, when contrasted with other experience replay (ER) techniques, our method demonstrates the added advantage of being computationally efficient in an online setting. We demonstrate that the proposed methodology enhances the efficiency of learning, showcasing its potential impact on neuromorphic and real-world applications.
Authors: Jonathan Richens, Tom Everitt
Abstract: It has long been hypothesised that causal reasoning plays a fundamental role in robust and general intelligence. However, it is not known if agents must learn causal models in order to generalise to new domains, or if other inductive biases are sufficient. We answer this question, showing that any agent capable of satisfying a regret bound under a large set of distributional shifts must have learned an approximate causal model of the data generating process, which converges to the true causal model for optimal agents. We discuss the implications of this result for several research areas including transfer learning and causal inference.
Authors: Andreas Bluhm, Matthias C. Caro, Aadil Oufkir
Abstract: Locality is a fundamental feature of many physical time evolutions. Assumptions on locality and related structural properties also underlie recently proposed procedures for learning an unknown Hamiltonian from access to the induced time evolution. However, no protocols to rigorously test whether an unknown Hamiltonian is local were known. We investigate Hamiltonian locality testing as a property testing problem, where the task is to determine whether an unknown $n$-qubit Hamiltonian $H$ is $k$-local or $\varepsilon$-far from all $k$-local Hamiltonians, given access to the time evolution along $H$. First, we emphasize the importance of the chosen distance measure: With respect to the operator norm, a worst-case distance measure, incoherent quantum locality testers require $\tilde{\Omega}(2^n)$ many time evolution queries and an expected total evolution time of $\tilde{\Omega}(2^n / \varepsilon)$, and even coherent testers need $\Omega(2^{n/2})$ many queries and $\Omega(2^{n/2}/\varepsilon)$ total evolution time. In contrast, when distances are measured according to the normalized Frobenius norm, corresponding to an average-case distance, we give a sample-, time-, and computationally efficient incoherent Hamiltonian locality testing algorithm based on randomized measurements. In fact, our procedure can be used to simultaneously test a wide class of Hamiltonian properties beyond locality. Finally, we prove that learning a general Hamiltonian remains exponentially hard with this average-case distance, thereby establishing an exponential separation between Hamiltonian testing and learning. Our work initiates the study of property testing for quantum Hamiltonians, demonstrating that a broad class of Hamiltonian properties is efficiently testable even with limited quantum capabilities, and positioning Hamiltonian testing as an independent area of research alongside Hamiltonian learning.
Authors: Wenxuan Song, Han Zhao, Pengxiang Ding, Can Cui, Shangke Lyu, Yaning Fan, Donglin Wang
Abstract: Multi-task robot learning holds significant importance in tackling diverse and complex scenarios. However, current approaches are hindered by performance issues and difficulties in collecting training datasets. In this paper, we propose GeRM (Generalist Robotic Model). We utilize offline reinforcement learning to optimize data utilization strategies to learn from both demonstrations and sub-optimal data, thus surpassing the limitations of human demonstrations. Thereafter, we employ a transformer-based VLA network to process multi-modal inputs and output actions. By introducing the Mixture-of-Experts structure, GeRM allows faster inference speed with higher whole model capacity, and thus resolves the issue of limited RL parameters, enhancing model performance in multi-task learning while controlling computational costs. Through a series of experiments, we demonstrate that GeRM outperforms other methods across all tasks, while also validating its efficiency in both training and inference processes. Additionally, we uncover its potential to acquire emergent skills. Additionally, we contribute the QUARD-Auto dataset, collected automatically to support our training approach and foster advancements in multi-task quadruped robot learning. This work presents a new paradigm for reducing the cost of collecting robot data and driving progress in the multi-task learning community. You can reach our project and video through the link: https://songwxuan.github.io/GeRM/ .
Authors: Ang Lv, Kaiyi Zhang, Yuhan Chen, Yulong Wang, Lifeng Liu, Ji-Rong Wen, Jian Xie, Rui Yan
Abstract: In this paper, we deeply explore the mechanisms employed by Transformer-based language models in factual recall tasks. In zero-shot scenarios, given a prompt like "The capital of France is," task-specific attention heads extract the topic entity, such as "France," from the context and pass it to subsequent MLPs to recall the required answer such as "Paris." We introduce a novel analysis method aimed at decomposing the outputs of the MLP into components understandable by humans. Through this method, we quantify the function of the MLP layer following these task-specific heads. In the residual stream, it either erases or amplifies the information originating from individual heads. Moreover, it generates a component that redirects the residual stream towards the direction of its expected answer. These zero-shot mechanisms are also employed in few-shot scenarios. Additionally, we observed a widely existent anti-overconfidence mechanism in the final layer of models, which suppresses correct predictions. We mitigate this suppression by leveraging our interpretation to improve factual recall performance. Our interpretations have been evaluated across various language models, from the GPT-2 families to 1.3B OPT, and across tasks covering different domains of factual knowledge.
Authors: Jiacheng Xie, Hua-Chieh Shao, Yunxiang Li, You Zhang
Abstract: Cone-beam computed tomography (CBCT) is widely used in image-guided radiotherapy. Reconstructing CBCTs from limited-angle acquisitions (LA-CBCT) is highly desired for improved imaging efficiency, dose reduction, and better mechanical clearance. LA-CBCT reconstruction, however, suffers from severe under-sampling artifacts, making it a highly ill-posed inverse problem. Diffusion models can generate data/images by reversing a data-noising process through learned data distributions; and can be incorporated as a denoiser/regularizer in LA-CBCT reconstruction. In this study, we developed a diffusion model-based framework, prior frequency-guided diffusion model (PFGDM), for robust and structure-preserving LA-CBCT reconstruction. PFGDM uses a conditioned diffusion model as a regularizer for LA-CBCT reconstruction, and the condition is based on high-frequency information extracted from patient-specific prior CT scans which provides a strong anatomical prior for LA-CBCT reconstruction. Specifically, we developed two variants of PFGDM (PFGDM-A and PFGDM-B) with different conditioning schemes. PFGDM-A applies the high-frequency CT information condition until a pre-optimized iteration step, and drops it afterwards to enable both similar and differing CT/CBCT anatomies to be reconstructed. PFGDM-B, on the other hand, continuously applies the prior CT information condition in every reconstruction step, while with a decaying mechanism, to gradually phase out the reconstruction guidance from the prior CT scans. The two variants of PFGDM were tested and compared with current available LA-CBCT reconstruction solutions, via metrics including PSNR and SSIM. PFGDM outperformed all traditional and diffusion model-based methods. PFGDM reconstructs high-quality LA-CBCTs under very-limited gantry angles, allowing faster and more flexible CBCT scans with dose reductions.
Authors: Maryam Ahmed, Tooba Bibi, Rizwan Ahmed Khan, Sidra Nasir
Abstract: The study introduces an integrated framework combining Convolutional Neural Networks (CNNs) and Explainable Artificial Intelligence (XAI) for the enhanced diagnosis of breast cancer using the CBIS-DDSM dataset. Utilizing a fine-tuned ResNet50 architecture, our investigation not only provides effective differentiation of mammographic images into benign and malignant categories but also addresses the opaque "black-box" nature of deep learning models by employing XAI methodologies, namely Grad-CAM, LIME, and SHAP, to interpret CNN decision-making processes for healthcare professionals. Our methodology encompasses an elaborate data preprocessing pipeline and advanced data augmentation techniques to counteract dataset limitations, and transfer learning using pre-trained networks, such as VGG-16, DenseNet and ResNet was employed. A focal point of our study is the evaluation of XAI's effectiveness in interpreting model predictions, highlighted by utilising the Hausdorff measure to assess the alignment between AI-generated explanations and expert annotations quantitatively. This approach plays a critical role for XAI in promoting trustworthiness and ethical fairness in AI-assisted diagnostics. The findings from our research illustrate the effective collaboration between CNNs and XAI in advancing diagnostic methods for breast cancer, thereby facilitating a more seamless integration of advanced AI technologies within clinical settings. By enhancing the interpretability of AI-driven decisions, this work lays the groundwork for improved collaboration between AI systems and medical practitioners, ultimately enriching patient care. Furthermore, the implications of our research extend well beyond the current methodologies, advocating for subsequent inquiries into the integration of multimodal data and the refinement of AI explanations to satisfy the needs of clinical practice.
Authors: Yuheng Lai, Leying Guan
Abstract: Equalized odds, as a popular notion of algorithmic fairness, aims to ensure that sensitive variables, such as race and gender, do not unfairly influence the algorithm prediction when conditioning on the true outcome. Despite rapid advancements, most of the current research focuses on the violation of equalized odds caused by one sensitive attribute, leaving the challenge of simultaneously accounting for multiple attributes under-addressed. We address this gap by introducing a fairness learning approach that integrates adversarial learning with a novel inverse conditional permutation. This approach effectively and flexibly handles multiple sensitive attributes, potentially of mixed data types. The efficacy and flexibility of our method are demonstrated through both simulation studies and empirical analysis of real-world datasets.