Authors: Rylan Schaeffer, Hailey Schoelkopf, Brando Miranda, Gabriel Mukobi, Varun Madan, Adam Ibrahim, Herbie Bradley, Stella Biderman, Sanmi Koyejo
Abstract: Predictable behavior from scaling advanced AI systems is an extremely desirable property. Although a well-established literature exists on how pretraining performance scales, the literature on how particular downstream capabilities scale is significantly muddier. In this work, we take a step back and ask: why has predicting specific downstream capabilities with scale remained elusive? While many factors are certainly responsible, we identify a new factor that makes modeling scaling behavior on widely used multiple-choice question-answering benchmarks challenging. Using five model families and twelve well-established multiple-choice benchmarks, we show that downstream performance is computed from negative log likelihoods via a sequence of transformations that progressively degrade the statistical relationship between performance and scale. We then reveal the mechanism causing this degradation: downstream metrics require comparing the correct choice against a small number of specific incorrect choices, meaning accurately predicting downstream capabilities requires predicting not just how probability mass concentrates on the correct choice with scale, but also how probability mass fluctuates on specific incorrect choices with scale. We empirically study how probability mass on the correct choice co-varies with probability mass on incorrect choices with increasing compute, suggesting that scaling laws for incorrect choices might be achievable. Our work also explains why pretraining scaling laws are commonly regarded as more predictable than downstream capabilities and contributes towards establishing scaling-predictable evaluations of frontier AI models.
Authors: Dongyoung Kim, Kimin Lee, Jinwoo Shin, Jaehyung Kim
Abstract: Aligning large language models (LLMs) with human preferences becomes a key component to obtaining state-of-the-art performance, but it yields a huge cost to construct a large human-annotated preference dataset. To tackle this problem, we propose a new framework that boosts the alignment of LLMs through Self-generated Preference data (Selfie) using only a very small amount of human-annotated preference data. Our key idea is leveraging the human prior knowledge within the small (seed) data and progressively improving the alignment of LLM, by iteratively generating the responses and learning from them with the self-annotated preference data. To be specific, we propose to derive the preference label from the logits of LLM to explicitly extract the model's inherent preference. Compared to the previous approaches using external reward models or implicit in-context learning, we observe that the proposed approach is significantly more effective. In addition, we introduce a noise-aware preference learning algorithm to mitigate the risk of low quality within generated preference data. Our experimental results demonstrate that the proposed framework significantly boosts the alignment of LLMs. For example, we achieve superior alignment performance on AlpacaEval 2.0 with only 3.3\% of the ground-truth preference labels in the Ultrafeedback data compared to the cases using the entire data or state-of-the-art baselines.
Authors: Md Atik Ahamed, Qiang Cheng
Abstract: Time series classification (TSC) on multivariate time series is a critical problem. We propose a novel multi-view approach integrating frequency-domain and time-domain features to provide complementary contexts for TSC. Our method fuses continuous wavelet transform spectral features with temporal convolutional or multilayer perceptron features. We leverage the Mamba state space model for efficient and scalable sequence modeling. We also introduce a novel tango scanning scheme to better model sequence relationships. Experiments on 10 standard benchmark datasets demonstrate our approach achieves an average 6.45% accuracy improvement over state-of-the-art TSC models.
Authors: Shuang Ni, Adrien Aumon, Guy Wolf, Kevin R. Moon, Jake S. Rhodes
Abstract: The value of supervised dimensionality reduction lies in its ability to uncover meaningful connections between data features and labels. Common dimensionality reduction methods embed a set of fixed, latent points, but are not capable of generalizing to an unseen test set. In this paper, we provide an out-of-sample extension method for the random forest-based supervised dimensionality reduction method, RF-PHATE, combining information learned from the random forest model with the function-learning capabilities of autoencoders. Through quantitative assessment of various autoencoder architectures, we identify that networks that reconstruct random forest proximities are more robust for the embedding extension problem. Furthermore, by leveraging proximity-based prototypes, we achieve a 40% reduction in training time without compromising extension quality. Our method does not require label information for out-of-sample points, thus serving as a semi-supervised method, and can achieve consistent quality using only 10% of the training data.
Authors: Rishi Sonthalia, Jackie Lok, Elizaveta Rebrova
Abstract: A fundamental problem in machine learning is understanding the effect of early stopping on the parameters obtained and the generalization capabilities of the model. Even for linear models, the effect is not fully understood for arbitrary learning rates and data. In this paper, we analyze the dynamics of discrete full batch gradient descent for linear regression. With minimal assumptions, we characterize the trajectory of the parameters and the expected excess risk. Using this characterization, we show that when training with a learning rate schedule $\eta_k$, and a finite time horizon $T$, the early stopped solution $\beta_T$ is equivalent to the minimum norm solution for a generalized ridge regularized problem. We also prove that early stopping is beneficial for generic data with arbitrary spectrum and for a wide variety of learning rate schedules. We provide an estimate for the optimal stopping time and empirically demonstrate the accuracy of our estimate.
Authors: Savelii Chezhegov, Yaroslav Klyukin, Andrei Semenov, Aleksandr Beznosikov, Alexander Gasnikov, Samuel Horv\'ath, Martin Tak\'a\v{c}, Eduard Gorbunov
Abstract: Methods with adaptive stepsizes, such as AdaGrad and Adam, are essential for training modern Deep Learning models, especially Large Language Models. Typically, the noise in the stochastic gradients is heavy-tailed for the later ones. Gradient clipping provably helps to achieve good high-probability convergence for such noises. However, despite the similarity between AdaGrad/Adam and Clip-SGD, the high-probability convergence of AdaGrad/Adam has not been studied in this case. In this work, we prove that AdaGrad (and its delayed version) can have provably bad high-probability convergence if the noise is heavy-tailed. To fix this issue, we propose a new version of AdaGrad called Clip-RAdaGradD (Clipped Reweighted AdaGrad with Delay) and prove its high-probability convergence bounds with polylogarithmic dependence on the confidence level for smooth convex/non-convex stochastic optimization with heavy-tailed noise. Our empirical evaluations, including NLP model fine-tuning, highlight the superiority of clipped versions of AdaGrad/Adam in handling the heavy-tailed noise.
Authors: Sarah Pratt, Seth Blumberg, Pietro Kreitlon Carolino, Meredith Ringel Morris
Abstract: Advances in deep learning systems have allowed large models to match or surpass human accuracy on a number of skills such as image classification, basic programming, and standardized test taking. As the performance of the most capable models begin to saturate on tasks where humans already achieve high accuracy, it becomes necessary to benchmark models on increasingly complex abilities. One such task is forecasting the future outcome of events. In this work we describe experiments using a novel dataset of real world events and associated human predictions, an evaluation metric to measure forecasting ability, and the accuracy of a number of different LLM based forecasting designs on the provided dataset. Additionally, we analyze the performance of the LLM forecasters against human predictions and find that models still struggle to make accurate predictions about the future. Our follow-up experiments indicate this is likely due to models' tendency to guess that most events are unlikely to occur (which tends to be true for many prediction datasets, but does not reflect actual forecasting abilities). We reflect on next steps for developing a systematic and reliable approach to studying LLM forecasting.
Authors: Jaron Maene, Vincent Derkinderen, Luc De Raedt
Abstract: The limitations of purely neural learning have sparked an interest in probabilistic neurosymbolic models, which combine neural networks with probabilistic logical reasoning. As these neurosymbolic models are trained with gradient descent, we study the complexity of differentiating probabilistic reasoning. We prove that although approximating these gradients is intractable in general, it becomes tractable during training. Furthermore, we introduce WeightME, an unbiased gradient estimator based on model sampling. Under mild assumptions, WeightME approximates the gradient with probabilistic guarantees using a logarithmic number of calls to a SAT solver. Lastly, we evaluate the necessity of these guarantees on the gradient. Our experiments indicate that the existing biased approximations indeed struggle to optimize even when exact solving is still feasible.
Authors: Sina Sharifi, Mahyar Fazlyab
Abstract: We propose a novel reachability analysis method tailored for neural networks with differentiable activations. Our idea hinges on a sound abstraction of the neural network map based on first-order Taylor expansion and bounding the remainder. To this end, we propose a method to compute analytical bounds on the network's first derivative (gradient) and second derivative (Hessian). A key aspect of our method is loop transformation on the activation functions to exploit their monotonicity effectively. The resulting end-to-end abstraction locally preserves the derivative information, yielding accurate bounds on small input sets. Finally, we employ a branch and bound framework for larger input sets to refine the abstraction recursively. We evaluate our method numerically via different examples and compare the results with relevant state-of-the-art methods.
Authors: Chandra Sekhar Mukherjee, Jiapeng Zhang
Abstract: Community and core-periphery are two widely studied graph structures, with their coexistence observed in real-world graphs (Rombach, Porter, Fowler \& Mucha [SIAM J. App. Math. 2014, SIAM Review 2017]). However, the nature of this coexistence is not well understood and has been pointed out as an open problem (Yanchenko \& Sengupta [Statistics Surveys, 2023]). Especially, the impact of inferring the core-periphery structure of a graph on understanding its community structure is not well utilized. In this direction, we introduce a novel quantification for graphs with ground truth communities, where each community has a densely connected part (the core), and the rest is more sparse (the periphery), with inter-community edges more frequent between the peripheries. Built on this structure, we propose a new algorithmic concept that we call relative centrality to detect the cores. We observe that core-detection algorithms based on popular centrality measures such as PageRank and degree centrality can show some bias in their outcome by selecting very few vertices from some cores. We show that relative centrality solves this bias issue and provide theoretical and simulation support, as well as experiments on real-world graphs. Core detection is known to have important applications with respect to core-periphery structures. In our model, we show a new application: relative-centrality-based algorithms can select a subset of the vertices such that it contains sufficient vertices from all communities, and points in this subset are better separable into their respective communities. We apply the methods to 11 biological datasets, with our methods resulting in a more balanced selection of vertices from all communities such that clustering algorithms have better performance on this set.
Authors: M. Jeffrey Mei, Oliver Bembom, Andreas F. Ehmann
Abstract: Next-item recommender systems are often trained using only positive feedback with randomly-sampled negative feedback. We show the benefits of using real negative feedback both as inputs into the user sequence and also as negative targets for training a next-song recommender system for internet radio. In particular, using explicit negative samples during training helps reduce training time by ~60% while also improving test accuracy by ~6%; adding user skips as additional inputs also can considerably increase user coverage alongside slightly improving accuracy. We test the impact of using a large number of random negative samples to capture a 'harder' one and find that the test accuracy increases with more randomly-sampled negatives, but only to a point. Too many random negatives leads to false negatives that limits the lift, which is still lower than if using true negative feedback. We also find that the test accuracy is fairly robust with respect to the proportion of different feedback types, and compare the learned embeddings for different feedback types.
Authors: Sakshi Mahendru
Abstract: Query Processing (QP) is optimized by a Cloud-based cache by storing the frequently accessed data closer to users. Nevertheless, the lack of focus on user intention type in queries affected the efficiency of QP in prevailing works. Thus, by using a Contextual Fuzzy Linguistic Inference System (CFLIS), this work analyzed the informational, navigational, and transactional-based intents in queries for enhanced QP. Primarily, the user query is parsed using tokenization, normalization, stop word removal, stemming, and POS tagging and then expanded using the WordNet technique. After expanding the queries, to enhance query understanding and to facilitate more accurate analysis and retrieval in query processing, the named entity is recognized using Bidirectional Encoder UnispecNorm Representations from Transformers (BEUNRT). Next, for efficient QP and retrieval of query information from the semantic cache database, the data is structured using Epanechnikov Kernel-Ordering Points To Identify the Clustering Structure (EK-OPTICS). The features are extracted from the structured data. Now, sentence type is identified and intent keywords are extracted from the parsed query. Next, the extracted features, detected intents and structured data are inputted to the Multi-head Gated Recurrent Learnable Attention Unit (MGR-LAU), which processes the query based on a semantic cache database (stores previously interpreted queries to expedite effective future searches). Moreover, the query is processed with a minimum latency of 12856ms. Lastly, the Semantic Similarity (SS) is analyzed between the retrieved query and the inputted user query, which continues until the similarity reaches 0.9 and above. Thus, the proposed work surpassed the previous methodologies.
Authors: Max Zhu, Adri\'an Bazaga, Pietro Li\`o
Abstract: Learning computational fluid dynamics (CFD) traditionally relies on computationally intensive simulations of the Navier-Stokes equations. Recently, large language models (LLMs) have shown remarkable pattern recognition and reasoning abilities in natural language processing (NLP) and computer vision (CV). However, these models struggle with the complex geometries inherent in fluid dynamics. We introduce FLUID-LLM, a novel framework combining pre-trained LLMs with spatiotemporal-aware encoding to predict unsteady fluid dynamics. Our approach leverages the temporal autoregressive abilities of LLMs alongside spatial-aware layers, bridging the gap between previous CFD prediction methods. Evaluations on standard benchmarks reveal significant performance improvements across various fluid datasets. Our results demonstrate that FLUID-LLM effectively integrates spatiotemporal information into pre-trained LLMs, enhancing CFD task performance.
Authors: Paul Mineiro
Abstract: A Flow is a collection of component models (``Agents'') which constructs the solution to a complex problem via iterative communication. Flows have emerged as state of the art architectures for code generation, and are the raison d'etre for frameworks like Autogen. However, flows are currently constructed via a combination of manual prompt engineering and stagewise supervised learning techniques; the latter is limited to acyclic flows with granular node supervision. In this writeup I describe a procedure for online joint fine-tuning of an entire flow inspired by the Learning to Search framework. The approach leverages simulator access to reduce preferences over entire episodes to preferences over individual node outputs; when the components are language models the latter is a well-studied problem. The approach is applicable to reward-free settings (e.g., text feedback) if an episode evaluator model is available. I apply to the multi-hop QA dataset Musique achieving a state-of-the-art result.
Authors: Eirini Katsidoniotaki, Biao Su, Eleni Kelasidi, Themistoklis P. Sapsis
Abstract: As the global population grows and climate change intensifies, sustainable food production is critical. Marine aquaculture offers a viable solution, providing a sustainable protein source. However, the industry's expansion requires novel technologies for remote management and autonomous operations. Digital twin technology can advance the aquaculture industry, but its adoption has been limited. Fish net cages, which are flexible floating structures, are critical yet vulnerable components of aquaculture farms. Exposed to harsh and dynamic marine environments, the cages experience significant loads and risk damage, leading to fish escapes, environmental impacts, and financial losses. We propose a multifidelity surrogate modeling framework for integration into a digital twin for real-time monitoring of aquaculture net cage structural dynamics under stochastic marine conditions. Central to this framework is the nonlinear autoregressive Gaussian process method, which learns complex, nonlinear cross-correlations between models of varying fidelity. It combines low-fidelity simulation data with a small set of high-fidelity field sensor measurements, which offer the real dynamics but are costly and spatially sparse. Validated at the SINTEF ACE fish farm in Norway, our digital twin receives online metocean data and accurately predicts net cage displacements and mooring line loads, aligning closely with field measurements. The proposed framework is beneficial where application-specific data are scarce, offering rapid predictions and real-time system representation. The developed digital twin prevents potential damages by assessing structural integrity and facilitates remote operations with unmanned underwater vehicles. Our work also compares GP and GCNs for predicting net cage deformation, highlighting the latter's effectiveness in complex structural applications.
Authors: Yutaka Shimizu, Joey Hong, Sergey Levine, Masayoshi Tomizuka
Abstract: Offline reinforcement learning (RL) is a compelling paradigm to extend RL's practical utility by leveraging pre-collected, static datasets, thereby avoiding the limitations associated with collecting online interactions. The major difficulty in offline RL is mitigating the impact of approximation errors when encountering out-of-distribution (OOD) actions; doing so ineffectively will lead to policies that prefer OOD actions, which can lead to unexpected and potentially catastrophic results. Despite the variety of works proposed to address this issue, they tend to excessively suppress the value function in and around OOD regions, resulting in overly pessimistic value estimates. In this paper, we propose a novel framework called Strategically Conservative Q-Learning (SCQ) that distinguishes between OOD data that is easy and hard to estimate, ultimately resulting in less conservative value estimates. Our approach exploits the inherent strengths of neural networks to interpolate, while carefully navigating their limitations in extrapolation, to obtain pessimistic yet still property calibrated value estimates. Theoretical analysis also shows that the value function learned by SCQ is still conservative, but potentially much less so than that of Conservative Q-learning (CQL). Finally, extensive evaluation on the D4RL benchmark tasks shows our proposed method outperforms state-of-the-art methods. Our code is available through \url{https://github.com/purewater0901/SCQ}.
Authors: Lexing Ying
Abstract: Differential privacy is a framework for protecting the identity of individual data points in the decision-making process. In this note, we propose a new form of differential privacy called tangent differential privacy. Compared with the usual differential privacy that is defined uniformly across data distributions, tangent differential privacy is tailored towards a specific data distribution of interest. It also allows for general distribution distances such as total variation distance and Wasserstein distance. In the case of risk minimization, we show that entropic regularization guarantees tangent differential privacy under rather general conditions on the risk function.
Authors: Hsiao-Ying Lu, Yiran Li, Ujwal Pratap Krishna Kaluvakolanu Thyagarajan, Kwan-Liu Ma
Abstract: Graph Neural Networks (GNNs) have proven highly effective in various machine learning (ML) tasks involving graphs, such as node/graph classification and link prediction. However, explaining the decisions made by GNNs poses challenges because of the aggregated relational information based on graph structure, leading to complex data transformations. Existing methods for explaining GNNs often face limitations in systematically exploring diverse substructures and evaluating results in the absence of ground truths. To address this gap, we introduce GNNAnatomy, a model- and dataset-agnostic visual analytics system designed to facilitate the generation and evaluation of multi-level explanations for GNNs. In GNNAnatomy, we employ graphlets to elucidate GNN behavior in graph-level classification tasks. By analyzing the associations between GNN classifications and graphlet frequencies, we formulate hypothesized factual and counterfactual explanations. To validate a hypothesized graphlet explanation, we introduce two metrics: (1) the correlation between its frequency and the classification confidence, and (2) the change in classification confidence after removing this substructure from the original graph. To demonstrate the effectiveness of GNNAnatomy, we conduct case studies on both real-world and synthetic graph datasets from various domains. Additionally, we qualitatively compare GNNAnatomy with a state-of-the-art GNN explainer, demonstrating the utility and versatility of our design.
Authors: Valentin Frank Ingmar Guenter, Athanasios Sideris
Abstract: We propose an algorithm capable of identifying and eliminating irrelevant layers of a neural network during the early stages of training. In contrast to weight or filter-level pruning, layer pruning reduces the harder to parallelize sequential computation of a neural network. We employ a structure using residual connections around nonlinear network sections that allow the flow of information through the network once a nonlinear section is pruned. Our approach is based on variational inference principles using Gaussian scale mixture priors on the neural network weights and allows for substantial cost savings during both training and inference. More specifically, the variational posterior distribution of scalar Bernoulli random variables multiplying a layer weight matrix of its nonlinear sections is learned, similarly to adaptive layer-wise dropout. To overcome challenges of concurrent learning and pruning such as premature pruning and lack of robustness with respect to weight initialization or the size of the starting network, we adopt the "flattening" hyper-prior on the prior parameters. We prove that, as a result of its usage, the solutions of the resulting optimization problem describe deterministic networks with parameters of the posterior distribution at either 0 or 1. We formulate a projected SGD algorithm and prove its convergence to such a solution using stochastic approximation results. In particular, we prove conditions that lead to a layer's weights converging to zero and derive practical pruning conditions from the theoretical results. The proposed algorithm is evaluated on the MNIST, CIFAR-10 and ImageNet datasets and common LeNet, VGG16 and ResNet architectures. The simulations demonstrate that our method achieves state-of the-art performance for layer pruning at reduced computational cost in distinction to competing methods due to the concurrent training and pruning.
Authors: Motahareh Sohrabi, Juan Ramirez, Tianyue H. Zhang, Simon Lacoste-Julien, Jose Gallego-Posada
Abstract: Constrained optimization offers a powerful framework to prescribe desired behaviors in neural network models. Typically, constrained problems are solved via their min-max Lagrangian formulations, which exhibit unstable oscillatory dynamics when optimized using gradient descent-ascent. The adoption of constrained optimization techniques in the machine learning community is currently limited by the lack of reliable, general-purpose update schemes for the Lagrange multipliers. This paper proposes the $\nu$PI algorithm and contributes an optimization perspective on Lagrange multiplier updates based on PI controllers, extending the work of Stooke, Achiam and Abbeel (2020). We provide theoretical and empirical insights explaining the inability of momentum methods to address the shortcomings of gradient descent-ascent, and contrast this with the empirical success of our proposed $\nu$PI controller. Moreover, we prove that $\nu$PI generalizes popular momentum methods for single-objective minimization. Our experiments demonstrate that $\nu$PI reliably stabilizes the multiplier dynamics and its hyperparameters enjoy robust and predictable behavior.
Authors: Binchuan Qi, Wei Gong, Li Li
Abstract: There remains a list of unanswered research questions on deep learning (DL), including the remarkable generalization power of overparametrized neural networks, the efficient optimization performance despite the non-convexity, and the mechanisms behind flat minima in generalization. In this paper, we adopt an information-theoretic perspective to explore the theoretical foundations of supervised classification using deep neural networks (DNNs). Our analysis introduces the concepts of fitting error and model risk, which, together with generalization error, constitute an upper bound on the expected risk. We demonstrate that the generalization errors are bounded by the complexity, influenced by both the smoothness of distribution and the sample size. Consequently, task complexity serves as a reliable indicator of the dataset's quality, guiding the setting of regularization hyperparameters. Furthermore, the derived upper bound fitting error links the back-propagated gradient, Neural Tangent Kernel (NTK), and the model's parameter count with the fitting error. Utilizing the triangle inequality, we establish an upper bound on the expected risk. This bound offers valuable insights into the effects of overparameterization, non-convex optimization, and the flat minima in DNNs.Finally, empirical verification confirms a significant positive correlation between the derived theoretical bounds and the practical expected risk, confirming the practical relevance of the theoretical findings.
Authors: Zhongzheng Wang, Yuntian Chen, Guodong Chen, Dongxiao Zhang
Abstract: Maximizing storage performance in geological carbon storage (GCS) is crucial for commercial deployment, but traditional optimization demands resource-intensive simulations, posing computational challenges. This study introduces the multimodal latent dynamic (MLD) model, a deep learning framework for fast flow prediction and well control optimization in GCS. The MLD model includes a representation module for compressed latent representations, a transition module for system state evolution, and a prediction module for flow responses. A novel training strategy combining regression loss and joint-embedding consistency loss enhances temporal consistency and multi-step prediction accuracy. Unlike existing models, the MLD supports diverse input modalities, allowing comprehensive data interactions. The MLD model, resembling a Markov decision process (MDP), can train deep reinforcement learning agents, specifically using the soft actor-critic (SAC) algorithm, to maximize net present value (NPV) through continuous interactions. The approach outperforms traditional methods, achieving the highest NPV while reducing computational resources by over 60%. It also demonstrates strong generalization performance, providing improved decisions for new scenarios based on knowledge from previous ones.
Authors: Haotian Zhang, Junting Zhou, Haowei Lin, Hang Ye, Jianhua Zhu, Zihao Wang, Liangcai Gao, Yizhou Wang, Yitao Liang
Abstract: Continual Learning (CL) poses a significant challenge in Artificial Intelligence, aiming to mirror the human ability to incrementally acquire knowledge and skills. While extensive research has focused on CL within the context of classification tasks, the advent of increasingly powerful generative models necessitates the exploration of Continual Learning of Generative models (CLoG). This paper advocates for shifting the research focus from classification-based CL to CLoG. We systematically identify the unique challenges presented by CLoG compared to traditional classification-based CL. We adapt three types of existing CL methodologies, replay-based, regularization-based, and parameter-isolation-based methods to generative tasks and introduce comprehensive benchmarks for CLoG that feature great diversity and broad task coverage. Our benchmarks and results yield intriguing insights that can be valuable for developing future CLoG methods. Additionally, we will release a codebase designed to facilitate easy benchmarking and experimentation in CLoG publicly at https://github.com/linhaowei1/CLoG. We believe that shifting the research focus to CLoG will benefit the continual learning community and illuminate the path for next-generation AI-generated content (AIGC) in a lifelong learning paradigm.
Authors: Renpu Liu, Cong Shen, Jing Yang
Abstract: Federated representation learning (FRL) is a popular personalized federated learning (FL) framework where clients work together to train a common representation while retaining their personalized heads. Existing studies, however, largely focus on the over-parameterized regime. In this paper, we make the initial efforts to investigate FRL in the under-parameterized regime, where the FL model is insufficient to express the variations in all ground-truth models. We propose a novel FRL algorithm FLUTE, and theoretically characterize its sample complexity and convergence rate for linear models in the under-parameterized regime. To the best of our knowledge, this is the first FRL algorithm with provable performance guarantees in this regime. FLUTE features a data-independent random initialization and a carefully designed objective function that aids the distillation of subspace spanned by the global optimal representation from the misaligned local representations. On the technical side, we bridge low-rank matrix approximation techniques with the FL analysis, which may be of broad interest. We also extend FLUTE beyond linear representations. Experimental results demonstrate that FLUTE outperforms state-of-the-art FRL solutions in both synthetic and real-world tasks.
Authors: Zheng Huang, Qihui Yang, Dawei Zhou, Yujun Yan
Abstract: Although most graph neural networks (GNNs) can operate on graphs of any size, their classification performance often declines on graphs larger than those encountered during training. Existing methods insufficiently address the removal of size information from graph representations, resulting in sub-optimal performance and reliance on backbone models. In response, we propose DISGEN, a novel and model-agnostic framework designed to disentangle size factors from graph representations. DISGEN employs size- and task-invariant augmentations and introduces a decoupling loss that minimizes shared information in hidden representations, with theoretical guarantees for its effectiveness. Our empirical results show that DISGEN outperforms the state-of-the-art models by up to 6% on real-world datasets, underscoring its effectiveness in enhancing the size generalizability of GNNs. Our codes are available at: https://github.com/GraphmindDartmouth/DISGEN.
Authors: Jingtan Wang, Xiaoqiang Lin, Rui Qiao, Chuan-Sheng Foo, Bryan Kian Hsiang Low
Abstract: The increasing complexity of foundational models underscores the necessity for explainability, particularly for fine-tuning, the most widely used training method for adapting models to downstream tasks. Instance attribution, one type of explanation, attributes the model prediction to each training example by an instance score. However, the robustness of instance scores, specifically towards dataset resampling, has been overlooked. To bridge this gap, we propose a notion of robustness on the sign of the instance score. We theoretically and empirically demonstrate that the popular leave-one-out-based methods lack robustness, while the Shapley value behaves significantly better, but at a higher computational cost. Accordingly, we introduce an efficient fine-tuning-free approximation of the Shapley value (FreeShap) for instance attribution based on the neural tangent kernel. We empirically demonstrate that FreeShap outperforms other methods for instance attribution and other data-centric applications such as data removal, data selection, and wrong label detection, and further generalize our scale to large language models (LLMs). Our code is available at https://github.com/JTWang2000/FreeShap.
Authors: Junru Zhang, Lang Feng, Zhidan Liu, Yuhan Wu, Yang He, Yabo Dong, Duanqing Xu
Abstract: Existing domain generalization (DG) methods for cross-person generalization tasks often face challenges in capturing intra- and inter-domain style diversity, resulting in domain gaps with the target domain. In this study, we explore a novel perspective to tackle this problem, a process conceptualized as domain padding. This proposal aims to enrich the domain diversity by synthesizing intra- and inter-domain style data while maintaining robustness to class labels. We instantiate this concept using a conditional diffusion model and introduce a style-fused sampling strategy to enhance data generation diversity. In contrast to traditional condition-guided sampling, our style-fused sampling strategy allows for the flexible use of one or more random styles to guide data synthesis. This feature presents a notable advancement: it allows for the maximum utilization of possible permutations and combinations among existing styles to generate a broad spectrum of new style instances. Empirical evaluations on a board of datasets demonstrate that our generated data achieves remarkable diversity within the domain space. Both intra- and inter-domain generated data have proven to be significant and valuable, contributing to varying degrees of performance enhancements. Notably, our approach outperforms state-of-the-art DG methods in all human activity recognition tasks.
Authors: Dung Nguyen, Ariel Vetzler, Sarit Kraus, Anil Vullikanti
Abstract: This paper presents a novel approach in Explainable AI (XAI), integrating contrastive explanations with differential privacy in clustering methods. For several basic clustering problems, including $k$-median and $k$-means, we give efficient differential private contrastive explanations that achieve essentially the same explanations as those that non-private clustering explanations can obtain. We define contrastive explanations as the utility difference between the original clustering utility and utility from clustering with a specifically fixed centroid. In each contrastive scenario, we designate a specific data point as the fixed centroid position, enabling us to measure the impact of this constraint on clustering utility under differential privacy. Extensive experiments across various datasets show our method's effectiveness in providing meaningful explanations without significantly compromising data privacy or clustering utility. This underscores our contribution to privacy-aware machine learning, demonstrating the feasibility of achieving a balance between privacy and utility in the explanation of clustering tasks.
Authors: Yong-Min Shin, Siqing Li, Xin Cao, Won-Yong Shin
Abstract: The self-attention mechanism has been adopted in several widely-used message-passing neural networks (MPNNs) (e.g., GATs), which adaptively controls the amount of information that flows along the edges of the underlying graph. This usage of attention has made such models a baseline for studies on explainable AI (XAI) since interpretations via attention have been popularized in various domains (e.g., natural language processing and computer vision). However, existing studies often use naive calculations to derive attribution scores from attention, and do not take the precise and careful calculation of edge attribution into consideration. In our study, we aim to fill the gap between the widespread usage of attention-enabled MPNNs and their potential in largely under-explored explainability, a topic that has been actively investigated in other areas. To this end, as the first attempt, we formalize the problem of edge attribution from attention weights in GNNs. Then, we propose GATT, an edge attribution calculation method built upon the computation tree. Through comprehensive experiments, we demonstrate the effectiveness of our proposed method when evaluating attributions from GATs. Conversely, we empirically validate that simply averaging attention weights over graph attention layers is insufficient to interpret the GAT model's behavior. Code is publicly available at https://github.com/jordan7186/GAtt/tree/main.
Authors: Xiaofeng Lin, Chenheng Xu, Matthew Yang, Guang Cheng
Abstract: Generative Foundation Models (GFMs) have produced synthetic data with remarkable quality in modalities such as images and text. However, applying GFMs to tabular data poses significant challenges due to the inherent heterogeneity of table features. Existing cross-table learning frameworks are hindered by the absence of both a generative model backbone and a decoding mechanism for heterogeneous feature values. To overcome these limitations, we introduce the Cross-Table Synthesizer (CTSyn), a diffusion-based foundational model tailored for tabular data generation. CTSyn introduces three major components: an aggregator that consolidates heterogeneous tables into a unified latent space; a conditional latent diffusion model for sampling from this space; and type-specific decoders that reconstruct values of varied data types from sampled latent vectors. Extensive testing on real-world datasets reveals that CTSyn not only significantly outperforms existing table synthesizers in utility and diversity, but also uniquely enhances performances of downstream machine learning beyond what is achievable with real data, thus establishing a new paradigm for synthetic data generation.
Authors: Sumanta Roy, Chandrasekhar Annavarapu, Pratanu Roy, Antareep Kumar Sarma
Abstract: We present an efficient physics-informed neural networks (PINNs) framework, termed Adaptive Interface-PINNs (AdaI-PINNs), to improve the modeling of interface problems with discontinuous coefficients and/or interfacial jumps. This framework is an enhanced version of its predecessor, Interface PINNs or I-PINNs (Sarma et al.; https://dx.doi.org/10.2139/ssrn.4766623), which involves domain decomposition and assignment of different predefined activation functions to the neural networks in each subdomain across a sharp interface, while keeping all other parameters of the neural networks identical. In AdaI-PINNs, the activation functions vary solely in their slopes, which are trained along with the other parameters of the neural networks. This makes the AdaI-PINNs framework fully automated without requiring preset activation functions. Comparative studies on one-dimensional, two-dimensional, and three-dimensional benchmark elliptic interface problems reveal that AdaI-PINNs outperform I-PINNs, reducing computational costs by 2-6 times while producing similar or better accuracy.
Authors: Shuang Zhou, Daochen Zha, Xiao Shen, Xiao Huang, Rui Zhang, Fu-Lai Chung
Abstract: Time series self-supervised learning (SSL) aims to exploit unlabeled data for pre-training to mitigate the reliance on labels. Despite the great success in recent years, there is limited discussion on the potential noise in the time series, which can severely impair the performance of existing SSL methods. To mitigate the noise, the de facto strategy is to apply conventional denoising methods before model training. However, this pre-processing approach may not fully eliminate the effect of noise in SSL for two reasons: (i) the diverse types of noise in time series make it difficult to automatically determine suitable denoising methods; (ii) noise can be amplified after mapping raw data into latent space. In this paper, we propose denoising-aware contrastive learning (DECL), which uses contrastive learning objectives to mitigate the noise in the representation and automatically selects suitable denoising methods for every sample. Extensive experiments on various datasets verify the effectiveness of our method. The code is open-sourced.
Authors: Jongyun Shin, Seunjin Han, Jangho Kim
Abstract: Model agnostic meta-learning (MAML) is one of the most widely used gradient-based meta-learning, consisting of two optimization loops: an inner loop and outer loop. MAML learns the new task from meta-initialization parameters with an inner update and finds the meta-initialization parameters in the outer loop. In general, the injection of noise into the gradient of the model for augmenting the gradient is one of the widely used regularization methods. In this work, we propose a novel cooperative meta-learning framework dubbed CML which leverages gradient-level regularization with gradient augmentation. We inject learnable noise into the gradient of the model for the model generalization. The key idea of CML is introducing the co-learner which has no inner update but the outer loop update to augment gradients for finding better meta-initialization parameters. Since the co-learner does not update in the inner loop, it can be easily deleted after meta-training. Therefore, CML infers with only meta-learner without additional cost and performance degradation. We demonstrate that CML is easily applicable to gradient-based meta-learning methods and CML leads to increased performance in few-shot regression, few-shot image classification and few-shot node classification tasks. Our codes are at https://github.com/JJongyn/CML.
Authors: Zhongmou He, Jing Zhu, Shengyi Qian, Joyce Chai, Danai Koutra
Abstract: Large Language Models (LLMs) have shown promising results on various language and vision tasks. Recently, there has been growing interest in applying LLMs to graph-based tasks, particularly on Text-Attributed Graphs (TAGs). However, most studies have focused on node classification, while the use of LLMs for link prediction (LP) remains understudied. In this work, we propose a new task on LLMs, where the objective is to leverage LLMs to predict missing links between nodes in a graph. This task evaluates an LLM's ability to reason over structured data and infer new facts based on learned patterns. This new task poses two key challenges: (1) How to effectively integrate pairwise structural information into the LLMs, which is known to be crucial for LP performance, and (2) how to solve the computational bottleneck when teaching LLMs to perform LP. To address these challenges, we propose LinkGPT, the first end-to-end trained LLM for LP tasks. To effectively enhance the LLM's ability to understand the underlying structure, we design a two-stage instruction tuning approach where the first stage fine-tunes the pairwise encoder, projector, and node projector, and the second stage further fine-tunes the LLMs to predict links. To address the efficiency challenges at inference time, we introduce a retrieval-reranking scheme. Experiments show that LinkGPT can achieve state-of-the-art performance on real-world graphs as well as superior generalization in zero-shot and few-shot learning, surpassing existing benchmarks. At inference time, it can achieve $10\times$ speedup while maintaining high LP accuracy.
Authors: Vignesh Kothapalli, Tianyu Pang, Shenyang Deng, Zongmin Liu, Yaoqing Yang
Abstract: Modern training strategies of deep neural networks (NNs) tend to induce a heavy-tailed (HT) spectra of layer weights. Extensive efforts to study this phenomenon have found that NNs with HT weight spectra tend to generalize well. A prevailing notion for the occurrence of such HT spectra attributes gradient noise during training as a key contributing factor. Our work shows that gradient noise is unnecessary for generating HT weight spectra: two-layer NNs trained with full-batch Gradient Descent/Adam can exhibit HT spectra in their weights after finite training steps. To this end, we first identify the scale of the learning rate at which one step of full-batch Adam can lead to feature learning in the shallow NN, particularly when learning a single index teacher model. Next, we show that multiple optimizer steps with such (sufficiently) large learning rates can transition the bulk of the weight's spectra into an HT distribution. To understand this behavior, we present a novel perspective based on the singular vectors of the weight matrices and optimizer updates. We show that the HT weight spectrum originates from the `spike', which is generated from feature learning and interacts with the main bulk to generate an HT spectrum. Finally, we analyze the correlations between the HT weight spectra and generalization after multiple optimizer updates with varying learning rates.
Authors: Yiheng Zhang, Yunkang Cao, Xiaohao Xu, Weiming Shen
Abstract: This paper presents LogiCode, a novel framework that leverages Large Language Models (LLMs) for identifying logical anomalies in industrial settings, moving beyond traditional focus on structural inconsistencies. By harnessing LLMs for logical reasoning, LogiCode autonomously generates Python codes to pinpoint anomalies such as incorrect component quantities or missing elements, marking a significant leap forward in anomaly detection technologies. A custom dataset "LOCO-Annotations" and a benchmark "LogiBench" are introduced to evaluate the LogiCode's performance across various metrics including binary classification accuracy, code generation success rate, and precision in reasoning. Findings demonstrate LogiCode's enhanced interpretability, significantly improving the accuracy of logical anomaly detection and offering detailed explanations for identified anomalies. This represents a notable shift towards more intelligent, LLM-driven approaches in industrial anomaly detection, promising substantial impacts on industry-specific applications.
Authors: Xu Yuan, Na Zhou, Shuo Yu, Huafei Huang, Zhikui Chen, Feng Xia
Abstract: Anomaly detection (such as telecom fraud detection and medical image detection) has attracted the increasing attention of people. The complex interaction between multiple entities widely exists in the network, which can reflect specific human behavior patterns. Such patterns can be modeled by higher-order network structures, thus benefiting anomaly detection on attributed networks. However, due to the lack of an effective mechanism in most existing graph learning methods, these complex interaction patterns fail to be applied in detecting anomalies, hindering the progress of anomaly detection to some extent. In order to address the aforementioned issue, we present a higher-order structure based anomaly detection (GUIDE) method. We exploit attribute autoencoder and structure autoencoder to reconstruct node attributes and higher-order structures, respectively. Moreover, we design a graph attention layer to evaluate the significance of neighbors to nodes through their higher-order structure differences. Finally, we leverage node attribute and higher-order structure reconstruction errors to find anomalies. Extensive experiments on five real-world datasets (i.e., ACM, Citation, Cora, DBLP, and Pubmed) are implemented to verify the effectiveness of GUIDE. Experimental results in terms of ROC-AUC, PR-AUC, and Recall@K show that GUIDE significantly outperforms the state-of-art methods.
Authors: Zhen Cai, Tao Tang, Shuo Yu, Yunpeng Xiao, Feng Xia
Abstract: Federated recommender systems have been crucially enhanced through data sharing and continuous model updates, attributed to the pervasive connectivity and distributed computing capabilities of Internet of Things (IoT) devices. Given the sensitivity of IoT data, transparent data processing in data sharing and model updates is paramount. However, existing methods fall short in tracing the flow of shared data and the evolution of model updates. Consequently, data sharing is vulnerable to exploitation by malicious entities, raising significant data privacy concerns, while excluding data sharing will result in sub-optimal recommendations. To mitigate these concerns, we present LIBERATE, a privacy-traceable federated recommender system. We design a blockchain-based traceability mechanism, ensuring data privacy during data sharing and model updates. We further enhance privacy protection by incorporating local differential privacy in user-server communication. Extensive evaluations with the real-world dataset corroborate LIBERATE's capabilities in ensuring data privacy during data sharing and model update while maintaining efficiency and performance. Results underscore blockchain-based traceability mechanism as a promising solution for privacy-preserving in federated recommender systems.
Authors: Victor Letzelter (LTCI, S2A, IDS, IP Paris), David Perera (LTCI, S2A, IDS, IP Paris), C\'edric Rommel (LTCI, S2A, IDS, IP Paris), Mathieu Fontaine (LTCI, S2A, IDS, IP Paris), Slim Essid (IDS, S2A, LTCI, IP Paris), Gael Richard (S2A, IDS, LTCI, IP Paris), Patrick P\'erez
Abstract: Winner-takes-all training is a simple learning paradigm, which handles ambiguous tasks by predicting a set of plausible hypotheses. Recently, a connection was established between Winner-takes-all training and centroidal Voronoi tessellations, showing that, once trained, hypotheses should quantize optimally the shape of the conditional distribution to predict. However, the best use of these hypotheses for uncertainty quantification is still an open question.In this work, we show how to leverage the appealing geometric properties of the Winner-takes-all learners for conditional density estimation, without modifying its original training scheme. We theoretically establish the advantages of our novel estimator both in terms of quantization and density estimation, and we demonstrate its competitiveness on synthetic and real-world datasets, including audio data.
Authors: Vladislav Trifonov, Alexander Rudikov, Oleg Iliev, Ivan Oseledets, Ekaterina Muravleva
Abstract: We present ConDiff, a novel dataset for scientific machine learning. ConDiff focuses on the diffusion equation with varying coefficients, a fundamental problem in many applications of parametric partial differential equations (PDEs). The main novelty of the proposed dataset is that we consider discontinuous coefficients with high contrast. These coefficient functions are sampled from a selected set of distributions. This class of problems is not only of great academic interest, but is also the basis for describing various environmental and industrial problems. In this way, ConDiff shortens the gap with real-world problems while remaining fully synthetic and easy to use. ConDiff consists of a diverse set of diffusion equations with coefficients covering a wide range of contrast levels and heterogeneity with a measurable complexity metric for clearer comparison between different coefficient functions. We baseline ConDiff on standard deep learning models in the field of scientific machine learning. By providing a large number of problem instances, each with its own coefficient function and right-hand side, we hope to encourage the development of novel physics-based deep learning approaches, such as neural operators and physics-informed neural networks, ultimately driving progress towards more accurate and efficient solutions of complex PDE problems.
Authors: Benjamin Kurt Miller, Ricky T. Q. Chen, Anuroop Sriram, Brandon M Wood
Abstract: Crystalline materials are a fundamental component in next-generation technologies, yet modeling their distribution presents unique computational challenges. Of the plausible arrangements of atoms in a periodic lattice only a vanishingly small percentage are thermodynamically stable, which is a key indicator of the materials that can be experimentally realized. Two fundamental tasks in this area are to (a) predict the stable crystal structure of a known composition of elements and (b) propose novel compositions along with their stable structures. We present FlowMM, a pair of generative models that achieve state-of-the-art performance on both tasks while being more efficient and more flexible than competing methods. We generalize Riemannian Flow Matching to suit the symmetries inherent to crystals: translation, rotation, permutation, and periodic boundary conditions. Our framework enables the freedom to choose the flow base distributions, drastically simplifying the problem of learning crystal structures compared with diffusion models. In addition to standard benchmarks, we validate FlowMM's generated structures with quantum chemistry calculations, demonstrating that it is about 3x more efficient, in terms of integration steps, at finding stable materials compared to previous open methods.
Authors: Roman Belaire, Arunesh Sinha, Pradeep Varakantham
Abstract: Deep Reinforcement Learning (DRL) policies are critically vulnerable to adversarial noise in observations, posing severe risks in safety-critical scenarios. For example, a self-driving car receiving manipulated sensory inputs about traffic signs could lead to catastrophic outcomes. Existing strategies to fortify RL algorithms against such adversarial perturbations generally fall into two categories: (a) using regularization methods that enhance robustness by incorporating adversarial loss terms into the value objectives, and (b) adopting "maximin" principles, which focus on maximizing the minimum value to ensure robustness. While regularization methods reduce the likelihood of successful attacks, their effectiveness drops significantly if an attack does succeed. On the other hand, maximin objectives, although robust, tend to be overly conservative. To address this challenge, we introduce a novel objective called Adversarial Counterfactual Error (ACoE), which naturally balances optimizing value and robustness against adversarial attacks. To optimize ACoE in a scalable manner in model-free settings, we propose a theoretically justified surrogate objective known as Cumulative-ACoE (C-ACoE). The core idea of optimizing C-ACoE is utilizing the belief about the underlying true state given the adversarially perturbed observation. Our empirical evaluations demonstrate that our method outperforms current state-of-the-art approaches for addressing adversarial RL problems across all established benchmarks (MuJoCo, Atari, and Highway) used in the literature.
Authors: Fanmeng Wang, Wentao Guo, Minjie Cheng, Shen Yuan, Hongteng Xu, Zhifeng Gao
Abstract: In the past few decades, polymers, high-molecular-weight compounds formed by bonding numerous identical or similar monomers covalently, have played an essential role in various scientific fields. In this context, accurate prediction of their properties is becoming increasingly crucial. Typically, the properties of a polymer, such as plasticity, conductivity, bio-compatibility, and so on, are highly correlated with its 3D structure. However, current methods for predicting polymer properties heavily rely on information from polymer SMILES sequences (P-SMILES strings) while ignoring crucial 3D structural information, leading to sub-optimal performance. In this work, we propose MMPolymer, a novel multimodal multitask pretraining framework incorporating both polymer 1D sequential information and 3D structural information to enhance downstream polymer property prediction tasks. Besides, to overcome the limited availability of polymer 3D data, we further propose the "Star Substitution" strategy to extract 3D structural information effectively. During pretraining, MMPolymer not only predicts masked tokens and recovers 3D coordinates but also achieves the cross-modal alignment of latent representation. Subsequently, we further fine-tune the pretrained MMPolymer for downstream polymer property prediction tasks in the supervised learning paradigm. Experimental results demonstrate that MMPolymer achieves state-of-the-art performance in various polymer property prediction tasks. Moreover, leveraging the pretrained MMPolymer and using only one modality (either P-SMILES string or 3D conformation) during fine-tuning can also surpass existing polymer property prediction methods, highlighting the exceptional capability of MMPolymer in polymer feature extraction and utilization. Our online platform for polymer property prediction is available at https://app.bohrium.dp.tech/mmpolymer.
Authors: Miguel Gonz\'alez-Duque, Richard Michael, Simon Bartels, Yevgen Zainchkovskyy, S{\o}ren Hauberg, Wouter Boomsma
Abstract: Optimizing discrete black-box functions is key in several domains, e.g. protein engineering and drug design. Due to the lack of gradient information and the need for sample efficiency, Bayesian optimization is an ideal candidate for these tasks. Several methods for high-dimensional continuous and categorical Bayesian optimization have been proposed recently. However, our survey of the field reveals highly heterogeneous experimental set-ups across methods and technical barriers for the replicability and application of published algorithms to real-world tasks. To address these issues, we develop a unified framework to test a vast array of high-dimensional Bayesian optimization methods and a collection of standardized black-box functions representing real-world application domains in chemistry and biology. These two components of the benchmark are each supported by flexible, scalable, and easily extendable software libraries (poli and poli-baselines), allowing practitioners to readily incorporate new optimization objectives or discrete optimizers. Project website: https://machinelearninglifescience.github.io/hdbo_benchmark
URLs: https://machinelearninglifescience.github.io/hdbo_benchmark
Authors: Lei Xu, Yulong Chen, Yuntian Chen, Longfeng Nie, Xuetao Wei, Liang Xue, Dongxiao Zhang
Abstract: Machine learning models offer the capability to forecast future energy production or consumption and infer essential unknown variables from existing data. However, legal and policy constraints within specific energy sectors render the data sensitive, presenting technical hurdles in utilizing data from diverse sources. Therefore, we propose adopting a Swarm Learning (SL) scheme, which replaces the centralized server with a blockchain-based distributed network to address the security and privacy issues inherent in Federated Learning (FL)'s centralized architecture. Within this distributed Collaborative Learning framework, each participating organization governs nodes for inter-organizational communication. Devices from various organizations utilize smart contracts for parameter uploading and retrieval. Consensus mechanism ensures distributed consistency throughout the learning process, guarantees the transparent trustworthiness and immutability of parameters on-chain. The efficacy of the proposed framework is substantiated across three real-world energy series modeling scenarios with superior performance compared to Local Learning approaches, simultaneously emphasizing enhanced data security and privacy over Centralized Learning and FL method. Notably, as the number of data volume and the count of local epochs increases within a threshold, there is an improvement in model performance accompanied by a reduction in the variance of performance errors. Consequently, this leads to an increased stability and reliability in the outcomes produced by the model.
Authors: Yu-Chang Wu, Shen-Huan Lyu, Haopu Shang, Xiangyu Wang, Chao Qian
Abstract: Selective classification enables models to make predictions only when they are sufficiently confident, aiming to enhance safety and reliability, which is important in high-stakes scenarios. Previous methods mainly use deep neural networks and focus on modifying the architecture of classification layers to enable the model to estimate the confidence of its prediction. This work provides a generalization bound for selective classification, disclosing that optimizing feature layers helps improve the performance of selective classification. Inspired by this theory, we propose to explicitly improve the selective classification model at the feature level for the first time, leading to a novel Confidence-aware Contrastive Learning method for Selective Classification, CCL-SC, which similarizes the features of homogeneous instances and differentiates the features of heterogeneous instances, with the strength controlled by the model's confidence. The experimental results on typical datasets, i.e., CIFAR-10, CIFAR-100, CelebA, and ImageNet, show that CCL-SC achieves significantly lower selective risk than state-of-the-art methods, across almost all coverage degrees. Moreover, it can be combined with existing methods to bring further improvement.
Authors: Joel Oskarsson, Tomas Landelius, Marc Peter Deisenroth, Fredrik Lindsten
Abstract: In recent years, machine learning has established itself as a powerful tool for high-resolution weather forecasting. While most current machine learning models focus on deterministic forecasts, accurately capturing the uncertainty in the chaotic weather system calls for probabilistic modeling. We propose a probabilistic weather forecasting model called Graph-EFM, combining a flexible latent-variable formulation with the successful graph-based forecasting framework. The use of a hierarchical graph construction allows for efficient sampling of spatially coherent forecasts. Requiring only a single forward pass per time step, Graph-EFM allows for fast generation of arbitrarily large ensembles. We experiment with the model on both global and limited area forecasting. Ensemble forecasts from Graph-EFM achieve equivalent or lower errors than comparable deterministic models, with the added benefit of accurately capturing forecast uncertainty.
Authors: Lucas Weber, Ana Bu\v{s}i\'c, Jiamin Zhu
Abstract: The expected regret of any reinforcement learning algorithm is lower bounded by $\Omega\left(\sqrt{DXAT}\right)$ for undiscounted returns, where $D$ is the diameter of the Markov decision process, $X$ the size of the state space, $A$ the size of the action space and $T$ the number of time steps. However, this lower bound is general. A smaller regret can be obtained by taking into account some specific knowledge of the problem structure. In this article, we consider an admission control problem to an $M/M/c/S$ queue with $m$ job classes and class-dependent rewards and holding costs. Queuing systems often have a diameter that is exponential in the buffer size $S$, making the previous lower bound prohibitive for any practical use. We propose an algorithm inspired by UCRL2, and use the structure of the problem to upper bound the expected total regret by $O(S\log T + \sqrt{mT \log T})$ in the finite server case. In the infinite server case, we prove that the dependence of the regret on $S$ disappears.
Authors: Sungho Jeon, Xinyue Ma, Kwang In Kim, Myeongjae Jeon
Abstract: On-device continual learning (CL) requires the co-optimization of model accuracy and resource efficiency to be practical. This is extremely challenging because it must preserve accuracy while learning new tasks with continuously drifting data and maintain both high energy and memory efficiency to be deployable on real-world devices. Typically, a CL method leverages one of two types of backbone networks: CNN or ViT. It is commonly believed that CNN-based CL excels in resource efficiency, whereas ViT-based CL is superior in model performance, making each option attractive only for a single aspect. In this paper, we revisit this comparison while embracing powerful pre-trained ViT models of various sizes, including ViT-Ti (5.8M parameters). Our detailed analysis reveals that many practical options exist today for making ViT-based methods more suitable for on-device CL, even when accuracy, energy, and memory are all considered. To further expand this impact, we introduce REP, which improves resource efficiency specifically targeting prompt-based rehearsal-free methods. Our key focus is on avoiding catastrophic trade-offs with accuracy while trimming computational and memory costs throughout the training process. We achieve this by exploiting swift prompt selection that enhances input data using a carefully provisioned model, and by developing two novel algorithms-adaptive token merging (AToM) and adaptive layer dropping (ALD)-that optimize the prompt updating stage. In particular, AToM and ALD perform selective skipping across the data and model-layer dimensions without compromising task-specific features in vision transformer models. Extensive experiments on three image classification datasets validate REP's superior resource efficiency over current state-of-the-art methods.
Authors: Qi Xiong, Kai Tang, Minbo Ma, Jie Xu, Tianrui Li
Abstract: Learning temporal dependencies among targets (TDT) benefits better time series forecasting, where targets refer to the predicted sequence. Although autoregressive methods model TDT recursively, they suffer from inefficient inference and error accumulation. We argue that integrating TDT learning into non-autoregressive methods is essential for pursuing effective and efficient time series forecasting. In this study, we introduce the differencing approach to represent TDT and propose a parameter-free and plug-and-play solution through an optimization objective, namely TDT Loss. It leverages the proportion of inconsistent signs between predicted and ground truth TDT as an adaptive weight, dynamically balancing target prediction and fine-grained TDT fitting. Importantly, TDT Loss incurs negligible additional cost, with only $\mathcal{O}(n)$ increased computation and $\mathcal{O}(1)$ memory requirements, while significantly enhancing the predictive performance of non-autoregressive models. To assess the effectiveness of TDT loss, we conduct extensive experiments on 7 widely used datasets. The experimental results of plugging TDT loss into 6 state-of-the-art methods show that out of the 168 experiments, 75.00\% and 94.05\% exhibit improvements in terms of MSE and MAE with the maximum 24.56\% and 16.31\%, respectively.
Authors: Shirwan Piroti, Ashima Chawla, Tahar Zanouda
Abstract: There are vast number of configurable parameters in a Radio Access Telecom Network. A significant amount of these parameters is configured by Radio Node or cell based on their deployment setting. Traditional methods rely on domain knowledge for individual parameter configuration, often leading to sub-optimal results. To improve this, a framework using a Deep Generative Graph Neural Network (GNN) is proposed. It encodes the network into a graph, extracts subgraphs for each RAN node, and employs a Siamese GNN (S-GNN) to learn embeddings. The framework recommends configuration parameters for a multitude of parameters and detects misconfigurations, handling both network expansion and existing cell reconfiguration. Tested on real-world data, the model surpasses baselines, demonstrating accuracy, generalizability, and robustness against concept drift.
Authors: Pavlin G. Poli\v{c}ar, Bla\v{z} Zupan
Abstract: Two-dimensional embeddings obtained from dimensionality reduction techniques, such as MDS, t-SNE, and UMAP, are widely used across various disciplines to visualize high-dimensional data. These visualizations provide a valuable tool for exploratory data analysis, allowing researchers to visually identify clusters, outliers, and other interesting patterns in the data. However, interpreting the resulting visualizations can be challenging, as it often requires additional manual inspection to understand the differences between data points in different regions of the embedding space. To address this issue, we propose Visual Explanations via Region Annotation (VERA), an automatic embedding-annotation approach that generates visual explanations for any two-dimensional embedding. VERA produces informative explanations that characterize distinct regions in the embedding space, allowing users to gain an overview of the embedding landscape at a glance. Unlike most existing approaches, which typically require some degree of manual user intervention, VERA produces static explanations, automatically identifying and selecting the most informative visual explanations to show to the user. We illustrate the usage of VERA on a real-world data set and validate the utility of our approach with a comparative user study. Our results demonstrate that the explanations generated by VERA are as useful as fully-fledged interactive tools on typical exploratory data analysis tasks but require significantly less time and effort from the user.
Authors: Alexandra Moringen, Elad Vromen, Helge Ritter, Jason Friedman
Abstract: A typical process of learning to play a piece on a piano consists of a progression through a series of practice units that focus on individual dimensions of the skill, the so-called practice modes. Practice modes in learning to play music comprise a particularly large set of possibilities, such as hand coordination, posture, articulation, ability to read a music score, correct timing or pitch, etc. Self-guided practice is known to be suboptimal, and a model that schedules optimal practice to maximize a learner's progress still does not exist. Because we each learn differently and there are many choices for possible piano practice tasks and methods, the set of practice modes should be dynamically adapted to the human learner, a process typically guided by a teacher. However, having a human teacher guide individual practice is not always feasible since it is time-consuming, expensive, and often unavailable. In this work, we present a modeling framework to guide the human learner through the learning process by choosing the practice modes generated by a policy model. To this end, we present a computational architecture building on a Gaussian process that incorporates 1) the learner state, 2) a policy that selects a suitable practice mode, 3) performance evaluation, and 4) expert knowledge. The proposed policy model is trained to approximate the expert-learner interaction during a practice session. In our future work, we will test different Bayesian optimization techniques, e.g., different acquisition functions, and evaluate their effect on the learning progress.
Authors: Xuehui Yu, Mhairi Dunion, Xin Li, Stefano V. Albrecht
Abstract: Meta-Reinforcement Learning (Meta-RL) agents can struggle to operate across tasks with varying environmental features that require different optimal skills (i.e., different modes of behaviours). Using context encoders based on contrastive learning to enhance the generalisability of Meta-RL agents is now widely studied but faces challenges such as the requirement for a large sample size, also referred to as the $\log$-$K$ curse. To improve RL generalisation to different tasks, we first introduce Skill-aware Mutual Information (SaMI), an optimisation objective that aids in distinguishing context embeddings according to skills, thereby equipping RL agents with the ability to identify and execute different skills across tasks. We then propose Skill-aware Noise Contrastive Estimation (SaNCE), a $K$-sample estimator used to optimise the SaMI objective. We provide a framework for equipping an RL agent with SaNCE in practice and conduct experimental validation on modified MuJoCo and Panda-gym benchmarks. We empirically find that RL agents that learn by maximising SaMI achieve substantially improved zero-shot generalisation to unseen tasks. Additionally, the context encoder equipped with SaNCE demonstrates greater robustness to reductions in the number of available samples, thus possessing the potential to overcome the $\log$-$K$ curse.
Authors: Zhihao Li, Zhilu Lai, Xiaobo Wang, Wei Wang
Abstract: Solving partial differential equations (PDEs) effectively necessitates a multi-scale approach, particularly critical in high-dimensional scenarios characterized by increasing grid points or resolution. Traditional methods often fail to capture the detailed features necessary for accurate modeling, presenting a significant challenge in scientific computing. In response, we introduce the Multiwavelet-based Algebraic Multigrid Neural Operator (M2NO), a novel deep learning framework that synergistically combines multiwavelet transformations and algebraic multigrid (AMG) techniques. By exploiting the inherent similarities between these two approaches, M2NO overcomes their individual limitations and enhances precision and flexibility across various PDE benchmarks. Employing Multiresolution Analysis (MRA) with high-pass and low-pass filters, the model executes hierarchical decomposition to accurately delineate both global trends and localized details within PDE solutions, supporting adaptive data representation at multiple scales. M2NO also automates node selection and adeptly manages complex boundary conditions through its multiwavelet-based operators. Extensive evaluations on a diverse array of PDE datasets with different boundary conditions confirm M2NO's superior performance. Furthermore, M2NO excels in handling high-resolution and super-resolution tasks, consistently outperforming competing models and demonstrating robust adaptability in complex computational scenarios.
Authors: Virginia Aglietti, Ira Ktena, Jessica Schrouff, Eleni Sgouritsa, Francisco J. R. Ruiz, Alexis Bellot, Silvia Chiappa
Abstract: The sample efficiency of Bayesian optimization algorithms depends on carefully crafted acquisition functions (AFs) guiding the sequential collection of function evaluations. The best-performing AF can vary significantly across optimization problems, often requiring ad-hoc and problem-specific choices. This work tackles the challenge of designing novel AFs that perform well across a variety of experimental settings. Based on FunSearch, a recent work using Large Language Models (LLMs) for discovery in mathematical sciences, we propose FunBO, an LLM-based method that can be used to learn new AFs written in computer code by leveraging access to a limited number of evaluations for a set of objective functions. We provide the analytic expression of all discovered AFs and evaluate them on various global optimization benchmarks and hyperparameter optimization tasks. We show how FunBO identifies AFs that generalize well in and out of the training distribution of functions, thus outperforming established general-purpose AFs and achieving competitive performance against AFs that are customized to specific function types and are learned via transfer-learning algorithms.
Authors: Appan Rakaraddi, Lam Siew-Kei, Mahardhika Pratama, Marcus de Carvalho
Abstract: Multitude of deep learning models have been proposed for node classification in graphs. However, they tend to perform poorly under labeled-data scarcity. Although Few-shot learning for graphs has been introduced to overcome this problem, the existing models are not easily adaptable for generic graph learning frameworks like Graph Neural Networks (GNNs). Our work proposes an Uncertainty Estimator framework that can be applied on top of any generic GNN backbone network (which are typically designed for supervised/semi-supervised node classification) to improve the node classification performance. A neural network is used to model the Uncertainty Estimator as a probability distribution rather than probabilistic discrete scalar values. We train these models under the classic episodic learning paradigm in the $n$-way, $k$-shot fashion, in an end-to-end setting. Our work demonstrates that implementation of the uncertainty estimator on a GNN backbone network improves the classification accuracy under Few-shot setting without any meta-learning specific architecture. We conduct experiments on multiple datasets under different Few-shot settings and different GNN-based backbone networks. Our method outperforms the baselines, which demonstrates the efficacy of the Uncertainty Estimator for Few-shot node classification on graphs with a GNN.
Authors: Antti Koskela, Jafar Mohammadi
Abstract: We present a practical method to audit the differential privacy (DP) guarantees of a machine learning model using a small hold-out dataset that is not exposed to the model during the training. Having a score function such as the loss function employed during the training, our method estimates the total variation (TV) distance between scores obtained with a subset of the training data and the hold-out dataset. With some meta information about the underlying DP training algorithm, these TV distance values can be converted to $(\varepsilon,\delta)$-guarantees for any $\delta$. We show that these score distributions asymptotically give lower bounds for the DP guarantees of the underlying training algorithm, however, we perform a one-shot estimation for practicality reasons. We specify conditions that lead to lower bounds for the DP guarantees with high probability. To estimate the TV distance between the score distributions, we use a simple density estimation method based on histograms. We show that the TV distance gives a very close to optimally robust estimator and has an error rate $\mathcal{O}(k^{-1/3})$, where $k$ is the total number of samples. Numerical experiments on benchmark datasets illustrate the effectiveness of our approach and show improvements over baseline methods for black-box auditing.
Authors: R. Sala
Abstract: Efficient numerical optimization methods can improve performance and reduce the environmental impact of computing in many applications. This work presents a proof-of-concept study combining primitive state representations and agent-environment interactions as first-order optimizers in the setting of budget-limited optimization. Through reinforcement learning (RL) over a set of training instances of an optimization problem class, optimal policies for sequential update selection of algorithmic iteration steps are approximated in generally formulated low-dimensional partial state representations that consider aspects of progress and resource use. For the investigated case studies, deployment of the trained agents to unseen instances of the quadratic optimization problem classes outperformed conventional optimal algorithms with optimized hyperparameters. The results show that elementary RL methods combined with succinct partial state representations can be used as heuristics to manage complexity in RL-based optimization, paving the way for agentic optimization approaches.
Authors: Floor Eijkelboom, Grigory Bartosh, Christian Andersson Naesseth, Max Welling, Jan-Willem van de Meent
Abstract: We present a formulation of flow matching as variational inference, which we refer to as variational flow matching (VFM). Based on this formulation we develop CatFlow, a flow matching method for categorical data. CatFlow is easy to implement, computationally efficient, and achieves strong results on graph generation tasks. In VFM, the objective is to approximate the posterior probability path, which is a distribution over possible end points of a trajectory. We show that VFM admits both the CatFlow objective and the original flow matching objective as special cases. We also relate VFM to score-based models, in which the dynamics are stochastic rather than deterministic, and derive a bound on the model likelihood based on a reweighted VFM objective. We evaluate CatFlow on one abstract graph generation task and two molecular generation tasks. In all cases, CatFlow exceeds or matches performance of the current state-of-the-art models.
Authors: Yuhao Mao, Stefan Balauca, Martin Vechev
Abstract: Training certifiably robust neural networks is an important but challenging task. While many algorithms for (deterministic) certified training have been proposed, they are often evaluated on different training schedules, certification methods, and systematically under-tuned hyperparameters, making it difficult to compare their performance. To address this challenge, we introduce CTBENCH, a unified library and a high-quality benchmark for certified training that evaluates all algorithms under fair settings and systematically tuned hyperparameters. We show that (1) almost all algorithms in CTBENCH surpass the corresponding reported performance in literature in the magnitude of algorithmic improvements, thus establishing new state-of-the-art, and (2) the claimed advantage of recent algorithms drops significantly when we enhance the outdated baselines with a fair training schedule, a fair certification method and well-tuned hyperparameters. Based on CTBENCH, we provide new insights into the current state of certified training and suggest future research directions. We are confident that CTBENCH will serve as a benchmark and testbed for future research in certified training.
Authors: Vincent Cohen-Addad, Tommaso d'Orsi, Silvio Lattanzi, Rajai Nasser
Abstract: Graph clustering is a central topic in unsupervised learning with a multitude of practical applications. In recent years, multi-view graph clustering has gained a lot of attention for its applicability to real-world instances where one has access to multiple data sources. In this paper we formalize a new family of models, called \textit{multi-view stochastic block models} that captures this setting. For this model, we first study efficient algorithms that naively work on the union of multiple graphs. Then, we introduce a new efficient algorithm that provably outperforms previous approaches by analyzing the structure of each graph separately. Furthermore, we complement our results with an information-theoretic lower bound studying the limits of what can be done in this model. Finally, we corroborate our results with experimental evaluations.
Authors: Sojung An, Tae-Jin Oh, Eunha Sohn, Donghyun Kim
Abstract: Deep learning-based time series forecasting has dominated the short-term precipitation forecasting field with the help of its ability to estimate motion flow in high-resolution datasets. The growing interest in precipitation nowcasting offers substantial opportunities for the advancement of current forecasting technologies. Nevertheless, there has been a scarcity of in-depth surveys of time series precipitation forecasting using deep learning. Thus, this paper systemically reviews recent progress in time series precipitation forecasting models. Specifically, we investigate the following key points within background components, covering: i) preprocessing, ii) objective functions, and iii) evaluation metrics. We then categorize forecasting models into \textit{recursive} and \textit{multiple} strategies based on their approaches to predict future frames, investigate the impacts of models using the strategies, and performance assessments. Finally, we evaluate current deep learning-based models for precipitation forecasting on a public benchmark, discuss their limitations and challenges, and present some promising research directions. Our contribution lies in providing insights for a better understanding of time series precipitation forecasting and in aiding the development of robust AI solutions for the future.
Authors: Vincent Cohen-Addad, Tommaso d'Orsi, Alessandro Epasto, Vahab Mirrokni, Peilin Zhong
Abstract: We revisit the input perturbations framework for differential privacy where noise is added to the input $A\in \mathcal{S}$ and the result is then projected back to the space of admissible datasets $\mathcal{S}$. Through this framework, we first design novel efficient algorithms to privately release pair-wise cosine similarities. Second, we derive a novel algorithm to compute $k$-way marginal queries over $n$ features. Prior work could achieve comparable guarantees only for $k$ even. Furthermore, we extend our results to $t$-sparse datasets, where our efficient algorithms yields novel, stronger guarantees whenever $t\le n^{5/6}/\log n\,.$ Finally, we provide a theoretical perspective on why \textit{fast} input perturbation algorithms works well in practice. The key technical ingredients behind our results are tight sum-of-squares certificates upper bounding the Gaussian complexity of sets of solutions.
Authors: Feng Hong, Yueming Lyu, Jiangchao Yao, Ya Zhang, Ivor W. Tsang, Yanfeng Wang
Abstract: The remarkable success of modern machine learning models on large datasets often demands extensive training time and resource consumption. To save cost, a prevalent research line, known as online batch selection, explores selecting informative subsets during the training process. Although recent efforts achieve advancements by measuring the impact of each sample on generalization, their reliance on additional reference models inherently limits their practical applications, when there are no such ideal models available. On the other hand, the vanilla reference-model-free methods involve independently scoring and selecting data in a sample-wise manner, which sacrifices the diversity and induces the redundancy. To tackle this dilemma, we propose Diversified Batch Selection (DivBS), which is reference-model-free and can efficiently select diverse and representative samples. Specifically, we define a novel selection objective that measures the group-wise orthogonalized representativeness to combat the redundancy issue of previous sample-wise criteria, and provide a principled selection-efficient realization. Extensive experiments across various tasks demonstrate the significant superiority of DivBS in the performance-speedup trade-off. The code is publicly available.
Authors: Zachari Thiry, Massimiliano Ruocco, Alessandro Nocente, Michail Spitieris
Abstract: Forecasting indoor temperatures is important to achieve efficient control of HVAC systems. In this task, the limited data availability presents a challenge as most of the available data is acquired during standard operation where extreme scenarios and transitory regimes such as major temperature increases or decreases are de-facto excluded. Acquisition of such data requires significant energy consumption and a dedicated facility, hindering the quantity and diversity of available data. Cost related constraints however do not allow for continuous year-around acquisition. To address this, we investigate the efficacy of data augmentation techniques leveraging SoTA AI-based methods for synthetic data generation. Inspired by practical and experimental motivations, we explore fusion strategies of real and synthetic data to improve forecasting models. This approach alleviates the need for continuously acquiring extensive time series data, especially in contexts involving repetitive heating and cooling cycles in buildings. In our evaluation 1) we assess the performance of synthetic data generators independently, particularly focusing on SoTA AI-based methods; 2) we measure the utility of incorporating synthetically augmented data in a subsequent forecasting tasks where we employ a simple model in two distinct scenarios: 1) we first examine an augmentation technique that combines real and synthetically generated data to expand the training dataset, 2) we delve into utilizing synthetic data to tackle dataset imbalances. Our results highlight the potential of synthetic data augmentation in enhancing forecasting accuracy while mitigating training variance. Through empirical experiments, we show significant improvements achievable by integrating synthetic data, thereby paving the way for more robust forecasting models in low-data regime.
Authors: Motoki Omura, Takayuki Osa, Yusuke Mukuta, Tatsuya Harada
Abstract: In Extreme Q-learning (XQL), Gumbel Regression is performed with an assumed Gumbel distribution for the error distribution. This allows learning of the value function without sampling out-of-distribution actions and has shown excellent performance mainly in Offline RL. However, issues remained, including the exponential term in the loss function causing instability and the potential for an error distribution diverging from the Gumbel distribution. Therefore, we propose Maclaurin Expanded Extreme Q-learning to enhance stability. In this method, applying Maclaurin expansion to the loss function in XQL enhances stability against large errors. It also allows adjusting the error distribution assumption from normal to Gumbel based on the expansion order. Our method significantly stabilizes learning in Online RL tasks from DM Control, where XQL was previously unstable. Additionally, it improves performance in several Offline RL tasks from D4RL, where XQL already showed excellent results.
Authors: Moritz Lampert, Christopher Bl\"ocker, Ingo Scholtes
Abstract: Dynamic link prediction is an important problem considered by many recent works proposing various approaches for learning temporal edge patterns. To assess their efficacy, models are evaluated on publicly available benchmark datasets involving continuous-time and discrete-time temporal graphs. However, as we show in this work, the suitability of common batch-oriented evaluation depends on the datasets' characteristics, which can cause two issues: First, for continuous-time temporal graphs, fixed-size batches create time windows with different durations, resulting in an inconsistent dynamic link prediction task. Second, for discrete-time temporal graphs, the sequence of batches can additionally introduce temporal dependencies that are not present in the data. In this work, we empirically show that this common evaluation approach leads to skewed model performance and hinders the fair comparison of methods. We mitigate this problem by reformulating dynamic link prediction as a link forecasting task that better accounts for temporal information present in the data. We provide implementations of our new evaluation method for commonly used graph learning frameworks.
Authors: Ayush K. Varshney, Vicenc Torra
Abstract: Deep neural networks (DNNs) are one of the most widely used machine learning algorithm. DNNs requires the training data to be available beforehand with true labels. This is not feasible for many real-world problems where data arrives in the streaming form and acquisition of true labels are scarce and expensive. In the literature, not much focus has been given to the privacy prospect of the streaming data, where data may change its distribution frequently. These concept drifts must be detected privately in order to avoid any disclosure risk from DNNs. Existing privacy models use concept drift detection schemes such ADWIN, KSWIN to detect the drifts. In this paper, we focus on the notion of integrally private DNNs to detect concept drifts. Integrally private DNNs are the models which recur frequently from different datasets. Based on this, we introduce an ensemble methodology which we call 'Integrally Private Drift Detection' (IPDD) method to detect concept drift from private models. Our IPDD method does not require labels to detect drift but assumes true labels are available once the drift has been detected. We have experimented with binary and multi-class synthetic and real-world data. Our experimental results show that our methodology can privately detect concept drift, has comparable utility (even better in some cases) with ADWIN and outperforms utility from different levels of differentially private models. The source code for the paper is available \hyperlink{https://github.com/Ayush-Umu/Concept-drift-detection-Using-Integrally-private-models}{here}.
URLs: https://github.com/Ayush-Umu/Concept-drift-detection-Using-Integrally-private-models
Authors: Binglei Lou, Richard Rademacher, David Boland, Philip H. W. Leong
Abstract: FPGAs have distinct advantages as a technology for deploying deep neural networks (DNNs) at the edge. Lookup Table (LUT) based networks, where neurons are directly modelled using LUTs, help maximize this promise of offering ultra-low latency and high area efficiency on FPGAs. Unfortunately, LUT resource usage scales exponentially with the number of inputs to the LUT, restricting PolyLUT to small LUT sizes. This work introduces PolyLUT-Add, a technique that enhances neuron connectivity by combining $A$ PolyLUT sub-neurons via addition to improve accuracy. Moreover, we describe a novel architecture to improve its scalability. We evaluated our implementation over the MNIST, Jet Substructure classification and Network Intrusion Detection benchmark and found that for similar accuracy, PolyLUT-Add achieves a LUT reduction of $1.3-7.7\times$ with a $1.2-2.2\times$ decrease in latency.
Authors: Piyushi Manupriya, Pratik Jawanpuria, Karthik S. Gurumoorthy, SakethaNath Jagarlapudi, Bamdev Mishra
Abstract: Unbalanced optimal transport (UOT) has recently gained much attention due to its flexible framework for handling un-normalized measures and its robustness properties. In this work, we explore learning (structured) sparse transport plans in the UOT setting, i.e., transport plans have an upper bound on the number of non-sparse entries in each column (structured sparse pattern) or in the whole plan (general sparse pattern). We propose novel sparsity-constrained UOT formulations building on the recently explored maximum mean discrepancy based UOT. We show that the proposed optimization problem is equivalent to the maximization of a weakly submodular function over a uniform matroid or a partition matroid. We develop efficient gradient-based discrete greedy algorithms and provide the corresponding theoretical guarantees. Empirically, we observe that our proposed greedy algorithms select a diverse support set and we illustrate the efficacy of the proposed approach in various applications.
Authors: Adrien Carrel
Abstract: Graph structures offer a versatile framework for representing diverse patterns in nature and complex systems, applicable across domains like molecular chemistry, social networks, and transportation systems. While diffusion models have excelled in generating various objects, generating graphs remains challenging. This thesis explores the potential of score-based generative models in generating such objects through a modelization as combinatorial complexes, which are powerful topological structures that encompass higher-order relationships. In this thesis, we propose a unified framework by employing stochastic differential equations. We not only generalize the generation of complex objects such as graphs and hypergraphs, but we also unify existing generative modelling approaches such as Score Matching with Langevin dynamics and Denoising Diffusion Probabilistic Models. This innovation overcomes limitations in existing frameworks that focus solely on graph generation, opening up new possibilities in generative AI. The experiment results showed that our framework could generate these complex objects, and could also compete against state-of-the-art approaches for mere graph and molecule generation tasks.
Authors: Christoph J\"urgen Hemmer, Manuel Brenner, Florian Hess, Daniel Durstewitz
Abstract: In dynamical systems reconstruction (DSR) we seek to infer from time series measurements a generative model of the underlying dynamical process. This is a prime objective in any scientific discipline, where we are particularly interested in parsimonious models with a low parameter load. A common strategy here is parameter pruning, removing all parameters with small weights. However, here we find this strategy does not work for DSR, where even low magnitude parameters can contribute considerably to the system dynamics. On the other hand, it is well known that many natural systems which generate complex dynamics, like the brain or ecological networks, have a sparse topology with comparatively few links. Inspired by this, we show that geometric pruning, where in contrast to magnitude-based pruning weights with a low contribution to an attractor's geometrical structure are removed, indeed manages to reduce parameter load substantially without significantly hampering DSR quality. We further find that the networks resulting from geometric pruning have a specific type of topology, and that this topology, and not the magnitude of weights, is what is most crucial to performance. We provide an algorithm that automatically generates such topologies which can be used as priors for generative modeling of dynamical systems by RNNs, and compare it to other well studied topologies like small-world or scale-free networks.
Authors: Xizhi Gu, Hongzheng Li, Shihong Gao, Xinyan Zhang, Lei Chen, Yingxia Shao
Abstract: Graph Neural Networks (GNNs) have superior capability in learning graph data. Full-graph GNN training generally has high accuracy, however, it suffers from large peak memory usage and encounters the Out-of-Memory problem when handling large graphs. To address this memory problem, a popular solution is mini-batch GNN training. However, mini-batch GNN training increases the training variance and sacrifices the model accuracy. In this paper, we propose a new memory-efficient GNN training method using spanning subgraph, called SpanGNN. SpanGNN trains GNN models over a sequence of spanning subgraphs, which are constructed from empty structure. To overcome the excessive peak memory consumption problem, SpanGNN selects a set of edges from the original graph to incrementally update the spanning subgraph between every epoch. To ensure the model accuracy, we introduce two types of edge sampling strategies (i.e., variance-reduced and noise-reduced), and help SpanGNN select high-quality edges for the GNN learning. We conduct experiments with SpanGNN on widely used datasets, demonstrating SpanGNN's advantages in the model performance and low peak memory usage.
Authors: Matthew Fortier, Mats L. Richter, Oliver Sonnentag, Chris Pal
Abstract: Terrestrial carbon fluxes provide vital information about our biosphere's health and its capacity to absorb anthropogenic CO$_2$ emissions. The importance of predicting carbon fluxes has led to the emerging field of data-driven carbon flux modelling (DDCFM), which uses statistical techniques to predict carbon fluxes from biophysical data. However, the field lacks a standardized dataset to promote comparisons between models. To address this gap, we present CarbonSense, the first machine learning-ready dataset for DDCFM. CarbonSense integrates measured carbon fluxes, meteorological predictors, and satellite imagery from 385 locations across the globe, offering comprehensive coverage and facilitating robust model training. Additionally, we provide a baseline model using a current state-of-the-art DDCFM approach and a novel transformer based model. Our experiments illustrate the potential gains that multimodal deep learning techniques can bring to this domain. By providing these resources, we aim to lower the barrier to entry for other deep learning researchers to develop new models and drive new advances in carbon flux modelling.
Authors: Qitian Wu, Fan Nie, Chenxiao Yang, Junchi Yan
Abstract: Real-world data generation often involves certain geometries (e.g., graphs) that induce instance-level interdependence. This characteristic makes the generalization of learning models more difficult due to the intricate interdependent patterns that impact data-generative distributions and can vary from training to testing. In this work, we propose a geometric diffusion model with learnable divergence fields for the challenging generalization problem with interdependent data. We generalize the diffusion equation with stochastic diffusivity at each time step, which aims to capture the multi-faceted information flows among interdependent data. Furthermore, we derive a new learning objective through causal inference, which can guide the model to learn generalizable patterns of interdependence that are insensitive across domains. Regarding practical implementation, we introduce three model instantiations that can be considered as the generalized versions of GCN, GAT, and Transformers, respectively, which possess advanced robustness against distribution shifts. We demonstrate their promising efficacy for out-of-distribution generalization on diverse real-world datasets.
Authors: Adrien Carrel
Abstract: Neural Laplace is a unified framework for learning diverse classes of differential equations (DE). For different classes of DE, this framework outperforms other approaches relying on neural networks that aim to learn classes of ordinary differential equations (ODE). However, many systems can't be modelled using ODEs. Stochastic differential equations (SDE) are the mathematical tool of choice when modelling spatiotemporal DE dynamics under the influence of randomness. In this work, we review the potential applications of Neural Laplace to learn diverse classes of SDE, both from a theoretical and a practical point of view.
Authors: Juncheng Liu, Chenghao Liu, Gerald Woo, Yiwei Wang, Bryan Hooi, Caiming Xiong, Doyen Sahoo
Abstract: Transformer-based models have emerged as powerful tools for multivariate time series forecasting (MTSF). However, existing Transformer models often fall short of capturing both intricate dependencies across variate and temporal dimensions in MTS data. Some recent models are proposed to separately capture variate and temporal dependencies through either two sequential or parallel attention mechanisms. However, these methods cannot directly and explicitly learn the intricate inter-series and intra-series dependencies. In this work, we first demonstrate that these dependencies are very important as they usually exist in real-world data. To directly model these dependencies, we propose a transformer-based model UniTST containing a unified attention mechanism on the flattened patch tokens. Additionally, we add a dispatcher module which reduces the complexity and makes the model feasible for a potentially large number of variates. Although our proposed model employs a simple architecture, it offers compelling performance as shown in our extensive experiments on several datasets for time series forecasting.
Authors: Nikolaos Tsilivis, Natalie Frank, Nathan Srebro, Julia Kempe
Abstract: We study the implicit bias of optimization in robust empirical risk minimization (robust ERM) and its connection with robust generalization. In classification settings under adversarial perturbations with linear models, we study what type of regularization should ideally be applied for a given perturbation set to improve (robust) generalization. We then show that the implicit bias of optimization in robust ERM can significantly affect the robustness of the model and identify two ways this can happen; either through the optimization algorithm or the architecture. We verify our predictions in simulations with synthetic data and experimentally study the importance of implicit bias in robust ERM with deep neural networks.
Authors: Feiyang Wang, Xingquan Zuo, Hai Huang, Gang Chen
Abstract: Many machine learning models are susceptible to adversarial attacks, with decision-based black-box attacks representing the most critical threat in real-world applications. These attacks are extremely stealthy, generating adversarial examples using hard labels obtained from the target machine learning model. This is typically realized by optimizing perturbation directions, guided by decision boundaries identified through query-intensive exact search, significantly limiting the attack success rate. This paper introduces a novel approach using the Approximation Decision Boundary (ADB) to efficiently and accurately compare perturbation directions without precisely determining decision boundaries. The effectiveness of our ADB approach (ADBA) hinges on promptly identifying suitable ADB, ensuring reliable differentiation of all perturbation directions. For this purpose, we analyze the probability distribution of decision boundaries, confirming that using the distribution's median value as ADB can effectively distinguish different perturbation directions, giving rise to the development of the ADBA-md algorithm. ADBA-md only requires four queries on average to differentiate any pair of perturbation directions, which is highly query-efficient. Extensive experiments on six well-known image classifiers clearly demonstrate the superiority of ADBA and ADBA-md over multiple state-of-the-art black-box attacks.
Authors: Jingyuan Wang, Perry Dong, Ying Jin, Ruohan Zhan, Zhengyuan Zhou
Abstract: Ranking algorithms are fundamental to various online platforms across e-commerce sites to content streaming services. Our research addresses the challenge of adaptively ranking items from a candidate pool for heterogeneous users, a key component in personalizing user experience. We develop a user response model that considers diverse user preferences and the varying effects of item positions, aiming to optimize overall user satisfaction with the ranked list. We frame this problem within a contextual bandits framework, with each ranked list as an action. Our approach incorporates an upper confidence bound to adjust predicted user satisfaction scores and selects the ranking action that maximizes these adjusted scores, efficiently solved via maximum weight imperfect matching. We demonstrate that our algorithm achieves a cumulative regret bound of $O(d\sqrt{NKT})$ for ranking $K$ out of $N$ items in a $d$-dimensional context space over $T$ rounds, under the assumption that user responses follow a generalized linear model. This regret alleviates dependence on the ambient action space, whose cardinality grows exponentially with $N$ and $K$ (thus rendering direct application of existing adaptive learning algorithms -- such as UCB or Thompson sampling -- infeasible). Experiments conducted on both simulated and real-world datasets demonstrate our algorithm outperforms the baseline.
Authors: Tim Weiland, Marvin Pf\"ortner, Philipp Hennig
Abstract: Modeling real-world problems with partial differential equations (PDEs) is a prominent topic in scientific machine learning. Classic solvers for this task continue to play a central role, e.g. to generate training data for deep learning analogues. Any such numerical solution is subject to multiple sources of uncertainty, both from limited computational resources and limited data (including unknown parameters). Gaussian process analogues to classic PDE simulation methods have recently emerged as a framework to construct fully probabilistic estimates of all these types of uncertainty. So far, much of this work focused on theoretical foundations, and as such is not particularly data efficient or scalable. Here we propose a framework combining a discretization scheme based on the popular Finite Volume Method with complementary numerical linear algebra techniques. Practical experiments, including a spatiotemporal tsunami simulation, demonstrate substantially improved scaling behavior of this approach over previous collocation-based techniques.
Authors: Jamie Lohoff, Emre Neftci
Abstract: Computing Jacobians with automatic differentiation is ubiquitous in many scientific domains such as machine learning, computational fluid dynamics, robotics and finance. Even small savings in the number of computations or memory usage in Jacobian computations can already incur massive savings in energy consumption and runtime. While there exist many methods that allow for such savings, they generally trade computational efficiency for approximations of the exact Jacobian. In this paper, we present a novel method to optimize the number of necessary multiplications for Jacobian computation by leveraging deep reinforcement learning (RL) and a concept called cross-country elimination while still computing the exact Jacobian. Cross-country elimination is a framework for automatic differentiation that phrases Jacobian accumulation as ordered elimination of all vertices on the computational graph where every elimination incurs a certain computational cost. We formulate the search for the optimal elimination order that minimizes the number of necessary multiplications as a single player game which is played by an RL agent. We demonstrate that this method achieves up to 33% improvements over state-of-the-art methods on several relevant tasks taken from diverse domains. Furthermore, we show that these theoretical gains translate into actual runtime improvements by providing a cross-country elimination interpreter in JAX that can efficiently execute the obtained elimination orders.
Authors: Si Yi Meng, Antonio Orvieto, Daniel Yiming Cao, Christopher De Sa
Abstract: We study gradient descent (GD) dynamics on logistic regression problems with large, constant step sizes. For linearly-separable data, it is known that GD converges to the minimizer with arbitrarily large step sizes, a property which no longer holds when the problem is not separable. In fact, the behaviour can be much more complex -- a sequence of period-doubling bifurcations begins at the critical step size $2/\lambda$, where $\lambda$ is the largest eigenvalue of the Hessian at the solution. Using a smaller-than-critical step size guarantees convergence if initialized nearby the solution: but does this suffice globally? In one dimension, we show that a step size less than $1/\lambda$ suffices for global convergence. However, for all step sizes between $1/\lambda$ and the critical step size $2/\lambda$, one can construct a dataset such that GD converges to a stable cycle. In higher dimensions, this is actually possible even for step sizes less than $1/\lambda$. Our results show that although local convergence is guaranteed for all step sizes less than the critical step size, global convergence is not, and GD may instead converge to a cycle depending on the initialization.
Authors: Ninghui Feng, Songning Lai, Fobao Zhou, Zhenxiao Yin, Hang Zhao
Abstract: Time series forecasting has become an increasingly popular research area due to its critical applications in various real-world domains such as traffic management, weather prediction, and financial analysis. Despite significant advancements, existing models face notable challenges, including the necessity of manual hyperparameter tuning for different datasets, and difficulty in effectively distinguishing signal from redundant features in data characterized by strong seasonality. These issues hinder the generalization and practical application of time series forecasting models. To solve this issues, we propose an innovative time series forecasting model TimeSieve designed to address these challenges. Our approach employs wavelet transforms to preprocess time series data, effectively capturing multi-scale features without the need for additional parameters or manual hyperparameter tuning. Additionally, we introduce the information bottleneck theory that filters out redundant features from both detail and approximation coefficients, retaining only the most predictive information. This combination reduces significantly improves the model's accuracy. Extensive experiments demonstrate that our model outperforms existing state-of-the-art methods on 70\% of the datasets, achieving higher predictive accuracy and better generalization across diverse datasets. Our results validate the effectiveness of our approach in addressing the key challenges in time series forecasting, paving the way for more reliable and efficient predictive models in practical applications. The code for our model is available at https://github.com/xll0328/TimeSieve.
Authors: Maude Lizaire, Michael Rizvi-Martel, Marawan Gamal Abdel Hameed, Guillaume Rabusseau
Abstract: Second-order Recurrent Neural Networks (2RNNs) extend RNNs by leveraging second-order interactions for sequence modelling. These models are provably more expressive than their first-order counterparts and have connections to well-studied models from formal language theory. However, their large parameter tensor makes computations intractable. To circumvent this issue, one approach known as MIRNN consists in limiting the type of interactions used by the model. Another is to leverage tensor decomposition to diminish the parameter count. In this work, we study the model resulting from parameterizing 2RNNs using the CP decomposition, which we call CPRNN. Intuitively, the rank of the decomposition should reduce expressivity. We analyze how rank and hidden size affect model capacity and show the relationships between RNNs, 2RNNs, MIRNNs, and CPRNNs based on these parameters. We support these results empirically with experiments on the Penn Treebank dataset which demonstrate that, with a fixed parameter budget, CPRNNs outperforms RNNs, 2RNNs, and MIRNNs with the right choice of rank and hidden size.
Authors: Nachiket Kotalwar, Alkis Gotovos, Adish Singla
Abstract: Generative AI and large language models hold great promise in enhancing programming education by generating individualized feedback and hints for learners. Recent works have primarily focused on improving the quality of generated feedback to achieve human tutors' quality. While quality is an important performance criterion, it is not the only criterion to optimize for real-world educational deployments. In this paper, we benchmark language models for programming feedback generation across several performance criteria, including quality, cost, time, and data privacy. The key idea is to leverage recent advances in the new paradigm of in-browser inference that allow running these models directly in the browser, thereby providing direct benefits across cost and data privacy. To boost the feedback quality of small models compatible with in-browser inference engines, we develop a fine-tuning pipeline based on GPT-4 generated synthetic data. We showcase the efficacy of fine-tuned Llama3-8B and Phi3-3.8B 4-bit quantized models using WebLLM's in-browser inference engine on three different Python programming datasets. We will release the full implementation along with a web app and datasets to facilitate further research on in-browser language models.
Authors: Subhojyoti Mukherjee, Josiah P. Hanna, Qiaomin Xie, Robert Nowak
Abstract: In this paper, we study multi-task structured bandit problem where the goal is to learn a near-optimal algorithm that minimizes cumulative regret. The tasks share a common structure and the algorithm exploits the shared structure to minimize the cumulative regret for an unseen but related test task. We use a transformer as a decision-making algorithm to learn this shared structure so as to generalize to the test task. The prior work of pretrained decision transformers like DPT requires access to the optimal action during training which may be hard in several scenarios. Diverging from these works, our learning algorithm does not need the knowledge of optimal action per task during training but predicts a reward vector for each of the actions using only the observed offline data from the diverse training tasks. Finally, during inference time, it selects action using the reward predictions employing various exploration strategies in-context for an unseen test task. Our model outperforms other SOTA methods like DPT, and Algorithmic Distillation over a series of experiments on several structured bandit problems (linear, bilinear, latent, non-linear). Interestingly, we show that our algorithm, without the knowledge of the underlying problem structure, can learn a near-optimal policy in-context by leveraging the shared structure across diverse tasks. We further extend the field of pre-trained decision transformers by showing that they can leverage unseen tasks with new actions and still learn the underlying latent structure to derive a near-optimal policy. We validate this over several experiments to show that our proposed solution is very general and has wide applications to potentially emergent online and offline strategies at test time. Finally, we theoretically analyze the performance of our algorithm and obtain generalization bounds in the in-context multi-task learning setting.
Authors: Emilia Magnani, Marvin Pf\"ortner, Tobias Weber, Philipp Hennig
Abstract: Modeling dynamical systems, e.g. in climate and engineering sciences, often necessitates solving partial differential equations. Neural operators are deep neural networks designed to learn nontrivial solution operators of such differential equations from data. As for all statistical models, the predictions of these models are imperfect and exhibit errors. Such errors are particularly difficult to spot in the complex nonlinear behaviour of dynamical systems. We introduce a new framework for approximate Bayesian uncertainty quantification in neural operators using function-valued Gaussian processes. Our approach can be interpreted as a probabilistic analogue of the concept of currying from functional programming and provides a practical yet theoretically sound way to apply the linearized Laplace approximation to neural operators. In a case study on Fourier neural operators, we show that, even for a discretized input, our method yields a Gaussian closure--a structured Gaussian process posterior capturing the uncertainty in the output function of the neural operator, which can be evaluated at an arbitrary set of points. The method adds minimal prediction overhead, can be applied post-hoc without retraining the neural operator, and scales to large models and datasets. We showcase the efficacy of our approach through applications to different types of partial differential equations.
Authors: Difan Deng, Marius Lindauer
Abstract: The rapid development of time series forecasting research has brought many deep learning-based modules in this field. However, despite the increasing amount of new forecasting architectures, it is still unclear if we have leveraged the full potential of these existing modules within a properly designed architecture. In this work, we propose a novel hierarchical neural architecture search approach for time series forecasting tasks. With the design of a hierarchical search space, we incorporate many architecture types designed for forecasting tasks and allow for the efficient combination of different forecasting architecture modules. Results on long-term-time-series-forecasting tasks show that our approach can search for lightweight high-performing forecasting architectures across different forecasting tasks.
Authors: Thomas Decker, Ananta R. Bhattarai, Jindong Gu, Volker Tresp, Florian Buettner
Abstract: Using feature attributions for post-hoc explanations is a common practice to understand and verify the predictions of opaque machine learning models. Despite the numerous techniques available, individual methods often produce inconsistent and unstable results, putting their overall reliability into question. In this work, we aim to systematically improve the quality of feature attributions by combining multiple explanations across distinct methods or their variations. For this purpose, we propose a novel approach to derive optimal convex combinations of feature attributions that yield provable improvements of desired quality criteria such as robustness or faithfulness to the model behavior. Through extensive experiments involving various model architectures and popular feature attribution techniques, we demonstrate that our combination strategy consistently outperforms individual methods and existing baselines.
Authors: Yu Wang, Ryan A. Rossi, Namyong Park, Huiyuan Chen, Nesreen K. Ahmed, Puja Trivedi, Franck Dernoncourt, Danai Koutra, Tyler Derr
Abstract: Large Generative Models (LGMs) such as GPT, Stable Diffusion, Sora, and Suno are trained on a huge amount of language corpus, images, videos, and audio that are extremely diverse from numerous domains. This training paradigm over diverse well-curated data lies at the heart of generating creative and sensible content. However, all previous graph generative models (e.g., GraphRNN, MDVAE, MoFlow, GDSS, and DiGress) have been trained only on one dataset each time, which cannot replicate the revolutionary success achieved by LGMs in other fields. To remedy this crucial gap, we propose a new class of graph generative model called Large Graph Generative Model (LGGM) that is trained on a large corpus of graphs (over 5000 graphs) from 13 different domains. We empirically demonstrate that the pre-trained LGGM has superior zero-shot generative capability to existing graph generative models. Furthermore, our pre-trained LGGM can be easily fine-tuned with graphs from target domains and demonstrate even better performance than those directly trained from scratch, behaving as a solid starting point for real-world customization. Inspired by Stable Diffusion, we further equip LGGM with the capability to generate graphs given text prompts (Text-to-Graph), such as the description of the network name and domain (i.e., "The power-1138-bus graph represents a network of buses in a power distribution system."), and network statistics (i.e., "The graph has a low average degree, suitable for modeling social media interactions."). This Text-to-Graph capability integrates the extensive world knowledge in the underlying language model, offering users fine-grained control of the generated graphs. We release the code, the model checkpoint, and the datasets at https://lggm-lg.github.io/.
Authors: Sandesh Kamath, Albin Soutif-Cormerais, Joost van de Weijer, Bogdan Raducanu
Abstract: Recent research identified a temporary performance drop on previously learned tasks when transitioning to a new one. This drop is called the stability gap and has great consequences for continual learning: it complicates the direct employment of continually learning since the worse-case performance at task-boundaries is dramatic, it limits its potential as an energy-efficient training paradigm, and finally, the stability drop could result in a reduced final performance of the algorithm. In this paper, we show that the stability gap also occurs when applying joint incremental training of homogeneous tasks. In this scenario, the learner continues training on the same data distribution and has access to all data from previous tasks. In addition, we show that in this scenario, there exists a low-loss linear path to the next minima, but that SGD optimization does not choose this path. We perform further analysis including a finer batch-wise analysis which could provide insights towards potential solution directions.
Authors: Taha Entesari, Sina Sharifi, Mahyar Fazlyab
Abstract: A key challenge that threatens the widespread use of neural networks in safety-critical applications is their vulnerability to adversarial attacks. In this paper, we study the second-order behavior of continuously differentiable deep neural networks, focusing on robustness against adversarial perturbations. First, we provide a theoretical analysis of robustness and attack certificates for deep classifiers by leveraging local gradients and upper bounds on the second derivative (curvature constant). Next, we introduce a novel algorithm to analytically compute provable upper bounds on the second derivative of neural networks. This algorithm leverages the compositional structure of the model to propagate the curvature bound layer-by-layer, giving rise to a scalable and modular approach. The proposed bound can serve as a differentiable regularizer to control the curvature of neural networks during training, thereby enhancing robustness. Finally, we demonstrate the efficacy of our method on classification tasks using the MNIST and CIFAR-10 datasets.
Authors: Frederik Baucks, Robin Schmucker, Conrad Borchers, Zachary A. Pardos, Laurenz Wiskott
Abstract: Curriculum Analytics (CA) studies curriculum structure and student data to ensure the quality of educational programs. One desirable property of courses within curricula is that they are not unexpectedly more difficult for students of different backgrounds. While prior work points to likely variations in course difficulty across student groups, robust methodologies for capturing such variations are scarce, and existing approaches do not adequately decouple course-specific difficulty from students' general performance levels. The present study introduces Differential Course Functioning (DCF) as an Item Response Theory (IRT)-based CA methodology. DCF controls for student performance levels and examines whether significant differences exist in how distinct student groups succeed in a given course. Leveraging data from over 20,000 students at a large public university, we demonstrate DCF's ability to detect inequities in undergraduate course difficulty across student groups described by grade achievement. We compare major pairs with high co-enrollment and transfer students to their non-transfer peers. For the former, our findings suggest a link between DCF effect sizes and the alignment of course content to student home department motivating interventions targeted towards improving course preparedness. For the latter, results suggest minor variations in course-specific difficulty between transfer and non-transfer students. While this is desirable, it also suggests that interventions targeted toward mitigating grade achievement gaps in transfer students should encompass comprehensive support beyond enhancing preparedness for individual courses. By providing more nuanced and equitable assessments of academic performance and difficulties experienced by diverse student populations, DCF could support policymakers, course articulation officers, and student advisors.
Authors: Manjie Xu, Chenxing Li, Duzhen zhang, Dan Su, Wei Liang, Dong Yu
Abstract: Audio editing involves the arbitrary manipulation of audio content through precise control. Although text-guided diffusion models have made significant advancements in text-to-audio generation, they still face challenges in finding a flexible and precise way to modify target events within an audio track. We present a novel approach, referred to as PPAE, which serves as a general module for diffusion models and enables precise audio editing. The editing is based on the input textual prompt only and is entirely training-free. We exploit the cross-attention maps of diffusion models to facilitate accurate local editing and employ a hierarchical local-global pipeline to ensure a smoother editing process. Experimental results highlight the effectiveness of our method in various editing tasks.
Authors: Isaac YL Lee, Thanh Nguyen-Duc, Ryo Ueno, Jesse Smith, Peter Y Chan
Abstract: Excessive caregiver workload in hospital nurses has been implicated in poorer patient care and increased worker burnout. Measurement of this workload in the Intensive Care Unit (ICU) is often done using the Nursing Activities Score (NAS), but this is usually recorded manually and sporadically. Previous work has made use of Ambient Intelligence (AmI) by using computer vision to passively derive caregiver-patient interaction times to monitor staff workload. In this letter, we propose using a Multiscale Vision Transformer (MViT) to passively predict the NAS from low-resolution thermal videos recorded in an ICU. 458 videos were obtained from an ICU in Melbourne, Australia and used to train a MViTv2 model using an indirect prediction and a direct prediction method. The indirect method predicted 1 of 8 potentially identifiable NAS activities from the video before inferring the NAS. The direct method predicted the NAS score immediately from the video. The indirect method yielded an average 5-fold accuracy of 57.21%, an area under the receiver operating characteristic curve (ROC AUC) of 0.865, a F1 score of 0.570 and a mean squared error (MSE) of 28.16. The direct method yielded a MSE of 18.16. We also showed that the MViTv2 outperforms similar models such as R(2+1)D and ResNet50-LSTM under identical settings. This study shows the feasibility of using a MViTv2 to passively predict the NAS in an ICU and monitor staff workload automatically. Our results above also show an increased accuracy in predicting NAS directly versus predicting NAS indirectly. We hope that our study can provide a direction for future work and further improve the accuracy of passive NAS monitoring.
Authors: Shengyu Chen, Peyman Givi, Can Zheng, Xiaowei Jia
Abstract: The precise simulation of turbulent flows is of immense importance in a variety of scientific and engineering fields, including climate science, freshwater science, and the development of energy-efficient manufacturing processes. Within the realm of turbulent flow simulation, direct numerical simulation (DNS) is widely considered to be the most reliable approach, but it is prohibitively expensive for long-term simulation at fine spatial scales. Given the pressing need for efficient simulation, there is an increasing interest in building machine learning models for turbulence, either by reconstructing DNS from alternative low-fidelity simulations or by predicting DNS based on the patterns learned from historical data. However, standard machine learning techniques remain limited in capturing complex spatio-temporal characteristics of turbulent flows, resulting in limited performance and generalizability. This paper presents a novel physics-enhanced neural operator (PENO) that incorporates physical knowledge of partial differential equations (PDEs) to accurately model flow dynamics. The model is further refined by a self-augmentation mechanism to reduce the accumulated error in long-term simulations. The proposed method is evaluated through its performance on two distinct sets of 3D turbulent flow data, showcasing the model's capability to reconstruct high-resolution DNS data, maintain the inherent physical properties of flow transport, and generate flow simulations across various resolutions. Additionally, experimental results on multiple 2D vorticity flow series, generated by different PDEs, highlight the transferability and generalizability of the proposed method. This confirms its applicability to a wide range of real-world scenarios in which extensive simulations are needed under diverse settings.
Authors: Tejaswini Pedapati, Amit Dhurandhar, Soumya Ghosh, Soham Dan, Prasanna Sattigeri
Abstract: Estimating uncertainty or confidence in the responses of a model can be significant in evaluating trust not only in the responses, but also in the model as a whole. In this paper, we explore the problem of estimating confidence for responses of large language models (LLMs) with simply black-box or query access to them. We propose a simple and extensible framework where, we engineer novel features and train a (interpretable) model (viz. logistic regression) on these features to estimate the confidence. We empirically demonstrate that our simple framework is effective in estimating confidence of flan-ul2, llama-13b and mistral-7b with it consistently outperforming existing black-box confidence estimation approaches on benchmark datasets such as TriviaQA, SQuAD, CoQA and Natural Questions by even over $10\%$ (on AUROC) in some cases. Additionally, our interpretable approach provides insight into features that are predictive of confidence, leading to the interesting and useful discovery that our confidence models built for one LLM generalize zero-shot across others on a given dataset.
Authors: Yuantong Li, Guang Cheng, Xiaowu Dai
Abstract: Recommender systems play a crucial role in internet economies by connecting users with relevant products or services. However, designing effective recommender systems faces two key challenges: (1) the exploration-exploitation tradeoff in balancing new product exploration against exploiting known preferences, and (2) dynamic incentive compatibility in accounting for users' self-interested behaviors and heterogeneous preferences. This paper formalizes these challenges into a Dynamic Bayesian Incentive-Compatible Recommendation Protocol (DBICRP). To address the DBICRP, we propose a two-stage algorithm (RCB) that integrates incentivized exploration with an efficient offline learning component for exploitation. In the first stage, our algorithm explores available products while maintaining dynamic incentive compatibility to determine sufficient sample sizes. The second stage employs inverse proportional gap sampling integrated with an arbitrary machine learning method to ensure sublinear regret. Theoretically, we prove that RCB achieves $O(\sqrt{KdT})$ regret and satisfies Bayesian incentive compatibility (BIC) under a Gaussian prior assumption. Empirically, we validate RCB's strong incentive gain, sublinear regret, and robustness through simulations and a real-world application on personalized warfarin dosing. Our work provides a principled approach for incentive-aware recommendation in online preference learning settings.
Authors: Ruiwen Ding, Kha-Dinh Luong, Erika Rodriguez, Ana Cristina Araujo Lemos da Silva, William Hsu
Abstract: In computational pathology, extracting spatial features from gigapixel whole slide images (WSIs) is a fundamental task, but due to their large size, WSIs are typically segmented into smaller tiles. A critical aspect of this analysis is aggregating information from these tiles to make predictions at the WSI level. We introduce a model that combines a message-passing graph neural network (GNN) with a state space model (Mamba) to capture both local and global spatial relationships among the tiles in WSIs. The model's effectiveness was demonstrated in predicting progression-free survival among patients with early-stage lung adenocarcinomas (LUAD). We compared the model with other state-of-the-art methods for tile-level information aggregation in WSIs, including tile-level information summary statistics-based aggregation, multiple instance learning (MIL)-based aggregation, GNN-based aggregation, and GNN-transformer-based aggregation. Additional experiments showed the impact of different types of node features and different tile sampling strategies on the model performance. This work can be easily extended to any WSI-based analysis. Code: https://github.com/rina-ding/gat-mamba.
Authors: J. T. Fry, Aobo Li, Lindley Winslow, Xinyi Hope Fu, Zhenghao Fu, Kaliroe M. W. Pappas
Abstract: Dark matter makes up approximately 85% of total matter in our universe, yet it has never been directly observed in any laboratory on Earth. The origin of dark matter is one of the most important questions in contemporary physics, and a convincing detection of dark matter would be a Nobel-Prize-level breakthrough in fundamental science. The ABRACADABRA experiment was specifically designed to search for dark matter. Although it has not yet made a discovery, ABRACADABRA has produced several dark matter search results widely endorsed by the physics community. The experiment generates ultra-long time-series data at a rate of 10 million samples per second, where the dark matter signal would manifest itself as a sinusoidal oscillation mode within the ultra-long time series. In this paper, we present the TIDMAD -- a comprehensive data release from the ABRACADABRA experiment including three key components: an ultra-long time series dataset divided into training, validation, and science subsets; a carefully-designed denoising score for direct model benchmarking; and a complete analysis framework which produces a community-standard dark matter search result suitable for publication as a physics paper. This data release enables core AI algorithms to extract the signal and produce real physics results thereby advancing fundamental science. The data downloading and associated analysis scripts are available at https://github.com/jessicafry/TIDMAD
Authors: Jiahui Wu, Vanessa Frias-Martinez
Abstract: Deep learning crime predictive tools use past crime data and additional behavioral datasets to forecast future crimes. Nevertheless, these tools have been shown to suffer from unfair predictions across minority racial and ethnic groups. Current approaches to address this unfairness generally propose either pre-processing methods that mitigate the bias in the training datasets by applying corrections to crime counts based on domain knowledge or in-processing methods that are implemented as fairness regularizers to optimize for both accuracy and fairness. In this paper, we propose a novel deep learning architecture that combines the power of these two approaches to increase prediction fairness. Our results show that the proposed model improves the fairness of crime predictions when compared to models with in-processing de-biasing approaches and with models without any type of bias correction, albeit at the cost of reducing accuracy.
Authors: Maximilian Balluff, Peter Mandl, Christian Wolff
Abstract: Cover songs are alternate versions of a song by a different artist. Long being a vital part of the music industry, cover songs significantly influence music culture and are commonly heard in public venues. The rise of online music platforms has further increased their prevalence, often as background music or video soundtracks. While current automatic identification methods serve adequately for original songs, they are less effective with cover songs, primarily because cover versions often significantly deviate from the original compositions. In this paper, we propose a novel method for cover song detection that utilizes the lyrics of a song. We introduce a new dataset for cover songs and their corresponding originals. The dataset contains 5078 cover songs and 2828 original songs. In contrast to other cover song datasets, it contains the annotated lyrics for the original song and the cover song. We evaluate our method on this dataset and compare it with multiple baseline approaches. Our results show that our method outperforms the baseline approaches.
Authors: Nina Horat, Sina Klerings, Sebastian Lerch
Abstract: Weather forecasts from numerical weather prediction models play a central role in solar energy forecasting, where a cascade of physics-based models is used in a model chain approach to convert forecasts of solar irradiance to solar power production, using additional weather variables as auxiliary information. Ensemble weather forecasts aim to quantify uncertainty in the future development of the weather, and can be used to propagate this uncertainty through the model chain to generate probabilistic solar energy predictions. However, ensemble prediction systems are known to exhibit systematic errors, and thus require post-processing to obtain accurate and reliable probabilistic forecasts. The overarching aim of our study is to systematically evaluate different strategies to apply post-processing methods in model chain approaches: Not applying any post-processing at all; post-processing only the irradiance predictions before the conversion; post-processing only the solar power predictions obtained from the model chain; or applying post-processing in both steps. In a case study based on a benchmark dataset for the Jacumba solar plant in the U.S., we develop statistical and machine learning methods for post-processing ensemble predictions of global horizontal irradiance and solar power generation. Further, we propose a neural network-based model for direct solar power forecasting that bypasses the model chain. Our results indicate that post-processing substantially improves the solar power generation forecasts, in particular when post-processing is applied to the power predictions. The machine learning methods for post-processing yield slightly better probabilistic forecasts, and the direct forecasting approach performs comparable to the post-processing strategies.
Authors: Sergio Casas, Ben Agro, Jiageng Mao, Thomas Gilles, Alexander Cui, Thomas Li, Raquel Urtasun
Abstract: The tasks of object detection and trajectory forecasting play a crucial role in understanding the scene for autonomous driving. These tasks are typically executed in a cascading manner, making them prone to compounding errors. Furthermore, there is usually a very thin interface between the two tasks, creating a lossy information bottleneck. To address these challenges, our approach formulates the union of the two tasks as a trajectory refinement problem, where the first pose is the detection (current time), and the subsequent poses are the waypoints of the multiple forecasts (future time). To tackle this unified task, we design a refinement transformer that infers the presence, pose, and multi-modal future behaviors of objects directly from LiDAR point clouds and high-definition maps. We call this model DeTra, short for object Detection and Trajectory forecasting. In our experiments, we observe that \ourmodel{} outperforms the state-of-the-art on Argoverse 2 Sensor and Waymo Open Dataset by a large margin, across a broad range of metrics. Last but not least, we perform extensive ablation studies that show the value of refinement for this task, that every proposed component contributes positively to its performance, and that key design choices were made.
Authors: Benjamin Parlier, Lou Sala\"un, Hong Yang
Abstract: We develop a graph neural network (GNN) to compute, within a time budget of 1 to 2 milliseconds required by practical systems, the optimal linear precoder (OLP) maximizing the minimal downlink user data rate for a Cell-Free Massive MIMO system - a key 6G wireless technology. The state-of-the-art method is a bisection search on second order cone programming feasibility test (B-SOCP) which is a magnitude too slow for practical systems. Our approach relies on representing OLP as a node-level prediction task on a graph. We construct a graph that accurately captures the interdependence relation between access points (APs) and user equipments (UEs), and the permutation equivariance of the Max-Min problem. Our neural network, named OLP-GNN, is trained on data obtained by B-SOCP. We tailor the OLP-GNN size, together with several artful data preprocessing and postprocessing methods to meet the runtime requirement. We show by extensive simulations that it achieves near optimal spectral efficiency in a range of scenarios with different number of APs and UEs, and for both line-of-sight and non-line-of-sight radio propagation environments.
Authors: Alexander Kovrigin, Aleksandra Eliseeva, Yaroslav Zharov, Timofey Bryksin
Abstract: Recent advancements in code-fluent Large Language Models (LLMs) enabled the research on repository-level code editing. In such tasks, the model navigates and modifies the entire codebase of a project according to request. Hence, such tasks require efficient context retrieval, i.e., navigating vast codebases to gather relevant context. Despite the recognized importance of context retrieval, existing studies tend to approach repository-level coding tasks in an end-to-end manner, rendering the impact of individual components within these complicated systems unclear. In this work, we decouple the task of context retrieval from the other components of the repository-level code editing pipelines. We lay the groundwork to define the strengths and weaknesses of this component and the role that reasoning plays in it by conducting experiments that focus solely on context retrieval. We conclude that while the reasoning helps to improve the precision of the gathered context, it still lacks the ability to identify its sufficiency. We also outline the ultimate role of the specialized tools in the process of context gathering. The code supplementing this paper is available at https://github.com/JetBrains-Research/ai-agents-code-editing.
URLs: https://github.com/JetBrains-Research/ai-agents-code-editing.
Authors: Tianrong Zhang, Zhaohan Xi, Ting Wang, Prasenjit Mitra, Jinghui Chen
Abstract: Pre-trained language models (PLMs) have attracted enormous attention over the past few years with their unparalleled performances. Meanwhile, the soaring cost to train PLMs as well as their amazing generalizability have jointly contributed to few-shot fine-tuning and prompting as the most popular training paradigms for natural language processing (NLP) models. Nevertheless, existing studies have shown that these NLP models can be backdoored such that model behavior is manipulated when trigger tokens are presented. In this paper, we propose PromptFix, a novel backdoor mitigation strategy for NLP models via adversarial prompt-tuning in few-shot settings. Unlike existing NLP backdoor removal methods, which rely on accurate trigger inversion and subsequent model fine-tuning, PromptFix keeps the model parameters intact and only utilizes two extra sets of soft tokens which approximate the trigger and counteract it respectively. The use of soft tokens and adversarial optimization eliminates the need to enumerate possible backdoor configurations and enables an adaptive balance between trigger finding and preservation of performance. Experiments with various backdoor attacks validate the effectiveness of the proposed method and the performances when domain shift is present further shows PromptFix's applicability to models pretrained on unknown data source which is the common case in prompt tuning scenarios.
Authors: Xiou Ge, Ali Mousavi, Edouard Grave, Armand Joulin, Kun Qian, Benjamin Han, Mostafa Arefiyan, Yunyao Li
Abstract: Large Language Models (LLMs) have demonstrated impressive capability in different tasks and are bringing transformative changes to many domains. However, keeping the knowledge in LLMs up-to-date remains a challenge once pretraining is complete. It is thus essential to design effective methods to both update obsolete knowledge and induce new knowledge into LLMs. Existing locate-and-edit knowledge editing (KE) method suffers from two limitations. First, the post-edit LLMs by such methods generally have poor capability in answering complex queries that require multi-hop reasoning. Second, the long run-time of such locate-and-edit methods to perform knowledge edits make it infeasible for large scale KE in practice. In this paper, we explore Parameter-Efficient Fine-Tuning (PEFT) techniques as an alternative for KE. We curate a more comprehensive temporal KE dataset with both knowledge update and knowledge injection examples for KE performance benchmarking. We further probe the effect of fine-tuning on a range of layers in an LLM for the multi-hop QA task. We find that PEFT performs better than locate-and-edit techniques for time-sensitive knowledge edits.
Authors: Muhammad Hanif Lashari, Wafa Batayneh, Ashfaq Khokhar
Abstract: Accurately estimating the position of a patient's side robotic arm in real time in a remote surgery task is a significant challenge, particularly in Tactile Internet (TI) environments. This paper presents a Kalman Filter (KF) based computationally efficient position estimation method. The study also assume no prior knowledge of the dynamic system model of the robotic arm system. Instead, The JIGSAW dataset, which is a comprehensive collection of robotic surgical data, and the Master Tool Manipulator's (MTM) input are utilized to learn the system model using System Identification (SI) toolkit available in Matlab. We further investigate the effectiveness of KF to determine the position of the Patient Side Manipulator (PSM) under simulated network conditions that include delays, jitter, and packet loss. These conditions reflect the typical challenges encountered in real-world Tactile Internet applications. The results of the study highlight KF's resilience and effectiveness in achieving accurate state estimation despite network-induced uncertainties with over 90\% estimation accuracy.
Authors: Dujian Ding, Bicheng Xu, Laks V. S. Lakshmanan
Abstract: Image classification is a fundamental building block for a majority of computer vision applications. With the growing popularity and capacity of machine learning models, people can easily access trained image classifiers as a service online or offline. However, model use comes with a cost and classifiers of higher capacity usually incur higher inference costs. To harness the respective strengths of different classifiers, we propose a principled approach, OCCAM, to compute the best classifier assignment strategy over image classification queries (termed as the optimal model portfolio) so that the aggregated accuracy is maximized, under user-specified cost budgets. Our approach uses an unbiased and low-variance accuracy estimator and effectively computes the optimal solution by solving an integer linear programming problem. On a variety of real-world datasets, OCCAM achieves 40% cost reduction with little to no accuracy drop.
Authors: Renjie Liu, Yanxiang Zhang, Yun Zhu, Haicheng Sun, Yuanbo Zhang, Michael Xuelin Huang, Shanqing Cai, Lei Meng, Shumin Zhai
Abstract: The impressive capabilities in Large Language Models (LLMs) provide a powerful approach to reimagine users' typing experience. This paper demonstrates Proofread, a novel Gboard feature powered by a server-side LLM in Gboard, enabling seamless sentence-level and paragraph-level corrections with a single tap. We describe the complete system in this paper, from data generation, metrics design to model tuning and deployment. To obtain models with sufficient quality, we implement a careful data synthetic pipeline tailored to online use cases, design multifaceted metrics, employ a two-stage tuning approach to acquire the dedicated LLM for the feature: the Supervised Fine Tuning (SFT) for foundational quality, followed by the Reinforcement Learning (RL) tuning approach for targeted refinement. Specifically, we find sequential tuning on Rewrite and proofread tasks yields the best quality in SFT stage, and propose global and direct rewards in the RL tuning stage to seek further improvement. Extensive experiments on a human-labeled golden set showed our tuned PaLM2-XS model achieved 85.56\% good ratio. We launched the feature to Pixel 8 devices by serving the model on TPU v5 in Google Cloud, with thousands of daily active users. Serving latency was significantly reduced by quantization, bucket inference, text segmentation, and speculative decoding. Our demo could be seen in \href{https://youtu.be/4ZdcuiwFU7I}{Youtube}.
Authors: Bastian Boll, Daniel Gonzalez-Alvarado, Stefania Petra, Christoph Schn\"orr
Abstract: We introduce a novel generative model for the representation of joint probability distributions of a possibly large number of discrete random variables. The approach uses measure transport by randomized assignment flows on the statistical submanifold of factorizing distributions, which also enables to sample efficiently from the target distribution and to assess the likelihood of unseen data points. The embedding of the flow via the Segre map in the meta-simplex of all discrete joint distributions ensures that any target distribution can be represented in principle, whose complexity in practice only depends on the parametrization of the affinity function of the dynamical assignment flow system. Our model can be trained in a simulation-free manner without integration by conditional Riemannian flow matching, using the training data encoded as geodesics in closed-form with respect to the e-connection of information geometry. By projecting high-dimensional flow matching in the meta-simplex of joint distributions to the submanifold of factorizing distributions, our approach has strong motivation from first principles of modeling coupled discrete variables. Numerical experiments devoted to distributions of structured image labelings demonstrate the applicability to large-scale problems, which may include discrete distributions in other application areas. Performance measures show that our approach scales better with the increasing number of classes than recent related work.
Authors: Abdelrahman Farrag, Mohammed-Khalil Ghali, Yu Jin
Abstract: The evolution of industry has enabled the integration of physical and digital systems, facilitating the collection of extensive data on manufacturing processes. This integration provides a reliable solution for improving process quality and managing equipment health. However, data collected from real manufacturing processes often exhibit challenging properties, such as severe class imbalance, high rates of missing values, and noisy features, which hinder effective machine learning implementation. In this study, a rare class prediction approach is developed for in situ data collected from a smart semiconductor manufacturing process. The primary objective is to build a model that addresses issues of noise and class imbalance, enhancing class separation. The developed approach demonstrated promising results compared to existing literature, which would allow the prediction of new observations that could give insights into future maintenance plans and production quality. The model was evaluated using various performance metrics, with ROC curves showing an AUC of 0.95, a precision of 0.66, and a recall of 0.96
Authors: Sabri Mustafa Kahya, Boran Hamdi Sivrikaya, Muhammet Sami Yavuz, Eckehard Steinbach
Abstract: This paper proposes a short-range FMCW radar-based facial authentication and out-of-distribution (OOD) detection framework. Our pipeline jointly estimates the correct classes for the in-distribution (ID) samples and detects the OOD samples to prevent their inaccurate prediction. Our reconstruction-based architecture consists of a main convolutional block with one encoder and multi-decoder configuration, and intermediate linear encoder-decoder parts. Together, these elements form an accurate human face classifier and a robust OOD detector. For our dataset, gathered using a 60 GHz short-range FMCW radar, our network achieves an average classification accuracy of 98.07% in identifying in-distribution human faces. As an OOD detector, it achieves an average Area Under the Receiver Operating Characteristic (AUROC) curve of 98.50% and an average False Positive Rate at 95% True Positive Rate (FPR95) of 6.20%. Also, our extensive experiments show that the proposed approach outperforms previous OOD detectors in terms of common OOD detection metrics.
Authors: Reyhane Askari Hemmat, Melissa Hall, Alicia Sun, Candace Ross, Michal Drozdzal, Adriana Romero-Soriano
Abstract: With the growing popularity of text-to-image generative models, there has been increasing focus on understanding their risks and biases. Recent work has found that state-of-the-art models struggle to depict everyday objects with the true diversity of the real world and have notable gaps between geographic regions. In this work, we aim to increase the diversity of generated images of common objects such that per-region variations are representative of the real world. We introduce an inference time intervention, contextualized Vendi Score Guidance (c-VSG), that guides the backwards steps of latent diffusion models to increase the diversity of a sample as compared to a "memory bank" of previously generated images while constraining the amount of variation within that of an exemplar set of real-world contextualizing images. We evaluate c-VSG with two geographically representative datasets and find that it substantially increases the diversity of generated images, both for the worst performing regions and on average, while simultaneously maintaining or improving image quality and consistency. Additionally, qualitative analyses reveal that diversity of generated images is significantly improved, including along the lines of reductive region portrayals present in the original model. We hope that this work is a step towards text-to-image generative models that reflect the true geographic diversity of the world.
Authors: Faisal Hamman, Sanghamitra Dutta
Abstract: This paper introduces a novel information-theoretic perspective on the relationship between prominent group fairness notions in machine learning, namely statistical parity, equalized odds, and predictive parity. It is well known that simultaneous satisfiability of these three fairness notions is usually impossible, motivating practitioners to resort to approximate fairness solutions rather than stringent satisfiability of these definitions. However, a comprehensive analysis of their interrelations, particularly when they are not exactly satisfied, remains largely unexplored. Our main contribution lies in elucidating an exact relationship between these three measures of (un)fairness by leveraging a body of work in information theory called partial information decomposition (PID). In this work, we leverage PID to identify the granular regions where these three measures of (un)fairness overlap and where they disagree with each other leading to potential tradeoffs. We also include numerical simulations to complement our results.
Authors: Md Imbesat Hassan Rizvi, Xiaodan Zhu, Iryna Gurevych
Abstract: Spatial reasoning is a crucial component of both biological and artificial intelligence. In this work, we present a comprehensive study of the capability of current state-of-the-art large language models (LLMs) on spatial reasoning. To support our study, we created and contribute a novel Spatial Reasoning Characterization (SpaRC) framework and Spatial Reasoning Paths (SpaRP) datasets, to enable an in-depth understanding of the spatial relations and compositions as well as the usefulness of spatial reasoning chains. We found that all the state-of-the-art LLMs do not perform well on the datasets -- their performances are consistently low across different setups. The spatial reasoning capability improves substantially as model sizes scale up. Finetuning both large language models (e.g., Llama-2-70B) and smaller ones (e.g., Llama-2-13B) can significantly improve their F1-scores by 7--32 absolute points. We also found that the top proprietary LLMs still significantly outperform their open-source counterparts in topological spatial understanding and reasoning.
Authors: Weike Fang, Zhejian Zhou, Junzhou He, Weihang Wang
Abstract: WebAssembly enables near-native execution in web applications and is increasingly adopted for tasks that demand high performance and robust security. However, its assembly-like syntax, implicit stack machine, and low-level data types make it extremely difficult for human developers to understand, spurring the need for effective WebAssembly reverse engineering techniques. In this paper, we propose StackSight, a novel neurosymbolic approach that combines Large Language Models (LLMs) with advanced program analysis to decompile complex WebAssembly code into readable C++ snippets. StackSight visualizes and tracks virtual stack alterations via a static analysis algorithm and then applies chain-of-thought prompting to harness LLM's complex reasoning capabilities. Evaluation results show that StackSight significantly improves WebAssembly decompilation. Our user study also demonstrates that code snippets generated by StackSight have significantly higher win rates and enable a better grasp of code semantics.
Authors: Devyani Maladkar, Ruichen Jiang, Aryan Mokhtari
Abstract: Adaptive gradient methods are arguably the most successful optimization algorithms for neural network training. While it is well-known that adaptive gradient methods can achieve better dimensional dependence than stochastic gradient descent (SGD) under favorable geometry for stochastic convex optimization, the theoretical justification for their success in stochastic non-convex optimization remains elusive. In this paper, we aim to close this gap by analyzing the convergence rates of AdaGrad measured by the $\ell_1$-norm of the gradient. Specifically, when the objective has $L$-Lipschitz gradient and the stochastic gradient variance is bounded by $\sigma^2$, we prove a worst-case convergence rate of $\tilde{\mathcal{O}}(\frac{\sqrt{d}L}{\sqrt{T}} + \frac{\sqrt{d} \sigma}{T^{1/4}})$, where $d$ is the dimension of the problem.We also present a lower bound of ${\Omega}(\frac{\sqrt{d}}{\sqrt{T}})$ for minimizing the gradient $\ell_1$-norm in the deterministic setting, showing the tightness of our upper bound in the noiseless case. Moreover, under more fine-grained assumptions on the smoothness structure of the objective and the gradient noise and under favorable gradient $\ell_1/\ell_2$ geometry, we show that AdaGrad can potentially shave a factor of $\sqrt{d}$ compared to SGD. To the best of our knowledge, this is the first result for adaptive gradient methods that demonstrates a provable gain over SGD in the non-convex setting.
Authors: Jianbo Dong, Bin Luo, Jun Zhang, Pengcheng Zhang, Fei Feng, Yikai Zhu, Ang Liu, Zian Chen, Yi Shi, Hairong Jiao, Gang Lu, Yu Guan, Ennan Zhai, Wencong Xiao, Hanyu Zhao, Man Yuan, Siran Yang, Xiang Li, Jiamang Wang, Rui Men, Jianwei Zhang, Huang Zhong, Dennis Cai, Yuan Xie, Binzhang Fu
Abstract: The emergence of Large Language Models (LLMs) has necessitated the adoption of parallel training techniques, involving the deployment of thousands of GPUs to train a single model. Unfortunately, we have found that the efficiency of current parallel training is often suboptimal, largely due to the following two main issues. Firstly, hardware failures are inevitable, leading to interruptions in the training tasks. The inability to quickly identify the faulty components results in a substantial waste of GPU resources. Secondly, since GPUs must wait for parameter synchronization to complete before proceeding to the next round of computation, network congestions can greatly increase the waiting time for GPUs. To address these challenges, this paper introduces a communication-driven solution, namely the C4. The key insights of C4 are two folds. First, in parallel training, collective communication exhibits periodic and homogeneous characteristics, so any anomalies are certainly due to some form of hardware malfunction. By leveraging this feature, C4 can rapidly identify the faulty components, swiftly isolate the anomaly, and restart the task, thereby avoiding resource wastage caused by delays in anomaly detection. Second, the predictable communication model of collective communication, involving few large flows, allows C4 to efficiently execute traffic planning, substantially reducing network congestion. C4 has been extensively implemented across our production systems, cutting error-induced overhead by roughly 30% and enhancing runtime performance by about 15% for certain applications with moderate communication costs.
Authors: Daniel Yun
Abstract: In this paper, we introduce a novel method for merging the weights of multiple pre-trained neural networks using a genetic algorithm called MeGA. Traditional techniques, such as weight averaging and ensemble methods, often fail to fully harness the capabilities of pre-trained networks. Our approach leverages a genetic algorithm with tournament selection, crossover, and mutation to optimize weight combinations, creating a more effective fusion. This technique allows the merged model to inherit advantageous features from both parent models, resulting in enhanced accuracy and robustness. Through experiments on the CIFAR-10 dataset, we demonstrate that our genetic algorithm-based weight merging method improves test accuracy compared to individual models and conventional methods. This approach provides a scalable solution for integrating multiple pre-trained networks across various deep learning applications. Github is available at: https://github.com/YUNBLAK/MeGA-Merging-Multiple-Independently-Trained-Neural-Networks-Based-on-Genetic-Algorithm
Authors: Vipin V
Abstract: A novel approach for forest fire detection using image processing technique is proposed. A rule-based color model for fire pixel classification is used. The proposed algorithm uses RGB and YCbCr color space. The advantage of using YCbCr color space is that it can separate the luminance from the chrominance more effectively than RGB color space. The performance of the proposed algorithm is tested on two sets of images, one of which contains fire; the other contains fire-like regions. Standard methods are used for calculating the performance of the algorithm. The proposed method has both higher detection rate and lower false alarm rate. Since the algorithm is cheap in computation, it can be used for real-time forest fire detection.
Authors: Diptanu De, Shankhanil Mitra, Rajiv Soundararajan
Abstract: The design of no-reference (NR) image quality assessment (IQA) algorithms is extremely important to benchmark and calibrate user experiences in modern visual systems. A major drawback of state-of-the-art NR-IQA methods is their limited ability to generalize across diverse IQA settings with reasonable distribution shifts. Recent text-to-image generative models such as latent diffusion models generate meaningful visual concepts with fine details related to text concepts. In this work, we leverage the denoising process of such diffusion models for generalized IQA by understanding the degree of alignment between learnable quality-aware text prompts and images. In particular, we learn cross-attention maps from intermediate layers of the denoiser of latent diffusion models to capture quality-aware representations of images. In addition, we also introduce learnable quality-aware text prompts that enable the cross-attention features to be better quality-aware. Our extensive cross database experiments across various user-generated, synthetic, and low-light content-based benchmarking databases show that latent diffusion models can achieve superior generalization in IQA when compared to other methods in the literature.
Authors: Qi Zheng, Chang Yu, Jin Cao, Yongshun Xu, Qianwen Xing, Yinxin Jin
Abstract: With the rise of various online and mobile payment systems, transaction fraud has become a significant threat to financial security. This study explores the application of advanced machine learning models, specifically XGBoost and LightGBM, for developing a more accurate and robust Payment Security Protection Model.To enhance data reliability, we meticulously processed the data sources and used SMOTE (Synthetic Minority Over-sampling Technique) to address class imbalance and improve data representation. By selecting highly correlated features, we aimed to strengthen the training process and boost model performance.We conducted thorough performance evaluations of our proposed models, comparing them against traditional methods including Random Forest, Neural Network, and Logistic Regression. Key metrics such as Precision, Recall, and F1 Score were used to rigorously assess their effectiveness.Our detailed analyses and comparisons reveal that the combination of SMOTE with XGBoost and LightGBM offers a highly efficient and powerful mechanism for payment security protection. The results show that these models not only outperform traditional approaches but also hold significant promise for advancing the field of transaction fraud prevention.
Authors: Jubi Taneja, Avery Laird, Cong Yan, Madan Musuvathi, Shuvendu K. Lahiri
Abstract: Vectorization is a powerful optimization technique that significantly boosts the performance of high performance computing applications operating on large data arrays. Despite decades of research on auto-vectorization, compilers frequently miss opportunities to vectorize code. On the other hand, writing vectorized code manually using compiler intrinsics is still a complex, error-prone task that demands deep knowledge of specific architecture and compilers. In this paper, we evaluate the potential of large-language models (LLMs) to generate vectorized (Single Instruction Multiple Data) code from scalar programs that process individual array elements. We propose a novel finite-state machine multi-agents based approach that harnesses LLMs and test-based feedback to generate vectorized code. Our findings indicate that LLMs are capable of producing high performance vectorized code with run-time speedup ranging from 1.1x to 9.4x as compared to the state-of-the-art compilers such as Intel Compiler, GCC, and Clang. To verify the correctness of vectorized code, we use Alive2, a leading bounded translation validation tool for LLVM IR. We describe a few domain-specific techniques to improve the scalability of Alive2 on our benchmark dataset. Overall, our approach is able to verify 38.2% of vectorizations as correct on the TSVC benchmark dataset.
Authors: Ioannis Mavrothalassitis, Stratis Skoulakis, Leello Tadesse Dadi, Volkan Cevher
Abstract: Given a sequence of functions $f_1,\ldots,f_n$ with $f_i:\mathcal{D}\mapsto \mathbb{R}$, finite-sum minimization seeks a point ${x}^\star \in \mathcal{D}$ minimizing $\sum_{j=1}^n f_j(x)/n$. In this work, we propose a key twist into the finite-sum minimization, dubbed as continual finite-sum minimization, that asks for a sequence of points ${x}_1^\star,\ldots,{x}_n^\star \in \mathcal{D}$ such that each ${x}^\star_i \in \mathcal{D}$ minimizes the prefix-sum $\sum_{j=1}^if_j(x)/i$. Assuming that each prefix-sum is strongly convex, we develop a first-order continual stochastic variance reduction gradient method ($\mathrm{CSVRG}$) producing an $\epsilon$-optimal sequence with $\mathcal{\tilde{O}}(n/\epsilon^{1/3} + 1/\sqrt{\epsilon})$ overall first-order oracles (FO). An FO corresponds to the computation of a single gradient $\nabla f_j(x)$ at a given $x \in \mathcal{D}$ for some $j \in [n]$. Our approach significantly improves upon the $\mathcal{O}(n/\epsilon)$ FOs that $\mathrm{StochasticGradientDescent}$ requires and the $\mathcal{O}(n^2 \log (1/\epsilon))$ FOs that state-of-the-art variance reduction methods such as $\mathrm{Katyusha}$ require. We also prove that there is no natural first-order method with $\mathcal{O}\left(n/\epsilon^\alpha\right)$ gradient complexity for $\alpha < 1/4$, establishing that the first-order complexity of our method is nearly tight.
Authors: Eduard Poesina, Adriana Valentina Costache, Adrian-Gabriel Chifu, Josiane Mothe, Radu Tudor Ionescu
Abstract: Text-to-image generation has recently emerged as a viable alternative to text-to-image retrieval, due to the visually impressive results of generative diffusion models. Although query performance prediction is an active research topic in information retrieval, to the best of our knowledge, there is no prior study that analyzes the difficulty of queries (prompts) in text-to-image generation, based on human judgments. To this end, we introduce the first dataset of prompts which are manually annotated in terms of image generation performance. In order to determine the difficulty of the same prompts in image retrieval, we also collect manual annotations that represent retrieval performance. We thus propose the first benchmark for joint text-to-image prompt and query performance prediction, comprising 10K queries. Our benchmark enables: (i) the comparative assessment of the difficulty of prompts/queries in image generation and image retrieval, and (ii) the evaluation of prompt/query performance predictors addressing both generation and retrieval. We present results with several pre-generation/retrieval and post-generation/retrieval performance predictors, thus providing competitive baselines for future research. Our benchmark and code is publicly available under the CC BY 4.0 license at https://github.com/Eduard6421/PQPP.
Authors: Weiran Lin, Anna Gerchanovsky, Omer Akgul, Lujo Bauer, Matt Fredrikson, Zifan Wang
Abstract: Large language model (LLM) users might rely on others (e.g., prompting services), to write prompts. However, the risks of trusting prompts written by others remain unstudied. In this paper, we assess the risk of using such prompts on brand recommendation tasks when shopping. First, we found that paraphrasing prompts can result in LLMs mentioning given brands with drastically different probabilities, including a pair of prompts where the probability changes by 100%. Next, we developed an approach that can be used to perturb an original base prompt to increase the likelihood that an LLM mentions a given brand. We designed a human-inconspicuous algorithm that perturbs prompts, which empirically forces LLMs to mention strings related to a brand more often, by absolute improvements up to 78.3%. Our results suggest that our perturbed prompts, 1) are inconspicuous to humans, 2) force LLMs to recommend a target brand more often, and 3) increase the perceived chances of picking targeted brands.
Authors: Michelle Espranita Liman, Daniel Rueckert, Florian J. Fintelmann, Philip M\"uller
Abstract: Field-of-view (FOV) recovery of truncated chest CT scans is crucial for accurate body composition analysis, which involves quantifying skeletal muscle and subcutaneous adipose tissue (SAT) on CT slices. This, in turn, enables disease prognostication. Here, we present a method for recovering truncated CT slices using generative image outpainting. We train a diffusion model and apply it to truncated CT slices generated by simulating a small FOV. Our model reliably recovers the truncated anatomy and outperforms the previous state-of-the-art despite being trained on 87% less data.
Authors: Ziyad Benomar, Christian Coester
Abstract: Priority queues are one of the most fundamental and widely used data structures in computer science. Their primary objective is to efficiently support the insertion of new elements with assigned priorities and the extraction of the highest priority element. In this study, we investigate the design of priority queues within the learning-augmented framework, where algorithms use potentially inaccurate predictions to enhance their worst-case performance. We examine three prediction models spanning different use cases, and show how the predictions can be leveraged to enhance the performance of priority queue operations. Moreover, we demonstrate the optimality of our solution and discuss some possible applications.
Authors: Bing Cao, Yinan Xia, Yi Ding, Changqing Zhang, Qinghua Hu
Abstract: Multimodal fusion is crucial in joint decision-making systems for rendering holistic judgments. Since multimodal data changes in open environments, dynamic fusion has emerged and achieved remarkable progress in numerous applications. However, most existing dynamic multimodal fusion methods lack theoretical guarantees and easily fall into suboptimal problems, yielding unreliability and instability. To address this issue, we propose a Predictive Dynamic Fusion (PDF) framework for multimodal learning. We proceed to reveal the multimodal fusion from a generalization perspective and theoretically derive the predictable Collaborative Belief (Co-Belief) with Mono- and Holo-Confidence, which provably reduces the upper bound of generalization error. Accordingly, we further propose a relative calibration strategy to calibrate the predicted Co-Belief for potential uncertainty. Extensive experiments on multiple benchmarks confirm our superiority. Our code is available at https://github.com/Yinan-Xia/PDF.
Authors: Venkata Sai Pranav Bachina, Ankit Gangwal, Aaryan Ajay Sharma, Charu Sharma
Abstract: Graph Neural Networks (GNNs) have advanced the field of machine learning by utilizing graph-structured data, which is ubiquitous in the real world. GNNs have applications in various fields, ranging from social network analysis to drug discovery. GNN training is strenuous, requiring significant computational resources and human expertise. It makes a trained GNN an indispensable Intellectual Property (IP) for its owner. Recent studies have shown GNNs to be vulnerable to model-stealing attacks, which raises concerns over IP rights protection. Watermarking has been shown to be effective at protecting the IP of a GNN model. Existing efforts to develop a watermarking scheme for GNNs have only focused on the node classification and the graph classification tasks. To the best of our knowledge, we introduce the first-ever watermarking scheme for GNNs tailored to the Link Prediction (LP) task. We call our proposed watermarking scheme GENIE (watermarking Graph nEural Networks for lInk prEdiction). We design GENIE using a novel backdoor attack to create a trigger set for two key methods of LP: (1) node representation-based and (2) subgraph-based. In GENIE, the watermark is embedded into the GNN model by training it on both the trigger set and a modified training set, resulting in a watermarked GNN model. To assess a suspect model, we verify the watermark against the trigger set. We extensively evaluate GENIE across 3 model architectures (i.e., SEAL, GCN, and GraphSAGE) and 7 real-world datasets. Furthermore, we validate the robustness of GENIE against 11 state-of-the-art watermark removal techniques and 3 model extraction attacks. We also demonstrate that GENIE is robust against ownership piracy attack. Our ownership demonstration scheme statistically guarantees both False Positive Rate (FPR) and False Negative Rate (FNR) to be less than $10^{-6}$.
Authors: Jason Yoo, Dylan Green, Geoff Pleiss, Frank Wood
Abstract: Diffusion models have shown exceptional capabilities in generating realistic videos. Yet, their training has been predominantly confined to offline environments where models can repeatedly train on i.i.d. data to convergence. This work explores the feasibility of training diffusion models from a semantically continuous video stream, where correlated video frames sequentially arrive one at a time. To investigate this, we introduce two novel continual video generative modeling benchmarks, Lifelong Bouncing Balls and Windows 95 Maze Screensaver, each containing over a million video frames generated from navigating stationary environments. Surprisingly, our experiments show that diffusion models can be effectively trained online using experience replay, achieving performance comparable to models trained with i.i.d. samples given the same number of gradient steps.
Authors: Andr\'es Holgado-S\'anchez, Joaqu\'in Arias, Holger Billhardt, Sascha Ossowski
Abstract: The emerging field of \emph{value awareness engineering} claims that software agents and systems should be value-aware, i.e. they must make decisions in accordance with human values. In this context, such agents must be capable of explicitly reasoning as to how far different courses of action are aligned with these values. For this purpose, values are often modelled as preferences over states or actions, which are then aggregated to determine the sequences of actions that are maximally aligned with a certain value. Recently, additional value admissibility constraints at this level have been considered as well. However, often relaxed versions of these constraints are needed, and this increases considerably the complexity of computing value-aligned policies. To obtain efficient algorithms that make value-aligned decisions considering admissibility relaxation, we propose the use of learning techniques, in particular, we have used constrained reinforcement learning algorithms. In this paper, we present two algorithms, $\epsilon\text{-}ADQL$ for strategies based on local alignment and its extension $\epsilon\text{-}CADQL$ for a sequence of decisions. We have validated their efficiency in a water distribution problem in a drought scenario.
Authors: Rui Ye, Rui Ge, Xinyu Zhu, Jingyi Chai, Yaxin Du, Yang Liu, Yanfeng Wang, Siheng Chen
Abstract: Federated learning has enabled multiple parties to collaboratively train large language models without directly sharing their data (FedLLM). Following this training paradigm, the community has put massive efforts from diverse aspects including framework, performance, and privacy. However, an unpleasant fact is that there are currently no realistic datasets and benchmarks for FedLLM and previous works all rely on artificially constructed datasets, failing to capture properties in real-world scenarios. Addressing this, we propose FedLLM-Bench, which involves 8 training methods, 4 training datasets, and 6 evaluation metrics, to offer a comprehensive testbed for the FedLLM community. FedLLM-Bench encompasses three datasets (e.g., user-annotated multilingual dataset) for federated instruction tuning and one dataset (e.g., user-annotated preference dataset) for federated preference alignment, whose scale of client number ranges from 38 to 747. Our datasets incorporate several representative diversities: language, quality, quantity, instruction, length, embedding, and preference, capturing properties in real-world scenarios. Based on FedLLM-Bench, we conduct experiments on all datasets to benchmark existing FL methods and provide empirical insights (e.g., multilingual collaboration). We believe that our FedLLM-Bench can benefit the FedLLM community by reducing required efforts, providing a practical testbed, and promoting fair comparisons. Code and datasets are available at https://github.com/rui-ye/FedLLM-Bench.
Authors: Abanoub M. Girgis, Alvaro Valcarce, Mehdi Bennis
Abstract: In remote control systems, transmitting large data volumes (e.g. video feeds) from wireless sensors to faraway controllers is challenging when the uplink channel capacity is limited (e.g. RedCap devices or massive wireless sensor networks). Furthermore, the controllers often only need the information-rich components of the original data. To address this, we propose a Time-Series Joint Embedding Predictive Architecture (TS-JEPA) and a semantic actor trained through self-supervised learning. This approach harnesses TS-JEPA's semantic representation power and predictive capabilities by capturing spatio-temporal correlations in the source data. We leverage this to optimize uplink channel utilization, while the semantic actor calculates control commands directly from the encoded representations, rather than from the original data. We test our model through multiple parallel instances of the well-known inverted cart-pole scenario, where the approach is validated through the maximization of stability under constrained uplink channel capacity.
Authors: Vincent Cohen-Addad, Tommaso d'Orsi, Aida Mousavifar
Abstract: We consider the semi-random graph model of [Makarychev, Makarychev and Vijayaraghavan, STOC'12], where, given a random bipartite graph with $\alpha$ edges and an unknown bipartition $(A, B)$ of the vertex set, an adversary can add arbitrary edges inside each community and remove arbitrary edges from the cut $(A, B)$ (i.e. all adversarial changes are \textit{monotone} with respect to the bipartition). For this model, a polynomial time algorithm is known to approximate the Balanced Cut problem up to value $O(\alpha)$ [MMV'12] as long as the cut $(A, B)$ has size $\Omega(\alpha)$. However, it consists of slow subroutines requiring optimal solutions for logarithmically many semidefinite programs. We study the fine-grained complexity of the problem and present the first near-linear time algorithm that achieves similar performances to that of [MMV'12]. Our algorithm runs in time $O(|V(G)|^{1+o(1)} + |E(G)|^{1+o(1)})$ and finds a balanced cut of value $O(\alpha)$. Our approach appears easily extendible to related problem, such as Sparsest Cut, and also yields an near-linear time $O(1)$-approximation to Dagupta's objective function for hierarchical clustering [Dasgupta, STOC'16] for the semi-random hierarchical stochastic block model inputs of [Cohen-Addad, Kanade, Mallmann-Trenn, Mathieu, JACM'19].
Authors: Yuke Xie, Herv\'e Chauris, Nicolas Desassis
Abstract: To obtain high-resolution images of subsurface structures from seismic data, seismic imaging techniques such as Full Waveform Inversion (FWI) serve as crucial tools. However, FWI involves solving a nonlinear and often non-unique inverse problem, presenting challenges such as local minima trapping and inadequate handling of inherent uncertainties. In addressing these challenges, we propose leveraging deep generative models as the prior distribution of geophysical parameters for stochastic Bayesian inversion. This approach integrates the adjoint state gradient for efficient back-propagation from the numerical solution of partial differential equations. Additionally, we introduce explicit and implicit variational Bayesian inference methods. The explicit method computes variational distribution density using a normalizing flow-based neural network, enabling computation of the Bayesian posterior of parameters. Conversely, the implicit method employs an inference network attached to a pretrained generative model to estimate density, incorporating an entropy estimator. Furthermore, we also experimented with the Stein Variational Gradient Descent (SVGD) method as another variational inference technique, using particles. We compare these variational Bayesian inference methods with conventional Markov chain Monte Carlo (McMC) sampling. Each method is able to quantify uncertainties and to generate seismic data-conditioned realizations of subsurface geophysical parameters. This framework provides insights into subsurface structures while accounting for inherent uncertainties.
Authors: Federico Malato, Ville Hautamaki
Abstract: Imitation learning enables autonomous agents to learn from human examples, without the need for a reward signal. Still, if the provided dataset does not encapsulate the task correctly, or when the task is too complex to be modeled, such agents fail to reproduce the expert policy. We propose to recover from these failures through online adaptation. Our approach combines the action proposal coming from a pre-trained policy with relevant experience recorded by an expert. The combination results in an adapted action that closely follows the expert. Our experiments show that an adapted agent performs better than its pure imitation learning counterpart. Notably, adapted agents can achieve reasonable performance even when the base, non-adapted policy catastrophically fails.
Authors: Arvi Jonnarth, Ola Johansson, Michael Felsberg
Abstract: Sim-to-real transfer presents a difficult challenge, where models trained in simulation are to be deployed in the real world. The distribution shift between the two settings leads to biased representations of the perceived real-world environment, and thus to suboptimal predictions. In this work, we tackle the challenge of sim-to-real transfer of reinforcement learning (RL) agents for coverage path planning (CPP). In CPP, the task is for a robot to find a path that visits every point of a confined area. Specifically, we consider the case where the environment is unknown, and the agent needs to plan the path online while mapping the environment. We bridge the sim-to-real gap through a semi-virtual environment with a simulated sensor and obstacles, while including real robot kinematics and real-time aspects. We investigate what level of fine-tuning is needed for adapting to a realistic setting, comparing to an agent trained solely in simulation. We find that a high model inference frequency is sufficient for reducing the sim-to-real gap, while fine-tuning degrades performance initially. By training the model in simulation and deploying it at a high inference frequency, we transfer state-of-the-art results from simulation to the real domain, where direct learning would take in the order of weeks with manual interaction, i.e., would be completely infeasible.
Authors: Micha{\l} Romaszewski, Przemys{\l}aw Seku{\l}a, Przemys{\l}aw G{\l}omb, Micha{\l} Cholewa, Katarzyna Ko{\l}odziej
Abstract: Large Language Models (LLMs) have shown exceptional performance in text processing. Notably, LLMs can synthesize information from large datasets and explain their decisions similarly to human reasoning through a chain of thought (CoT). An emerging application of LLMs is the handling and interpreting of numerical data, where fine-tuning enhances their performance over basic inference methods. This paper proposes a novel approach to training LLMs using knowledge transfer from a random forest (RF) ensemble, leveraging its efficiency and accuracy. By converting RF decision paths into natural language statements, we generate outputs for LLM fine-tuning, enhancing the model's ability to classify and explain its decisions. Our method includes verifying these rules through established classification metrics, ensuring their correctness. We also examine the impact of preprocessing techniques on the representation of numerical data and their influence on classification accuracy and rule correctness
Authors: Ghjulia Sialelli, Torben Peters, Jan D. Wegner, Konrad Schindler
Abstract: Accurate estimates of Above Ground Biomass (AGB) are essential in addressing two of humanity's biggest challenges, climate change and biodiversity loss. Existing datasets for AGB estimation from satellite imagery are limited. Either they focus on specific, local regions at high resolution, or they offer global coverage at low resolution. There is a need for a machine learning-ready, globally representative, high-resolution benchmark. Our findings indicate significant variability in biomass estimates across different vegetation types, emphasizing the necessity for a dataset that accurately captures global diversity. To address these gaps, we introduce a comprehensive new dataset that is globally distributed, covers a range of vegetation types, and spans several years. This dataset combines AGB reference data from the GEDI mission with data from Sentinel-2 and PALSAR-2 imagery. Additionally, it includes pre-processed high-level features such as a dense canopy height map, an elevation map, and a land-cover classification map. We also produce a dense, high-resolution (10m) map of AGB predictions for the entire area covered by the dataset. Rigorously tested, our dataset is accompanied by several benchmark models and is publicly available. It can be easily accessed using a single line of code, offering a solid basis for efforts towards global AGB estimation. The GitHub repository github.com/ghjuliasialelli/AGBD serves as a one-stop shop for all code and data.
Authors: Oscar Lao, Konstantinos Zacharopoulos, Apostolos Fournaris, Rossano Schifanella, Ioannis Arapakis
Abstract: In the present article, we propose a paradigm shift on evolving Artificial Neural Networks (ANNs) towards a new bio-inspired design that is grounded on the structural properties, interactions, and dynamics of protein networks (PNs): the Artificial Protein Network (APN). This introduces several advantages previously unrealized by state-of-the-art approaches in NE: (1) We can draw inspiration from how nature, thanks to millions of years of evolution, efficiently encodes protein interactions in the DNA to translate our APN to silicon DNA. This helps bridge the gap between syntax and semantics observed in current NE approaches. (2) We can learn from how nature builds networks in our genes, allowing us to design new and smarter networks through EA evolution. (3) We can perform EA crossover/mutation operations and evolution steps, replicating the operations observed in nature directly on the genotype of networks, thus exploring and exploiting the phenotypic space, such that we avoid getting trapped in sub-optimal solutions. (4) Our novel definition of APN opens new ways to leverage our knowledge about different living things and processes from biology. (5) Using biologically inspired encodings, we can model more complex demographic and ecological relationships (e.g., virus-host or predator-prey interactions), allowing us to optimise for multiple, often conflicting objectives.
Authors: Lanzino Romeo, Fontana Federico, Diko Anxhelo, Marini Marco Raoul, Cinque Luigi
Abstract: Deepfake detection aims to contrast the spread of deep-generated media that undermines trust in online content. While existing methods focus on large and complex models, the need for real-time detection demands greater efficiency. With this in mind, unlike previous work, we introduce a novel deepfake detection approach on images using Binary Neural Networks (BNNs) for fast inference with minimal accuracy loss. Moreover, our method incorporates Fast Fourier Transform (FFT) and Local Binary Pattern (LBP) as additional channel features to uncover manipulation traces in frequency and texture domains. Evaluations on COCOFake, DFFD, and CIFAKE datasets demonstrate our method's state-of-the-art performance in most scenarios with a significant efficiency gain of up to a $20\times$ reduction in FLOPs during inference. Finally, by exploring BNNs in deepfake detection to balance accuracy and efficiency, this work paves the way for future research on efficient deepfake detection.
Authors: Davor Bokan, Zlatan Ajanovic, Bakir Lacevic
Abstract: Heuristic search is often used for motion planning and pathfinding problems, for finding the shortest path in a graph while also promising completeness and optimal efficiency. The drawback is it's space complexity, specifically storing all expanded child nodes in memory and sorting large lists of active nodes, which can be a problem in real-time scenarios with limited on-board computation. To combat this, we present the Search with Learned Optimal Pruning-based Expansion (SLOPE), which, learns the distance of a node from a possible optimal path, unlike other approaches that learn a cost-to-go value. The unfavored nodes are then pruned according to the said distance, which in turn reduces the size of the open list. This ensures that the search explores only the region close to optimal paths while lowering memory and computational costs. Unlike traditional learning methods, our approach is orthogonal to estimating cost-to-go heuristics, offering a complementary strategy for improving search efficiency. We demonstrate the effectiveness of our approach evaluating it as a standalone search method and in conjunction with learned heuristic functions, achieving comparable-or-better node expansion metrics, while lowering the number of child nodes in the open list. Our code is available at https://github.com/dbokan1/SLOPE.
Authors: James Wilson, Max D. Champneys, Matt Tipuric, Robin Mills, David J. Wagg, Timothy J. Rogers
Abstract: The use of measured vibration data from structures has a long history of enabling the development of methods for inference and monitoring. In particular, applications based on system identification and structural health monitoring have risen to prominence over recent decades and promise significant benefits when implemented in practice. However, significant challenges remain in the development of these methods. The introduction of realistic, full-scale datasets will be an important contribution to overcoming these challenges. This paper presents a new benchmark dataset capturing the dynamic response of a decommissioned BAE Systems Hawk T1A. The dataset reflects the behaviour of a complex structure with a history of service that can still be tested in controlled laboratory conditions, using a variety of known loading and damage simulation conditions. As such, it provides a key stepping stone between simple laboratory test structures and in-service structures. In this paper, the Hawk structure is described in detail, alongside a comprehensive summary of the experimental work undertaken. Following this, key descriptive highlights of the dataset are presented, before a discussion of the research challenges that the data present. Using the dataset, non-linearity in the structure is demonstrated, as well as the sensitivity of the structure to damage of different types. The dataset is highly applicable to many academic enquiries and additional analysis techniques which will enable further advancement of vibration-based engineering techniques.
Authors: Venkanna Babu Guthula, Stefan Oehmcke, Remigio Chilaule, Hui Zhang, Nico Lang, Ankit Kariryaa, Johan Mottelson, Christian Igel
Abstract: As low-quality housing and in particular certain roof characteristics are associated with an increased risk of malaria, classification of roof types based on remote sensing imagery can support the assessment of malaria risk and thereby help prevent the disease. To support research in this area, we release the Nacala-Roof-Material dataset, which contains high-resolution drone images from Mozambique with corresponding labels delineating houses and specifying their roof types. The dataset defines a multi-task computer vision problem, comprising object detection, classification, and segmentation. In addition, we benchmarked various state-of-the-art approaches on the dataset. Canonical U-Nets, YOLOv8, and a custom decoder on pretrained DINOv2 served as baselines. We show that each of the methods has its advantages but none is superior on all tasks, which highlights the potential of our dataset for future research in multi-task learning. While the tasks are closely related, accurate segmentation of objects does not necessarily imply accurate instance separation, and vice versa. We address this general issue by introducing a variant of the deep ordinal watershed (DOW) approach that additionally separates the interior of objects, allowing for improved object delineation and separation. We show that our DOW variant is a generic approach that improves the performance of both U-Net and DINOv2 backbones, leading to a better trade-off between semantic segmentation and instance segmentation.
Authors: David Benrimoh, Caitrin Armstrong, Joseph Mehltretter, Robert Fratila, Kelly Perlman, Sonia Israel, Adam Kapelner, Sagar V. Parikh, Jordan F. Karp, Katherine Heller, Gustavo Turecki
Abstract: INTRODUCTION: The pharmacological treatment of Major Depressive Disorder (MDD) relies on a trial-and-error approach. We introduce an artificial intelligence (AI) model aiming to personalize treatment and improve outcomes, which was deployed in the Artificial Intelligence in Depression Medication Enhancement (AIDME) Study. OBJECTIVES: 1) Develop a model capable of predicting probabilities of remission across multiple pharmacological treatments for adults with at least moderate major depression. 2) Validate model predictions and examine them for amplification of harmful biases. METHODS: Data from previous clinical trials of antidepressant medications were standardized into a common framework and included 9,042 adults with moderate to severe major depression. Feature selection retained 25 clinical and demographic variables. Using Bayesian optimization, a deep learning model was trained on the training set, refined using the validation set, and tested once on the held-out test set. RESULTS: In the evaluation on the held-out test set, the model demonstrated achieved an AUC of 0.65. The model outperformed a null model on the test set (p = 0.01). The model demonstrated clinical utility, achieving an absolute improvement in population remission rate in hypothetical and actual improvement testing. While the model did identify one drug (escitalopram) as generally outperforming the other drugs (consistent with the input data), there was otherwise significant variation in drug rankings. On bias testing, the model did not amplify potentially harmful biases. CONCLUSIONS: We demonstrate the first model capable of predicting outcomes for 10 different treatment options for patients with MDD, intended to be used at or near the start of treatment to personalize treatment. The model was put into clinical practice during the AIDME randomized controlled trial whose results are reported separately.
Authors: Yi-Cheng Lin, Tzu-Quan Lin, Hsi-Che Lin, Andy T. Liu, Hung-yi Lee
Abstract: Self-supervised learning (SSL) speech models have achieved remarkable performance in various tasks, yet the biased outcomes, especially affecting marginalized groups, raise significant concerns. Social bias refers to the phenomenon where algorithms potentially amplify disparate properties between social groups present in the data used for training. Bias in SSL models can perpetuate injustice by automating discriminatory patterns and reinforcing inequitable systems. This work reveals that prevalent SSL models inadvertently acquire biased associations. We probe how various factors, such as model architecture, size, and training methodologies, influence the propagation of social bias within these models. Finally, we explore the efficacy of debiasing SSL models through regularization techniques, specifically via model compression. Our findings reveal that employing techniques such as row-pruning and training wider, shallower models can effectively mitigate social bias within SSL model.
Authors: Nastaran Okati, Sergio Hernan Garrido Mejia, William Roy Orchard, Patrick Bl\"obaum, Dominik Janzing
Abstract: Recent work conceptualized root cause analysis (RCA) of anomalies via quantitative contribution analysis using causal counterfactuals in structural causal models (SCMs). The framework comes with three practical challenges: (1) it requires the causal directed acyclic graph (DAG), together with an SCM, (2) it is statistically ill-posed since it probes regression models in regions of low probability density, (3) it relies on Shapley values which are computationally expensive to find. In this paper, we propose simplified, efficient methods of root cause analysis when the task is to identify a unique root cause instead of quantitative contribution analysis. Our proposed methods run in linear order of SCM nodes and they require only the causal DAG without counterfactuals. Furthermore, for those use cases where the causal DAG is unknown, we justify the heuristic of identifying root causes as the variables with the highest anomaly score.
Authors: Shentong Mo
Abstract: Recent advancements in sequence modeling have led to the development of the Mamba architecture, noted for its selective state space approach, offering a promising avenue for efficient long sequence handling. However, its application in 3D shape generation, particularly at high resolutions, remains underexplored. Traditional diffusion transformers (DiT) with self-attention mechanisms, despite their potential, face scalability challenges due to the cubic complexity of attention operations as input length increases. This complexity becomes a significant hurdle when dealing with high-resolution voxel sizes. To address this challenge, we introduce a novel diffusion architecture tailored for 3D point clouds generation-Diffusion Mamba (DiM-3D). This architecture forgoes traditional attention mechanisms, instead utilizing the inherent efficiency of the Mamba architecture to maintain linear complexity with respect to sequence length. DiM-3D is characterized by fast inference times and substantially lower computational demands, quantified in reduced Gflops, thereby addressing the key scalability issues of prior models. Our empirical results on the ShapeNet benchmark demonstrate that DiM-3D achieves state-of-the-art performance in generating high-fidelity and diverse 3D shapes. Additionally, DiM-3D shows superior capabilities in tasks like 3D point cloud completion. This not only proves the model's scalability but also underscores its efficiency in generating detailed, high-resolution voxels necessary for advanced 3D shape modeling, particularly excelling in environments requiring high-resolution voxel sizes. Through these findings, we illustrate the exceptional scalability and efficiency of the Diffusion Mamba framework in 3D shape generation, setting a new standard for the field and paving the way for future explorations in high-resolution 3D modeling technologies.
Authors: Anastasios Giovanidis, Mathieu Leconte, Sabrine Aroua, Tor Kvernvik, David Sandberg
Abstract: Radio Resource Management is a challenging topic in future 6G networks where novel applications create strong competition among the users for the available resources. In this work we consider the frequency scheduling problem in a multi-user MIMO system. Frequency resources need to be assigned to a set of users while allowing for concurrent transmissions in the same sub-band. Traditional methods are insufficient to cope with all the involved constraints and uncertainties, whereas reinforcement learning can directly learn near-optimal solutions for such complex environments. However, the scheduling problem has an enormous action space accounting for all the combinations of users and sub-bands, so out-of-the-box algorithms cannot be used directly. In this work, we propose a scheduler based on action-branching over sub-bands, which is a deep Q-learning architecture with parallel decision capabilities. The sub-bands learn correlated but local decision policies and altogether they optimize a global reward. To improve the scaling of the architecture with the number of sub-bands, we propose variations (Unibranch, Graph Neural Network-based) that reduce the number of parameters to learn. The parallel decision making of the proposed architecture allows to meet short inference time requirements in real systems. Furthermore, the deep Q-learning approach permits online fine-tuning after deployment to bridge the sim-to-real gap. The proposed architectures are evaluated against relevant baselines from the literature showing competitive performance and possibilities of online adaptation to evolving environments.
Authors: Parnian Kassraie, Aram-Alexandre Pooladian, Michal Klein, James Thornton, Jonathan Niles-Weed, Marco Cuturi
Abstract: Optimal transport (OT) has profoundly impacted machine learning by providing theoretical and computational tools to realign datasets. In this context, given two large point clouds of sizes $n$ and $m$ in $\mathbb{R}^d$, entropic OT (EOT) solvers have emerged as the most reliable tool to either solve the Kantorovich problem and output a $n\times m$ coupling matrix, or to solve the Monge problem and learn a vector-valued push-forward map. While the robustness of EOT couplings/maps makes them a go-to choice in practical applications, EOT solvers remain difficult to tune because of a small but influential set of hyperparameters, notably the omnipresent entropic regularization strength $\varepsilon$. Setting $\varepsilon$ can be difficult, as it simultaneously impacts various performance metrics, such as compute speed, statistical performance, generalization, and bias. In this work, we propose a new class of EOT solvers (ProgOT), that can estimate both plans and transport maps. We take advantage of several opportunities to optimize the computation of EOT solutions by dividing mass displacement using a time discretization, borrowing inspiration from dynamic OT formulations, and conquering each of these steps using EOT with properly scheduled parameters. We provide experimental evidence demonstrating that ProgOT is a faster and more robust alternative to standard solvers when computing couplings at large scales, even outperforming neural network-based approaches. We also prove statistical consistency of our approach for estimating optimal transport maps.
Authors: Kyoung Whan Choe, Ryan Sullivan, Joseph Su\'arez
Abstract: We present Meta MMO, a collection of many-agent minigames for use as a reinforcement learning benchmark. Meta MMO is built on top of Neural MMO, a massively multiagent environment that has been the subject of two previous NeurIPS competitions. Our work expands Neural MMO with several computationally efficient minigames. We explore generalization across Meta MMO by learning to play several minigames with a single set of weights. We release the environment, baselines, and training code under the MIT license. We hope that Meta MMO will spur additional progress on Neural MMO and, more generally, will serve as a useful benchmark for many-agent generalization.
Authors: Eunjeong Hwang, Yichao Zhou, Beliz Gunel, James Bradley Wendt, Sandeep Tata
Abstract: No existing dataset adequately tests how well language models can incrementally update entity summaries - a crucial ability as these models rapidly advance. The Incremental Entity Summarization (IES) task is vital for maintaining accurate, up-to-date knowledge. To address this, we introduce SUMIE, a fully synthetic dataset designed to expose real-world IES challenges. This dataset effectively highlights problems like incorrect entity association and incomplete information presentation. Unlike common synthetic datasets, ours captures the complexity and nuances found in real-world data. We generate informative and diverse attributes, summaries, and unstructured paragraphs in sequence, ensuring high quality. The alignment between generated summaries and paragraphs exceeds 96%, confirming the dataset's quality. Extensive experiments demonstrate the dataset's difficulty - state-of-the-art LLMs struggle to update summaries with an F1 higher than 80.4%. We will open source the benchmark and the evaluation metrics to help the community make progress on IES tasks.
Authors: Dinh Viet Cuong, Branislava Lali\'c, Mina Petri\'c, Binh Nguyen, Mark Roantree
Abstract: Physics informed neural networks have been gaining popularity due to their unique ability to incorporate physics laws into data-driven models, ensuring that the predictions are not only consistent with empirical data but also align with domain-specific knowledge in the form of physics equations. The integration of physics principles enables the method to require less data while maintaining the robustness of deep learning in modeling complex dynamical systems. However, current PINN frameworks are not sufficiently mature for real-world ODE systems, especially those with extreme multi-scale behavior such as mosquito population dynamical modelling. In this research, we propose a PINN framework with several improvements for forward and inverse problems for ODE systems with a case study application in modelling the dynamics of mosquito populations. The framework tackles the gradient imbalance and stiff problems posed by mosquito ordinary differential equations. The method offers a simple but effective way to resolve the time causality issue in PINNs by gradually expanding the training time domain until it covers entire domain of interest. As part of a robust evaluation, we conduct experiments using simulated data to evaluate the effectiveness of the approach. Preliminary results indicate that physics-informed machine learning holds significant potential for advancing the study of ecological systems.
Authors: Lukas Helff, Felix Friedrich, Manuel Brack, Kristian Kersting, Patrick Schramowski
Abstract: We introduce LlavaGuard, a family of VLM-based safeguard models, offering a versatile framework for evaluating the safety compliance of visual content. Specifically, we designed LlavaGuard for dataset annotation and generative model safeguarding. To this end, we collected and annotated a high-quality visual dataset incorporating a broad safety taxonomy, which we use to tune VLMs on context-aware safety risks. As a key innovation, LlavaGuard's new responses contain comprehensive information, including a safety rating, the violated safety categories, and an in-depth rationale. Further, our introduced customizable taxonomy categories enable the context-specific alignment of LlavaGuard to various scenarios. Our experiments highlight the capabilities of LlavaGuard in complex and real-world applications. We provide checkpoints ranging from 7B to 34B parameters demonstrating state-of-the-art performance, with even the smallest models outperforming baselines like GPT-4. We make our dataset and model weights publicly available and invite further research to address the diverse needs of communities and contexts.
Authors: Jianing Yang, Xuweiyi Chen, Nikhil Madaan, Madhavan Iyengar, Shengyi Qian, David F. Fouhey, Joyce Chai
Abstract: The integration of language and 3D perception is crucial for developing embodied agents and robots that comprehend and interact with the physical world. While large language models (LLMs) have demonstrated impressive language understanding and generation capabilities, their adaptation to 3D environments (3D-LLMs) remains in its early stages. A primary challenge is the absence of large-scale datasets that provide dense grounding between language and 3D scenes. In this paper, we introduce 3D-GRAND, a pioneering large-scale dataset comprising 40,087 household scenes paired with 6.2 million densely-grounded scene-language instructions. Our results show that instruction tuning with 3D-GRAND significantly enhances grounding capabilities and reduces hallucinations in 3D-LLMs. As part of our contributions, we propose a comprehensive benchmark 3D-POPE to systematically evaluate hallucination in 3D-LLMs, enabling fair comparisons among future models. Our experiments highlight a scaling effect between dataset size and 3D-LLM performance, emphasizing the critical role of large-scale 3D-text datasets in advancing embodied AI research. Notably, our results demonstrate early signals for effective sim-to-real transfer, indicating that models trained on large synthetic data can perform well on real-world 3D scans. Through 3D-GRAND and 3D-POPE, we aim to equip the embodied AI community with essential resources and insights, setting the stage for more reliable and better-grounded 3D-LLMs. Project website: https://3d-grand.github.io
Authors: Anran Jiao, Haiyang He, Rishikesh Ranade, Jay Pathak, Lu Lu
Abstract: Learning and solving governing equations of a physical system, represented by partial differential equations (PDEs), from data is a central challenge in a variety of areas of science and engineering. Traditional numerical methods for solving PDEs can be computationally expensive for complex systems and require the complete PDEs of the physical system. On the other hand, current data-driven machine learning methods require a large amount of data to learn a surrogate model of the PDE solution operator, which could be impractical. Here, we propose the first solution operator learning method that only requires one PDE solution, i.e., one-shot learning. By leveraging the principle of locality of PDEs, we consider small local domains instead of the entire computational domain and define a local solution operator. The local solution operator is then trained using a neural network, and utilized to predict the solution of a new input function via mesh-based fixed-point iteration (FPI), meshfree local-solution-operator informed neural network (LOINN) or local-solution-operator informed neural network with correction (cLOINN). We test our method on diverse PDEs, including linear or nonlinear PDEs, PDEs defined on complex geometries, and PDE systems, demonstrating the effectiveness and generalization capabilities of our method across these varied scenarios.
Authors: Kareem Ahmed, Zhe Zeng, Mathias Niepert, Guy Van den Broeck
Abstract: $k$-subset sampling is ubiquitous in machine learning, enabling regularization and interpretability through sparsity. The challenge lies in rendering $k$-subset sampling amenable to end-to-end learning. This has typically involved relaxing the reparameterized samples to allow for backpropagation, with the risk of introducing high bias and high variance. In this work, we fall back to discrete $k$-subset sampling on the forward pass. This is coupled with using the gradient with respect to the exact marginals, computed efficiently, as a proxy for the true gradient. We show that our gradient estimator, SIMPLE, exhibits lower bias and variance compared to state-of-the-art estimators, including the straight-through Gumbel estimator when $k = 1$. Empirical results show improved performance on learning to explain and sparse linear regression. We provide an algorithm for computing the exact ELBO for the $k$-subset distribution, obtaining significantly lower loss compared to SOTA.
Authors: Hongchang Gao
Abstract: Minimax optimization problems have attracted significant attention in recent years due to their widespread application in numerous machine learning models. To solve the minimax problem, a wide variety of stochastic optimization methods have been proposed. However, most of them ignore the distributed setting where the training data is distributed on multiple workers. In this paper, we developed a novel decentralized stochastic gradient descent ascent method for the finite-sum minimax problem. In particular, by employing the variance-reduced gradient, our method can achieve $O(\frac{\sqrt{n}\kappa^3}{(1-\lambda)^2\epsilon^2})$ sample complexity and $O(\frac{\kappa^3}{(1-\lambda)^2\epsilon^2})$ communication complexity for the nonconvex-strongly-concave minimax problem. As far as we know, our work is the first one to achieve such theoretical complexities for this kind of minimax problem. At last, we apply our method to AUC maximization, and the experimental results confirm the effectiveness of our method.
Authors: Manuel Brenner, Florian Hess, Georgia Koppe, Daniel Durstewitz
Abstract: Many, if not most, systems of interest in science are naturally described as nonlinear dynamical systems. Empirically, we commonly access these systems through time series measurements. Often such time series may consist of discrete random variables rather than continuous measurements, or may be composed of measurements from multiple data modalities observed simultaneously. For instance, in neuroscience we may have behavioral labels in addition to spike counts and continuous physiological recordings. While by now there is a burgeoning literature on deep learning for dynamical systems reconstruction (DSR), multimodal data integration has hardly been considered in this context. Here we provide such an efficient and flexible algorithmic framework that rests on a multimodal variational autoencoder for generating a sparse teacher signal that guides training of a reconstruction model, exploiting recent advances in DSR training techniques. It enables to combine various sources of information for optimal reconstruction, even allows for reconstruction from symbolic data (class labels) alone, and connects different types of observations within a common latent dynamics space. In contrast to previous multimodal data integration techniques for scientific applications, our framework is fully \textit{generative}, producing, after training, trajectories with the same geometrical and temporal structure as those of the ground truth system.
Authors: Hankyul Koh, Joon-hyuk Ko, Wonho Jhe
Abstract: We propose a new high-performance activation function, Moderate Adaptive Linear Units (MoLU), for the deep neural network. The MoLU is a simple, beautiful and powerful activation function that can be a good main activation function among hundreds of activation functions. Because the MoLU is made up of the elementary functions, not only it is a infinite diffeomorphism (i.e. smooth and infinitely differentiable over whole domains), but also it decreases training time.
Authors: Ori Linial, Orly Avner, Dotan Di Castro
Abstract: We introduce a method for inferring an explicit PDE from a data sample generated by previously unseen dynamics, based on a learned context. The training phase integrates knowledge of the form of the equation with a differential scheme, while the inference phase yields a PDE that fits the data sample and enables both signal prediction and data explanation. We include results of extensive experimentation, comparing our method to SOTA approaches, together with ablation studies that examine different flavors of our solution.
Authors: Ji Won Park, Nata\v{s}a Tagasovska, Michael Maser, Stephen Ra, Kyunghyun Cho
Abstract: Many scientific and industrial applications require the joint optimization of multiple, potentially competing objectives. Multi-objective Bayesian optimization (MOBO) is a sample-efficient framework for identifying Pareto-optimal solutions. At the heart of MOBO is the acquisition function, which determines the next candidate to evaluate by navigating the best compromises among the objectives. In this paper, we show a natural connection between non-dominated solutions and the extreme quantile of the joint cumulative distribution function (CDF). Motivated by this link, we propose the Pareto-compliant CDF indicator and the associated acquisition function, BOtied. BOtied inherits desirable invariance properties of the CDF, and an efficient implementation with copulas allows it to scale to many objectives. Our experiments on a variety of synthetic and real-world problems demonstrate that BOtied outperforms state-of-the-art MOBO acquisition functions while being computationally efficient for many objectives.
Authors: Sungmin Cha, Kyunghyun Cho, Taesup Moon
Abstract: We introduce a novel Pseudo-Negative Regularization (PNR) framework for effective continual self-supervised learning (CSSL). Our PNR leverages pseudo-negatives obtained through model-based augmentation in a way that newly learned representations may not contradict what has been learned in the past. Specifically, for the InfoNCE-based contrastive learning methods, we define symmetric pseudo-negatives obtained from current and previous models and use them in both main and regularization loss terms. Furthermore, we extend this idea to non-contrastive learning methods which do not inherently rely on negatives. For these methods, a pseudo-negative is defined as the output from the previous model for a differently augmented version of the anchor sample and is asymmetrically applied to the regularization term. Extensive experimental results demonstrate that our PNR framework achieves state-of-the-art performance in representation learning during CSSL by effectively balancing the trade-off between plasticity and stability.
Authors: Nikhil Vyas, Depen Morwani, Rosie Zhao, Gal Kaplun, Sham Kakade, Boaz Barak
Abstract: The success of SGD in deep learning has been ascribed by prior works to the implicit bias induced by finite batch sizes ("SGD noise"). While prior works focused on offline learning (i.e., multiple-epoch training), we study the impact of SGD noise on online (i.e., single epoch) learning. Through an extensive empirical analysis of image and language data, we demonstrate that small batch sizes do not confer any implicit bias advantages in online learning. In contrast to offline learning, the benefits of SGD noise in online learning are strictly computational, facilitating more cost-effective gradient steps. This suggests that SGD in the online regime can be construed as taking noisy steps along the "golden path" of the noiseless gradient descent algorithm. We study this hypothesis and provide supporting evidence in loss and function space. Our findings challenge the prevailing understanding of SGD and offer novel insights into its role in online learning.
Authors: Liam Collins, Hamed Hassani, Mahdi Soltanolkotabi, Aryan Mokhtari, Sanjay Shakkottai
Abstract: An increasingly popular machine learning paradigm is to pretrain a neural network (NN) on many tasks offline, then adapt it to downstream tasks, often by re-training only the last linear layer of the network. This approach yields strong downstream performance in a variety of contexts, demonstrating that multitask pretraining leads to effective feature learning. Although several recent theoretical studies have shown that shallow NNs learn meaningful features when either (i) they are trained on a {\em single} task or (ii) they are {\em linear}, very little is known about the closer-to-practice case of {\em nonlinear} NNs trained on {\em multiple} tasks. In this work, we present the first results proving that feature learning occurs during training with a nonlinear model on multiple tasks. Our key insight is that multi-task pretraining induces a pseudo-contrastive loss that favors representations that align points that typically have the same label across tasks. Using this observation, we show that when the tasks are binary classification tasks with labels depending on the projection of the data onto an $r$-dimensional subspace within the $d\gg r$-dimensional input space, a simple gradient-based multitask learning algorithm on a two-layer ReLU NN recovers this projection, allowing for generalization to downstream tasks with sample and neuron complexity independent of $d$. In contrast, we show that with high probability over the draw of a single task, training on this single task cannot guarantee to learn all $r$ ground-truth features.
Authors: Filip Szatkowski, Bartosz W\'ojcik, Miko{\l}aj Pi\'orczy\'nski, Simone Scardapane
Abstract: Transformer models can face practical limitations due to their high computational requirements. At the same time, such models exhibit significant activation sparsity, which can be leveraged to reduce the inference cost by converting parts of the network into equivalent Mixture-of-Experts (MoE) layers. Despite the crucial role played by activation sparsity, its impact on this process remains unexplored. In particular, we show that the efficiency of the conversion can be significantly enhanced by a proper regularization of the activation sparsity of the base model. Moreover, motivated by the high variance of the number of activated neurons for different inputs, we introduce a more effective dynamic-k expert selection rule that adjusts the number of executed experts on a per-token basis. Finally, we extend this approach to multi-head attention projections, which results in additional savings compared to only converting the FFN blocks. The proposed method, Dense to Dynamic-$k$ Mixture-of-Experts (D2DMoE), outperforms existing approaches on common NLP and vision tasks, allowing us to save up to 60% of inference cost without significantly affecting model performance.
Authors: Tzu-Yuan Lin, Minghan Zhu, Maani Ghaffari
Abstract: This paper proposes an equivariant neural network that takes data in any semi-simple Lie algebra as input. The corresponding group acts on the Lie algebra as adjoint operations, making our proposed network adjoint-equivariant. Our framework generalizes the Vector Neurons, a simple $\mathrm{SO}(3)$-equivariant network, from 3-D Euclidean space to Lie algebra spaces, building upon the invariance property of the Killing form. Furthermore, we propose novel Lie bracket layers and geometric channel mixing layers that extend the modeling capacity. Experiments are conducted for the $\mathfrak{so}(3)$, $\mathfrak{sl}(3)$, and $\mathfrak{sp}(4)$ Lie algebras on various tasks, including fitting equivariant and invariant functions, learning system dynamics, point cloud registration, and homography-based shape classification. Our proposed equivariant network shows wide applicability and competitive performance in various domains.
Authors: Yu-Lin Tsai, Chia-Yi Hsu, Chulin Xie, Chih-Hsun Lin, Jia-You Chen, Bo Li, Pin-Yu Chen, Chia-Mu Yu, Chun-Ying Huang
Abstract: Diffusion models for text-to-image (T2I) synthesis, such as Stable Diffusion (SD), have recently demonstrated exceptional capabilities for generating high-quality content. However, this progress has raised several concerns of potential misuse, particularly in creating copyrighted, prohibited, and restricted content, or NSFW (not safe for work) images. While efforts have been made to mitigate such problems, either by implementing a safety filter at the evaluation stage or by fine-tuning models to eliminate undesirable concepts or styles, the effectiveness of these safety measures in dealing with a wide range of prompts remains largely unexplored. In this work, we aim to investigate these safety mechanisms by proposing one novel concept retrieval algorithm for evaluation. We introduce Ring-A-Bell, a model-agnostic red-teaming tool for T2I diffusion models, where the whole evaluation can be prepared in advance without prior knowledge of the target model. Specifically, Ring-A-Bell first performs concept extraction to obtain holistic representations for sensitive and inappropriate concepts. Subsequently, by leveraging the extracted concept, Ring-A-Bell automatically identifies problematic prompts for diffusion models with the corresponding generation of inappropriate content, allowing the user to assess the reliability of deployed safety mechanisms. Finally, we empirically validate our method by testing online services such as Midjourney and various methods of concept removal. Our results show that Ring-A-Bell, by manipulating safe prompting benchmarks, can transform prompts that were originally regarded as safe to evade existing safety mechanisms, thus revealing the defects of the so-called safety mechanisms which could practically lead to the generation of harmful contents. Our codes are available at https://github.com/chiayi-hsu/Ring-A-Bell.
Authors: Lanxiang Xing, Haixu Wu, Yuezhou Ma, Jianmin Wang, Mingsheng Long
Abstract: Fluid prediction is a long-standing challenge due to the intrinsic high-dimensional non-linear dynamics. Previous methods usually utilize the non-linear modeling capability of deep models to directly estimate velocity fields for future prediction. However, skipping over inherent physical properties but directly learning superficial velocity fields will overwhelm the model from generating precise or physics-reliable results. In this paper, we propose the HelmFluid toward an accurate and interpretable predictor for fluid. Inspired by the Helmholtz theorem, we design a HelmDynamics block to learn Helmholtz dynamics, which decomposes fluid dynamics into more solvable curl-free and divergence-free parts, physically corresponding to potential and stream functions of fluid. By embedding the HelmDynamics block into a Multiscale Multihead Integral Architecture, HelmFluid can integrate learned Helmholtz dynamics along temporal dimension in multiple spatial scales to yield future fluid. Compared with previous velocity estimating methods, HelmFluid is faithfully derived from Helmholtz theorem and ravels out complex fluid dynamics with physically interpretable evidence. Experimentally, HelmFluid achieves consistent state-of-the-art in both numerical simulated and real-world observed benchmarks, even for scenarios with complex boundaries.
Authors: Travers Rhodes, Daniel D. Lee
Abstract: Human demonstrations of trajectories are an important source of training data for many machine learning problems. However, the difficulty of collecting human demonstration data for complex tasks makes learning efficient representations of those trajectories challenging. For many problems, such as for dexterous manipulation, the exact timings of the trajectories should be factored from their spatial path characteristics. In this work, we propose TimewarpVAE, a fully differentiable manifold-learning algorithm that incorporates Dynamic Time Warping (DTW) to simultaneously learn both timing variations and latent factors of spatial variation. We show how the TimewarpVAE algorithm learns appropriate time alignments and meaningful representations of spatial variations in handwriting and fork manipulation datasets. Our results have lower spatial reconstruction test error than baseline approaches and the learned low-dimensional representations can be used to efficiently generate semantically meaningful novel trajectories. We demonstrate the utility of our algorithm to generate novel high-speed trajectories for a robotic arm.
Authors: Titing Cui, Su Jia, Thomas Lavastida
Abstract: Dynamic pricing models often posit that a $\textbf{stream}$ of customer interactions occur sequentially, where customers' valuations are drawn independently. However, this model is not entirely reflective of the real world, as it overlooks a critical aspect, the law of diminishing marginal utility, which states that a customer's marginal utility from each additional unit declines. This causes the valuation distribution to shift towards the lower end, which is not captured by the stream model. This motivates us to study a pool-based model, where a $\textbf{pool}$ of customers repeatedly interacts with a monopolist seller, each of whose valuation diminishes in the number of purchases made according to a discount function. In particular, when the discount function is constant, our pool model recovers the stream model. We focus on the most fundamental special case, where a customer's valuation becomes zero once a purchase is made. Given $k$ prices, we present a non-adaptive, detail-free (i.e., does not "know" the valuations) policy that achieves a $1/k$ competitive ratio, which is optimal among non-adaptive policies. Furthermore, based on a novel debiasing technique, we propose an adaptive learn-then-earn policy with a $\tilde O(k^{2/3} n^{2/3})$ regret.
Authors: Wenjie Ou, Zhishuo Zhao, Dongyue Guo, Zheng Zhang, Yi Lin
Abstract: Deep learning models have recently achieved significant performance improvements in time series forecasting. We present a highly accurate and simply structured CNN-based model with only one convolutional layer, called WinNet, including (i) Sub-window Division block to transform the series into 2D tensor, (ii) Dual-Forecasting mechanism to capture the short- and long-term variations, (iii) Two-dimensional Hybrid Decomposition (TDD) block to decompose the 2D tensor into the trend and seasonal terms to eliminate the non-stationarity, and (iv) Decomposition Correlation Block (DCB) to leverage the correlation between the trend and seasonal terms by the convolution layer. Results on eight benchmark datasets demonstrate that WinNet can achieve SOTA performance and lower computational complexity over CNN-, MLP- and Transformer-based methods. The code will be available at: https://github.com/ouwen18/WinNet.
Authors: Grigory Malinovsky, Peter Richt\'arik, Samuel Horv\'ath, Eduard Gorbunov
Abstract: Distributed learning has emerged as a leading paradigm for training large machine learning models. However, in real-world scenarios, participants may be unreliable or malicious, posing a significant challenge to the integrity and accuracy of the trained models. Byzantine fault tolerance mechanisms have been proposed to address these issues, but they often assume full participation from all clients, which is not always practical due to the unavailability of some clients or communication constraints. In our work, we propose the first distributed method with client sampling and provable tolerance to Byzantine workers. The key idea behind the developed method is the use of gradient clipping to control stochastic gradient differences in recursive variance reduction. This allows us to bound the potential harm caused by Byzantine workers, even during iterations when all sampled clients are Byzantine. Furthermore, we incorporate communication compression into the method to enhance communication efficiency. Under general assumptions, we prove convergence rates for the proposed method that match the existing state-of-the-art (SOTA) theoretical results. We also propose a heuristic on adjusting any Byzantine-robust method to a partial participation scenario via clipping.
Authors: Alexandru Tifrea, Preethi Lahoti, Ben Packer, Yoni Halpern, Ahmad Beirami, Flavien Prost
Abstract: Despite achieving promising fairness-error trade-offs, in-processing mitigation techniques for group fairness cannot be employed in numerous practical applications with limited computation resources or no access to the training pipeline of the prediction model. In these situations, post-processing is a viable alternative. However, current methods are tailored to specific problem settings and fairness definitions and hence, are not as broadly applicable as in-processing. In this work, we propose a framework that turns any regularized in-processing method into a post-processing approach. This procedure prescribes a way to obtain post-processing techniques for a much broader range of problem settings than the prior post-processing literature. We show theoretically and through extensive experiments that our framework preserves the good fairness-error trade-offs achieved with in-processing and can improve over the effectiveness of prior post-processing methods. Finally, we demonstrate several advantages of a modular mitigation strategy that disentangles the training of the prediction model from the fairness mitigation, including better performance on tasks with partial group labels.
Authors: Shuze Liu, Shuhang Chen, Shangtong Zhang
Abstract: Stochastic approximation is a class of algorithms that update a vector iteratively, incrementally, and stochastically, including, e.g., stochastic gradient descent and temporal difference learning. One fundamental challenge in analyzing a stochastic approximation algorithm is to establish its stability, i.e., to show that the stochastic vector iterates are bounded almost surely. In this paper, we extend the celebrated Borkar-Meyn theorem for stability from the Martingale difference noise setting to the Markovian noise setting, which greatly improves its applicability in reinforcement learning, especially in those off-policy reinforcement learning algorithms with linear function approximation and eligibility traces. Central to our analysis is the diminishing asymptotic rate of change of a few functions, which is implied by both a form of strong law of large numbers and a commonly used V4 Lyapunov drift condition and trivially holds if the Markov chain is finite and irreducible.
Authors: Anke Tang, Li Shen, Yong Luo, Nan Yin, Lefei Zhang, Dacheng Tao
Abstract: Merging various task-specific Transformer-based models trained on different tasks into a single unified model can execute all the tasks concurrently. Previous methods, exemplified by task arithmetic, have been proven to be both effective and scalable. Existing methods have primarily focused on seeking a static optimal solution within the original model parameter space. A notable challenge is mitigating the interference between parameters of different models, which can substantially deteriorate performance. In this paper, we propose to merge most of the parameters while upscaling the MLP of the Transformer layers to a weight-ensembling mixture of experts (MoE) module, which can dynamically integrate shared and task-specific knowledge based on the input, thereby providing a more flexible solution that can adapt to the specific needs of each instance. Our key insight is that by identifying and separating shared knowledge and task-specific knowledge, and then dynamically integrating them, we can mitigate the parameter interference problem to a great extent. We conduct the conventional multi-task model merging experiments and evaluate the generalization and robustness of our method. The results demonstrate the effectiveness of our method and provide a comprehensive understanding of our method. The code is available at https://github.com/tanganke/weight-ensembling_MoE
Authors: Yun-Wei Chu, Dong-Jun Han, Seyyedali Hosseinalipour, Christopher G. Brinton
Abstract: A few recent studies have demonstrated that leveraging centrally pre-trained models can offer advantageous initializations for federated learning (FL). However, existing pre-training methods do not generalize well when faced with an arbitrary set of downstream FL tasks. Specifically, they often (i) achieve limited average accuracy, particularly when there are unseen downstream labels, and (ii) result in significant accuracy variance, failing to provide a balanced performance across clients. To address these challenges, we propose CoPreFL, a collaborative/distributed pre-training approach which provides a robust initialization for downstream FL tasks. The key idea of CoPreFL is a model-agnostic meta-learning (MAML) procedure that tailors the global model to closely mimic heterogeneous and unseen FL scenarios, resulting in a pre-trained model that is rapidly adaptable to arbitrary FL tasks. Our MAML procedure incorporates performance variance into the meta-objective function, balancing performance across clients rather than solely optimizing for accuracy. Through extensive experiments, we demonstrate that CoPreFL obtains significant improvements in both average accuracy and variance across arbitrary downstream FL tasks with unseen/seen labels, compared with various pre-training baselines. We also show how CoPreFL is compatible with different well-known FL algorithms applied by the downstream tasks, enhancing performance in each case.
Authors: Jiaxiang Dong, Haixu Wu, Yuxuan Wang, Yunzhong Qiu, Li Zhang, Jianmin Wang, Mingsheng Long
Abstract: Time series pre-training has recently garnered wide attention for its potential to reduce labeling expenses and benefit various downstream tasks. Prior methods are mainly based on pre-training techniques well-acknowledged in vision or language, such as masked modeling and contrastive learning. However, randomly masking time series or calculating series-wise similarity will distort or neglect inherent temporal correlations crucial in time series data. To emphasize temporal correlation modeling, this paper proposes TimeSiam as a simple but effective self-supervised pre-training framework for Time series based on Siamese networks. Concretely, TimeSiam pre-trains Siamese encoders to capture intrinsic temporal correlations between randomly sampled past and current subseries. With a simple data augmentation method (e.g.~masking), TimeSiam can benefit from diverse augmented subseries and learn internal time-dependent representations through a past-to-current reconstruction. Moreover, learnable lineage embeddings are also introduced to distinguish temporal distance between sampled series and further foster the learning of diverse temporal correlations. TimeSiam consistently outperforms extensive advanced pre-training baselines, demonstrating superior forecasting and classification capabilities across 13 standard benchmarks in both intra- and cross-domain scenarios.
Authors: Yuka Hashimoto, Masahiro Ikeda, Hachem Kadri
Abstract: Machine learning has a long collaborative tradition with several fields of mathematics, such as statistics, probability and linear algebra. We propose a new direction for machine learning research: $C^*$-algebraic ML $-$ a cross-fertilization between $C^*$-algebra and machine learning. The mathematical concept of $C^*$-algebra is a natural generalization of the space of complex numbers. It enables us to unify existing learning strategies, and construct a new framework for more diverse and information-rich data models. We explain why and how to use $C^*$-algebras in machine learning, and provide technical considerations that go into the design of $C^*$-algebraic learning models in the contexts of kernel methods and neural networks. Furthermore, we discuss open questions and challenges in $C^*$-algebraic ML and give our thoughts for future development and applications.
Authors: Alexander Kolesov, Petr Mokrov, Igor Udovichenko, Milena Gazdieva, Gudmund Pammer, Evgeny Burnaev, Alexander Korotin
Abstract: Given a collection of probability measures, a practitioner sometimes needs to find an "average" distribution which adequately aggregates reference distributions. A theoretically appealing notion of such an average is the Wasserstein barycenter, which is the primal focus of our work. By building upon the dual formulation of Optimal Transport (OT), we propose a new scalable approach for solving the Wasserstein barycenter problem. Our methodology is based on the recent Neural OT solver: it has bi-level adversarial learning objective and works for general cost functions. These are key advantages of our method since the typical adversarial algorithms leveraging barycenter tasks utilize tri-level optimization and focus mostly on quadratic cost. We also establish theoretical error bounds for our proposed approach and showcase its applicability and effectiveness in illustrative scenarios and image data setups. Our source code is available at https://github.com/justkolesov/NOTBarycenters.
Authors: Mustapha Bounoua, Giulio Franzese, Pietro Michiardi
Abstract: The analysis of scientific data and complex multivariate systems requires information quantities that capture relationships among multiple random variables. Recently, new information-theoretic measures have been developed to overcome the shortcomings of classical ones, such as mutual information, that are restricted to considering pairwise interactions. Among them, the concept of information synergy and redundancy is crucial for understanding the high-order dependencies between variables. One of the most prominent and versatile measures based on this concept is O-information, which provides a clear and scalable way to quantify the synergy-redundancy balance in multivariate systems. However, its practical application is limited to simplified cases. In this work, we introduce S$\Omega$I, which allows for the first time to compute O-information without restrictive assumptions about the system. Our experiments validate our approach on synthetic data, and demonstrate the effectiveness of S$\Omega$I in the context of a real-world use case.
Authors: Alexander Pan, Erik Jones, Meena Jagadeesan, Jacob Steinhardt
Abstract: Language models influence the external world: they query APIs that read and write to web pages, generate content that shapes human behavior, and run system commands as autonomous agents. These interactions form feedback loops: LLM outputs affect the world, which in turn affect subsequent LLM outputs. In this work, we show that feedback loops can cause in-context reward hacking (ICRH), where the LLM at test-time optimizes a (potentially implicit) objective but creates negative side effects in the process. For example, consider an LLM agent deployed to increase Twitter engagement; the LLM may retrieve its previous tweets into the context window and make them more controversial, increasing engagement but also toxicity. We identify and study two processes that lead to ICRH: output-refinement and policy-refinement. For these processes, evaluations on static datasets are insufficient -- they miss the feedback effects and thus cannot capture the most harmful behavior. In response, we provide three recommendations for evaluation to capture more instances of ICRH. As AI development accelerates, the effects of feedback loops will proliferate, increasing the need to understand their role in shaping LLM behavior.
Authors: Xingang Guo, Fangxu Yu, Huan Zhang, Lianhui Qin, Bin Hu
Abstract: Jailbreaks on large language models (LLMs) have recently received increasing attention. For a comprehensive assessment of LLM safety, it is essential to consider jailbreaks with diverse attributes, such as contextual coherence and sentiment/stylistic variations, and hence it is beneficial to study controllable jailbreaking, i.e. how to enforce control on LLM attacks. In this paper, we formally formulate the controllable attack generation problem, and build a novel connection between this problem and controllable text generation, a well-explored topic of natural language processing. Based on this connection, we adapt the Energy-based Constrained Decoding with Langevin Dynamics (COLD), a state-of-the-art, highly efficient algorithm in controllable text generation, and introduce the COLD-Attack framework which unifies and automates the search of adversarial LLM attacks under a variety of control requirements such as fluency, stealthiness, sentiment, and left-right-coherence. The controllability enabled by COLD-Attack leads to diverse new jailbreak scenarios which not only cover the standard setting of generating fluent (suffix) attack with continuation constraint, but also allow us to address new controllable attack settings such as revising a user query adversarially with paraphrasing constraint, and inserting stealthy attacks in context with position constraint. Our extensive experiments on various LLMs (Llama-2, Mistral, Vicuna, Guanaco, GPT-3.5, and GPT-4) show COLD-Attack's broad applicability, strong controllability, high success rate, and attack transferability. Our code is available at https://github.com/Yu-Fangxu/COLD-Attack.
Authors: Jason Yoo, Yunpeng Liu, Frank Wood, Geoff Pleiss
Abstract: In online continual learning, a neural network incrementally learns from a non-i.i.d. data stream. Nearly all online continual learning methods employ experience replay to simultaneously prevent catastrophic forgetting and underfitting on past data. Our work demonstrates a limitation of this approach: neural networks trained with experience replay tend to have unstable optimization trajectories, impeding their overall accuracy. Surprisingly, these instabilities persist even when the replay buffer stores all previous training examples, suggesting that this issue is orthogonal to catastrophic forgetting. We minimize these instabilities through a simple modification of the optimization geometry. Our solution, Layerwise Proximal Replay (LPR), balances learning from new and replay data while only allowing for gradual changes in the hidden activation of past data. We demonstrate that LPR consistently improves replay-based online continual learning methods across multiple problem settings, regardless of the amount of available replay memory.
Authors: Chi Zhang, Jingjing Fan, Man Ho Au, Siu Ming Yiu
Abstract: Replacing non-polynomial functions (e.g., non-linear activation functions such as ReLU) in a neural network with their polynomial approximations is a standard practice in privacy-preserving machine learning. The resulting neural network, called polynomial approximation of neural network (PANN) in this paper, is compatible with advanced cryptosystems to enable privacy-preserving model inference. Using ``highly precise'' approximation, state-of-the-art PANN offers similar inference accuracy as the underlying backbone model. However, little is known about the effect of approximation, and existing literature often determined the required approximation precision empirically. In this paper, we initiate the investigation of PANN as a standalone object. Specifically, our contribution is two-fold. Firstly, we provide an explanation on the effect of approximate error in PANN. In particular, we discovered that (1) PANN is susceptible to some type of perturbations; and (2) weight regularisation significantly reduces PANN's accuracy. We support our explanation with experiments. Secondly, based on the insights from our investigations, we propose solutions to increase inference accuracy for PANN. Experiments showed that combination of our solutions is very effective: at the same precision, our PANN is 10% to 50% more accurate than state-of-the-arts; and at the same accuracy, our PANN only requires a precision of 2^{-9} while state-of-the-art solution requires a precision of 2^{-12} using the ResNet-20 model on CIFAR-10 dataset.
Authors: Zijian Li, Ruichu Cai, Zhenhui Yang, Haiqin Huang, Guangyi Chen, Yifan Shen, Zhengming Chen, Xiangchen Song, Kun Zhang
Abstract: Temporal distribution shifts are ubiquitous in time series data. One of the most popular methods assumes that the temporal distribution shift occurs uniformly to disentangle the stationary and nonstationary dependencies. But this assumption is difficult to meet, as we do not know when the distribution shifts occur. To solve this problem, we propose to learn IDentifiable latEnt stAtes (IDEA) to detect when the distribution shifts occur. Beyond that, we further disentangle the stationary and nonstationary latent states via sufficient observation assumption to learn how the latent states change. Specifically, we formalize the causal process with environment-irrelated stationary and environment-related nonstationary variables. Under mild conditions, we show that latent environments and stationary/nonstationary variables are identifiable. Based on these theories, we devise the IDEA model, which incorporates an autoregressive hidden Markov model to estimate latent environments and modular prior networks to identify latent states. The IDEA model outperforms several latest nonstationary forecasting methods on various benchmark datasets, highlighting its advantages in real-world scenarios.
Authors: Azmine Toushik Wasi
Abstract: Precise glucose level monitoring is critical for people with diabetes to avoid serious complications. While there are several methods for continuous glucose level monitoring, research on maintenance devices is limited. To mitigate the gap, we provide a novel neural control system for continuous glucose monitoring and management that uses differential predictive control. Our approach, led by a sophisticated neural policy and differentiable modeling, constantly adjusts insulin supply in real-time, thereby improving glucose level optimization in the body. This end-to-end method maximizes efficiency, providing personalized care and improved health outcomes, as confirmed by empirical evidence. Code and data are available at: \url{https://github.com/azminewasi/NeuralCGMM}.
Authors: Gergely Neu, Nneka Okolo
Abstract: We study the performance of stochastic first-order methods for finding saddle points of convex-concave functions. A notorious challenge faced by such methods is that the gradients can grow arbitrarily large during optimization, which may result in instability and divergence. In this paper, we propose a simple and effective regularization technique that stabilizes the iterates and yields meaningful performance guarantees even if the domain and the gradient noise scales linearly with the size of the iterates (and is thus potentially unbounded). Besides providing a set of general results, we also apply our algorithm to a specific problem in reinforcement learning, where it leads to performance guarantees for finding near-optimal policies in an average-reward MDP without prior knowledge of the bias span.
Authors: Juan L. Valerdi
Abstract: A characterization of the representability of neural networks is relevant to comprehend their success in artificial intelligence. This study investigate two topics on ReLU neural network expressivity and their connection with a conjecture related to the minimum depth required for representing any continuous piecewise linear (CPWL) function. The topics are the minimal depth representation of the sum and max operations, as well as the exploration of polytope neural networks. For the sum operation, we establish a sufficient condition on the minimal depth of the operands to find the minimal depth of the operation. In contrast, regarding the max operation, a comprehensive set of examples is presented, demonstrating that no sufficient conditions, depending solely on the depth of the operands, would imply a minimal depth for the operation. The study also examine the minimal depth relationship between convex CPWL functions. On polytope neural networks, we investigate basic depth properties from Minkowski sums, convex hulls, number of vertices, faces, affine transformations, and indecomposable polytopes. More significant findings include depth characterization of polygons; identification of polytopes with an increasing number of vertices, exhibiting small depth and others with arbitrary large depth; and most notably, the minimal depth of simplices, which is strictly related to the minimal depth conjecture in ReLU networks.
Authors: Bernardo Esteves, Miguel Vasco, Francisco S. Melo
Abstract: We propose NeuralThink, a novel deep thinking architecture that can efficiently and consistently extrapolate, i.e., learn algorithms from smaller problems (in terms of observation size) and execute those algorithms in large problems. Contrary to previous deep thinking architectures, NeuralThink can be naturally applied in both same-size problems, where the input and output sizes are the same, and in different-size problems, where the size of the input and output differ. To allow for this versatility, we design NeuralThink with three main components: a recurrent module, that iteratively processes input information at different scales, a processing module, responsible for aggregating the previously processed information, and a curriculum-based training scheme, that improves the extrapolation performance of the method. To evaluate our method we introduce a set of novel different-size tasks and we show that NeuralThink consistently outperforms the prior state-of-the-art deep thinking approaches in extrapolating to larger problems, considering smaller training problems and requiring less parameters than other approaches.
Authors: Swaroop Nath, Harshad Khadilkar, Pushpak Bhattacharyya
Abstract: Transformers have become pivotal in Natural Language Processing, demonstrating remarkable success in applications like Machine Translation and Summarization. Given their widespread adoption, several works have attempted to analyze the expressivity of Transformers. Expressivity of a neural network is the class of functions it can approximate. A neural network is fully expressive if it can act as a universal function approximator. We attempt to analyze the same for Transformers. Contrary to existing claims, our findings reveal that Transformers struggle to reliably approximate smooth functions, relying on piecewise constant approximations with sizable intervals. The central question emerges as: "Are Transformers truly Universal Function Approximators?" To address this, we conduct a thorough investigation, providing theoretical insights and supporting evidence through experiments. Theoretically, we prove that Transformer Encoders cannot approximate smooth functions. Experimentally, we complement our theory and show that the full Transformer architecture cannot approximate smooth functions. By shedding light on these challenges, we advocate a refined understanding of Transformers' capabilities.
Authors: Ahmed Imtiaz Humayun, Randall Balestriero, Richard Baraniuk
Abstract: Grokking, or delayed generalization, is a phenomenon where generalization in a deep neural network (DNN) occurs long after achieving near zero training error. Previous studies have reported the occurrence of grokking in specific controlled settings, such as DNNs initialized with large-norm parameters or transformers trained on algorithmic datasets. We demonstrate that grokking is actually much more widespread and materializes in a wide range of practical settings, such as training of a convolutional neural network (CNN) on CIFAR10 or a Resnet on Imagenette. We introduce the new concept of delayed robustness, whereby a DNN groks adversarial examples and becomes robust, long after interpolation and/or generalization. We develop an analytical explanation for the emergence of both delayed generalization and delayed robustness based on the local complexity of a DNN's input-output mapping. Our local complexity measures the density of so-called linear regions (aka, spline partition regions) that tile the DNN input space and serves as a utile progress measure for training. We provide the first evidence that, for classification problems, the linear regions undergo a phase transition during training whereafter they migrate away from the training samples (making the DNN mapping smoother there) and towards the decision boundary (making the DNN mapping less smooth there). Grokking occurs post phase transition as a robust partition of the input space thanks to the linearization of the DNN mapping around the training points. Website: https://bit.ly/grok-adversarial
Authors: Bangchao Deng, Bingqing Qu, Pengyang Wang, Dingqi Yang, Benjamin Fankhauser, Philippe Cudre-Mauroux
Abstract: Location prediction forecasts a user's location based on historical user mobility traces. To tackle the intrinsic sparsity issue of real-world user mobility traces, spatiotemporal contexts have been shown as significantly useful. Existing solutions mostly incorporate spatiotemporal distances between locations in mobility traces, either by feeding them as additional inputs to Recurrent Neural Networks (RNNs) or by using them to search for informative past hidden states for prediction. However, such distance-based methods fail to capture the time-varying temporal regularities of human mobility, where human mobility is often more regular in the morning than in other periods, for example; this suggests the usefulness of the actual timestamps besides the temporal distances. Against this background, we propose REPLAY, a general RNN architecture learning to capture the time-varying temporal regularities for location prediction. Specifically, REPLAY not only resorts to the spatiotemporal distances in sparse trajectories to search for the informative past hidden states, but also accommodates the time-varying temporal regularities by incorporating smoothed timestamp embeddings using Gaussian weighted averaging with timestamp-specific learnable bandwidths, which can flexibly adapt to the temporal regularities of different strengths across different timestamps. Our extensive evaluation compares REPLAY against a sizable collection of state-of-the-art techniques on two real-world datasets. Results show that REPLAY consistently and significantly outperforms state-of-the-art methods by 7.7\%-10.9\% in the location prediction task, and the bandwidths reveal interesting patterns of the time-varying temporal regularities.
Authors: Zhanyu Liu, Chaolv Zeng, Guanjie Zheng
Abstract: With the increasing demands of training graph neural networks (GNNs) on large-scale graphs, graph data condensation has emerged as a critical technique to relieve the storage and time costs during the training phase. It aims to condense the original large-scale graph to a much smaller synthetic graph while preserving the essential information necessary for efficiently training a downstream GNN. However, existing methods concentrate either on optimizing node features exclusively or endeavor to independently learn node features and the graph structure generator. They could not explicitly leverage the information of the original graph structure and failed to construct an interpretable graph structure for the synthetic dataset. To address these issues, we introduce a novel framework named \textbf{G}raph Data \textbf{C}ondensation via \textbf{S}elf-expressive Graph Structure \textbf{R}econstruction (\textbf{GCSR}). Our method stands out by (1) explicitly incorporating the original graph structure into the condensing process and (2) capturing the nuanced interdependencies between the condensed nodes by reconstructing an interpretable self-expressive graph structure. Extensive experiments and comprehensive analysis validate the efficacy of the proposed method across diverse GNN models and datasets. Our code is available at \url{https://github.com/zclzcl0223/GCSR}.
Authors: Vitaliy Pozdnyakov, Aleksandr Kovalenko, Ilya Makarov, Mikhail Drobyshevskiy, Kirill Lukyanov
Abstract: Integrating machine learning into Automated Control Systems (ACS) enhances decision-making in industrial process management. One of the limitations to the widespread adoption of these technologies in industry is the vulnerability of neural networks to adversarial attacks. This study explores the threats in deploying deep learning models for fault diagnosis in ACS using the Tennessee Eastman Process dataset. By evaluating three neural networks with different architectures, we subject them to six types of adversarial attacks and explore five different defense methods. Our results highlight the strong vulnerability of models to adversarial samples and the varying effectiveness of defense strategies. We also propose a novel protection approach by combining multiple defense methods and demonstrate it's efficacy. This research contributes several insights into securing machine learning within ACS, ensuring robust fault diagnosis in industrial processes.
Authors: George Panagopoulos, Daniele Malitesta, Fragkiskos D. Malliaros, Jun Pang
Abstract: Estimating causal effects in e-commerce tends to involve costly treatment assignments which can be impractical in large-scale settings. Leveraging machine learning to predict such treatment effects without actual intervention is a standard practice to diminish the risk. However, existing methods for treatment effect prediction tend to rely on training sets of substantial size, which are built from real experiments and are thus inherently risky to create. In this work we propose a graph neural network to diminish the required training set size, relying on graphs that are common in e-commerce data. Specifically, we view the problem as node regression with a restricted number of labeled instances, develop a two-model neural architecture akin to previous causal effect estimators, and test varying message-passing layers for encoding. Furthermore, as an extra step, we combine the model with an acquisition function to guide the creation of the training set in settings with extremely low experimental budget. The framework is flexible since each step can be used separately with other models or treatment policies. The experiments on real large-scale networks indicate a clear advantage of our methodology over the state of the art, which in many cases performs close to random, underlining the need for models that can generalize with limited supervision to reduce experimental risks.
Authors: Xinyu Ma, Xu Chu, Zhibang Yang, Yang Lin, Xin Gao, Junfeng Zhao
Abstract: With the increasingly powerful performances and enormous scales of pretrained models, promoting parameter efficiency in fine-tuning has become a crucial need for effective and efficient adaptation to various downstream tasks. One representative line of fine-tuning methods is Orthogonal Fine-tuning (OFT), which rigorously preserves the angular distances within the parameter space to preserve the pretrained knowledge. Despite the empirical effectiveness, OFT still suffers low parameter efficiency at $\mathcal{O}(d^2)$ and limited capability of downstream adaptation. Inspired by Givens rotation, in this paper, we proposed quasi-Givens Orthogonal Fine-Tuning (qGOFT) to address the problems. We first use $\mathcal{O}(d)$ Givens rotations to accomplish arbitrary orthogonal transformation in $SO(d)$ with provable equivalence, reducing parameter complexity from $\mathcal{O}(d^2)$ to $\mathcal{O}(d)$. Then we introduce flexible norm and relative angular adjustments under soft orthogonality regularization to enhance the adaptation capability of downstream semantic deviations. Extensive experiments on various tasks and pretrained models validate the effectiveness of our methods.
Authors: Xikun Jiang, He Lyu, Chenhao Ying, Yibin Xu, Boris D\"udder, Yuan Luo
Abstract: With the increasingly widespread application of machine learning, how to strike a balance between protecting the privacy of data and algorithm parameters and ensuring the verifiability of machine learning has always been a challenge. This study explores the intersection of reinforcement learning and data privacy, specifically addressing the Multi-Armed Bandit (MAB) problem with the Upper Confidence Bound (UCB) algorithm. We introduce zkUCB, an innovative algorithm that employs the Zero-Knowledge Succinct Non-Interactive Argument of Knowledge (zk-SNARKs) to enhance UCB. zkUCB is carefully designed to safeguard the confidentiality of training data and algorithmic parameters, ensuring transparent UCB decision-making. Experiments highlight zkUCB's superior performance, attributing its enhanced reward to judicious quantization bit usage that reduces information entropy in the decision-making process. zkUCB's proof size and verification time scale linearly with the execution steps of zkUCB. This showcases zkUCB's adept balance between data security and operational efficiency. This approach contributes significantly to the ongoing discourse on reinforcing data privacy in complex decision-making processes, offering a promising solution for privacy-sensitive applications.
Authors: Shangding Gu, Bilgehan Sel, Yuhao Ding, Lu Wang, Qingwei Lin, Ming Jin, Alois Knoll
Abstract: Ensuring the safety of Reinforcement Learning (RL) is crucial for its deployment in real-world applications. Nevertheless, managing the trade-off between reward and safety during exploration presents a significant challenge. Improving reward performance through policy adjustments may adversely affect safety performance. In this study, we aim to address this conflicting relation by leveraging the theory of gradient manipulation. Initially, we analyze the conflict between reward and safety gradients. Subsequently, we tackle the balance between reward and safety optimization by proposing a soft switching policy optimization method, for which we provide convergence analysis. Based on our theoretical examination, we provide a safe RL framework to overcome the aforementioned challenge, and we develop a Safety-MuJoCo Benchmark to assess the performance of safe RL algorithms. Finally, we evaluate the effectiveness of our method on the Safety-MuJoCo Benchmark and a popular safe RL benchmark, Omnisafe. Experimental results demonstrate that our algorithms outperform several state-of-the-art baselines in terms of balancing reward and safety optimization.
Authors: Emile Pierret, Bruno Galerne
Abstract: Diffusion or score-based models recently showed high performance in image generation. They rely on a forward and a backward stochastic differential equations (SDE). The sampling of a data distribution is achieved by solving numerically the backward SDE or its associated flow ODE. Studying the convergence of these models necessitates to control four different types of error: the initialization error, the truncation error, the discretization and the score approximation. In this paper, we study theoretically the behavior of diffusion models and their numerical implementation when the data distribution is Gaussian. In this restricted framework where the score function is a linear operator, we can derive the analytical solutions of the forward and backward SDEs as well as the associated flow ODE. This provides exact expressions for various Wasserstein errors which enable us to compare the influence of each error type for any sampling scheme, thus allowing to monitor convergence directly in the data space instead of relying on Inception features. Our experiments show that the recommended numerical schemes from the diffusion models literature are also the best sampling schemes for Gaussian distributions.
Authors: Nicholas Gao, Stephan G\"unnemann
Abstract: Neural wave functions accomplished unprecedented accuracies in approximating the ground state of many-electron systems, though at a high computational cost. Recent works proposed amortizing the cost by learning generalized wave functions across different structures and compounds instead of solving each problem independently. Enforcing the permutation antisymmetry of electrons in such generalized neural wave functions remained challenging as existing methods require discrete orbital selection via non-learnable hand-crafted algorithms. This work tackles the problem by defining overparametrized, fully learnable neural wave functions suitable for generalization across molecules. We achieve this by relying on Pfaffians rather than Slater determinants. The Pfaffian allows us to enforce the antisymmetry on arbitrary electronic systems without any constraint on electronic spin configurations or molecular structure. Our empirical evaluation finds that a single neural Pfaffian calculates the ground state and ionization energies with chemical accuracy across various systems. On the TinyMol dataset, we outperform the `gold-standard' CCSD(T) CBS reference energies by 1.9m$E_h$ and reduce energy errors compared to previous generalized neural wave functions by up to an order of magnitude.
Authors: Zijian Li, Yifan Shen, Kaitao Zheng, Ruichu Cai, Xiangchen Song, Mingming Gong, Zhengmao Zhu, Guangyi Chen, Kun Zhang
Abstract: Temporally causal representation learning aims to identify the latent causal process from time series observations, but most methods require the assumption that the latent causal processes do not have instantaneous relations. Although some recent methods achieve identifiability in the instantaneous causality case, they require either interventions on the latent variables or grouping of the observations, which are in general difficult to obtain in real-world scenarios. To fill this gap, we propose an \textbf{ID}entification framework for instantane\textbf{O}us \textbf{L}atent dynamics (\textbf{IDOL}) by imposing a sparse influence constraint that the latent causal processes have sparse time-delayed and instantaneous relations. Specifically, we establish identifiability results of the latent causal process based on sufficient variability and the sparse influence constraint by employing contextual information of time series data. Based on these theories, we incorporate a temporally variational inference architecture to estimate the latent variables and a gradient-based sparsity regularization to identify the latent causal process. Experimental results on simulation datasets illustrate that our method can identify the latent causal process. Furthermore, evaluations on multiple human motion forecasting benchmarks with instantaneous dependencies indicate the effectiveness of our method in real-world settings.
Authors: Chendi Qian, Andrei Manolache, Christopher Morris, Mathias Niepert
Abstract: Message-passing graph neural networks (MPNNs) have emerged as a powerful paradigm for graph-based machine learning. Despite their effectiveness, MPNNs face challenges such as under-reaching and over-squashing, where limited receptive fields and structural bottlenecks hinder information flow in the graph. While graph transformers hold promise in addressing these issues, their scalability is limited due to quadratic complexity regarding the number of nodes, rendering them impractical for larger graphs. Here, we propose implicitly rewired message-passing neural networks (IPR-MPNNs), a novel approach that integrates implicit probabilistic graph rewiring into MPNNs. By introducing a small number of virtual nodes, i.e., adding additional nodes to a given graph and connecting them to existing nodes, in a differentiable, end-to-end manner, IPR-MPNNs enable long-distance message propagation, circumventing quadratic complexity. Theoretically, we demonstrate that IPR-MPNNs surpass the expressiveness of traditional MPNNs. Empirically, we validate our approach by showcasing its ability to mitigate under-reaching and over-squashing effects, achieving state-of-the-art performance across multiple graph datasets. Notably, IPR-MPNNs outperform graph transformers while maintaining significantly faster computational efficiency.
Authors: Lang Feng, Pengjie Gu, Bo An, Gang Pan
Abstract: Diffusion planners have shown promise in handling long-horizon and sparse-reward tasks due to the non-autoregressive plan generation. However, their inherent stochastic risk of generating infeasible trajectories presents significant challenges to their reliability and stability. We introduce a novel approach, the Trajectory Aggregation Tree (TAT), to address this issue in diffusion planners. Compared to prior methods that rely solely on raw trajectory predictions, TAT aggregates information from both historical and current trajectories, forming a dynamic tree-like structure. Each trajectory is conceptualized as a branch and individual states as nodes. As the structure evolves with the integration of new trajectories, unreliable states are marginalized, and the most impactful nodes are prioritized for decision-making. TAT can be deployed without modifying the original training and sampling pipelines of diffusion planners, making it a training-free, ready-to-deploy solution. We provide both theoretical analysis and empirical evidence to support TAT's effectiveness. Our results highlight its remarkable ability to resist the risk from unreliable trajectories, guarantee the performance boosting of diffusion planners in $100\%$ of tasks, and exhibit an appreciable tolerance margin for sample quality, thereby enabling planning with a more than $3\times$ acceleration.
Authors: Renato M. Silva, Greg\'orio F. Azevedo, Matheus V. V. Berto, Jean R. Rocha, Eduardo C. Fidelis, Matheus V. Nogueira, Pedro H. Lisboa, Tiago A. Almeida
Abstract: Traffic incidents involving vulnerable road users (VRUs) constitute a significant proportion of global road accidents. Advances in traffic communication ecosystems, coupled with sophisticated signal processing and machine learning techniques, have facilitated the utilization of data from diverse sensors. Despite these advancements and the availability of extensive datasets, substantial progress is required to mitigate traffic casualties. This paper provides a comprehensive survey of state-of-the-art technologies and methodologies to enhance the safety of VRUs. The study delves into the communication networks between vehicles and VRUs, emphasizing the integration of advanced sensors and the availability of relevant datasets. It explores preprocessing techniques and data fusion methods to enhance sensor data quality. Furthermore, our study assesses critical simulation environments essential for developing and testing VRU safety systems. Our research also highlights recent advances in VRU detection and classification algorithms, addressing challenges such as variable environmental conditions. Additionally, we cover cutting-edge research in predicting VRU intentions and behaviors, which is crucial for proactive collision avoidance strategies. Through this survey, we aim to provide a comprehensive understanding of the current landscape of VRU safety technologies, identifying areas of progress and areas needing further research and development.
Authors: Charles Westphal, Stephen Hailes, Mirco Musolesi
Abstract: In this paper, we introduce Partial Information Decomposition of Features (PIDF), a new paradigm for simultaneous data interpretability and feature selection. Contrary to traditional methods that assign a single importance value, our approach is based on three metrics per feature: the mutual information shared with the target variable, the feature's contribution to synergistic information, and the amount of this information that is redundant. In particular, we develop a novel procedure based on these three metrics, which reveals not only how features are correlated with the target but also the additional and overlapping information provided by considering them in combination with other features. We extensively evaluate PIDF using both synthetic and real-world data, demonstrating its potential applications and effectiveness, by considering case studies from genetics and neuroscience.
Authors: Gezheng Xu, Qi Chen, Charles Ling, Boyu Wang, Changjian Shui
Abstract: AI systems have been shown to produce unfair results for certain subgroups of population, highlighting the need to understand bias on certain sensitive attributes. Current research often falls short, primarily focusing on the subgroups characterized by a single sensitive attribute, while neglecting the nature of intersectional fairness of multiple sensitive attributes. This paper focuses on its one fundamental aspect by discovering diverse high-bias subgroups under intersectional sensitive attributes. Specifically, we propose a Bias-Guided Generative Network (BGGN). By treating each bias value as a reward, BGGN efficiently generates high-bias intersectional sensitive attributes. Experiments on real-world text and image datasets demonstrate a diverse and efficient discovery of BGGN. To further evaluate the generated unseen but possible unfair intersectional sensitive attributes, we formulate them as prompts and use modern generative AI to produce new texts and images. The results of frequently generating biased data provides new insights of discovering potential unfairness in popular modern generative AI systems. Warning: This paper contains generative examples that are offensive in nature.
Authors: Jacob Si, Wendy Yusi Cheng, Michael Cooper, Rahul G. Krishnan
Abstract: Tabular data are omnipresent in various sectors of industries. Neural networks for tabular data such as TabNet have been proposed to make predictions while leveraging the attention mechanism for interpretability. However, the inferred attention masks are often dense, making it challenging to come up with rationales about the predictive signal. To remedy this, we propose InterpreTabNet, a variant of the TabNet model that models the attention mechanism as a latent variable sampled from a Gumbel-Softmax distribution. This enables us to regularize the model to learn distinct concepts in the attention masks via a KL Divergence regularizer. It prevents overlapping feature selection by promoting sparsity which maximizes the model's efficacy and improves interpretability to determine the important features when predicting the outcome. To assist in the interpretation of feature interdependencies from our model, we employ a large language model (GPT-4) and use prompt engineering to map from the learned feature mask onto natural language text describing the learned signal. Through comprehensive experiments on real-world datasets, we demonstrate that InterpreTabNet outperforms previous methods for interpreting tabular data while attaining competitive accuracy.
Authors: Tianqi Zhao, Alan Hanjalic, Megha Khosla
Abstract: In recent years, continual learning (CL) techniques have made significant progress in learning from streaming data while preserving knowledge across sequential tasks, particularly in the realm of euclidean data. To foster fair evaluation and recognize challenges in CL settings, several evaluation frameworks have been proposed, focusing mainly on the single- and multi-label classification task on euclidean data. However, these evaluation frameworks are not trivially applicable when the input data is graph-structured, as they do not consider the topological structure inherent in graphs. Existing continual graph learning (CGL) evaluation frameworks have predominantly focussed on single-label scenarios in the node classification (NC) task. This focus has overlooked the complexities of multi-label scenarios, where nodes may exhibit affiliations with multiple labels, simultaneously participating in multiple tasks. We develop a graph-aware evaluation (\agale) framework that accommodates both single-labeled and multi-labeled nodes, addressing the limitations of previous evaluation frameworks. In particular, we define new incremental settings and devise data partitioning algorithms tailored to CGL datasets. We perform extensive experiments comparing methods from the domains of continual learning, continual graph learning, and dynamic graph learning (DGL). We theoretically analyze \agale and provide new insights about the role of homophily in the performance of compared methods. We release our framework at https://github.com/Tianqi-py/AGALE.
Authors: Jiaxu Liu, Xinping Yi, Sihao Wu, Xiangyu Yin, Tianle Zhang, Xiaowei Huang, Shi Jin
Abstract: While Hyperbolic Graph Neural Network (HGNN) has recently emerged as a powerful tool dealing with hierarchical graph data, the limitations of scalability and efficiency hinder itself from generalizing to deep models. In this paper, by envisioning depth as a continuous-time embedding evolution, we decouple the HGNN and reframe the information propagation as a partial differential equation, letting node-wise attention undertake the role of diffusivity within the Hyperbolic Neural PDE (HPDE). By introducing theoretical principles \textit{e.g.,} field and flow, gradient, divergence, and diffusivity on a non-Euclidean manifold for HPDE integration, we discuss both implicit and explicit discretization schemes to formulate numerical HPDE solvers. Further, we propose the Hyperbolic Graph Diffusion Equation (HGDE) -- a flexible vector flow function that can be integrated to obtain expressive hyperbolic node embeddings. By analyzing potential energy decay of embeddings, we demonstrate that HGDE is capable of modeling both low- and high-order proximity with the benefit of local-global diffusivity functions. Experiments on node classification and link prediction and image-text classification tasks verify the superiority of the proposed method, which consistently outperforms various competitive models by a significant margin.
Authors: Eugene Choi, Arash Ahmadian, Matthieu Geist, Oilvier Pietquin, Mohammad Gheshlaghi Azar
Abstract: Both online and offline RLHF methods such as PPO and DPO have been extremely successful in aligning AI with human preferences. Despite their success, the existing methods suffer from a fundamental problem that their optimal solution is highly task-dependent (i.e., not robust to out-of-distribution (OOD) tasks). Here we address this challenge by proposing Self-Improving Robust Preference Optimization SRPO, a practical and mathematically principled offline RLHF framework that is completely robust to the changes in the task. The key idea of SRPO is to cast the problem of learning from human preferences as a self-improvement process, which can be mathematically expressed in terms of a min-max objective that aims at joint optimization of self-improvement policy and the generative policy in an adversarial fashion. The solution for this optimization problem is independent of the training task and thus it is robust to its changes. We then show that this objective can be re-expressed in the form of a non-adversarial offline loss which can be optimized using standard supervised optimization techniques at scale without any need for reward model and online inference. We show the effectiveness of SRPO in terms of AI Win-Rate (WR) against human (GOLD) completions. In particular, when SRPO is evaluated on the OOD XSUM dataset, it outperforms the celebrated DPO by a clear margin of 15% after 5 self-revisions, achieving WR of 90%.
Authors: Guy Amir, Osher Maayan, Tom Zelazny, Guy Katz, Michael Schapira
Abstract: Deep neural networks (DNNs) play a crucial role in the field of machine learning, demonstrating state-of-the-art performance across various application domains. However, despite their success, DNN-based models may occasionally exhibit challenges with generalization, i.e., may fail to handle inputs that were not encountered during training. This limitation is a significant challenge when it comes to deploying deep learning for safety-critical tasks, as well as in real-world settings characterized by substantial variability. We introduce a novel approach for harnessing DNN verification technology to identify DNN-driven decision rules that exhibit robust generalization to previously unencountered input domains. Our method assesses generalization within an input domain by measuring the level of agreement between independently trained deep neural networks for inputs in this domain. We also efficiently realize our approach by using off-the-shelf DNN verification engines, and extensively evaluate it on both supervised and unsupervised DNN benchmarks, including a deep reinforcement learning (DRL) system for Internet congestion control -- demonstrating the applicability of our approach for real-world settings. Moreover, our research introduces a fresh objective for formal verification, offering the prospect of mitigating the challenges linked to deploying DNN-driven systems in real-world scenarios.
Authors: Advait Gadhikar, Sree Harsha Nelaturu, Rebekka Burkholz
Abstract: The success of iterative pruning methods in achieving state-of-the-art sparse networks has largely been attributed to improved mask identification and an implicit regularization induced by pruning. We challenge this hypothesis and instead posit that their repeated cyclic training schedules enable improved optimization. To verify this, we show that pruning at initialization is significantly boosted by repeated cyclic training, even outperforming standard iterative pruning methods. The dominant mechanism how this is achieved, as we conjecture, can be attributed to a better exploration of the loss landscape leading to a lower training loss. However, at high sparsity, repeated cyclic training alone is not enough for competitive performance. A strong coupling between learnt parameter initialization and mask seems to be required. Standard methods obtain this coupling via expensive pruning-training iterations, starting from a dense network. To achieve this with sparse training instead, we propose SCULPT-ing, i.e., repeated cyclic training of any sparse mask followed by a single pruning step to couple the parameters and the mask, which is able to match the performance of state-of-the-art iterative pruning methods in the high sparsity regime at reduced computational cost.
Authors: Shahaf Bassan, Guy Amir, Guy Katz
Abstract: The local and global interpretability of various ML models has been studied extensively in recent years. However, despite significant progress in the field, many known results remain informal or lack sufficient mathematical rigor. We propose a framework for bridging this gap, by using computational complexity theory to assess local and global perspectives of interpreting ML models. We begin by proposing proofs for two novel insights that are essential for our analysis: (1) a duality between local and global forms of explanations; and (2) the inherent uniqueness of certain global explanation forms. We then use these insights to evaluate the complexity of computing explanations, across three model types representing the extremes of the interpretability spectrum: (1) linear models; (2) decision trees; and (3) neural networks. Our findings offer insights into both the local and global interpretability of these models. For instance, under standard complexity assumptions such as P != NP, we prove that selecting global sufficient subsets in linear models is computationally harder than selecting local subsets. Interestingly, with neural networks and decision trees, the opposite is true: it is harder to carry out this task locally than globally. We believe that our findings demonstrate how examining explainability through a computational complexity lens can help us develop a more rigorous grasp of the inherent interpretability of ML models.
Authors: Anke Tang, Li Shen, Yong Luo, Han Hu, Bo Do, Dacheng Tao
Abstract: Deep model fusion is an emerging technique that unifies the predictions or parameters of several deep neural networks into a single model in a cost-effective and data-efficient manner. This enables the unified model to take advantage of the original models' strengths, potentially exceeding their performance. Although a variety of deep model fusion techniques have been introduced, their evaluations tend to be inconsistent and often inadequate to validate their effectiveness and robustness against distribution shifts. To address this issue, we introduce FusionBench, which is the first comprehensive benchmark dedicated to deep model fusion. FusionBench covers a wide range of tasks, including open-vocabulary image classification, text classification, and text-to-text generation. Each category includes up to eight tasks with corresponding task-specific models, featuring both full fine-tuning and LoRA fine-tuning, as well as models of different sizes, to ensure fair and balanced comparisons of various multi-task model fusion techniques across different tasks, model scales, and fine-tuning strategies. We implement and evaluate a broad spectrum of deep model fusion techniques. These techniques range from model ensemble methods, which combine the predictions to improve the overall performance, to model merging, which integrates different models into a single one, and model mixing methods, which upscale or recombine the components of the original models. FusionBench now contains 26 distinct tasks, 74 fine-tuned models, and 16 fusion techniques, and we are committed to consistently expanding the benchmark with more tasks, models, and fusion techniques. In addition, we offer a well-documented set of resources and guidelines to aid researchers in understanding and replicating the benchmark results. Homepage https://github.com/tanganke/fusion_bench
Authors: Max Mueller-Eberstein, Dianna Yee, Karren Yang, Gautam Varma Mantena, Colin Lea
Abstract: Parameter-efficient fine-tuning (PEFT) for personalizing automatic speech recognition (ASR) has recently shown promise for adapting general population models to atypical speech. However, these approaches assume a priori knowledge of the atypical speech disorder being adapted for -- the diagnosis of which requires expert knowledge that is not always available. Even given this knowledge, data scarcity and high inter/intra-speaker variability further limit the effectiveness of traditional fine-tuning. To circumvent these challenges, we first identify the minimal set of model parameters required for ASR adaptation. Our analysis of each individual parameter's effect on adaptation performance allows us to reduce Word Error Rate (WER) by half while adapting 0.03% of all weights. Alleviating the need for cohort-specific models, we next propose the novel use of a meta-learned hypernetwork to generate highly individualized, utterance-level adaptations on-the-fly for a diverse set of atypical speech characteristics. Evaluating adaptation at the global, cohort and individual-level, we show that hypernetworks generalize better to out-of-distribution speakers, while maintaining an overall relative WER reduction of 75.2% using 0.1% of the full parameter budget.
Authors: Zhonghao Wang, Danyu Sun, Sheng Zhou, Haobo Wang, Jiapei Fan, Longtao Huang, Jiajun Bu
Abstract: Graph Neural Networks (GNNs) exhibit strong potential in node classification task through a message-passing mechanism. However, their performance often hinges on high-quality node labels, which are challenging to obtain in real-world scenarios due to unreliable sources or adversarial attacks. Consequently, label noise is common in real-world graph data, negatively impacting GNNs by propagating incorrect information during training. To address this issue, the study of Graph Neural Networks under Label Noise (GLN) has recently gained traction. However, due to variations in dataset selection, data splitting, and preprocessing techniques, the community currently lacks a comprehensive benchmark, which impedes deeper understanding and further development of GLN. To fill this gap, we introduce NoisyGL in this paper, the first comprehensive benchmark for graph neural networks under label noise. NoisyGL enables fair comparisons and detailed analyses of GLN methods on noisy labeled graph data across various datasets, with unified experimental settings and interface. Our benchmark has uncovered several important insights that were missed in previous research, and we believe these findings will be highly beneficial for future studies. We hope our open-source benchmark library will foster further advancements in this field. The code of the benchmark can be found in https://github.com/eaglelab-zju/NoisyGL.
Authors: Di Luo, Zhuo Chen, Kaiwen Hu, Zhizhen Zhao, Vera Mikyoung Hur, Bryan K. Clark
Abstract: Symmetries such as gauge invariance and anyonic symmetry play a crucial role in quantum many-body physics. We develop a general approach to constructing gauge invariant or anyonic symmetric autoregressive neural network quantum states, including a wide range of architectures such as Transformer and recurrent neural network (RNN), for quantum lattice models. These networks can be efficiently sampled and explicitly obey gauge symmetries or anyonic constraint. We prove that our methods can provide exact representation for the ground and excited states of the 2D and 3D toric codes, and the X-cube fracton model. We variationally optimize our symmetry incorporated autoregressive neural networks for ground states as well as real-time dynamics for a variety of models. We simulate the dynamics and the ground states of the quantum link model of $\text{U(1)}$ lattice gauge theory, obtain the phase diagram for the 2D $\mathbb{Z}_2$ gauge theory, determine the phase transition and the central charge of the $\text{SU(2)}_3$ anyonic chain, and also compute the ground state energy of the SU(2) invariant Heisenberg spin chain. Our approach provides powerful tools for exploring condensed matter physics, high energy physics and quantum information science.
Authors: Jayanta Dey, Ali Geisa, Ronak Mehta, Tyler M. Tomita, Hayden S. Helm, Haoyin Xu, Eric Eaton, Jeffery Dick, Carey E. Priebe, Joshua T. Vogelstein
Abstract: Learning is a process wherein a learning agent enhances its performance through exposure of experience or data. Throughout this journey, the agent may encounter diverse learning environments. For example, data may be presented to the leaner all at once, in multiple batches, or sequentially. Furthermore, the distribution of each data sample could be either identical and independent (iid) or non-iid. Additionally, there may exist computational and space constraints for the deployment of the learning algorithms. The complexity of a learning task can vary significantly, depending on the learning setup and the constraints imposed upon it. However, it is worth noting that the current literature lacks formal definitions for many of the in-distribution and out-of-distribution learning paradigms. Establishing proper and universally agreed-upon definitions for these learning setups is essential for thoroughly exploring the evolution of ideas across different learning scenarios and deriving generalized mathematical bounds for these learners. In this paper, we aim to address this issue by proposing a chronological approach to defining different learning tasks using the provably approximately correct (PAC) learning framework. We will start with in-distribution learning and progress to recently proposed lifelong or continual learning. We employ consistent terminology and notation to demonstrate how each of these learning frameworks represents a specific instance of a broader, more generalized concept of learnability. Our hope is that this work will inspire a universally agreed-upon approach to quantifying different types of learning, fostering greater understanding and progress in the field.
Authors: Ronald Davis III, Zaijun Chen, Ryan Hamerly, Dirk Englund
Abstract: Edholm's Law predicts exponential growth in data rate and spectrum bandwidth for communications and is forecasted to remain true for the upcoming deployment of 6G. Compounding this issue is the exponentially increasing demand for deep neural network (DNN) compute, including DNNs for signal processing. However, the slowing of Moore's Law due to the limitations of transistor-based electronics means that completely new paradigms for computing will be required to meet these increasing demands for advanced communications. Optical neural networks (ONNs) are promising DNN accelerators with ultra-low latency and energy consumption. Yet state-of-the-art ONNs struggle with scalability and implementing linear with in-line nonlinear operations. Here we introduce our multiplicative analog frequency transform ONN (MAFT-ONN) that encodes the data in the frequency domain, achieves matrix-vector products in a single shot using photoelectric multiplication, and uses a single electro-optic modulator for the nonlinear activation of all neurons in each layer. We experimentally demonstrate the first hardware accelerator that computes fully-analog deep learning on raw RF signals, performing single-shot modulation classification with 85% accuracy, where a 'majority vote' multi-measurement scheme can boost the accuracy to 95% within 5 consecutive measurements. In addition, we demonstrate frequency-domain finite impulse response (FIR) linear-time-invariant (LTI) operations, enabling a powerful combination of traditional and AI signal processing. We also demonstrate the scalability of our architecture by computing nearly 4 million fully-analog multiplies-and-accumulates for MNIST digit classification. Our latency estimation model shows that due to the Shannon capacity-limited analog data movement, MAFT-ONN is hundreds of times faster than traditional RF receivers operating at their theoretical peak performance.
Authors: Alex Vicente-Sola, Davide L. Manna, Paul Kirkland, Gaetano Di Caterina, Trevor Bihl
Abstract: Spiking Neural Networks (SNN) are characterised by their unique temporal dynamics, but the properties and advantages of such computations are still not well understood. In order to provide answers, in this work we demonstrate how Spiking neurons can enable temporal feature extraction in feed-forward neural networks without the need for recurrent synapses, and how recurrent SNNs can achieve comparable results to LSTM with a smaller number of parameters. This shows how their bio-inspired computing principles can be successfully exploited beyond energy efficiency gains and evidences their differences with respect to conventional artificial neural networks. These results are obtained through a new task, DVS-Gesture-Chain (DVS-GC), which allows, for the first time, to evaluate the perception of temporal dependencies in a real event-based action recognition dataset. Our study proves how the widely used DVS Gesture benchmark can be solved by networks without temporal feature extraction when its events are accumulated in frames, unlike the new DVS-GC which demands an understanding of the order in which events happen. Furthermore, this setup allowed us to reveal the role of the leakage rate in spiking neurons for temporal processing tasks and demonstrated the benefits of "hard reset" mechanisms. Additionally, we also show how time-dependent weights and normalization can lead to understanding order by means of temporal attention.
Authors: Jay Bhanushali, Manivannan Muniyandi, Praneeth Chakravarthula
Abstract: We present a cross-domain inference technique that learns from synthetic data to estimate depth and normals for in-the-wild omnidirectional 3D scenes encountered in real-world uncontrolled settings. To this end, we introduce UBotNet, an architecture that combines UNet and Bottleneck Transformer elements to predict consistent scene normals and depth. We also introduce the OmniHorizon synthetic dataset containing 24,335 omnidirectional images that represent a wide variety of outdoor environments, including buildings, streets, and diverse vegetation. This dataset is generated from expansive, lifelike virtual spaces and encompasses dynamic scene elements, such as changing lighting conditions, different times of day, pedestrians, and vehicles. Our experiments show that UBotNet achieves significantly improved accuracy in depth estimation and normal estimation compared to existing models. Lastly, we validate cross-domain synthetic-to-real depth and normal estimation on real outdoor images using UBotNet trained solely on our synthetic OmniHorizon dataset, demonstrating the potential of both the synthetic dataset and the proposed network for real-world scene understanding applications.
Authors: Pierre-Fran\c{c}ois Massiani, Mona Buisson-Fenet, Friedrich Solowjow, Florent Di Meglio, Sebastian Trimpe
Abstract: Distinguishability and, by extension, observability are key properties of dynamical systems. Establishing these properties is challenging, especially when no analytical model is available and they are to be inferred directly from measurement data. The presence of noise further complicates this analysis, as standard notions of distinguishability are tailored to deterministic systems. We build on distributional distinguishability, which extends the deterministic notion by comparing distributions of outputs of stochastic systems. We first show that both concepts are equivalent for a class of systems that includes linear systems. We then present a method to assess and quantify distributional distinguishability from output data. Specifically, our quantification measures how much data is required to tell apart two initial states, inducing a continuous spectrum of distinguishability. We propose a statistical test to determine a threshold above which two states can be considered distinguishable with high confidence. We illustrate these tools by computing distinguishability maps over the state space in simulation, then leverage the test to compare sensor configurations on hardware.
Authors: Ahmed Imtiaz Humayun, Randall Balestriero, Guha Balakrishnan, Richard Baraniuk
Abstract: Current Deep Network (DN) visualization and interpretability methods rely heavily on data space visualizations such as scoring which dimensions of the data are responsible for their associated prediction or generating new data features or samples that best match a given DN unit or representation. In this paper, we go one step further by developing the first provably exact method for computing the geometry of a DN's mapping - including its decision boundary - over a specified region of the data space. By leveraging the theory of Continuous Piece-Wise Linear (CPWL) spline DNs, SplineCam exactly computes a DNs geometry without resorting to approximations such as sampling or architecture simplification. SplineCam applies to any DN architecture based on CPWL nonlinearities, including (leaky-)ReLU, absolute value, maxout, and max-pooling and can also be applied to regression DNs such as implicit neural representations. Beyond decision boundary visualization and characterization, SplineCam enables one to compare architectures, measure generalizability and sample from the decision boundary on or off the manifold. Project Website: bit.ly/splinecam.
Authors: Arvi Jonnarth, Jie Zhao, Michael Felsberg
Abstract: Coverage path planning (CPP) is the problem of finding a path that covers the entire free space of a confined area, with applications ranging from robotic lawn mowing to search-and-rescue. When the environment is unknown, the path needs to be planned online while mapping the environment, which cannot be addressed by offline planning methods that do not allow for a flexible path space. We investigate how suitable reinforcement learning is for this challenging problem, and analyze the involved components required to efficiently learn coverage paths, such as action space, input feature representation, neural network architecture, and reward function. We propose a computationally feasible egocentric map representation based on frontiers, and a novel reward term based on total variation to promote complete coverage. Through extensive experiments, we show that our approach surpasses the performance of both previous RL-based approaches and highly specialized methods across multiple CPP variations.
Authors: Francesco Bacchiocchi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
Abstract: We study principal-agent problems in which a principal commits to an outcome-dependent payment scheme -- called contract -- in order to induce an agent to take a costly, unobservable action leading to favorable outcomes. We consider a generalization of the classical (single-round) version of the problem in which the principal interacts with the agent by committing to contracts over multiple rounds. The principal has no information about the agent, and they have to learn an optimal contract by only observing the outcome realized at each round. We focus on settings in which the size of the agent's action space is small. We design an algorithm that learns an approximately-optimal contract with high probability in a number of rounds polynomial in the size of the outcome space, when the number of actions is constant. Our algorithm solves an open problem by Zhu et al.[2022]. Moreover, it can also be employed to provide a $\tilde{\mathcal{O}}(T^{4/5})$ regret bound in the related online learning setting in which the principal aims at maximizing their cumulative utility, thus considerably improving previously-known regret bounds.
Authors: Guanting Dong, Hongyi Yuan, Keming Lu, Chengpeng Li, Mingfeng Xue, Dayiheng Liu, Wei Wang, Zheng Yuan, Chang Zhou, Jingren Zhou
Abstract: Large language models (LLMs) with enormous pre-training tokens and parameters emerge diverse abilities, including math reasoning, code generation, and instruction following. These abilities are further enhanced by supervised fine-tuning (SFT). While the open-source community has explored ad-hoc SFT for enhancing individual capabilities, proprietary LLMs exhibit versatility across various skills. Therefore, understanding the facilitation of multiple abilities via SFT is paramount. In this study, we specifically focuses on the interplay of data composition between mathematical reasoning, code generation, and general human-aligning abilities during SFT. We propose four intriguing research questions to explore the association between model performance and various factors including data amount, composition ratio, model size and SFT strategies. Our experiments reveal that distinct capabilities scale differently and larger models generally show superior performance with same amount of data. Mathematical reasoning and code generation consistently improve with increasing data amount, whereas general abilities plateau after roughly a thousand samples. Moreover, we observe data composition appears to enhance various abilities under limited data conditions, yet can lead to performance conflicts when data is plentiful. Our findings also suggest the amount of composition data influences performance more than the composition ratio. In analysis of SFT strategies, we find that sequentially learning multiple skills risks catastrophic forgetting. Our proposed Dual-stage Mixed Fine-tuning (DMT) strategy offers a promising solution to learn multiple abilities with different scaling patterns.
Authors: Xiaoxuan Liu, Lanxiang Hu, Peter Bailis, Ion Stoica, Zhijie Deng, Alvin Cheung, Hao Zhang
Abstract: Speculative decoding is a pivotal technique to accelerate the inference of large language models (LLMs) by employing a smaller draft model to predict the target model's outputs. However, its efficacy can be limited due to the low predictive accuracy of the draft model, particularly when faced with diverse text inputs and a significant capability gap between the draft and target models. We introduce online speculative decoding to address this challenge. The main idea is to continuously update the (multiple) draft model(s) on observed user query data. Adapting to query distribution mitigates the shifts between the training distribution of the draft model and the query distribution, enabling the draft model to more accurately predict the target model's outputs. We develop a prototype of online speculative decoding based on knowledge distillation and evaluate it using both synthetic and real query data. The results show a substantial increase in the token acceptance rate by 0.1 to 0.65, bringing 1.42x to 2.17x latency reduction. Our code is available at https://github.com/LiuXiaoxuanPKU/OSD.
Authors: Takeru Miyato, Bernhard Jaeger, Max Welling, Andreas Geiger
Abstract: As transformers are equivariant to the permutation of input tokens, encoding the positional information of tokens is necessary for many tasks. However, since existing positional encoding schemes have been initially designed for NLP tasks, their suitability for vision tasks, which typically exhibit different structural properties in their data, is questionable. We argue that existing positional encoding schemes are suboptimal for 3D vision tasks, as they do not respect their underlying 3D geometric structure. Based on this hypothesis, we propose a geometry-aware attention mechanism that encodes the geometric structure of tokens as relative transformation determined by the geometric relationship between queries and key-value pairs. By evaluating on multiple novel view synthesis (NVS) datasets in the sparse wide-baseline multi-view setting, we show that our attention, called Geometric Transform Attention (GTA), improves learning efficiency and performance of state-of-the-art transformer-based NVS models without any additional learned parameters and only minor computational overhead.
Authors: Ilya Musabirov, Angela Zavaleta-Bernuy, Pan Chen, Michael Liut, Joseph Jay Williams
Abstract: Randomized A/B comparisons of alternative pedagogical strategies or other course improvements could provide useful empirical evidence for instructor decision-making. However, traditional experiments do not provide a straightforward pathway to rapidly utilize data, increasing the chances that students in an experiment experience the best conditions. Drawing inspiration from the use of machine learning and experimentation in product development at leading technology companies, we explore how adaptive experimentation might aid continuous course improvement. In adaptive experiments, data is analyzed and utilized as different conditions are deployed to students. This can be achieved using machine learning algorithms to identify which actions are more beneficial in improving students' learning experiences and outcomes. These algorithms can then dynamically deploy the most effective conditions in subsequent interactions with students, resulting in better support for students' needs. We illustrate this approach with a case study that provides a side-by-side comparison of traditional and adaptive experiments on adding self-explanation prompts in online homework problems in a CS1 course. This work paves the way for exploring the importance of adaptive experiments in bridging research and practice to achieve continuous improvement in educational settings.
Authors: Swarnadeep Saha, Omer Levy, Asli Celikyilmaz, Mohit Bansal, Jason Weston, Xian Li
Abstract: Large Language Models (LLMs) are frequently used for multi-faceted language generation and evaluation tasks that involve satisfying intricate user constraints or taking into account multiple aspects and criteria. However, their performance can fall short, due to the model's lack of coherence and inability to plan and decompose the problem. We propose Branch-Solve-Merge (BSM), a Large Language Model program (Schlag et al., 2023) for tackling such challenging natural language tasks. It consists of branch, solve, and merge modules that are parameterized with specific prompts to the base LLM. These three modules plan a decomposition of the task into multiple parallel sub-tasks, independently solve them, and fuse the solutions to the sub-tasks. We apply our method to the tasks of LLM response evaluation and constrained text generation and evaluate its effectiveness with multiple LLMs, including Vicuna, LLaMA-2-chat, and GPT-4. BSM improves the evaluation correctness and consistency for each LLM by enhancing human-LLM agreement by up to 26%, reducing length and pairwise position biases by up to 50%, and allowing LLaMA2-chat to match or outperform GPT-4 on most domains. On a constraint story generation task, BSM improves the coherence of stories while also improving constraint satisfaction by 12%.
Authors: Hiroshi Morioka, Aapo Hyv\"arinen
Abstract: A topic of great current interest is Causal Representation Learning (CRL), whose goal is to learn a causal model for hidden features in a data-driven manner. Unfortunately, CRL is severely ill-posed since it is a combination of the two notoriously ill-posed problems of representation learning and causal discovery. Yet, finding practical identifiability conditions that guarantee a unique solution is crucial for its practical applicability. Most approaches so far have been based on assumptions on the latent causal mechanisms, such as temporal causality, or existence of supervision or interventions; these can be too restrictive in actual applications. Here, we show identifiability based on novel, weak constraints, which requires no temporal structure, intervention, nor weak supervision. The approach is based on assuming the observational mixing exhibits a suitable grouping of the observational variables. We also propose a novel self-supervised estimation framework consistent with the model, prove its statistical consistency, and experimentally show its superior CRL performances compared to the state-of-the-art baselines. We further demonstrate its robustness against latent confounders and causal cycles.
Authors: Aaron Lou, Chenlin Meng, Stefano Ermon
Abstract: Despite their groundbreaking performance for many generative modeling tasks, diffusion models have fallen short on discrete data domains such as natural language. Crucially, standard diffusion models rely on the well-established theory of score matching, but efforts to generalize this to discrete structures have not yielded the same empirical gains. In this work, we bridge this gap by proposing score entropy, a novel loss that naturally extends score matching to discrete spaces, integrates seamlessly to build discrete diffusion models, and significantly boosts performance. Experimentally, we test our Score Entropy Discrete Diffusion models (SEDD) on standard language modeling tasks. For comparable model sizes, SEDD beats existing language diffusion paradigms (reducing perplexity by $25$-$75$\%) and is competitive with autoregressive models, in particular outperforming GPT-2. Furthermore, compared to autoregressive mdoels, SEDD generates faithful text without requiring distribution annealing techniques like temperature scaling (around $6$-$8\times$ better generative perplexity than un-annealed GPT-2), can trade compute and quality (similar quality with $32\times$ fewer network evaluations), and enables controllable infilling (matching nucleus sampling quality while enabling other strategies besides left to right prompting).
Authors: Maria Cuellar, Sheng Gao, Heike Hofmann
Abstract: Forensic toolmark analysis traditionally relies on subjective human judgment, leading to inconsistencies and lack of transparency. The multitude of variables, including angles and directions of mark generation, further complicates comparisons. To address this, we first generate a dataset of 3D toolmarks from various angles and directions using consecutively manufactured slotted screwdrivers. By using PAM clustering, we find that there is clustering by tool rather than angle or direction. Using Known Match and Known Non-Match densities, we establish thresholds for classification. Fitting Beta distributions to the densities, we allow for the derivation of likelihood ratios for new toolmark pairs. With a cross-validated sensitivity of 98% and specificity of 96%, our approach enhances the reliability of toolmark analysis. This approach is applicable to slotted screwdrivers, and for screwdrivers that are made with a similar production method. With data collection of other tools and factors, it could be applied to compare toolmarks of other types. This empirically trained, open-source solution offers forensic examiners a standardized means to objectively compare toolmarks, potentially decreasing the number of miscarriages of justice in the legal system.
Authors: Easton K. Huch, Jieru Shi, Madeline R. Abbott, Jessica R. Golbus, Alexander Moreno, Walter H. Dempsey
Abstract: Mobile health leverages personalized, contextually-tailored interventions optimized through bandit and reinforcement learning algorithms. Despite its promise, challenges like participant heterogeneity, nonstationarity, and nonlinearity in rewards hinder algorithm performance. We propose a robust contextual bandit algorithm, termed "DML-TS-NNR", that simultaneously addresses these challenges via (1) modeling the differential reward with user- and time-specific incidental parameters, (2) network cohesion penalties, and (3) debiased machine learning for flexible estimation of baseline rewards. We establish a high-probability regret bound that depends solely on the dimension of the differential reward model. This feature enables us to achieve robust regret bounds even when the baseline reward is highly complex. We demonstrate the superior performance of the DML-TS-NNR algorithm in a simulation and two off-policy evaluation studies.
Authors: Joseph Sobek, Jose R. Medina Inojosa, Betsy J. Medina Inojosa, S. M. Rassoulinejad-Mousavi, Gian Marco Conte, Francisco Lopez-Jimenez, Bradley J. Erickson
Abstract: Artificial intelligence-enhanced identification of organs, lesions, and other structures in medical imaging is typically done using convolutional neural networks (CNNs) designed to make voxel-accurate segmentations of the region of interest. However, the labels required to train these CNNs are time-consuming to generate and require attention from subject matter experts to ensure quality. For tasks where voxel-level precision is not required, object detection models offer a viable alternative that can reduce annotation effort. Despite this potential application, there are few options for general purpose object detection frameworks available for 3-D medical imaging. We report on MedYOLO, a 3-D object detection framework using the one-shot detection method of the YOLO family of models and designed for use with medical imaging. We tested this model on four different datasets: BRaTS, LIDC, an abdominal organ Computed Tomography (CT) dataset, and an ECG-gated heart CT dataset. We found our models achieve high performance on commonly present medium and large-sized structures such as the heart, liver, and pancreas even without hyperparameter tuning. However, the models struggle with very small or rarely present structures.
Authors: Micha{\l} Derezi\'nski, Jiaming Yang
Abstract: We give a stochastic optimization algorithm that solves a dense $n\times n$ real-valued linear system $Ax=b$, returning $\tilde x$ such that $\|A\tilde x-b\|\leq \epsilon\|b\|$ in time: $$\tilde O((n^2+nk^{\omega-1})\log1/\epsilon),$$ where $k$ is the number of singular values of $A$ larger than $O(1)$ times its smallest positive singular value, $\omega < 2.372$ is the matrix multiplication exponent, and $\tilde O$ hides a poly-logarithmic in $n$ factor. When $k=O(n^{1-\theta})$ (namely, $A$ has a flat-tailed spectrum, e.g., due to noisy data or regularization), this improves on both the cost of solving the system directly, as well as on the cost of preconditioning an iterative method such as conjugate gradient. In particular, our algorithm has an $\tilde O(n^2)$ runtime when $k=O(n^{0.729})$. We further adapt this result to sparse positive semidefinite matrices and least squares regression. Our main algorithm can be viewed as a randomized block coordinate descent method, where the key challenge is simultaneously ensuring good convergence and fast per-iteration time. In our analysis, we use theory of majorization for elementary symmetric polynomials to establish a sharp convergence guarantee when coordinate blocks are sampled using a determinantal point process. We then use a Markov chain coupling argument to show that similar convergence can be attained with a cheaper sampling scheme, and accelerate the block coordinate descent update via matrix sketching.
Authors: Andr\'e Silva, Sen Fang, Martin Monperrus
Abstract: Automated Program Repair (APR) has evolved significantly with the advent of Large Language Models (LLMs). Fine-tuning LLMs for program repair is a recent avenue of research, with many dimensions which have not been explored. Existing work mostly fine-tune LLMs with naive code representations and does not scale to frontier models. To address this problem, we propose RepairLLaMA, a novel program repair approach that 1) identifies optimal code representations for APR with fine-tuned models, and 2) pioneers state-of-the-art parameter-efficient fine-tuning technique (PEFT) for program repair. This results in RepairLLaMA producing a highly effective `program repair adapter' for fixing bugs with AI. Our experiments demonstrate the validity of both concepts. First, fine-tuning adapters with program repair specific code representations enables the model to use meaningful repair signals and produce better patches. Second, parameter-efficient fine-tuning helps fine-tuning to converge and clearly contributes to the effectiveness of RepairLLaMA in fixing bugs outside the fine-tuning data distribution. Overall, RepairLLaMA correctly fixes 144 Defects4J v2 and 109 HumanEval-Java bugs, outperforming all baselines.
Authors: Michael Potter, Stefano Maxenti, Michael Everett
Abstract: Survival Analysis (SA) is about modeling the time for an event of interest to occur, which has important applications in many fields, including medicine, defense, finance, and aerospace. Recent work has demonstrated the benefits of using Neural Networks (NNs) to capture complicated relationships in SA. However, the datasets used to train these models are often subject to uncertainty (e.g., noisy measurements, human error), which we show can substantially degrade the performance of existing techniques. To address this issue, this work leverages recent advances in NN verification to provide new algorithms for generating fully parametric survival models that are robust to such uncertainties. In particular, we introduce a robust loss function for training the models and use CROWN-IBP regularization to address the computational challenges with solving the resulting Min-Max problem. To evaluate the proposed approach, we apply relevant perturbations to publicly available datasets in the SurvSet repository and compare survival models against several baselines. We empirically show that Survival Analysis with Adversarial Regularization (SAWAR) method on average ranks best for dataset perturbations of varying magnitudes on metrics such as Negative Log Likelihood (NegLL), Integrated Brier Score (IBS), and Concordance Index (CI), concluding that adversarial regularization enhances performance in SA. Code: https://github.com/mlpotter/SAWAR
Authors: Asma Ghandeharioun, Avi Caciularu, Adam Pearce, Lucas Dixon, Mor Geva
Abstract: Understanding the internal representations of large language models (LLMs) can help explain models' behavior and verify their alignment with human values. Given the capabilities of LLMs in generating human-understandable text, we propose leveraging the model itself to explain its internal representations in natural language. We introduce a framework called Patchscopes and show how it can be used to answer a wide range of questions about an LLM's computation. We show that many prior interpretability methods based on projecting representations into the vocabulary space and intervening on the LLM computation can be viewed as instances of this framework. Moreover, several of their shortcomings such as failure in inspecting early layers or lack of expressivity can be mitigated by Patchscopes. Beyond unifying prior inspection techniques, Patchscopes also opens up new possibilities such as using a more capable model to explain the representations of a smaller model, and multihop reasoning error correction.
Authors: Bang An, Mucong Ding, Tahseen Rabbani, Aakriti Agrawal, Yuancheng Xu, Chenghao Deng, Sicheng Zhu, Abdirisak Mohamed, Yuxin Wen, Tom Goldstein, Furong Huang
Abstract: In the burgeoning age of generative AI, watermarks act as identifiers of provenance and artificial content. We present WAVES (Watermark Analysis Via Enhanced Stress-testing), a benchmark for assessing image watermark robustness, overcoming the limitations of current evaluation methods. WAVES integrates detection and identification tasks and establishes a standardized evaluation protocol comprised of a diverse range of stress tests. The attacks in WAVES range from traditional image distortions to advanced, novel variations of diffusive, and adversarial attacks. Our evaluation examines two pivotal dimensions: the degree of image quality degradation and the efficacy of watermark detection after attacks. Our novel, comprehensive evaluation reveals previously undetected vulnerabilities of several modern watermarking algorithms. We envision WAVES as a toolkit for the future development of robust watermarks. The project is available at https://wavesbench.github.io/
Authors: Li Meng, Morten Goodwin, Anis Yazidi, Paal Engelstad
Abstract: Vision Transformers implement multi-head self-attention via stacking multiple attention blocks. The query, key, and value are often intertwined and generated within those blocks via a single, shared linear transformation. This paper explores the concept of disentangling the key from the query and value, and adopting a manifold representation for the key. Our experiments reveal that decoupling and endowing the key with a manifold structure can enhance the model's performance. Specifically, ViT-B exhibits a 0.87% increase in top-1 accuracy, while Swin-T sees a boost of 0.52% in top-1 accuracy on the ImageNet-1K dataset, with eight charts in the manifold key. Our approach also yields positive results in object detection and instance segmentation tasks on the COCO dataset. We establish that these performance gains are not merely due to the simplicity of adding more parameters and computations. Future research may investigate strategies for cutting the budget of such representations and aim for further performance improvements based on our findings.
Authors: Lijun Li, Bowen Dong, Ruohui Wang, Xuhao Hu, Wangmeng Zuo, Dahua Lin, Yu Qiao, Jing Shao
Abstract: In the rapidly evolving landscape of Large Language Models (LLMs), ensuring robust safety measures is paramount. To meet this crucial need, we propose \emph{SALAD-Bench}, a safety benchmark specifically designed for evaluating LLMs, attack, and defense methods. Distinguished by its breadth, SALAD-Bench transcends conventional benchmarks through its large scale, rich diversity, intricate taxonomy spanning three levels, and versatile functionalities.SALAD-Bench is crafted with a meticulous array of questions, from standard queries to complex ones enriched with attack, defense modifications and multiple-choice. To effectively manage the inherent complexity, we introduce an innovative evaluators: the LLM-based MD-Judge for QA pairs with a particular focus on attack-enhanced queries, ensuring a seamless, and reliable evaluation. Above components extend SALAD-Bench from standard LLM safety evaluation to both LLM attack and defense methods evaluation, ensuring the joint-purpose utility. Our extensive experiments shed light on the resilience of LLMs against emerging threats and the efficacy of contemporary defense tactics. Data and evaluator are released under https://github.com/OpenSafetyLab/SALAD-BENCH.
Authors: Carlo Alfano, Sebastian Towers, Silvia Sapora, Chris Lu, Patrick Rebeschini
Abstract: Policy Mirror Descent (PMD) is a popular framework in reinforcement learning, serving as a unifying perspective that encompasses numerous algorithms. These algorithms are derived through the selection of a mirror map and enjoy finite-time convergence guarantees. Despite its popularity, the exploration of PMD's full potential is limited, with the majority of research focusing on a particular mirror map -- namely, the negative entropy -- which gives rise to the renowned Natural Policy Gradient (NPG) method. It remains uncertain from existing theoretical studies whether the choice of mirror map significantly influences PMD's efficacy. In our work, we conduct empirical investigations to show that the conventional mirror map choice (NPG) often yields less-than-optimal outcomes across several standard benchmark environments. Using evolutionary strategies, we identify more efficient mirror maps that enhance the performance of PMD. We first focus on a tabular environment, i.e. Grid-World, where we relate existing theoretical bounds with the performance of PMD for a few standard mirror maps and the learned one. We then show that it is possible to learn a mirror map that outperforms the negative entropy in more complex environments, such as the MinAtar suite. Our results suggest that mirror maps generalize well across various environments, raising questions about how to best match a mirror map to an environment's structure and characteristics.
Authors: Mario Truss, Marc Schmitt
Abstract: This paper addresses the complexities inherent in AI product prototyping, focusing on the challenges posed by the probabilistic nature of AI behavior and the limited accessibility of prototyping tools to non-experts. A Design Science Research (DSR) approach is presented which culminates in a conceptual framework aimed at improving the AI prototyping process. Through a comprehensive literature review, key challenges were identified and no-code AutoML was analyzed as a solution. The framework describes the seamless incorporation of non-expert input and evaluation during prototyping, leveraging the potential of no-code AutoML to enhance accessibility and interpretability. A hybrid approach of combining naturalistic (case study) and artificial evaluation methods (criteria-based analysis) validated the utility of our approach, highlighting its efficacy in supporting AI non-experts and streamlining decision-making and its limitations. Implications for academia and industry, emphasizing the strategic integration of no-code AutoML to enhance AI product development processes, mitigate risks, and foster innovation, are discussed.
Authors: Jiaheng Wei, Yuanshun Yao, Jean-Francois Ton, Hongyi Guo, Andrew Estornell, Yang Liu
Abstract: LLM hallucination, i.e. generating factually incorrect yet seemingly convincing answers, is currently a major threat to the trustworthiness and reliability of LLMs. The first step towards solving this complicated problem is to measure it. However, existing hallucination metrics require having a benchmark dataset with gold-standard answers, i.e. "best" or "correct" answers written by humans. Such requirements make hallucination measurement costly and prone to human errors. In this work, we propose Factualness Evaluations via Weighting LLMs (FEWL), an innovative hallucination metric that is specifically designed for the scenario when gold-standard answers are absent. FEWL leverages the answers from off-the-shelf LLMs that serve as a proxy of gold-standard answers. The key challenge is how to quantify the expertise of reference LLMs resourcefully. We show FEWL has certain theoretical guarantees and demonstrate empirically it gives more accurate hallucination measures than naively using reference LLMs. We also show how to leverage FEWL to reduce hallucination through both in-context learning and supervised fine-tuning. Extensive experiment results on Truthful-QA, CHALE, and HaluEval datasets demonstrate the effectiveness of FEWL.
Authors: Henry W. Sprueill, Carl Edwards, Khushbu Agarwal, Mariefel V. Olarte, Udishnu Sanyal, Conrad Johnston, Hongbin Liu, Heng Ji, Sutanay Choudhury
Abstract: The discovery of new catalysts is essential for the design of new and more efficient chemical processes in order to transition to a sustainable future. We introduce an AI-guided computational screening framework unifying linguistic reasoning with quantum-chemistry based feedback from 3D atomistic representations. Our approach formulates catalyst discovery as an uncertain environment where an agent actively searches for highly effective catalysts via the iterative combination of large language model (LLM)-derived hypotheses and atomistic graph neural network (GNN)-derived feedback. Identified catalysts in intermediate search steps undergo structural evaluation based on spatial orientation, reaction pathways, and stability. Scoring functions based on adsorption energies and reaction energy barriers steer the exploration in the LLM's knowledge space toward energetically favorable, high-efficiency catalysts. We introduce planning methods that automatically guide the exploration without human input, providing competitive performance against expert-enumerated chemical descriptor-based implementations. By integrating language-guided reasoning with computational chemistry feedback, our work pioneers AI-accelerated, trustworthy catalyst discovery.
Authors: Kaijie Zhu, Jindong Wang, Qinlin Zhao, Ruochen Xu, Xing Xie
Abstract: Evaluation of large language models (LLMs) has raised great concerns in the community due to the issue of data contamination. Existing work designed evaluation protocols using well-defined algorithms for specific tasks, which cannot be easily extended to diverse scenarios. Moreover, current evaluation benchmarks can only provide the overall benchmark results and cannot support a fine-grained and multifaceted analysis of LLMs' abilities. In this paper, we propose meta probing agents (MPA), a general dynamic evaluation protocol inspired by psychometrics to evaluate LLMs. MPA is the key component of DyVal 2, which naturally extends the previous DyVal~\citep{zhu2023dyval}. MPA designs the probing and judging agents to automatically transform an original evaluation problem into a new one following psychometric theory on three basic cognitive abilities: language understanding, problem solving, and domain knowledge. These basic abilities are also dynamically configurable, allowing multifaceted analysis. We conducted extensive evaluations using MPA and found that most LLMs achieve poorer performance, indicating room for improvement. Our multifaceted analysis demonstrated the strong correlation between the basic abilities and an implicit Matthew effect on model size, i.e., larger models possess stronger correlations of the abilities. MPA can also be used as a data augmentation approach to enhance LLMs. Code is available at: https://github.com/microsoft/promptbench.
Authors: Michael J. Ryan, William Held, Diyi Yang
Abstract: Before being deployed for user-facing applications, developers align Large Language Models (LLMs) to user preferences through a variety of procedures, such as Reinforcement Learning From Human Feedback (RLHF) and Direct Preference Optimization (DPO). Current evaluations of these procedures focus on benchmarks of instruction following, reasoning, and truthfulness. However, human preferences are not universal, and aligning to specific preference sets may have unintended effects. We explore how alignment impacts performance along three axes of global representation: English dialects, multilingualism, and opinions from and about countries worldwide. Our results show that current alignment procedures create disparities between English dialects and global opinions. We find alignment improves capabilities in several languages. We conclude by discussing design decisions that led to these unintended impacts and recommendations for more equitable preference tuning. We make our code and data publicly available on Github.
Authors: Ekaterina Fadeeva, Aleksandr Rubashevskii, Artem Shelmanov, Sergey Petrakov, Haonan Li, Hamdy Mubarak, Evgenii Tsymbalov, Gleb Kuzmin, Alexander Panchenko, Timothy Baldwin, Preslav Nakov, Maxim Panov
Abstract: Large language models (LLMs) are notorious for hallucinating, i.e., producing erroneous claims in their output. Such hallucinations can be dangerous, as occasional factual inaccuracies in the generated text might be obscured by the rest of the output being generally factually correct, making it extremely hard for the users to spot them. Current services that leverage LLMs usually do not provide any means for detecting unreliable generations. Here, we aim to bridge this gap. In particular, we propose a novel fact-checking and hallucination detection pipeline based on token-level uncertainty quantification. Uncertainty scores leverage information encapsulated in the output of a neural network or its layers to detect unreliable predictions, and we show that they can be used to fact-check the atomic claims in the LLM output. Moreover, we present a novel token-level uncertainty quantification method that removes the impact of uncertainty about what claim to generate on the current step and what surface form to use. Our method Claim Conditioned Probability (CCP) measures only the uncertainty of a particular claim value expressed by the model. Experiments on the task of biography generation demonstrate strong improvements for CCP compared to the baselines for seven LLMs and four languages. Human evaluation reveals that the fact-checking pipeline based on uncertainty quantification is competitive with a fact-checking tool that leverages external knowledge.
Authors: Charles C. Margossian, Loucas Pillaud-Vivien, Lawrence K. Saul
Abstract: Given an intractable distribution $p$, the problem of variational inference (VI) is to find the best approximation from some more tractable family $Q$. Commonly, one chooses $Q$ to be a family of factorized distributions (i.e., the mean-field assumption), even though~$p$ itself does not factorize. We show that this mismatch leads to an impossibility theorem: if $p$ does not factorize, then any factorized approximation $q\in Q$ can correctly estimate at most one of the following three measures of uncertainty: (i) the marginal variances, (ii) the marginal precisions, or (iii) the generalized variance (which can be related to the entropy). In practice, the best variational approximation in $Q$ is found by minimizing some divergence $D(q,p)$ between distributions, and so we ask: how does the choice of divergence determine which measure of uncertainty, if any, is correctly estimated by VI? We consider the classic Kullback-Leibler divergences, the more general R\'enyi divergences, and a score-based divergence which compares $\nabla \log p$ and $\nabla \log q$. We provide a thorough theoretical analysis in the setting where $p$ is a Gaussian and $q$ is a (factorized) Gaussian. We show that all the considered divergences can be \textit{ordered} based on the estimates of uncertainty they yield as objective functions for~VI. Finally, we empirically evaluate the validity of this ordering when the target distribution $p$ is not Gaussian.
Authors: Yi Luo, Jianwei Yu, Hangting Chen, Rongzhi Gu, Chao Weng
Abstract: We introduce Gull, a generative multifunctional audio codec. Gull is a general purpose neural audio compression and decompression model which can be applied to a wide range of tasks and applications such as real-time communication, audio super-resolution, and codec language models. The key components of Gull include (1) universal-sample-rate modeling via subband modeling schemes motivated by recent progress in audio source separation, (2) gain-shape representations motivated by traditional audio codecs, (3) improved residual vector quantization modules, (4) elastic decoder network that enables user-defined model size and complexity during inference time, (5) built-in ability for audio super-resolution without the increase of bitrate. We compare Gull with existing traditional and neural audio codecs and show that Gull is able to achieve on par or better performance across various sample rates, bitrates and model complexities in both subjective and objective evaluation metrics.
Authors: Julia Linhart, Gabriel Victorino Cardoso, Alexandre Gramfort, Sylvain Le Corff, Pedro L. C. Rodrigues
Abstract: Determining which parameters of a non-linear model best describe a set of experimental data is a fundamental problem in science and it has gained much traction lately with the rise of complex large-scale simulators. The likelihood of such models is typically intractable, which is why classical MCMC methods can not be used. Simulation-based inference (SBI) stands out in this context by only requiring a dataset of simulations to train deep generative models capable of approximating the posterior distribution that relates input parameters to a given observation. In this work, we consider a tall data extension in which multiple observations are available to better infer the parameters of the model. The proposed method is built upon recent developments from the flourishing score-based diffusion literature and allows to estimate the tall data posterior distribution, while simply using information from a score network trained for a single context observation. We compare our method to recently proposed competing approaches on various numerical experiments and demonstrate its superiority in terms of numerical stability and computational cost.
Authors: Emile van Krieken, Pasquale Minervini, Edoardo M. Ponti, Antonio Vergari
Abstract: State-of-the-art neurosymbolic learning systems use probabilistic reasoning to guide neural networks towards predictions that conform to logical constraints over symbols. Many such systems assume that the probabilities of the considered symbols are conditionally independent given the input to simplify learning and reasoning. We study and criticise this assumption, highlighting how it can hinder optimisation and prevent uncertainty quantification. We prove that loss functions bias conditionally independent neural networks to become overconfident in their predictions. As a result, they are unable to represent uncertainty over multiple valid options. Furthermore, we prove that these loss functions are difficult to optimise: they are non-convex, and their minima are usually highly disconnected. Our theoretical analysis gives the foundation for replacing the conditional independence assumption and designing more expressive neurosymbolic probabilistic models.
Authors: Rahul Srinivasan, Marco Crisostomi, Roberto Trotta, Enrico Barausse, Matteo Breschi
Abstract: We introduce $floZ$, an improved method based on normalizing flows, for estimating the Bayesian evidence (and its numerical uncertainty) from a set of samples drawn from the unnormalized posterior distribution. We validate it on distributions whose evidence is known analytically, up to 15 parameter space dimensions, and compare with two state-of-the-art techniques for estimating the evidence: nested sampling (which computes the evidence as its main target) and a $k$-nearest-neighbors technique that produces evidence estimates from posterior samples. Provided representative samples from the target posterior are available, our method is more robust to posterior distributions with sharp features, especially in higher dimensions. For a simple multivariate Gaussian, we demonstrate its accuracy for up to 200 dimensions with $10^5$ posterior samples. $floZ$ has wide applicability, e.g., to estimate the evidence from variational inference, Markov Chain Monte Carlo samples, or any other method that delivers samples from the unnormalized posterior density, such as simulation-based inference. We apply $floZ$ to compute the Bayes factor for the presence of the first overtone in the ringdown signal of the gravitational wave data of GW150914, finding good agreement with nested sampling.
Authors: Yifeng Ding, Jiawei Liu, Yuxiang Wei, Terry Yue Zhuo, Lingming Zhang
Abstract: We introduce XFT, a simple yet powerful training scheme, by simply merging upcycled Mixture-of-Experts (MoE) to unleash the performance limit of instruction-tuned code Large Language Models (LLMs). While vanilla sparse upcycling fails to improve instruction tuning, XFT introduces a shared expert mechanism with a novel routing weight normalization strategy into sparse upcycling, which significantly boosts instruction tuning. After fine-tuning the upcycled MoE model, XFT introduces a learnable model merging mechanism to compile the upcycled MoE model back to a dense model, achieving upcycled MoE-level performance with only dense-model compute. By applying XFT to a 1.3B model, we create a new state-of-the-art tiny code LLM (<3B) with 67.1 and 64.6 pass@1 on HumanEval and HumanEval+ respectively. With the same data and model architecture, XFT improves supervised fine-tuning (SFT) by 13% on HumanEval+, along with consistent improvements from 2% to 13% on MBPP+, MultiPL-E, and DS-1000, demonstrating its generalizability. XFT is fully orthogonal to existing techniques such as Evol-Instruct and OSS-Instruct, opening a new dimension for improving code instruction tuning. Codes are available at https://github.com/ise-uiuc/xft.
Authors: Robert McCarthy, Daniel C. H. Tan, Dominik Schmidt, Fernando Acero, Nathan Herr, Yilun Du, Thomas G. Thuruthel, Zhibin Li
Abstract: This survey presents an overview of methods for learning from video (LfV) in the context of reinforcement learning (RL) and robotics. We focus on methods capable of scaling to large internet video datasets and, in the process, extracting foundational knowledge about the world's dynamics and physical human behaviour. Such methods hold great promise for developing general-purpose robots. We open with an overview of fundamental concepts relevant to the LfV-for-robotics setting. This includes a discussion of the exciting benefits LfV methods can offer (e.g., improved generalization beyond the available robot data) and commentary on key LfV challenges (e.g., missing information in video and LfV distribution shifts). Our literature review begins with an analysis of video foundation model techniques that can extract knowledge from large, heterogeneous video datasets. Next, we review methods that specifically leverage video data for robot learning. Here, we categorise work according to which RL knowledge modality (KM) benefits from the use of video data. We additionally highlight techniques for mitigating LfV challenges, including reviewing action representations that address missing action labels in video. Finally, we examine LfV datasets and benchmarks, before concluding with a discussion of challenges and opportunities in LfV. Here, we advocate for scalable foundation model approaches that can leverage the full range of internet video data, and that target the learning of the most promising RL KMs: the policy and dynamics model. Overall, we hope this survey will serve as a comprehensive reference for the emerging field of LfV, catalysing further research in the area and facilitating progress towards the development of general-purpose robots.
Authors: Yanjun Fu, Ethan Baker, Yu Ding, Yizheng Chen
Abstract: Code Large Language Models (Code LLMs) have been increasingly used by developers to boost productivity, but they often generate vulnerable code. Thus, there is an urgent need to ensure that code generated by Code LLMs is correct and secure. Previous research has primarily focused on generating secure code, overlooking the fact that secure code also needs to be correct. This oversight can lead to a false sense of security. Currently, the community lacks a method to measure actual progress in this area, and we need solutions that address both security and correctness of code generation. This paper introduces a new benchmark, CodeGuard+, along with two new metrics, to measure Code LLMs' ability to generate both secure and correct code. Using our new evaluation methods, we show that the state-of-the-art defense technique, prefix tuning, may not be as strong as previously believed, since it generates secure code but sacrifices functional correctness. We also demonstrate that different decoding methods significantly affect the security of Code LLMs. Furthermore, we explore a new defense direction: constrained decoding for secure code generation. We propose new constrained decoding techniques to generate secure code. Our results reveal that constrained decoding is more effective than prefix tuning to improve the security of Code LLMs, without requiring a specialized training dataset. Moreover, our evaluations over eight state-of-the-art Code LLMs show that constrained decoding has strong performance to improve the security of Code LLMs, and our technique outperforms GPT-4.
Authors: Hanyin Wang, Chufan Gao, Bolun Liu, Qiping Xu, Guleid Hussein, Mohamad El Labban, Kingsley Iheasirim, Hariprasad Korsapati, Chuck Outcalt, Jimeng Sun
Abstract: Proprietary Large Language Models (LLMs) such as GPT-4 and Gemini have demonstrated promising capabilities in clinical text summarization tasks. However, due to patient data privacy concerns and computational costs, many healthcare providers prefer using small, locally-hosted models over external generic LLMs. This study presents a comprehensive domain- and task-specific adaptation process for the open-source LLaMA-2 13 billion parameter model, enabling it to generate high-quality clinical notes from outpatient patient-doctor dialogues. Our process incorporates continued pre-training, supervised fine-tuning, and reinforcement learning from both AI and human feedback. We introduced a new approach, DistillDirect, for performing on-policy reinforcement learning with Gemini 1.0 Pro as the teacher model. Our resulting model, LLaMA-Clinic, can generate clinical notes comparable in quality to those authored by physicians. In a blinded physician reader study, the majority (90.4%) of individual evaluations rated the notes generated by LLaMA-Clinic as "acceptable" or higher across all three criteria: real-world readiness, completeness, and accuracy. In the more challenging "Assessment and Plan" section, LLaMA-Clinic scored higher (4.2/5) in real-world readiness than physician-authored notes (4.1/5). Our cost analysis for inference shows that our LLaMA-Clinic model achieves a 4.375-fold cost reduction compared to an external generic LLM service. Additionally, we highlight key considerations for future clinical note-generation tasks, emphasizing the importance of pre-defining a best-practice note format, rather than relying on LLMs to determine this for clinical practice. We have made our newly created synthetic clinic dialogue-note dataset and the physician feedback dataset publicly available to foster future research.
Authors: Abrar Fahim, Alex Murphy, Alona Fyshe
Abstract: Multi-modal contrastive models such as CLIP achieve state-of-the-art performance in zero-shot classification by embedding input images and texts on a joint representational space. Recently, a modality gap has been reported in two-encoder contrastive models like CLIP, meaning that the image and text embeddings reside in disjoint areas of the latent space. Previous studies suggest that this gap exists due to 1) the cone effect, 2) mismatched pairs in the dataset, and 3) insufficient training. We show that, even when accounting for all these factors, and even when using the same modality, the contrastive loss actually creates a gap during training. As a result, We propose that the modality gap is inherent to the two-encoder contrastive loss and rename it the contrastive gap. We present evidence that attributes this contrastive gap to low uniformity in CLIP space, resulting in embeddings that occupy only a small portion of the latent space. To close the gap, we adapt the uniformity and alignment properties of unimodal contrastive loss to the multi-modal setting and show that simply adding these terms to the CLIP loss distributes the embeddings more uniformly in the representational space, closing the gap. In our experiments, we show that the modified representational space achieves better performance than default CLIP loss in downstream tasks such as zero-shot image classification and multi-modal arithmetic.
Authors: Wenbo Hu, Zi-Yi Dou, Liunian Harold Li, Amita Kamath, Nanyun Peng, Kai-Wei Chang
Abstract: Large Vision-Language Models (LVLMs) typically encode an image into a fixed number of visual tokens (e.g., 576) and process these tokens with a language model. Despite their strong performance, LVLMs face challenges in adapting to varying computational constraints. This raises the question: can we achieve flexibility in the number of visual tokens to suit different tasks and computational resources? We answer this with an emphatic yes. Inspired by Matryoshka Representation Learning, we introduce the Matryoshka Query Transformer (MQT), capable of encoding an image into m visual tokens during inference, where m can be any number up to a predefined maximum. This is achieved by employing a query transformer with M latent query tokens to compress the visual embeddings. During each training step, we randomly select m <= M latent query tokens and train the model using only these first m tokens, discarding the rest. Combining MQT with LLaVA, we train a single model once, and flexibly and drastically reduce the number of inference-time visual tokens while maintaining similar or better performance compared to training independent models for each number of tokens. Our model, MQT-LLAVA, matches LLaVA-1.5 performance across 11 benchmarks using a maximum of 256 tokens instead of LLaVA's fixed 576. Reducing to 16 tokens (8x less TFLOPs) only sacrifices the performance by 2.4 points on MMBench. On certain tasks such as ScienceQA and MMMU, we can even go down to only 2 visual tokens with performance drops of just 3% and 6% each. Our exploration of the trade-off between the accuracy and computational cost brought about by the number of visual tokens facilitates future research to achieve the best of both worlds.
Authors: Maya Anderson, Guy Amit, Abigail Goldsteen
Abstract: Retrieval Augmented Generation (RAG) systems have shown great promise in natural language processing. However, their reliance on data stored in a retrieval database, which may contain proprietary or sensitive information, introduces new privacy concerns. Specifically, an attacker may be able to infer whether a certain text passage appears in the retrieval database by observing the outputs of the RAG system, an attack known as a Membership Inference Attack (MIA). Despite the significance of this threat, MIAs against RAG systems have yet remained under-explored. This study addresses this gap by introducing an efficient and easy-to-use method for conducting MIA against RAG systems. We demonstrate the effectiveness of our attack using two benchmark datasets and multiple generative models, showing that the membership of a document in the retrieval database can be efficiently determined through the creation of an appropriate prompt in both black-box and gray-box settings. Moreover, we introduce an initial defense strategy based on adding instructions to the RAG template, which shows high effectiveness for some datasets and models. Our findings highlight the importance of implementing security countermeasures in deployed RAG systems and developing more advanced defenses to protect the privacy and security of retrieval databases.
Authors: Yunling Ma, Chaojun Zhang, Xiaochuan Wang, Qianqian Wang, Liang Cao, Limei Zhang, Mingxia Liu
Abstract: Major depressive disorder (MDD) is a common mental disorder that typically affects a person's mood, cognition, behavior, and physical health. Resting-state functional magnetic resonance imaging (rs-fMRI) data are widely used for computer-aided diagnosis of MDD. While multi-site fMRI data can provide more data for training reliable diagnostic models, significant cross-site data heterogeneity would result in poor model generalizability. Many domain adaptation methods are designed to reduce the distributional differences between sites to some extent, but usually ignore overfitting problem of the model on the source domain. Intuitively, target data augmentation can alleviate the overfitting problem by forcing the model to learn more generalized features and reduce the dependence on source domain data. In this work, we propose a new augmentation-based unsupervised cross-domain fMRI adaptation (AUFA) framework for automatic diagnosis of MDD. The AUFA consists of 1) a graph representation learning module for extracting rs-fMRI features with spatial attention, 2) a domain adaptation module for feature alignment between source and target data, 3) an augmentation-based self-optimization module for alleviating model overfitting on the source domain, and 4) a classification module. Experimental results on 1,089 subjects suggest that AUFA outperforms several state-of-the-art methods in MDD identification. Our approach not only reduces data heterogeneity between different sites, but also localizes disease-related functional connectivity abnormalities and provides interpretability for the model.
Authors: Alexis M. H. Teter, Wenqing Wang, Abhishek Halder
Abstract: Schr\"odinger bridge is a diffusion process that steers a given distribution to another in a prescribed time while minimizing the effort to do so. It can be seen as the stochastic dynamical version of the optimal mass transport, and has growing applications in generative diffusion models and stochastic optimal control. In this work, we propose a regularized variant of the Schr\"odinger bridge with a quadratic state cost-to-go that incentivizes the optimal sample paths to stay close to a nominal level. Unlike the conventional Schr\"odinger bridge, the regularization induces a state-dependent rate of killing and creation of probability mass, and its solution requires determining the Markov kernel of a reaction-diffusion partial differential equation. We derive this Markov kernel in closed form. Our solution recovers the heat kernel in the vanishing regularization (i.e., diffusion without reaction) limit, thereby recovering the solution of the conventional Schr\"odinger bridge. Our results enable the use of dynamic Sinkhorn recursion for computing the Schr\"odinger bridge with a quadratic state cost-to-go, which would otherwise be challenging to use in this setting. We deduce properties of the new kernel and explain its connections with certain exactly solvable models in quantum mechanics.
Authors: Wei Chen, Yuanyuan Yang, Jianyu Liu
Abstract: Accurate prediction of financial time series is a key concern for market economy makers and investors. The article selects online store sales and Australian beer sales as representatives of non-stationary, trending, and seasonal financial time series, and constructs a new SGVMD-ARIMA combination model in a non-linear combination way to predict financial time series. The ARIMA model, LSTM model, and other classic decomposition prediction models are used as control models to compare the accuracy of different models. The empirical results indicate that the constructed combination prediction model has universal advantages over the single prediction model and linear combination prediction model of the control group. Within the prediction interval, our proposed combination model has improved advantages over traditional decomposition prediction control group models.
Authors: Fang Chen, Gourav Datta, Mujahid Al Rafi, Hyeran Jeon, Meng Tang
Abstract: The expansion of neural network sizes and the enhancement of image resolution through modern camera sensors result in heightened memory and power demands for neural networks. Reducing peak memory, which is the maximum memory consumed during the execution of a neural network, is critical to deploy neural networks on edge devices with limited memory budget. A naive approach to reducing peak memory is aggressive down-sampling of feature maps via pooling with large stride, which often results in unacceptable degradation in network performance. To mitigate this problem, we propose residual encoded distillation (ReDistill) for peak memory reduction in a teacher-student framework, in which a student network with less memory is derived from the teacher network using aggressive pooling. We apply our distillation method to multiple problems in computer vision including image classification and diffusion based image generation. For image classification, our method yields 2x-3.2x measured peak memory on an edge GPU with negligible degradation in accuracy for most CNN based architectures. Additionally, our method yields improved test accuracy for tiny vision transformer (ViT) based models distilled from large CNN based teacher architectures. For diffusion-based image generation, our proposed distillation method yields a denoising network with 4x lower theoretical peak memory while maintaining decent diversity and fidelity for image generation. Experiments demonstrate our method's superior performance compared to other feature-based and response-based distillation methods.