Authors: Omead Pooladzandi, Jeffrey Jiang, Sunay Bhat, Gregory Pottie
Abstract: Data poisoning attacks pose a significant threat to the integrity of machine learning models by leading to misclassification of target distribution test data by injecting adversarial examples during training. Existing state-of-the-art (SoTA) defense methods suffer from a variety of limitations, such as significantly reduced generalization performance, specificity to particular attack types and classifiers, and significant overhead during training, making them impractical or limited for real-world applications. In response to this challenge, we introduce a universal data purification method that defends naturally trained classifiers from malicious white-, gray-, and black-box image poisons by applying a universal stochastic preprocessing step $\Psi_{T}(x)$, realized by iterative Langevin sampling of a convergent Energy Based Model (EBM) initialized with an image $x.$ Mid-run dynamics of $\Psi_{T}(x)$ purify poison information with minimal impact on features important to the generalization of a classifier network. We show that the contrastive learning process of EBMs allows them to remain universal purifiers, even in the presence of poisoned EBM training data, and to achieve SoTA defense on leading triggered poison Narcissus and triggerless poisons Gradient Matching and Bullseye Polytope. This work is a subset of a larger framework introduced in PureGen with a more detailed focus on EBM purification and poison defense.
Authors: Alexander Politowicz, Sahisnu Mazumder, Bing Liu
Abstract: Designing Reinforcement Learning (RL) solutions for real-life problems remains a significant challenge. A major area of concern is safety. "Shielding" is a popular technique to enforce safety in RL by turning user-defined safety specifications into safe agent behavior. However, these methods either suffer from extreme learning delays, demand extensive human effort in designing models and safe domains in the problem, or require pre-computation. In this paper, we propose a new permissibility-based framework to deal with safety and shield construction. Permissibility was originally designed for eliminating (non-permissible) actions that will not lead to an optimal solution to improve RL training efficiency. This paper shows that safety can be naturally incorporated into this framework, i.e. extending permissibility to include safety, and thereby we can achieve both safety and improved efficiency. Experimental evaluation using three standard RL applications shows the effectiveness of the approach.
Authors: Raja Marjieh, Sreejan Kumar, Declan Campbell, Liyi Zhang, Gianluca Bencomo, Jake Snell, Thomas L. Griffiths
Abstract: Humans rely on strong inductive biases to learn from few examples and abstract useful information from sensory data. Instilling such biases in machine learning models has been shown to improve their performance on various benchmarks including few-shot learning, robustness, and alignment. However, finding effective training procedures to achieve that goal can be challenging as psychologically-rich training data such as human similarity judgments are expensive to scale, and Bayesian models of human inductive biases are often intractable for complex, realistic domains. Here, we address this challenge by introducing a Bayesian notion of generative similarity whereby two datapoints are considered similar if they are likely to have been sampled from the same distribution. This measure can be applied to complex generative processes, including probabilistic programs. We show that generative similarity can be used to define a contrastive learning objective even when its exact form is intractable, enabling learning of spatial embeddings that express specific inductive biases. We demonstrate the utility of our approach by showing how it can be used to capture human inductive biases for geometric shapes, and to better distinguish different abstract drawing styles that are parameterized by probabilistic programs.
Authors: Qi Zhang, Peiyao Xiao, Kaiyi Ji, Shaofeng Zou
Abstract: Multi-objective optimization (MOO) is receiving more attention in various fields such as multi-task learning. Recent works provide some effective algorithms with theoretical analysis but they are limited by the standard $L$-smooth or bounded-gradient assumptions, which are typically unsatisfactory for neural networks, such as recurrent neural networks (RNNs) and transformers. In this paper, we study a more general and realistic class of $\ell$-smooth loss functions, where $\ell$ is a general non-decreasing function of gradient norm. We develop two novel single-loop algorithms for $\ell$-smooth MOO problems, Generalized Smooth Multi-objective Gradient descent (GSMGrad) and its stochastic variant, Stochastic Generalized Smooth Multi-objective Gradient descent (SGSMGrad), which approximate the conflict-avoidant (CA) direction that maximizes the minimum improvement among objectives. We provide a comprehensive convergence analysis of both algorithms and show that they converge to an $\epsilon$-accurate Pareto stationary point with a guaranteed $\epsilon$-level average CA distance (i.e., the gap between the updating direction and the CA direction) over all iterations, where totally $\mathcal{O}(\epsilon^{-2})$ and $\mathcal{O}(\epsilon^{-4})$ samples are needed for deterministic and stochastic settings, respectively. Our algorithms can also guarantee a tighter $\epsilon$-level CA distance in each iteration using more samples. Moreover, we propose a practical variant of GSMGrad named GSMGrad-FA using only constant-level time and space, while achieving the same performance guarantee as GSMGrad. Our experiments validate our theory and demonstrate the effectiveness of the proposed methods.
Authors: Simin Fan, Razvan Pascanu, Martin Jaggi
Abstract: Recent research on the grokking phenomenon has illuminated the intricacies of neural networks' training dynamics and their generalization behaviors. Grokking refers to a sharp rise of the network's generalization accuracy on the test set, which occurs long after an extended overfitting phase, during which the network perfectly fits the training set. While the existing research primarily focus on shallow networks such as 2-layer MLP and 1-layer Transformer, we explore grokking on deep networks (e.g. 12-layer MLP). We empirically replicate the phenomenon and find that deep neural networks can be more susceptible to grokking than its shallower counterparts. Meanwhile, we observe an intriguing multi-stage generalization phenomenon when increase the depth of the MLP model where the test accuracy exhibits a secondary surge, which is scarcely seen on shallow models. We further uncover compelling correspondences between the decreasing of feature ranks and the phase transition from overfitting to the generalization stage during grokking. Additionally, we find that the multi-stage generalization phenomenon often aligns with a double-descent pattern in feature ranks. These observations suggest that internal feature rank could serve as a more promising indicator of the model's generalization behavior compared to the weight-norm. We believe our work is the first one to dive into grokking in deep neural networks, and investigate the relationship of feature rank and generalization performance.
Authors: Andrea Napoli, Paul White
Abstract: This paper considers the problem of model selection under domain shift. In this setting, it is proposed that a high maximum mean discrepancy (MMD) between the training and validation sets increases the generalisability of selected models. A data splitting algorithm based on kernel k-means clustering, which maximises this objective, is presented. The algorithm leverages linear programming to control the size, label, and (optionally) group distributions of the splits, and comes with convergence guarantees. The technique consistently outperforms alternative splitting strategies across a range of datasets and training algorithms, for both domain generalisation (DG) and unsupervised domain adaptation (UDA) tasks. Analysis also shows the MMD between the training and validation sets to be strongly rank-correlated ($\rho=0.63$) with test domain accuracy, further substantiating the validity of this approach.
Authors: Kelly W Zhang (Tianhui), Tiffany (Tianhui), Cai, Hongseok Namkoong, Daniel Russo
Abstract: Real-world decision-making requires grappling with a perpetual lack of data as environments change; intelligent agents must comprehend uncertainty and actively gather information to resolve it. We propose a new framework for learning bandit algorithms from massive historical data, which we demonstrate in a cold-start recommendation problem. First, we use historical data to pretrain an autoregressive model to predict a sequence of repeated feedback/rewards (e.g., responses to news articles shown to different users over time). In learning to make accurate predictions, the model implicitly learns an informed prior based on rich action features (e.g., article headlines) and how to sharpen beliefs as more rewards are gathered (e.g., clicks as each article is recommended). At decision-time, we autoregressively sample (impute) an imagined sequence of rewards for each action, and choose the action with the largest average imputed reward. Far from a heuristic, our approach is an implementation of Thompson sampling (with a learned prior), a prominent active exploration algorithm. We prove our pretraining loss directly controls online decision-making performance, and we demonstrate our framework on a news recommendation task where we integrate end-to-end fine-tuning of a pretrained language model to process news article headline text to improve performance.
Authors: Prakhar Ganesh, Cuong Tran, Reza Shokri, Ferdinando Fioretto
Abstract: The principle of data minimization aims to reduce the amount of data collected, processed or retained to minimize the potential for misuse, unauthorized access, or data breaches. Rooted in privacy-by-design principles, data minimization has been endorsed by various global data protection regulations. However, its practical implementation remains a challenge due to the lack of a rigorous formulation. This paper addresses this gap and introduces an optimization framework for data minimization based on its legal definitions. It then adapts several optimization algorithms to perform data minimization and conducts a comprehensive evaluation in terms of their compliance with minimization objectives as well as their impact on user privacy. Our analysis underscores the mismatch between the privacy expectations of data minimization and the actual privacy benefits, emphasizing the need for approaches that account for multiple facets of real-world privacy risks.
Authors: Han Wang, Sihong He, Zhili Zhang, Fei Miao, James Anderson
Abstract: We explore a Federated Reinforcement Learning (FRL) problem where $N$ agents collaboratively learn a common policy without sharing their trajectory data. To date, existing FRL work has primarily focused on agents operating in the same or ``similar" environments. In contrast, our problem setup allows for arbitrarily large levels of environment heterogeneity. To obtain the optimal policy which maximizes the average performance across all potentially completely different environments, we propose two algorithms: FedSVRPG-M and FedHAPG-M. In contrast to existing results, we demonstrate that both FedSVRPG-M and FedHAPG-M, both of which leverage momentum mechanisms, can exactly converge to a stationary point of the average performance function, regardless of the magnitude of environment heterogeneity. Furthermore, by incorporating the benefits of variance-reduction techniques or Hessian approximation, both algorithms achieve state-of-the-art convergence results, characterized by a sample complexity of $\mathcal{O}\left(\epsilon^{-\frac{3}{2}}/N\right)$. Notably, our algorithms enjoy linear convergence speedups with respect to the number of agents, highlighting the benefit of collaboration among agents in finding a common policy.
Authors: Tomas Ortega, Hamid Jafarkhani
Abstract: We consider a decentralized optimization problem for networks affected by communication delays. Examples of such networks include collaborative machine learning, sensor networks, and multi-agent systems. To mimic communication delays, we add virtual non-computing nodes to the network, resulting in directed graphs. This motivates investigating decentralized optimization solutions on directed graphs. Existing solutions assume nodes know their out-degrees, resulting in limited applicability. To overcome this limitation, we introduce a novel gossip-based algorithm, called DT-GO, that does not need to know the out-degrees. The algorithm is applicable in general directed networks, for example networks with delays or limited acknowledgment capabilities. We derive convergence rates for both convex and non-convex objectives, showing that our algorithm achieves the same complexity order as centralized Stochastic Gradient Descent. In other words, the effects of the graph topology and delays are confined to higher-order terms. Additionally, we extend our analysis to accommodate time-varying network topologies. Numerical simulations are provided to support our theoretical findings.
Authors: Seong Woo Han, Ozan Ad{\i}g\"uzel, Bob Carpenter
Abstract: In applied statistics and machine learning, the "gold standards" used for training are often biased and almost always noisy. Dawid and Skene's justifiably popular crowdsourcing model adjusts for rater (coder, annotator) sensitivity and specificity, but fails to capture distributional properties of rating data gathered for training, which in turn biases training. In this study, we introduce a general purpose measurement-error model with which we can infer consensus categories by adding item-level effects for difficulty, discriminativeness, and guessability. We further show how to constrain the bimodal posterior of these models to avoid (or if necessary, allow) adversarial raters. We validate our model's goodness of fit with posterior predictive checks, the Bayesian analogue of $\chi^2$ tests. Dawid and Skene's model is rejected by goodness of fit tests, whereas our new model, which adjusts for item heterogeneity, is not rejected. We illustrate our new model with two well-studied data sets, binary rating data for caries in dental X-rays and implication in natural language.
Authors: Zoe Piran, Michal Klein, James Thornton, Marco Cuturi
Abstract: Learning meaningful representations of complex objects that can be seen through multiple ($k\geq 3$) views or modalities is a core task in machine learning. Existing methods use losses originally intended for paired views, and extend them to $k$ views, either by instantiating $\tfrac12k(k-1)$ loss-pairs, or by using reduced embeddings, following a \textit{one vs. average-of-rest} strategy. We propose the multi-marginal matching gap (M3G), a loss that borrows tools from multi-marginal optimal transport (MM-OT) theory to simultaneously incorporate all $k$ views. Given a batch of $n$ points, each seen as a $k$-tuple of views subsequently transformed into $k$ embeddings, our loss contrasts the cost of matching these $n$ ground-truth $k$-tuples with the MM-OT polymatching cost, which seeks $n$ optimally arranged $k$-tuples chosen within these $n\times k$ vectors. While the exponential complexity $O(n^k$) of the MM-OT problem may seem daunting, we show in experiments that a suitable generalization of the Sinkhorn algorithm for that problem can scale to, e.g., $k=3\sim 6$ views using mini-batches of size $64~\sim128$. Our experiments demonstrate improved performance over multiview extensions of pairwise losses, for both self-supervised and multimodal tasks.
Authors: Angelica Chen, Sadhika Malladi, Lily H. Zhang, Xinyi Chen, Qiuyi Zhang, Rajesh Ranganath, Kyunghyun Cho
Abstract: Preference learning algorithms (e.g., RLHF and DPO) are frequently used to steer LLMs to produce generations that are more preferred by humans, but our understanding of their inner workings is still limited. In this work, we study the conventional wisdom that preference learning trains models to assign higher likelihoods to more preferred outputs than less preferred outputs, measured via $\textit{ranking accuracy}$. Surprisingly, we find that most state-of-the-art preference-tuned models achieve a ranking accuracy of less than 60% on common preference datasets. We furthermore derive the $\textit{idealized ranking accuracy}$ that a preference-tuned LLM would achieve if it optimized the DPO or RLHF objective perfectly. We demonstrate that existing models exhibit a significant $\textit{alignment gap}$ -- $\textit{i.e.}$, a gap between the observed and idealized ranking accuracies. We attribute this discrepancy to the DPO objective, which is empirically and theoretically ill-suited to fix even mild ranking errors in the reference model, and derive a simple and efficient formula for quantifying the difficulty of learning a given preference datapoint. Finally, we demonstrate that ranking accuracy strongly correlates with the empirically popular win rate metric when the model is close to the reference model used in the objective, shedding further light on the differences between on-policy (e.g., RLHF) and off-policy (e.g., DPO) preference learning algorithms.
Authors: Yiping Wang, Yifang Chen, Wendan Yan, Alex Fang, Wenjing Zhou, Kevin Jamieson, Simon Shaolei Du
Abstract: Data selection has emerged as a core issue for large-scale visual-language model pretaining (e.g., CLIP), particularly with noisy web-curated datasets. Three main data selection approaches are: (1) leveraging external non-CLIP models to aid data selection, (2) training new CLIP-style embedding models that are more effective at selecting high-quality data than the original OpenAI CLIP model, and (3) designing better metrics or strategies universally applicable to any CLIP embedding without requiring specific model properties (e.g., CLIPScore is one popular metric). While the first two approaches have been extensively studied, the third remains under-explored. In this paper, we advance the third approach by proposing two new methods. Firstly, instead of classical CLIP scores that only consider the alignment between two modalities from a single sample, we introduce negCLIPLoss, a CLIP loss-inspired method that adds the alignment between one sample and its contrastive pairs as an extra normalization term for better quality measurement. Secondly, when downstream tasks are known, we propose a new norm-based metric, NormSim, to measure the similarity between pretraining data and target data. We test our methods on the data selection benchmark, DataComp~\cite{gadre2023datacomp}. Compared to the best baseline using only OpenAI's CLIP-L/14, our methods achieve a 5.3\% improvement on ImageNet-1k and a 2.8\% improvement on 38 downstream evaluation tasks. Moreover, both negCLIPLoss and NormSim are compatible with existing techniques. By combining our methods with the current best methods DFN~\cite{fang2023data} and HYPE~\cite{kim2024hype}, we can boost average performance on downstream tasks by 0.9\%, achieving a new state-of-the-art.
Authors: Mingqi Yuan, Roger Creus Castanyer, Bo Li, Xin Jin, Glen Berseth, Wenjun Zeng
Abstract: Extrinsic rewards can effectively guide reinforcement learning (RL) agents in specific tasks. However, extrinsic rewards frequently fall short in complex environments due to the significant human effort needed for their design and annotation. This limitation underscores the necessity for intrinsic rewards, which offer auxiliary and dense signals and can enable agents to learn in an unsupervised manner. Although various intrinsic reward formulations have been proposed, their implementation and optimization details are insufficiently explored and lack standardization, thereby hindering research progress. To address this gap, we introduce RLeXplore, a unified, highly modularized, and plug-and-play framework offering reliable implementations of eight state-of-the-art intrinsic reward algorithms. Furthermore, we conduct an in-depth study that identifies critical implementation details and establishes well-justified standard practices in intrinsically-motivated RL. The source code for RLeXplore is available at https://github.com/RLE-Foundation/RLeXplore.
Authors: Ryan Greenblatt, Fabien Roger, Dmitrii Krasheninnikov, David Krueger
Abstract: To determine the safety of large language models (LLMs), AI developers must be able to assess their dangerous capabilities. But simple prompting strategies often fail to elicit an LLM's full capabilities. One way to elicit capabilities more robustly is to fine-tune the LLM to complete the task. In this paper, we investigate the conditions under which fine-tuning-based elicitation suffices to elicit capabilities. To do this, we introduce password-locked models, LLMs fine-tuned such that some of their capabilities are deliberately hidden. Specifically, these LLMs are trained to exhibit these capabilities only when a password is present in the prompt, and to imitate a much weaker LLM otherwise. Password-locked models enable a novel method of evaluating capabilities elicitation methods, by testing whether these password-locked capabilities can be elicited without using the password. We find that a few high-quality demonstrations are often sufficient to fully elicit password-locked capabilities. More surprisingly, fine-tuning can elicit other capabilities that have been locked using the same password, or even different passwords. Furthermore, when only evaluations, and not demonstrations, are available, approaches like reinforcement learning are still often able to elicit capabilities. Overall, our findings suggest that fine-tuning is an effective method of eliciting hidden capabilities of current models, but may be unreliable when high-quality demonstrations are not available, e.g. as may be the case when models' (hidden) capabilities exceed those of human demonstrators.
Authors: Mohamed Seif, Yanxi Chen
Abstract: In this note, we provide a refined analysis of Mitra's algorithm \cite{mitra2008clustering} for classifying general discrete mixture distribution models. Built upon spectral clustering \cite{mcsherry2001spectral}, this algorithm offers compelling conditions for probability distributions. We enhance this analysis by tailoring the model to bipartite stochastic block models, resulting in more refined conditions. Compared to those derived in \cite{mitra2008clustering}, our improved separation conditions are obtained.
Authors: Junbin Zhuang, Guiguang Din, Yunyi Yan
Abstract: Weight play an essential role in deep learning network models. Unlike network structure design, this article proposes the concept of weight augmentation, focusing on weight exploration. The core of Weight Augmentation Strategy (WAS) is to adopt random transformed weight coefficients training and transformed coefficients, named Shadow Weight(SW), for networks that can be used to calculate loss function to affect parameter updates. However, stochastic gradient descent is applied to Plain Weight(PW), which is referred to as the original weight of the network before the random transformation. During training, numerous SW collectively form high-dimensional space, while PW is directly learned from the distribution of SW instead of the data. The weight of the accuracy-oriented mode(AOM) relies on PW, which guarantees the network is highly robust and accurate. The desire-oriented mode(DOM) weight uses SW, which is determined by the network model's unique functions based on WAT's performance desires, such as lower computational complexity, lower sensitivity to particular data, etc. The dual mode be switched at anytime if needed. WAT extends the augmentation technique from data augmentation to weight, and it is easy to understand and implement, but it can improve almost all networks amazingly. Our experimental results show that convolutional neural networks, such as VGG-16, ResNet-18, ResNet-34, GoogleNet, MobilementV2, and Efficientment-Lite, can benefit much at little or no cost. The accuracy of models is on the CIFAR100 and CIFAR10 datasets, which can be evaluated to increase by 7.32\% and 9.28\%, respectively, with the highest values being 13.42\% and 18.93\%, respectively. In addition, DOM can reduce floating point operations (FLOPs) by up to 36.33\%. The code is available at https://github.com/zlearh/Weight-Augmentation-Technology.
URLs: https://github.com/zlearh/Weight-Augmentation-Technology.
Authors: Zhenmei Shi, Junyi Wei, Zhuoyan Xu, Yingyu Liang
Abstract: Large language models (LLM) have emerged as a powerful tool for AI, with the key ability of in-context learning (ICL), where they can perform well on unseen tasks based on a brief series of task examples without necessitating any adjustments to the model parameters. One recent interesting mysterious observation is that models of different scales may have different ICL behaviors: larger models tend to be more sensitive to noise in the test context. This work studies this observation theoretically aiming to improve the understanding of LLM and ICL. We analyze two stylized settings: (1) linear regression with one-layer single-head linear transformers and (2) parity classification with two-layer multiple attention heads transformers (non-linear data and non-linear model). In both settings, we give closed-form optimal solutions and find that smaller models emphasize important hidden features while larger ones cover more hidden features; thus, smaller models are more robust to noise while larger ones are more easily distracted, leading to different ICL behaviors. This sheds light on where transformers pay attention to and how that affects ICL. Preliminary experimental results on large base and chat models provide positive support for our analysis.
Authors: Vijay Lingam, Atula Tejaswi, Aditya Vavre, Aneesh Shetty, Gautham Krishna Gudur, Joydeep Ghosh, Alex Dimakis, Eunsol Choi, Aleksandar Bojchevski, Sujay Sanghavi
Abstract: Popular parameter-efficient fine-tuning (PEFT) methods, such as LoRA and its variants, freeze pre-trained model weights \(W\) and inject learnable matrices \(\Delta W\). These \(\Delta W\) matrices are structured for efficient parameterization, often using techniques like low-rank approximations or scaling vectors. However, these methods typically show a performance gap compared to full fine-tuning. Although recent PEFT methods have narrowed this gap, they do so at the cost of additional learnable parameters. We propose SVFT, a simple approach that fundamentally differs from existing methods: the structure imposed on \(\Delta W\) depends on the specific weight matrix \(W\). Specifically, SVFT updates \(W\) as a sparse combination of outer products of its singular vectors, training only the coefficients (scales) of these sparse combinations. This approach allows fine-grained control over expressivity through the number of coefficients. Extensive experiments on language and vision benchmarks show that SVFT recovers up to 96% of full fine-tuning performance while training only 0.006 to 0.25% of parameters, outperforming existing methods that only recover up to 85% performance using 0.03 to 0.8% of the trainable parameter budget.
Authors: Xiangru Jian, Xinjian Zhao, Wei Pang, Chaolong Ying, Yimu Wang, Yaoyao Xu, Tianshu Yu
Abstract: The recent surge in contrast-based graph self-supervised learning has prominently featured an intensified exploration of spectral cues. However, an intriguing paradox emerges, as methods grounded in seemingly conflicting assumptions or heuristic approaches regarding the spectral domain demonstrate notable enhancements in learning performance. This paradox prompts a critical inquiry into the genuine contribution of spectral information to contrast-based graph self-supervised learning. This study undertakes an extensive investigation into this inquiry, conducting a thorough study of the relationship between spectral characteristics and the learning outcomes of contemporary methodologies. Based on this analysis, we claim that the effectiveness and significance of spectral information need to be questioned. Instead, we revisit simple edge perturbation: random edge dropping designed for node-level self-supervised learning and random edge adding intended for graph-level self-supervised learning. Compelling evidence is presented that these simple yet effective strategies consistently yield superior performance while demanding significantly fewer computational resources compared to all prior spectral augmentation methods. The proposed insights represent a significant leap forward in the field, potentially reshaping the understanding and implementation of graph self-supervised learning.
Authors: Songning Lai, Ninghui Feng, Haochen Sui, Ze Ma, Hao Wang, Zichen Song, Hang Zhao, Yutao Yue
Abstract: The field of time series forecasting has garnered significant attention in recent years, prompting the development of advanced models like TimeSieve, which demonstrates impressive performance. However, an analysis reveals certain unfaithfulness issues, including high sensitivity to random seeds and minute input noise perturbations. Recognizing these challenges, we embark on a quest to define the concept of \textbf{\underline{F}aithful \underline{T}ime\underline{S}ieve \underline{(FTS)}}, a model that consistently delivers reliable and robust predictions. To address these issues, we propose a novel framework aimed at identifying and rectifying unfaithfulness in TimeSieve. Our framework is designed to enhance the model's stability and resilience, ensuring that its outputs are less susceptible to the aforementioned factors. Experimentation validates the effectiveness of our proposed framework, demonstrating improved faithfulness in the model's behavior. Looking forward, we plan to expand our experimental scope to further validate and optimize our algorithm, ensuring comprehensive faithfulness across a wide range of scenarios. Ultimately, we aspire to make this framework can be applied to enhance the faithfulness of not just TimeSieve but also other state-of-the-art temporal methods, thereby contributing to the reliability and robustness of temporal modeling as a whole.
Authors: Xingyi Zhang, Zixuan Weng, Sibo Wang
Abstract: Node embedding learns low-dimensional vectors for nodes in the graph. Recent state-of-the-art embedding approaches take Personalized PageRank (PPR) as the proximity measure and factorize the PPR matrix or its adaptation to generate embeddings. However, little previous work analyzes what information is encoded by these approaches, and how the information correlates with their superb performance in downstream tasks. In this work, we first show that state-of-the-art embedding approaches that factorize a PPR-related matrix can be unified into a closed-form framework. Then, we study whether the embeddings generated by this strategy can be inverted to better recover the graph topology information than random-walk based embeddings. To achieve this, we propose two methods for recovering graph topology via PPR-based embeddings, including the analytical method and the optimization method. Extensive experimental results demonstrate that the embeddings generated by factorizing a PPR-related matrix maintain more topological information, such as common edges and community structures, than that generated by random walks, paving a new way to systematically comprehend why PPR-based node embedding approaches outperform random walk-based alternatives in various downstream tasks. To the best of our knowledge, this is the first work that focuses on the interpretability of PPR-based node embedding approaches.
Authors: Xi Lin, Yilu Liu, Xiaoyuan Zhang, Fei Liu, Zhenkun Wang, Qingfu Zhang
Abstract: Multi-objective optimization can be found in many real-world applications where some conflicting objectives can not be optimized by a single solution. Existing optimization methods often focus on finding a set of Pareto solutions with different optimal trade-offs among the objectives. However, the required number of solutions to well approximate the whole Pareto optimal set could be exponentially large with respect to the number of objectives, which makes these methods unsuitable for handling many optimization objectives. In this work, instead of finding a dense set of Pareto solutions, we propose a novel Tchebycheff set scalarization method to find a few representative solutions (e.g., 5) to cover a large number of objectives (e.g., $>100$) in a collaborative and complementary manner. In this way, each objective can be well addressed by at least one solution in the small solution set. In addition, we further develop a smooth Tchebycheff set scalarization approach for efficient optimization with good theoretical guarantees. Experimental studies on different problems with many optimization objectives demonstrate the effectiveness of our proposed method.
Authors: Patrick Emami, Zhaonan Li, Saumya Sinha, Truc Nguyen
Abstract: Data-driven simulation surrogates help computational scientists study complex systems. They can also help inform impactful policy decisions. We introduce a learning framework for surrogate modeling where language is used to interface with the underlying system being simulated. We call a language description of a system a "system caption", or SysCap. To address the lack of datasets of paired natural language SysCaps and simulation runs, we use large language models (LLMs) to synthesize high-quality captions. Using our framework, we train multimodal text and timeseries regression models for two real-world simulators of complex energy systems. Our experiments demonstrate the feasibility of designing language interfaces for real-world surrogate models at comparable accuracy to standard baselines. We qualitatively and quantitatively show that SysCaps unlock text-prompt-style surrogate modeling and new generalization abilities beyond what was previously possible. We will release the generated SysCaps datasets and our code to support follow-on studies.
Authors: Zhicheng Chen, Xi Xiao, Ke Xu, Zhong Zhang, Yu Rong, Qing Li, Guojun Gan, Zhiqiang Xu, Peilin Zhao
Abstract: Multivariate time series prediction is widely used in daily life, which poses significant challenges due to the complex correlations that exist at multi-grained levels. Unfortunately, the majority of current time series prediction models fail to simultaneously learn the correlations of multivariate time series at multi-grained levels, resulting in suboptimal performance. To address this, we propose a Multi-Grained Correlations-based Prediction (MGCP) Network, which simultaneously considers the correlations at three granularity levels to enhance prediction performance. Specifically, MGCP utilizes Adaptive Fourier Neural Operators and Graph Convolutional Networks to learn the global spatiotemporal correlations and inter-series correlations, enabling the extraction of potential features from multivariate time series at fine-grained and medium-grained levels. Additionally, MGCP employs adversarial training with an attention mechanism-based predictor and conditional discriminator to optimize prediction results at coarse-grained level, ensuring high fidelity between the generated forecast results and the actual data distribution. Finally, we compare MGCP with several state-of-the-art time series prediction algorithms on real-world benchmark datasets, and our results demonstrate the generality and effectiveness of the proposed model.
Authors: Ally Yalei Du, Dung Daniel Ngo, Zhiwei Steven Wu
Abstract: We consider the problem of model multiplicity in downstream decision-making, a setting where two predictive models of equivalent accuracy cannot agree on the best-response action for a downstream loss function. We show that even when the two predictive models approximately agree on their individual predictions almost everywhere, it is still possible for their induced best-response actions to differ on a substantial portion of the population. We address this issue by proposing a framework that calibrates the predictive models with regard to both the downstream decision-making problem and the individual probability prediction. Specifically, leveraging tools from multi-calibration, we provide an algorithm that, at each time-step, first reconciles the differences in individual probability prediction, then calibrates the updated models such that they are indistinguishable from the true probability distribution to the decision-maker. We extend our results to the setting where one does not have direct access to the true probability distribution and instead relies on a set of i.i.d data to be the empirical distribution. Finally, we provide a set of experiments to empirically evaluate our methods: compared to existing work, our proposed algorithm creates a pair of predictive models with both improved downstream decision-making losses and agrees on their best-response actions almost everywhere.
Authors: Masatoshi Uehara, Yulai Zhao, Ehsan Hajiramezanali, Gabriele Scalia, G\"okcen Eraslan, Avantika Lal, Sergey Levine, Tommaso Biancalani
Abstract: AI-driven design problems, such as DNA/protein sequence design, are commonly tackled from two angles: generative modeling, which efficiently captures the feasible design space (e.g., natural images or biological sequences), and model-based optimization, which utilizes reward models for extrapolation. To combine the strengths of both approaches, we adopt a hybrid method that fine-tunes cutting-edge diffusion models by optimizing reward models through RL. Although prior work has explored similar avenues, they primarily focus on scenarios where accurate reward models are accessible. In contrast, we concentrate on an offline setting where a reward model is unknown, and we must learn from static offline datasets, a common scenario in scientific domains. In offline scenarios, existing approaches tend to suffer from overoptimization, as they may be misled by the reward model in out-of-distribution regions. To address this, we introduce a conservative fine-tuning approach, BRAID, by optimizing a conservative reward model, which includes additional penalization outside of offline data distributions. Through empirical and theoretical analysis, we demonstrate the capability of our approach to outperform the best designs in offline data, leveraging the extrapolation capabilities of reward models while avoiding the generation of invalid designs through pre-trained diffusion models.
Authors: Amartya Banerjee, Harlin Lee, Nir Sharon, Caroline Moosm\"uller
Abstract: Capturing data from dynamic processes through cross-sectional measurements is seen in many fields such as computational biology. Trajectory inference deals with the challenge of reconstructing continuous processes from such observations. In this work, we propose methods for B-spline approximation and interpolation of point clouds through consecutive averaging that is instrinsic to the Wasserstein space. Combining subdivision schemes with optimal transport-based geodesic, our methods carry out trajectory inference at a chosen level of precision and smoothness, and can automatically handle scenarios where particles undergo division over time. We rigorously evaluate our method by providing convergence guarantees and testing it on simulated cell data characterized by bifurcations and merges, comparing its performance against state-of-the-art trajectory inference and interpolation methods. The results not only underscore the effectiveness of our method in inferring trajectories, but also highlight the benefit of performing interpolation and approximation that respect the inherent geometric properties of the data.
Authors: Tianyu Chen, Zhendong Wang, Mingyuan Zhou
Abstract: Offline reinforcement learning (RL) leverages pre-collected datasets to train optimal policies. Diffusion Q-Learning (DQL), introducing diffusion models as a powerful and expressive policy class, significantly boosts the performance of offline RL. However, its reliance on iterative denoising sampling to generate actions slows down both training and inference. While several recent attempts have tried to accelerate diffusion-QL, the improvement in training and/or inference speed often results in degraded performance. In this paper, we introduce a dual policy approach, Diffusion Trusted Q-Learning (DTQL), which comprises a diffusion policy for pure behavior cloning and a practical one-step policy. We bridge the two polices by a newly introduced diffusion trust region loss. The diffusion policy maintains expressiveness, while the trust region loss directs the one-step policy to explore freely and seek modes within the region defined by the diffusion policy. DTQL eliminates the need for iterative denoising sampling during both training and inference, making it remarkably computationally efficient. We evaluate its effectiveness and algorithmic characteristics against popular Kullback-Leibler (KL) based distillation methods in 2D bandit scenarios and gym tasks. We then show that DTQL could not only outperform other methods on the majority of the D4RL benchmark tasks but also demonstrate efficiency in training and inference speeds. The PyTorch implementation will be made available.
Authors: Duhun Hwang, Suhyun Kang, Moonjung Eo, Jimyeong Kim, Wonjong Rhee
Abstract: The objective of Domain Generalization (DG) is to devise algorithms and models capable of achieving high performance on previously unseen test distributions. In the pursuit of this objective, average measure has been employed as the prevalent measure for evaluating models and comparing algorithms in the existing DG studies. Despite its significance, a comprehensive exploration of the average measure has been lacking and its suitability in approximating the true domain generalization performance has been questionable. In this study, we carefully investigate the limitations inherent in the average measure and propose worst+gap measure as a robust alternative. We establish theoretical grounds of the proposed measure by deriving two theorems starting from two different assumptions. We conduct extensive experimental investigations to compare the proposed worst+gap measure with the conventional average measure. Given the indispensable need to access the true DG performance for studying measures, we modify five existing datasets to come up with SR-CMNIST, C-Cats&Dogs, L-CIFAR10, PACS-corrupted, and VLCS-corrupted datasets. The experiment results unveil an inferior performance of the average measure in approximating the true DG performance and confirm the robustness of the theoretically supported worst+gap measure.
Authors: Wenhao Yang, Yibo Wang, Peng Zhao, Lijun Zhang
Abstract: To address the uncertainty in function types, recent progress in online convex optimization (OCO) has spurred the development of universal algorithms that simultaneously attain minimax rates for multiple types of convex functions. However, for a $T$-round online problem, state-of-the-art methods typically conduct $O(\log T)$ projections onto the domain in each round, a process potentially time-consuming with complicated feasible sets. In this paper, inspired by the black-box reduction of Cutkosky and Orabona (2018), we employ a surrogate loss defined over simpler domains to develop universal OCO algorithms that only require $1$ projection. Embracing the framework of prediction with expert advice, we maintain a set of experts for each type of functions and aggregate their predictions via a meta-algorithm. The crux of our approach lies in a uniquely designed expert-loss for strongly convex functions, stemming from an innovative decomposition of the regret into the meta-regret and the expert-regret. Our analysis sheds new light on the surrogate loss, facilitating a rigorous examination of the discrepancy between the regret of the original loss and that of the surrogate loss, and carefully controlling meta-regret under the strong convexity condition. In this way, with only $1$ projection per round, we establish optimal regret bounds for general convex, exponentially concave, and strongly convex functions simultaneously. Furthermore, we enhance the expert-loss to exploit the smoothness property, and demonstrate that our algorithm can attain small-loss regret for multiple types of convex and smooth functions.
Authors: Yutong Chen, Jiandong Gao, Ji Wu
Abstract: In this paper, we investigate dynamic feature selection within multivariate time-series scenario, a common occurrence in clinical prediction monitoring where each feature corresponds to a bio-test result. Many existing feature selection methods fall short in effectively leveraging time-series information, primarily because they are designed for static data. Our approach addresses this limitation by enabling the selection of time-varying feature subsets for each patient. Specifically, we employ reinforcement learning to optimize a policy under maximum cost restrictions. The prediction model is subsequently updated using synthetic data generated by trained policy. Our method can seamlessly integrate with non-differentiable prediction models. We conducted experiments on a sizable clinical dataset encompassing regression and classification tasks. The results demonstrate that our approach outperforms strong feature selection baselines, particularly when subjected to stringent cost limitations. Code will be released once paper is accepted.
Authors: Abhinav Agrawal, Justin Domke
Abstract: Predictive posterior densities (PPDs) are of interest in approximate Bayesian inference. Typically, these are estimated by simple Monte Carlo (MC) averages using samples from the approximate posterior. We observe that the signal-to-noise ratio (SNR) of such estimators can be extremely low. An analysis for exact inference reveals SNR decays exponentially as there is an increase in (a) the mismatch between training and test data, (b) the dimensionality of the latent space, or (c) the size of the test data relative to the training data. Further analysis extends these results to approximate inference. To remedy the low SNR problem, we propose replacing simple MC sampling with importance sampling using a proposal distribution optimized at test time on a variational proxy for the SNR and demonstrate that this yields greatly improved estimates.
Authors: Yuchen He, Zichun Ye, Chihao Zhang
Abstract: We study the stochastic multi-armed bandit problem in the $P$-pass streaming model. In this problem, the $n$ arms are present in a stream and at most $m
Authors: Sungchul Hong, Seunghwan An, Jong-June Jeon
Abstract: Recent advances in a generative neural network model extend the development of data augmentation methods. However, the augmentation methods based on the modern generative models fail to achieve notable performance for class imbalance data compared to the conventional model, the SMOTE. We investigate the problem of the generative model for imbalanced classification and introduce a framework to enhance the SMOTE algorithm using Variational Autoencoders (VAE). Our approach systematically quantifies the density of data points in a low-dimensional latent space using the VAE, simultaneously incorporating information on class labels and classification difficulty. Then, the data points potentially degrading the augmentation are systematically excluded, and the neighboring observations are directly augmented on the data space. Empirical studies on several imbalanced datasets represent that this simple process innovatively improves the conventional SMOTE algorithm over the deep learning models. Consequently, we conclude that the selection of minority data and the interpolation in the data space are beneficial for imbalanced classification problems with a relatively small number of data points.
Authors: Nicol\`o Botteghi, Paolo Motta, Andrea Manzoni, Paolo Zunino, Mengwu Guo
Abstract: Digital twins require computationally-efficient reduced-order models (ROMs) that can accurately describe complex dynamics of physical assets. However, constructing ROMs from noisy high-dimensional data is challenging. In this work, we propose a data-driven, non-intrusive method that utilizes stochastic variational deep kernel learning (SVDKL) to discover low-dimensional latent spaces from data and a recurrent version of SVDKL for representing and predicting the evolution of latent dynamics. The proposed method is demonstrated with two challenging examples -- a double pendulum and a reaction-diffusion system. Results show that our framework is capable of (i) denoising and reconstructing measurements, (ii) learning compact representations of system states, (iii) predicting system evolution in low-dimensional latent spaces, and (iv) quantifying modeling uncertainties.
Authors: Guogang Zhu, Xuefeng Liu, Xinghao Wu, Shaojie Tang, Chao Tang, Jianwei Niu, Hao Su
Abstract: Federated Semi-Supervised Learning (FSSL) leverages both labeled and unlabeled data on clients to collaboratively train a model.In FSSL, the heterogeneous data can introduce prediction bias into the model, causing the model's prediction to skew towards some certain classes. Existing FSSL methods primarily tackle this issue by enhancing consistency in model parameters or outputs. However, as the models themselves are biased, merely constraining their consistency is not sufficient to alleviate prediction bias. In this paper, we explore this bias from a Bayesian perspective and demonstrate that it principally originates from label prior bias within the training data. Building upon this insight, we propose a debiasing method for FSSL named FedDB. FedDB utilizes the Average Prediction Probability of Unlabeled Data (APP-U) to approximate the biased prior.During local training, FedDB employs APP-U to refine pseudo-labeling through Bayes' theorem, thereby significantly reducing the label prior bias. Concurrently, during the model aggregation, FedDB uses APP-U from participating clients to formulate unbiased aggregate weights, thereby effectively diminishing bias in the global model. Experimental results show that FedDB can surpass existing FSSL methods. The code is available at https://github.com/GuogangZhu/FedDB.
Authors: Tianyi Chen, Hua Wang, Yutong Cai, Maohan Liang, Qiang Meng
Abstract: Factor analysis acts a pivotal role in enhancing maritime safety. Most previous studies conduct factor analysis within the framework of incident-related label prediction, where the developed models can be categorized into short-term and long-term prediction models. The long-term models offer a more strategic approach, enabling more proactive risk management, compared to the short-term ones. Nevertheless, few studies have devoted to rigorously identifying the key factors for the long-term prediction and undertaking comprehensive factor analysis. Hence, this study aims to delve into the key factors for predicting the incident risk levels in the subsequent year given a specific datestamp. The majority of candidate factors potentially contributing to the incident risk are collected from vessels' historical safety performance data spanning up to five years. An improved embedded feature selection, which integrates Random Forest classifier with a feature filtering process is proposed to identify key risk-contributing factors from the candidate pool. The results demonstrate superior performance of the proposed method in incident prediction and factor interpretability. Comprehensive analysis is conducted upon the key factors, which could help maritime stakeholders formulate management strategies for incident prevenion.
Authors: Minu Kim, Yongsik Lee, Sehyeok Kang, Jihwan Oh, Song Chong, Seyoung Yun
Abstract: We present Preference Flow Matching (PFM), a new framework for preference-based reinforcement learning (PbRL) that streamlines the integration of preferences into an arbitrary class of pre-trained models. Existing PbRL methods require fine-tuning pre-trained models, which presents challenges such as scalability, inefficiency, and the need for model modifications, especially with black-box APIs like GPT-4. In contrast, PFM utilizes flow matching techniques to directly learn from preference data, thereby reducing the dependency on extensive fine-tuning of pre-trained models. By leveraging flow-based models, PFM transforms less preferred data into preferred outcomes, and effectively aligns model outputs with human preferences without relying on explicit or implicit reward function estimation, thus avoiding common issues like overfitting in reward models. We provide theoretical insights that support our method's alignment with standard PbRL objectives. Experimental results indicate the practical effectiveness of our method, offering a new direction in aligning a pre-trained model to preference.
Authors: Bianca Marin Moreno (UGA, Thoth, EDF R&D, FiME Lab), Margaux Br\'eg\`ere (LPSM, EDF R&D), Pierre Gaillard (UGA, Thoth), Nadia Oudjane (EDF R&D, FiME Lab)
Abstract: We explore online learning in episodic loop-free Markov decision processes on non-stationary environments (changing losses and probability transitions). Our focus is on the Concave Utility Reinforcement Learning problem (CURL), an extension of classical RL for handling convex performance criteria in state-action distributions induced by agent policies. While various machine learning problems can be written as CURL, its non-linearity invalidates traditional Bellman equations. Despite recent solutions to classical CURL, none address non-stationary MDPs. This paper introduces MetaCURL, the first CURL algorithm for non-stationary MDPs. It employs a meta-algorithm running multiple black-box algorithms instances over different intervals, aggregating outputs via a sleeping expert framework. The key hurdle is partial information due to MDP uncertainty. Under partial information on the probability transitions (uncertainty and non-stationarity coming only from external noise, independent of agent state-action pairs), we achieve optimal dynamic regret without prior knowledge of MDP changes. Unlike approaches for RL, MetaCURL handles full adversarial losses, not just stochastic ones. We believe our approach for managing non-stationarity with experts can be of interest to the RL community.
Authors: Ruiyang Jin, Zaiwei Chen, Yiheng Lin, Jie Song, Adam Wierman
Abstract: Independent learning (IL), despite being a popular approach in practice to achieve scalability in large-scale multi-agent systems, usually lacks global convergence guarantees. In this paper, we study two representative algorithms, independent $Q$-learning and independent natural actor-critic, within value-based and policy-based frameworks, and provide the first finite-sample analysis for approximate global convergence. The results imply a sample complexity of $\tilde{\mathcal{O}}(\epsilon^{-2})$ up to an error term that captures the dependence among agents and characterizes the fundamental limit of IL in achieving global convergence. To establish the result, we develop a novel approach for analyzing IL by constructing a separable Markov decision process (MDP) for convergence analysis and then bounding the gap due to model difference between the separable MDP and the original one. Moreover, we conduct numerical experiments using a synthetic MDP and an electric vehicle charging example to verify our theoretical findings and to demonstrate the practical applicability of IL.
Authors: Junqi Chen, Xu Tan, Sylwan Rahardja, Jiawei Yang, Susanto Rahardja
Abstract: Deep learning-based sequence models are extensively employed in Time Series Anomaly Detection (TSAD) tasks due to their effective sequential modeling capabilities. However, the ability of TSAD is limited by two key challenges: (i) the ability to model long-range dependency and (ii) the generalization issue in the presence of non-stationary data. To tackle these challenges, an anomaly detector that leverages the selective state space model known for its proficiency in capturing long-term dependencies across various domains is proposed. Additionally, a multi-stage detrending mechanism is introduced to mitigate the prominent trend component in non-stationary data to address the generalization issue. Extensive experiments conducted on realworld public datasets demonstrate that the proposed methods surpass all 12 compared baseline methods.
Authors: Nikolas Kirschstein, Yixuan Sun
Abstract: Climate change exacerbates riverine floods, which occur with higher frequency and intensity than ever. The much-needed forecasting systems typically rely on accurate river discharge predictions. To this end, the SOTA data-driven approaches treat forecasting at spatially distributed gauge stations as isolated problems, even within the same river network. However, incorporating the known topology of the river network into the prediction model has the potential to leverage the adjacency relationship between gauges. Thus, we model river discharge for a network of gauging stations with GNNs and compare the forecasting performance achieved by different adjacency definitions. Our results show that the model fails to benefit from the river network topology information, both on the entire network and small subgraphs. The learned edge weights correlate with neither of the static definitions and exhibit no regular pattern. Furthermore, the GNNs struggle to predict sudden, narrow discharge spikes. Our work hints at a more general underlying phenomenon of neural prediction not always benefitting from graphical structure and may inspire a systematic study of the conditions under which this happens.
Authors: Taisei Tosaki, Eiichiro Uchino, Ryosuke Kojima, Yohei Mineharu, Mikio Arita, Nobuyuki Miyai, Yoshinori Tamada, Tatsuya Mikami, Koichi Murashita, Shigeyuki Nakaji, Yasushi Okuno
Abstract: Machine learning is increasingly used to predict lifestyle-related disease onset using health and medical data. However, the prediction effectiveness is hindered by dataset shift, which involves discrepancies in data distribution between the training and testing datasets, misclassifying out-of-distribution (OOD) data. To diminish dataset shift effects, this paper proposes the out-of-distribution reject option for prediction (ODROP), which integrates OOD detection models to preclude OOD data from the prediction phase. We investigated the efficacy of five OOD detection methods (variational autoencoder, neural network ensemble std, neural network ensemble epistemic, neural network energy, and neural network gaussian mixture based energy measurement) across two datasets, the Hirosaki and Wakayama health checkup data, in the context of three disease onset prediction tasks: diabetes, dyslipidemia, and hypertension. To evaluate the ODROP method, we trained disease onset prediction models and OOD detection models on Hirosaki data and used AUROC-rejection curve plots from Wakayama data. The variational autoencoder method showed superior stability and magnitude of improvement in Area Under the Receiver Operating Curve (AUROC) in five cases: AUROC in the Wakayama data was improved from 0.80 to 0.90 at a 31.1% rejection rate for diabetes onset and from 0.70 to 0.76 at a 34% rejection rate for dyslipidemia. We categorized dataset shifts into two types using SHAP clustering - those that considerably affect predictions and those that do not. We expect that this classification will help standardize measuring instruments. This study is the first to apply OOD detection to actual health and medical data, demonstrating its potential to substantially improve the accuracy and reliability of disease prediction models amidst dataset shift.
Authors: Andreas Tritsarolis, Nikos Pelekis, Konstantina Bereta, Dimitris Zissis, Yannis Theodoridis
Abstract: The wide spread of Automatic Identification System (AIS) has motivated several maritime analytics operations. Vessel Location Forecasting (VLF) is one of the most critical operations for maritime awareness. However, accurate VLF is a challenging problem due to the complexity and dynamic nature of maritime traffic conditions. Furthermore, as privacy concerns and restrictions have grown, training data has become increasingly fragmented, resulting in dispersed databases of several isolated data silos among different organizations, which in turn decreases the quality of learning models. In this paper, we propose an efficient VLF solution based on LSTM neural networks, in two variants, namely Nautilus and FedNautilus for the centralized and the federated learning approach, respectively. We also demonstrate the superiority of the centralized approach with respect to current state of the art and discuss the advantages and disadvantages of the federated against the centralized approach.
Authors: Zeyu Fang, Tian Lan
Abstract: Generative models such as diffusion have been employed as world models in offline reinforcement learning to generate synthetic data for more effective learning. Existing work either generates diffusion models one-time prior to training or requires additional interaction data to update it. In this paper, we propose a novel approach for offline reinforcement learning with closed-loop policy evaluation and world-model adaptation. It iteratively leverages a guided diffusion world model to directly evaluate the offline target policy with actions drawn from it, and then performs an importance-sampled world model update to adaptively align the world model with the updated policy. We analyzed the performance of the proposed method and provided an upper bound on the return gap between our method and the real environment under an optimal policy. The result sheds light on various factors affecting learning performance. Evaluations in the D4RL environment show significant improvement over state-of-the-art baselines, especially when only random or medium-expertise demonstrations are available -- thus requiring improved alignment between the world model and offline policy evaluation.
Authors: Jianliang He, Siyu Chen, Fengzhuo Zhang, Zhuoran Yang
Abstract: In this work, from a theoretical lens, we aim to understand why large language model (LLM) empowered agents are able to solve decision-making problems in the physical world. To this end, consider a hierarchical reinforcement learning (RL) model where the LLM Planner and the Actor perform high-level task planning and low-level execution, respectively. Under this model, the LLM Planner navigates a partially observable Markov decision process (POMDP) by iteratively generating language-based subgoals via prompting. Under proper assumptions on the pretraining data, we prove that the pretrained LLM Planner effectively performs Bayesian aggregated imitation learning (BAIL) through in-context learning. Additionally, we highlight the necessity for exploration beyond the subgoals derived from BAIL by proving that naively executing the subgoals returned by LLM leads to a linear regret. As a remedy, we introduce an $\epsilon$-greedy exploration strategy to BAIL, which is proven to incur sublinear regret when the pretraining error is small. Finally, we extend our theoretical framework to include scenarios where the LLM Planner serves as a world model for inferring the transition model of the environment and to multi-agent settings, enabling coordination among multiple Actors.
Authors: Hengkai Tan, Songming Liu, Kai Ma, Chengyang Ying, Xingxing Zhang, Hang Su, Jun Zhu
Abstract: Reinforcement learning is able to obtain generalized low-level robot policies on diverse robotics datasets in embodied learning scenarios, and Transformer has been widely used to model time-varying features. However, it still suffers from the issues of low data efficiency and high inference latency. In this paper, we propose to investigate the task from a new perspective of the frequency domain. We first observe that the energy density in the frequency domain of a robot's trajectory is mainly concentrated in the low-frequency part. Then, we present the Fourier Controller Network (FCNet), a new network that utilizes the Short-Time Fourier Transform (STFT) to extract and encode time-varying features through frequency domain interpolation. We further achieve parallel training and efficient recurrent inference by using FFT and Sliding DFT methods in the model architecture for real-time decision-making. Comprehensive analyses in both simulated (e.g., D4RL) and real-world environments (e.g., robot locomotion) demonstrate FCNet's substantial efficiency and effectiveness over existing methods such as Transformer, e.g., FCNet outperforms Transformer on multi-environmental robotics datasets of all types of sizes (from 1.9M to 120M). The project page and code can be found https://thkkk.github.io/fcnet.
Authors: Chaofan Lin, Zhenhua Han, Chengruidong Zhang, Yuqing Yang, Fan Yang, Chen Chen, Lili Qiu
Abstract: The rise of large language models (LLMs) has enabled LLM-based applications (a.k.a. AI agents or co-pilots), a new software paradigm that combines the strength of LLM and conventional software. Diverse LLM applications from different tenants could design complex workflows using multiple LLM requests to accomplish one task. However, they have to use the over-simplified request-level API provided by today's public LLM services, losing essential application-level information. Public LLM services have to blindly optimize individual LLM requests, leading to sub-optimal end-to-end performance of LLM applications. This paper introduces Parrot, an LLM service system that focuses on the end-to-end experience of LLM-based applications. Parrot proposes Semantic Variable, a unified abstraction to expose application-level knowledge to public LLM services. A Semantic Variable annotates an input/output variable in the prompt of a request, and creates the data pipeline when connecting multiple LLM requests, providing a natural way to program LLM applications. Exposing Semantic Variables to the public LLM service allows it to perform conventional data flow analysis to uncover the correlation across multiple LLM requests. This correlation opens a brand-new optimization space for the end-to-end performance of LLM-based applications. Extensive evaluations demonstrate that Parrot can achieve up to an order-of-magnitude improvement for popular and practical use cases of LLM applications.
Authors: Chunjing Gan, Dan Yang, Binbin Hu, Hanxiao Zhang, Siyuan Li, Ziqi Liu, Yue Shen, Lin Ju, Zhiqiang Zhang, Jinjie Gu, Lei Liang, Jun Zhou
Abstract: In recent years, large language models (LLMs) have made remarkable achievements in various domains. However, the untimeliness and cost of knowledge updates coupled with hallucination issues of LLMs have curtailed their applications in knowledge intensive tasks, where retrieval augmented generation (RAG) can be of help. Nevertheless, existing retrieval augmented models typically use similarity as a bridge between queries and documents and follow a retrieve then read procedure. In this work, we argue that similarity is not always the panacea and totally relying on similarity would sometimes degrade the performance of retrieval augmented generation. To this end, we propose MetRag, a Multi layEred Thoughts enhanced Retrieval Augmented Generation framework. To begin with, beyond existing similarity oriented thought, we embrace a small scale utility model that draws supervision from an LLM for utility oriented thought and further come up with a smarter model by comprehensively combining the similarity and utility oriented thoughts. Furthermore, given the fact that the retrieved document set tends to be huge and using them in isolation makes it difficult to capture the commonalities and characteristics among them, we propose to make an LLM as a task adaptive summarizer to endow retrieval augmented generation with compactness-oriented thought. Finally, with multi layered thoughts from the precedent stages, an LLM is called for knowledge augmented generation. Extensive experiments on knowledge-intensive tasks have demonstrated the superiority of MetRag.
Authors: Giacomo Blanco, Luca Barco, Lorenzo Innocenti, Claudio Rossi
Abstract: Air pollution poses a significant threat to public health and well-being, particularly in urban areas. This study introduces a series of machine-learning models that integrate data from the Sentinel-5P satellite, meteorological conditions, and topological characteristics to forecast future levels of five major pollutants. The investigation delineates the process of data collection, detailing the combination of diverse data sources utilized in the study. Through experiments conducted in the Milan metropolitan area, the models demonstrate their efficacy in predicting pollutant levels for the forthcoming day, achieving a percentage error of around 30%. The proposed models are advantageous as they are independent of monitoring stations, facilitating their use in areas without existing infrastructure. Additionally, we have released the collected dataset to the public, aiming to stimulate further research in this field. This research contributes to advancing our understanding of urban air quality dynamics and emphasizes the importance of amalgamating satellite, meteorological, and topographical data to develop robust pollution forecasting models.
Authors: Suyeon Kim, Dongha Lee, SeongKu Kang, Sukang Chae, Sanghwan Jang, Hwanjo Yu
Abstract: Label noise, commonly found in real-world datasets, has a detrimental impact on a model's generalization. To effectively detect incorrectly labeled instances, previous works have mostly relied on distinguishable training signals, such as training loss, as indicators to differentiate between clean and noisy labels. However, they have limitations in that the training signals incompletely reveal the model's behavior and are not effectively generalized to various noise types, resulting in limited detection accuracy. In this paper, we propose DynaCor framework that distinguishes incorrectly labeled instances from correctly labeled ones based on the dynamics of the training signals. To cope with the absence of supervision for clean and noisy labels, DynaCor first introduces a label corruption strategy that augments the original dataset with intentionally corrupted labels, enabling indirect simulation of the model's behavior on noisy labels. Then, DynaCor learns to identify clean and noisy instances by inducing two clearly distinguishable clusters from the latent representations of training dynamics. Our comprehensive experiments show that DynaCor outperforms the state-of-the-art competitors and shows strong robustness to various noise types and noise rates.
Authors: Tenglong Liu, Yang Li, Yixing Lan, Hao Gao, Wei Pan, Xin Xu
Abstract: In offline reinforcement learning, the challenge of out-of-distribution (OOD) is pronounced. To address this, existing methods often constrain the learned policy through policy regularization. However, these methods often suffer from the issue of unnecessary conservativeness, hampering policy improvement. This occurs due to the indiscriminate use of all actions from the behavior policy that generates the offline dataset as constraints. The problem becomes particularly noticeable when the quality of the dataset is suboptimal. Thus, we propose Adaptive Advantage-guided Policy Regularization (A2PR), obtaining high-advantage actions from an augmented behavior policy combined with VAE to guide the learned policy. A2PR can select high-advantage actions that differ from those present in the dataset, while still effectively maintaining conservatism from OOD actions. This is achieved by harnessing the VAE capacity to generate samples matching the distribution of the data points. We theoretically prove that the improvement of the behavior policy is guaranteed. Besides, it effectively mitigates value overestimation with a bounded performance gap. Empirically, we conduct a series of experiments on the D4RL benchmark, where A2PR demonstrates state-of-the-art performance. Furthermore, experimental results on additional suboptimal mixed datasets reveal that A2PR exhibits superior performance. Code is available at https://github.com/ltlhuuu/A2PR.
Authors: Yuhao Wu, Jiangchao Yao, Bo Han, Lina Yao, Tongliang Liu
Abstract: While Positive-Unlabeled (PU) learning is vital in many real-world scenarios, its application to graph data still remains under-explored. We unveil that a critical challenge for PU learning on graph lies on the edge heterophily, which directly violates the irreducibility assumption for Class-Prior Estimation (class prior is essential for building PU learning algorithms) and degenerates the latent label inference on unlabeled nodes during classifier training. In response to this challenge, we introduce a new method, named Graph PU Learning with Label Propagation Loss (GPL). Specifically, GPL considers learning from PU nodes along with an intermediate heterophily reduction, which helps mitigate the negative impact of the heterophilic structure. We formulate this procedure as a bilevel optimization that reduces heterophily in the inner loop and efficiently learns a classifier in the outer loop. Extensive experiments across a variety of datasets have shown that GPL significantly outperforms baseline methods, confirming its effectiveness and superiority.
Authors: Xiaoyun Xu, Zhuoran Liu, Stefanos Koffas, Shujian Yu, Stjepan Picek
Abstract: Backdoor attacks on deep learning represent a recent threat that has gained significant attention in the research community. Backdoor defenses are mainly based on backdoor inversion, which has been shown to be generic, model-agnostic, and applicable to practical threat scenarios. State-of-the-art backdoor inversion recovers a mask in the feature space to locate prominent backdoor features, where benign and backdoor features can be disentangled. However, it suffers from high computational overhead, and we also find that it overly relies on prominent backdoor features that are highly distinguishable from benign features. To tackle these shortcomings, this paper improves backdoor feature inversion for backdoor detection by incorporating extra neuron activation information. In particular, we adversarially increase the loss of backdoored models with respect to weights to activate the backdoor effect, based on which we can easily differentiate backdoored and clean models. Experimental results demonstrate our defense, BAN, is 1.37$\times$ (on CIFAR-10) and 5.11$\times$ (on ImageNet200) more efficient with 9.99% higher detect success rate than the state-of-the-art defense BTI-DBF. Our code and trained models are publicly available.\url{https://anonymous.4open.science/r/ban-4B32}
Authors: Alessandro Manenti, Daniele Zambon, Cesare Alippi
Abstract: Within a prediction task, Graph Neural Networks (GNNs) use relational information as an inductive bias to enhance the model's accuracy. As task-relevant relations might be unknown, graph structure learning approaches have been proposed to learn them while solving the downstream prediction task. In this paper, we demonstrate that minimization of a point-prediction loss function, e.g., the mean absolute error, does not guarantee proper learning of the latent relational information and its associated uncertainty. Conversely, we prove that a suitable loss function on the stochastic model outputs simultaneously grants (i) the unknown adjacency matrix latent distribution and (ii) optimal performance on the prediction task. Finally, we propose a sampling-based method that solves this joint learning task. Empirical results validate our theoretical claims and demonstrate the effectiveness of the proposed approach.
Authors: Konstantin Hemker, Nikola Simidjievski, Mateja Jamnik
Abstract: Learning holistic computational representations in physical, chemical or biological systems requires the ability to process information from different distributions and modalities within the same model. Thus, the demand for multimodal machine learning models has sharply risen for modalities that go beyond vision and language, such as sequences, graphs, time series, or tabular data. While there are many available multimodal fusion and alignment approaches, most of them require end-to-end training, scale quadratically with the number of modalities, cannot handle cases of high modality imbalance in the training set, or are highly topology-specific, making them too restrictive for many biomedical learning tasks. This paper presents Multimodal Lego (MM-Lego), a modular and general-purpose fusion and model merging framework to turn any set of encoders into a competitive multimodal model with no or minimal fine-tuning. We achieve this by introducing a wrapper for unimodal encoders that enforces lightweight dimensionality assumptions between modalities and harmonises their representations by learning features in the frequency domain to enable model merging with little signal interference. We show that MM-Lego 1) can be used as a model merging method which achieves competitive performance with end-to-end fusion models without any fine-tuning, 2) can operate on any unimodal encoder, and 3) is a model fusion method that, with minimal fine-tuning, achieves state-of-the-art results on six benchmarked multimodal biomedical tasks.
Authors: Kiyoung Seong, Seonghyun Park, Seonghwan Kim, Woo Youn Kim, Sungsoo Ahn
Abstract: Understanding transition paths between meta-stable states in molecular systems is fundamental for material design and drug discovery. However, sampling these paths via molecular dynamics simulations is computationally prohibitive due to the high-energy barriers between the meta-stable states. Recent machine learning approaches are often restricted to simple systems or rely on collective variables (CVs) extracted from expensive domain knowledge. In this work, we propose to leverage generative flow networks (GFlowNets) to sample transition paths without relying on CVs. We reformulate the problem as amortized energy-based sampling over molecular trajectories and train a bias potential by minimizing the squared log-ratio between the target distribution and the generator, derived from the flow matching objective of GFlowNets. Our evaluation on three proteins (Alanine Dipeptide, Polyproline, and Chignolin) demonstrates that our approach, called TPS-GFN, generates more realistic and diverse transition paths than the previous CV-free machine learning approach.
Authors: Wenzhe Yin, Shujian Yu, Yicong Lin, Jie Liu, Jan-Jakob Sonke, Efstratios Gavves
Abstract: Domain adaptation aims to use training data from one or multiple source domains to learn a hypothesis that can be generalized to a different, but related, target domain. As such, having a reliable measure for evaluating the discrepancy of both marginal and conditional distributions is crucial. We introduce Cauchy-Schwarz (CS) divergence to the problem of unsupervised domain adaptation (UDA). The CS divergence offers a theoretically tighter generalization error bound than the popular Kullback-Leibler divergence. This holds for the general case of supervised learning, including multi-class classification and regression. Furthermore, we illustrate that the CS divergence enables a simple estimator on the discrepancy of both marginal and conditional distributions between source and target domains in the representation space, without requiring any distributional assumptions. We provide multiple examples to illustrate how the CS divergence can be conveniently used in both distance metric- or adversarial training-based UDA frameworks, resulting in compelling performance.
Authors: Alexander Nikitin, Jannik Kossen, Yarin Gal, Pekka Marttinen
Abstract: Uncertainty quantification in Large Language Models (LLMs) is crucial for applications where safety and reliability are important. In particular, uncertainty can be used to improve the trustworthiness of LLMs by detecting factually incorrect model responses, commonly called hallucinations. Critically, one should seek to capture the model's semantic uncertainty, i.e., the uncertainty over the meanings of LLM outputs, rather than uncertainty over lexical or syntactic variations that do not affect answer correctness. To address this problem, we propose Kernel Language Entropy (KLE), a novel method for uncertainty estimation in white- and black-box LLMs. KLE defines positive semidefinite unit trace kernels to encode the semantic similarities of LLM outputs and quantifies uncertainty using the von Neumann entropy. It considers pairwise semantic dependencies between answers (or semantic clusters), providing more fine-grained uncertainty estimates than previous methods based on hard clustering of answers. We theoretically prove that KLE generalizes the previous state-of-the-art method called semantic entropy and empirically demonstrate that it improves uncertainty quantification performance across multiple natural language generation datasets and LLM architectures.
Authors: Zhiheng Zhou, Sihao Liu, Weichen Zhao
Abstract: Graph Neural Networks (GNNs) are powerful tools for handling graph-type data. Recently, GNNs have been widely applied in various domains, but they also face some issues, such as overfitting, over-smoothing and non-robustness. The existing research indicates that random dropout methods are an effective way to address these issues. However, random dropout methods in GNNs still face unresolved problems. Currently, the choice of dropout rate, often determined by heuristic or grid search methods, can increase the generalization error, contradicting the principal aims of dropout. In this paper, we propose a novel random dropout method for GNNs called FlexiDrop. First, we conduct a theoretical analysis of dropout in GNNs using rademacher complexity and demonstrate that the generalization error of traditional random dropout methods is constrained by a function related to the dropout rate. Subsequently, we use this function as a regularizer to unify the dropout rate and empirical loss within a single loss function, optimizing them simultaneously. Therefore, our method enables adaptive adjustment of the dropout rate and theoretically balances the trade-off between model complexity and generalization ability. Furthermore, extensive experimental results on benchmark datasets show that FlexiDrop outperforms traditional random dropout methods in GNNs.
Authors: Zeyneddin Oz, Ceylan Soygul Oz, Abdollah Malekjafarian, Nima Afraz, Fatemeh Golpayegani
Abstract: Federated Learning (FL) is commonly used in systems with distributed and heterogeneous devices with access to varying amounts of data and diverse computing and storage capacities. FL training process enables such devices to update the weights of a shared model locally using their local data and then a trusted central server combines all of those models to generate a global model. In this way, a global model is generated while the data remains local to devices to preserve privacy. However, training large models such as Deep Neural Networks (DNNs) on resource-constrained devices can take a prohibitively long time and consume a large amount of energy. In the current process, the low-capacity devices are excluded from the training process, although they might have access to unseen data. To overcome this challenge, we propose a model compression approach that enables heterogeneous devices with varying computing capacities to participate in the FL process. In our approach, the server shares a dense model with all devices to train it: Afterwards, the trained model is gradually compressed to obtain submodels with varying levels of sparsity to be used as suitable initial global models for resource-constrained devices that were not capable of train the first dense model. This results in an increased participation rate of resource-constrained devices while the transferred weights from the previous round of training are preserved. Our validation experiments show that despite reaching about 50 per cent global sparsity, generated submodels maintain their accuracy while can be shared to increase participation by around 50 per cent.
Authors: Taira Tsuchiya, Shinji Ito
Abstract: Follow-the-Regularized-Leader (FTRL) is a powerful framework for various online learning problems. By designing its regularizer and learning rate to be adaptive to past observations, FTRL is known to work adaptively to various properties of an underlying environment. However, most existing adaptive learning rates are for online learning problems with a minimax regret of $\Theta(\sqrt{T})$ for the number of rounds $T$, and there are only a few studies on adaptive learning rates for problems with a minimax regret of $\Theta(T^{2/3})$, which include several important problems dealing with indirect feedback. To address this limitation, we establish a new adaptive learning rate framework for problems with a minimax regret of $\Theta(T^{2/3})$. Our learning rate is designed by matching the stability, penalty, and bias terms that naturally appear in regret upper bounds for problems with a minimax regret of $\Theta(T^{2/3})$. As applications of this framework, we consider two major problems dealing with indirect feedback: partial monitoring and graph bandits. We show that FTRL with our learning rate and the Tsallis entropy regularizer improves existing Best-of-Both-Worlds (BOBW) regret upper bounds, which achieve simultaneous optimality in the stochastic and adversarial regimes. The resulting learning rate is surprisingly simple compared to the existing learning rates for BOBW algorithms for problems with a minimax regret of $\Theta(T^{2/3})$.
Authors: Zishuo Zhu
Abstract: At present, most of the prediction studies related to antagonistic event-group competitions focus on the prediction of competition results, and less on the prediction of the competition process, which can not provide real-time feedback of the athletes' state information in the actual competition, and thus can not analyze the changes of the competition situation. In order to solve this problem, this paper proposes a prediction model based on Random Forest for the turning point of the antagonistic event-group. Firstly, the quantitative equation of competitive potential energy is proposed; Secondly, the quantitative value of competitive potential energy is obtained by using the dynamic combination of weights method, and the turning point of the competition situation of the antagonistic event-group is marked according to the quantitative time series graph; Finally, the random forest prediction model based on the optimisation of the KM-SMOTE algorithm and the grid search method is established. The experimental analysis shows that: the quantitative equation of competitive potential energy can effectively reflect the dynamic situation of the competition; The model can effectively predict the turning point of the competition situation of the antagonistic event-group, and the recall rate of the model in the test set is 86.13%; the model has certain significance for the future study of the competition situation of the antagonistic event-group.
Authors: Jieun Yook, Junpyo Seo, Joon Huh, Han Joon Byun, Byung-ro Mooon
Abstract: We propose a new transformer model for the Traveling Salesman Problem (TSP) called CycleFormer. We identified distinctive characteristics that need to be considered when applying a conventional transformer model to TSP and aimed to fully incorporate these elements into the TSP-specific transformer. Unlike the token sets in typical language models, which are limited and static, the token (node) set in TSP is unlimited and dynamic. To exploit this fact to the fullest, we equated the encoder output with the decoder linear layer and directly connected the context vector of the encoder to the decoder encoding. Additionally, we added a positional encoding to the encoder tokens that reflects the two-dimensional nature of TSP, and devised a circular positional encoding for the decoder tokens that considers the cyclic properties of a tour. By incorporating these ideas, CycleFormer outperforms state-of-the-art (SOTA) transformer models for TSP from TSP-50 to TSP-500. Notably, on TSP-500, the optimality gap was reduced by approximately 2.8 times, from 3.09% to 1.10%, compared to the existing SOTA. The code will be made available at https://github.com/Giventicket/CycleFormer.
Authors: John W. Brooks, Christine M. Greve
Abstract: The sudden onset of deleterious and oscillatory dynamics (often called instabilities) is a known challenge in many fluid, plasma, and aerospace systems. These dynamics are difficult to address because they are nonlinear, chaotic, and are often too fast for active control schemes. In this work, we develop an alternative active controls system using an iterative, trajectory-optimization and parameter-tuning approach based on Iterative Learning Control (ILC), Time-Lagged Phase Portraits (TLPP) and Gaussian Process Regression (GPR). The novelty of this approach is that it can control a system's dynamics despite the controller being much slower than the dynamics. We demonstrate this controller on the Lorenz system of equations where it iteratively adjusts (tunes) the system's input parameters to successfully reproduce a desired oscillatory trajectory or state. Additionally, we investigate the system's dynamical sensitivity to its control parameters, identify continuous and bounded regions of desired dynamical trajectories, and demonstrate that the controller is robust to missing information and uncontrollable parameters as long as certain requirements are met. The controller presented in this work provides a framework for low-speed control for a variety of fast, nonlinear systems that may aid in instability suppression and mitigation.
Authors: Mohammad Hossein Moslemi, Mostafa Milani
Abstract: Entity Matching (EM) is a critical task in numerous fields, such as healthcare, finance, and public administration, as it identifies records that refer to the same entity within or across different databases. EM faces considerable challenges, particularly with false positives and negatives. These are typically addressed by generating matching scores and apply thresholds to balance false positives and negatives in various contexts. However, adjusting these thresholds can affect the fairness of the outcomes, a critical factor that remains largely overlooked in current fair EM research. The existing body of research on fair EM tends to concentrate on static thresholds, neglecting their critical impact on fairness. To address this, we introduce a new approach in EM using recent metrics for evaluating biases in score based binary classification, particularly through the lens of distributional parity. This approach enables the application of various bias metrics like equalized odds, equal opportunity, and demographic parity without depending on threshold settings. Our experiments with leading matching methods reveal potential biases, and by applying a calibration technique for EM scores using Wasserstein barycenters, we not only mitigate these biases but also preserve accuracy across real world datasets. This paper contributes to the field of fairness in data cleaning, especially within EM, which is a central task in data cleaning, by promoting a method for generating matching scores that reduce biases across different thresholds.
Authors: Shivam Grover, Amin Jalali, Ali Etemad
Abstract: Existing approaches for learning representations of time-series keep the temporal arrangement of the time-steps intact with the presumption that the original order is the most optimal for learning. However, non-adjacent sections of real-world time-series may have strong dependencies. Accordingly we raise the question: Is there an alternative arrangement for time-series which could enable more effective representation learning? To address this, we propose a simple plug-and-play mechanism called Segment, Shuffle, and Stitch (S3) designed to improve time-series representation learning of existing models. S3 works by creating non-overlapping segments from the original sequence and shuffling them in a learned manner that is the most optimal for the task at hand. It then re-attaches the shuffled segments back together and performs a learned weighted sum with the original input to capture both the newly shuffled sequence along with the original sequence. S3 is modular and can be stacked to create various degrees of granularity, and can be added to many forms of neural architectures including CNNs or Transformers with negligible computation overhead. Through extensive experiments on several datasets and state-of-the-art baselines, we show that incorporating S3 results in significant improvements for the tasks of time-series classification and forecasting, improving performance on certain datasets by up to 68\%. We also show that S3 makes the learning more stable with a smoother training loss curve and loss landscape compared to the original baseline. The code is available at https://github.com/shivam-grover/S3-TimeSeries .
Authors: Tom\'as Huttebraucker, Mohamed Sana, Emilio Calvanese Strinati
Abstract: Semantic channel equalization has emerged as a solution to address language mismatch in multi-user semantic communications. This approach aims to align the latent spaces of an encoder and a decoder which were not jointly trained and it relies on a partition of the semantic (latent) space into atoms based on the the semantic meaning. In this work we explore the role of the semantic space partition in scenarios where the task structure involves a one-to-many mapping between the semantic space and the action space. In such scenarios, partitioning based on hard inference results results in loss of information which degrades the equalization performance. We propose a soft criterion to derive the atoms of the partition which leverages the soft decoder's output and offers a more comprehensive understanding of the semantic space's structure. Through empirical validation, we demonstrate that soft partitioning yields a more descriptive and regular partition of the space, consequently enhancing the performance of the equalization algorithm.
Authors: Rustem Islamov, Yuan Gao, Sebastian U. Stich
Abstract: Communication efficiency has garnered significant attention as it is considered the main bottleneck for large-scale decentralized Machine Learning applications in distributed and federated settings. In this regime, clients are restricted to transmitting small amounts of quantized information to their neighbors over a communication graph. Numerous endeavors have been made to address this challenging problem by developing algorithms with compressed communication for decentralized non-convex optimization problems. Despite considerable efforts, the current results suffer from various issues such as non-scalability with the number of clients, requirements for large batches, or bounded gradient assumption. In this paper, we introduce MoTEF, a novel approach that integrates communication compression with Momentum Tracking and Error Feedback. Our analysis demonstrates that MoTEF achieves most of the desired properties, and significantly outperforms existing methods under arbitrary data heterogeneity. We provide numerical experiments to validate our theoretical findings and confirm the practical superiority of MoTEF.
Authors: Shiv Bhatia, Yueqi Cao, Paul Lezeau, Anthea Monod
Abstract: We propose an algebraic geometric framework to study the expressivity of linear activation neural networks. A particular quantity that has been actively studied in the field of deep learning is the number of linear regions, which gives an estimate of the information capacity of the architecture. To study and evaluate information capacity and expressivity, we work in the setting of tropical geometry -- a combinatorial and polyhedral variant of algebraic geometry -- where there are known connections between tropical rational maps and feedforward neural networks. Our work builds on and expands this connection to capitalize on the rich theory of tropical geometry to characterize and study various architectural aspects of neural networks. Our contributions are threefold: we provide a novel tropical geometric approach to selecting sampling domains among linear regions; an algebraic result allowing for a guided restriction of the sampling domain for network architectures with symmetries; and an open source library to analyze neural networks as tropical Puiseux rational maps. We provide a comprehensive set of proof-of-concept numerical experiments demonstrating the breadth of neural network architectures to which tropical geometric theory can be applied to reveal insights on expressivity characteristics of a network. Our work provides the foundations for the adaptation of both theory and existing software from computational tropical geometry and symbolic computation to deep learning.
Authors: Francesco Petri, Luigi Asprino, Aldo Gangemi
Abstract: World modelling, i.e. building a representation of the rules that govern the world so as to predict its evolution, is an essential ability for any agent interacting with the physical world. Recent applications of the Transformer architecture to the problem of world modelling from video input show notable improvements in sample efficiency. However, existing approaches tend to work only at the image level thus disregarding that the environment is composed of objects interacting with each other. In this paper, we propose an architecture combining Transformers for world modelling with the slot-attention paradigm, an approach for learning representations of objects appearing in a scene. We describe the resulting neural architecture and report experimental results showing an improvement over the existing solutions in terms of sample efficiency and a reduction of the variation of the performance over the training examples. The code for our architecture and experiments is available at https://github.com/torchipeppo/transformers-and-slot-encoding-for-wm
URLs: https://github.com/torchipeppo/transformers-and-slot-encoding-for-wm
Authors: B. N. Kausik
Abstract: Deep learning neural network models must be large enough to adapt to their problem domain, while small enough to avoid overfitting training data during gradient descent. To balance these competing demands, overprovisioned deep learning models such as transformers are trained for a single epoch on large data sets, and hence inefficient with both computing resources and training data. In response to these inefficiencies, we exploit learning theory to derive Occam Gradient Descent, an algorithm that interleaves adaptive reduction of model size to minimize generalization error, with gradient descent on model weights to minimize fitting error. In contrast, traditional gradient descent greedily minimizes fitting error without regard to generalization error. Our algorithm simultaneously descends the space of weights and topological size of any neural network without modification, and is effective in our experiments in outperforming traditional gradient descent with or without post-train pruning in accuracy, compute and model compression.
Authors: Jacob Dineen, Don Kridel, Daniel Dolk, David Castillo
Abstract: A high-velocity paradigm shift towards Explainable Artificial Intelligence (XAI) has emerged in recent years. Highly complex Machine Learning (ML) models have flourished in many tasks of intelligence, and the questions have started to shift away from traditional metrics of validity towards something deeper: What is this model telling me about my data, and how is it arriving at these conclusions? Inconsistencies between XAI and modeling techniques can have the undesirable effect of casting doubt upon the efficacy of these explainability approaches. To address these problems, we propose a systematic, perturbation-based analysis against a popular, model-agnostic method in XAI, SHapley Additive exPlanations (Shap). We devise algorithms to generate relative feature importance in settings of dynamic inference amongst a suite of popular machine learning and deep learning methods, and metrics that allow us to quantify how well explanations generated under the static case hold. We propose a taxonomy for feature importance methodology, measure alignment, and observe quantifiable similarity amongst explanation models across several datasets.
Authors: Derek Lim, Moe Putterman, Robin Walters, Haggai Maron, Stefanie Jegelka
Abstract: Many algorithms and observed phenomena in deep learning appear to be affected by parameter symmetries -- transformations of neural network parameters that do not change the underlying neural network function. These include linear mode connectivity, model merging, Bayesian neural network inference, metanetworks, and several other characteristics of optimization or loss-landscapes. However, theoretical analysis of the relationship between parameter space symmetries and these phenomena is difficult. In this work, we empirically investigate the impact of neural parameter symmetries by introducing new neural network architectures that have reduced parameter space symmetries. We develop two methods, with some provable guarantees, of modifying standard neural networks to reduce parameter space symmetries. With these new methods, we conduct a comprehensive experimental study consisting of multiple tasks aimed at assessing the effect of removing parameter symmetries. Our experiments reveal several interesting observations on the empirical impact of parameter symmetries; for instance, we observe linear mode connectivity between our networks without alignment of weight spaces, and we find that our networks allow for faster and more effective Bayesian neural network training.
Authors: Jaerin Lee, Bong Gyun Kang, Kihoon Kim, Kyoung Mu Lee
Abstract: One puzzling artifact in machine learning dubbed grokking is where delayed generalization is achieved tenfolds of iterations after near perfect overfitting to the training data. Focusing on the long delay itself on behalf of machine learning practitioners, our goal is to accelerate generalization of a model under grokking phenomenon. By regarding a series of gradients of a parameter over training iterations as a random signal over time, we can spectrally decompose the parameter trajectories under gradient descent into two components: the fast-varying, overfitting-yielding component and the slow-varying, generalization-inducing component. This analysis allows us to accelerate the grokking phenomenon more than $\times 50$ with only a few lines of code that amplifies the slow-varying components of gradients. The experiments show that our algorithm applies to diverse tasks involving images, languages, and graphs, enabling practical availability of this peculiar artifact of sudden generalization. Our code is available at \url{https://github.com/ironjr/grokfast}.
Authors: Massimo Bini, Karsten Roth, Zeynep Akata, Anna Khoreva
Abstract: Parameter-efficient finetuning (PEFT) has become ubiquitous to adapt foundation models to downstream task requirements while retaining their generalization ability. However, the amount of additionally introduced parameters and compute for successful adaptation and hyperparameter searches can explode quickly, especially when deployed at scale to serve numerous individual requests. To ensure effective, parameter-efficient, and hyperparameter-robust adaptation, we propose the ETHER transformation family, which performs Efficient fineTuning via HypErplane Reflections. By design, ETHER transformations require a minimal number of parameters, are less likely to deteriorate model performance, and exhibit robustness to hyperparameter and learning rate choices. In particular, we introduce ETHER and its relaxation ETHER+, which match or outperform existing PEFT methods with significantly fewer parameters ($\sim$$10$-$100$ times lower than LoRA or OFT) across multiple image synthesis and natural language tasks without exhaustive hyperparameter tuning. Finally, we investigate the recent emphasis on Hyperspherical Energy retention for adaptation and raise questions on its practical utility. The code is available at https://github.com/mwbini/ether.
Authors: Martin Bertran, Shuai Tang, Michael Kearns, Jamie Morgenstern, Aaron Roth, Zhiwei Steven Wu
Abstract: Machine unlearning is motivated by desire for data autonomy: a person can request to have their data's influence removed from deployed models, and those models should be updated as if they were retrained without the person's data. We show that, counter-intuitively, these updates expose individuals to high-accuracy reconstruction attacks which allow the attacker to recover their data in its entirety, even when the original models are so simple that privacy risk might not otherwise have been a concern. We show how to mount a near-perfect attack on the deleted data point from linear regression models. We then generalize our attack to other loss functions and architectures, and empirically demonstrate the effectiveness of our attacks across a wide range of datasets (capturing both tabular and image data). Our work highlights that privacy risk is significant even for extremely simple model classes when individuals can request deletion of their data from the model.
Authors: D\'aniel R\'acz, Mih\'aly Petreczky, B\'alint Dar\'oczy
Abstract: Many state-of-the-art models trained on long-range sequences, for example S4, S5 or LRU, are made of sequential blocks combining State-Space Models (SSMs) with neural networks. In this paper we provide a PAC bound that holds for these kind of architectures with stable SSM blocks and does not depend on the length of the input sequence. Imposing stability of the SSM blocks is a standard practice in the literature, and it is known to help performance. Our results provide a theoretical justification for the use of stable SSM blocks as the proposed PAC bound decreases as the degree of stability of the SSM blocks increases.
Authors: Maria B{\aa}nkestad, Olof Mogren, Aleksis Pirinen
Abstract: This paper presents a novel approach for constructing graph neural networks equivariant to 2D rotations and translations and leveraging them as PDE surrogates on non-gridded domains. We show that aligning the representations with the principal axis allows us to sidestep many constraints while preserving SE(2) equivariance. By applying our model as a surrogate for fluid flow simulations and conducting thorough benchmarks against non-equivariant models, we demonstrate significant gains in terms of both data efficiency and accuracy.
Authors: Ajay Patel, Markus Hofmarcher, Claudiu Leoveanu-Condrei, Marius-Constantin Dinu, Chris Callison-Burch, Sepp Hochreiter
Abstract: Training models to act as agents that can effectively navigate and perform actions in a complex environment, such as a web browser, has typically been challenging due to lack of training data. Large language models (LLMs) have recently demonstrated some capability to navigate novel environments as agents in a zero-shot or few-shot fashion, purely guided by natural language instructions as prompts. Recent research has also demonstrated LLMs have the capability to exceed their base performance through self-improvement, i.e. fine-tuning on data generated by the model itself. In this work, we explore the extent to which LLMs can self-improve their performance as agents in long-horizon tasks in a complex environment using the WebArena benchmark. In WebArena, an agent must autonomously navigate and perform actions on web pages to achieve a specified objective. We explore fine-tuning on three distinct synthetic training data mixtures and achieve a 31\% improvement in task completion rate over the base model on the WebArena benchmark through a self-improvement procedure. We additionally contribute novel evaluation metrics for assessing the performance, robustness, capabilities, and quality of trajectories of our fine-tuned agent models to a greater degree than simple, aggregate-level benchmark scores currently used to measure self-improvement.
Authors: Guillaume Huguet, James Vuckovic, Kilian Fatras, Eric Thibodeau-Laufer, Pablo Lemos, Riashat Islam, Cheng-Hao Liu, Jarrid Rector-Brooks, Tara Akhound-Sadegh, Michael Bronstein, Alexander Tong, Avishek Joey Bose
Abstract: Proteins are essential for almost all biological processes and derive their diverse functions from complex 3D structures, which are in turn determined by their amino acid sequences. In this paper, we exploit the rich biological inductive bias of amino acid sequences and introduce FoldFlow-2, a novel sequence-conditioned SE(3)-equivariant flow matching model for protein structure generation. FoldFlow-2 presents substantial new architectural features over the previous FoldFlow family of models including a protein large language model to encode sequence, a new multi-modal fusion trunk that combines structure and sequence representations, and a geometric transformer based decoder. To increase diversity and novelty of generated samples -- crucial for de-novo drug design -- we train FoldFlow-2 at scale on a new dataset that is an order of magnitude larger than PDB datasets of prior works, containing both known proteins in PDB and high-quality synthetic structures achieved through filtering. We further demonstrate the ability to align FoldFlow-2 to arbitrary rewards, e.g. increasing secondary structures diversity, by introducing a Reinforced Finetuning (ReFT) objective. We empirically observe that FoldFlow-2 outperforms previous state-of-the-art protein structure-based generative models, improving over RFDiffusion in terms of unconditional generation across all metrics including designability, diversity, and novelty across all protein lengths, as well as exhibiting generalization on the task of equilibrium conformation sampling. Finally, we demonstrate that a fine-tuned FoldFlow-2 makes progress on challenging conditional design tasks such as designing scaffolds for the VHH nanobody.
Authors: Laura Kopf, Philine Lou Bommer, Anna Hedstr\"om, Sebastian Lapuschkin, Marina M. -C. H\"ohne, Kirill Bykov
Abstract: A crucial aspect of understanding the complex nature of Deep Neural Networks (DNNs) is the ability to explain learned concepts within their latent representations. While various methods exist to connect neurons to textual descriptions of human-understandable concepts, evaluating the quality of these explanation methods presents a major challenge in the field due to a lack of unified, general-purpose quantitative evaluation. In this work, we introduce CoSy (Concept Synthesis) -- a novel, architecture-agnostic framework to evaluate the quality of textual explanations for latent neurons. Given textual explanations, our proposed framework leverages a generative model conditioned on textual input to create data points representing the textual explanation. Then, the neuron's response to these explanation data points is compared with the response to control data points, providing a quality estimate of the given explanation. We ensure the reliability of our proposed framework in a series of meta-evaluation experiments and demonstrate practical value through insights from benchmarking various concept-based textual explanation methods for Computer Vision tasks, showing that tested explanation methods significantly differ in quality.
Authors: Tal Reiss, George Kour, Naama Zwerdling, Ateret Anaby-Tavor, Yedid Hoshen
Abstract: When first deploying an anomaly detection system, e.g., to detect out-of-scope queries in chatbots, there are no observed data, making data-driven approaches ineffective. Zero-shot anomaly detection methods offer a solution to such "cold-start" cases, but unfortunately they are often not accurate enough. This paper studies the realistic but underexplored cold-start setting where an anomaly detection model is initialized using zero-shot guidance, but subsequently receives a small number of contaminated observations (namely, that may include anomalies). The goal is to make efficient use of both the zero-shot guidance and the observations. We propose ColdFusion, a method that effectively adapts the zero-shot anomaly detector to contaminated observations. To support future development of this new setting, we propose an evaluation suite consisting of evaluation protocols and metrics.
Authors: M. V. Ushakova, Yu. A. Ushakov, L. V. Legashev
Abstract: The field of machine learning is developing rapidly and is being used in various fields of science and technology. In this way, machine learning can be used to optimize the functions of latest generation data networks such as 5G and 6G. This also applies to functions at a lower level. A feature of the use of machine learning in the radio path for targeted radiation generation in modern ultra-massive MIMO, reconfigurable intelligent interfaces and other technologies is the complex acquisition and processing of data from the physical layer. Additionally, adversarial measures that manipulate the behaviour of intelligent machine learning models are becoming a major concern, as many machine learning models are sensitive to incorrect input data. To obtain data on attacks directly from processing service information, a simulation model is proposed that works in conjunction with machine learning applications.
Authors: Chlo\'e Sekkat, Fanny Leroy, Salima Mdhaffar, Blake Perry Smith, Yannick Est\`eve, Joseph Dureau, Alice Coucke
Abstract: Recent works demonstrate that voice assistants do not perform equally well for everyone, but research on demographic robustness of speech technologies is still scarce. This is mainly due to the rarity of large datasets with controlled demographic tags. This paper introduces the Sonos Voice Control Bias Assessment Dataset, an open dataset composed of voice assistant requests for North American English in the music domain (1,038 speakers, 166 hours, 170k audio samples, with 9,040 unique labelled transcripts) with a controlled demographic diversity (gender, age, dialectal region and ethnicity). We also release a statistical demographic bias assessment methodology, at the univariate and multivariate levels, tailored to this specific use case and leveraging spoken language understanding metrics rather than transcription accuracy, which we believe is a better proxy for user experience. To demonstrate the capabilities of this dataset and statistical method to detect demographic bias, we consider a pair of state-of-the-art Automatic Speech Recognition and Spoken Language Understanding models. Results show statistically significant differences in performance across age, dialectal region and ethnicity. Multivariate tests are crucial to shed light on mixed effects between dialectal region, gender and age.
Authors: Pierre Guetschel, Sara Ahmadi, Michael Tangermann
Abstract: In the field of brain-computer interfaces (BCIs), the potential for leveraging deep learning techniques for representing electroencephalogram (EEG) signals has gained substantial interest. This review synthesizes empirical findings from a collection of articles using deep representation learning techniques for BCI decoding, to provide a comprehensive analysis of the current state-of-the-art. Each article was scrutinized based on three criteria: (1) the deep representation learning technique employed, (2) the underlying motivation for its utilization, and (3) the approaches adopted for characterizing the learned representations. Among the 81 articles finally reviewed in depth, our analysis reveals a predominance of 31 articles using autoencoders. We identified 13 studies employing self-supervised learning (SSL) techniques, among which ten were published in 2022 or later, attesting to the relative youth of the field. However, at the time being, none of these have led to standard foundation models that are picked up by the BCI community. Likewise, only a few studies have introspected their learned representations. We observed that the motivation in most studies for using representation learning techniques is for solving transfer learning tasks, but we also found more specific motivations such as to learn robustness or invariances, as an algorithmic bridge, or finally to uncover the structure of the data. Given the potential of foundation models to effectively tackle these challenges, we advocate for a continued dedication to the advancement of foundation models specifically designed for EEG signal decoding by using SSL techniques. We also underline the imperative of establishing specialized benchmarks and datasets to facilitate the development and continuous improvement of such foundation models.
Authors: Sion An, Myeongkyun Kang, Soopil Kim, Philip Chikontwe, Li Shen, Sang Hyun Park
Abstract: Electroencephalography (EEG) motor imagery (MI) classification is a fundamental, yet challenging task due to the variation of signals between individuals i.e., inter-subject variability. Previous approaches try to mitigate this using task-specific (TS) EEG signals from the target subject in training. However, recording TS EEG signals requires time and limits its applicability in various fields. In contrast, resting state (RS) EEG signals are a viable alternative due to ease of acquisition with rich subject information. In this paper, we propose a novel subject-adaptive transfer learning strategy that utilizes RS EEG signals to adapt models on unseen subject data. Specifically, we disentangle extracted features into task- and subject-dependent features and use them to calibrate RS EEG signals for obtaining task information while preserving subject characteristics. The calibrated signals are then used to adapt the model to the target subject, enabling the model to simulate processing TS EEG signals of the target subject. The proposed method achieves state-of-the-art accuracy on three public benchmarks, demonstrating the effectiveness of our method in cross-subject EEG MI classification. Our findings highlight the potential of leveraging RS EEG signals to advance practical brain-computer interface systems.
Authors: Mohammad Amir Fallah, Mehdi Monemi, Mehdi Rasti, Matti Latva-Aho
Abstract: 3D spot beamfocusing (SBF), in contrast to conventional angular-domain beamforming, concentrates radiating power within very small volume in both radial and angular domains in the near-field zone. Recently the implementation of channel-state-information (CSI)-independent machine learning (ML)-based approaches have been developed for effective SBF using extremely-largescale-programable-metasurface (ELPMs). These methods involve dividing the ELPMs into subarrays and independently training them with Deep Reinforcement Learning to jointly focus the beam at the Desired Focal Point (DFP). This paper explores near-field SBF using ELPMs, addressing challenges associated with lengthy training times resulting from independent training of subarrays. To achieve a faster CSIindependent solution, inspired by the correlation between the beamfocusing matrices of the subarrays, we leverage transfer learning techniques. First, we introduce a novel similarity criterion based on the Phase Distribution Image of subarray apertures. Then we devise a subarray policy propagation scheme that transfers the knowledge from trained to untrained subarrays. We further enhance learning by introducing Quasi-Liquid-Layers as a revised version of the adaptive policy reuse technique. We show through simulations that the proposed scheme improves the training speed about 5 times. Furthermore, for dynamic DFP management, we devised a DFP policy blending process, which augments the convergence rate up to 8-fold.
Authors: Gouthamaan Manimaran, Sadasivan Puthusserypady, Helena Dom\'inguez, Adrian Atienza, Jakob E. Bardram
Abstract: Electrocardiogram (ECG) signals are critical for diagnosing heart conditions and capturing detailed cardiac patterns. As wearable single-lead ECG devices become more common, efficient analysis methods are essential. We present NERULA (Non-contrastive ECG and Reconstruction Unsupervised Learning Algorithm), a self-supervised framework designed for single-lead ECG signals. NERULA's dual-pathway architecture combines ECG reconstruction and non-contrastive learning to extract detailed cardiac features. Our 50% masking strategy, using both masked and inverse-masked signals, enhances model robustness against real-world incomplete or corrupted data. The non-contrastive pathway aligns representations of masked and inverse-masked signals, while the reconstruction pathway comprehends and reconstructs missing features. We show that combining generative and discriminative paths into the training spectrum leads to better results by outperforming state-of-the-art self-supervised learning benchmarks in various tasks, demonstrating superior performance in ECG analysis, including arrhythmia classification, gender classification, age regression, and human activity recognition. NERULA's dual-pathway design offers a robust, efficient solution for comprehensive ECG signal interpretation.
Authors: Shuai Shao, Yu Guan, Victor Sanchez
Abstract: Human Activity Recognition (HAR) has become increasingly popular with ubiquitous computing, driven by the popularity of wearable sensors in fields like healthcare and sports. While Convolutional Neural Networks (ConvNets) have significantly contributed to HAR, they often adopt a frame-by-frame analysis, concentrating on individual frames and potentially overlooking the broader temporal dynamics inherent in human activities. To address this, we propose the intra- and inter-frame attention model. This model captures both the nuances within individual frames and the broader contextual relationships across multiple frames, offering a comprehensive perspective on sequential data. We further enrich the temporal understanding by proposing a novel time-sequential batch learning strategy. This learning strategy preserves the chronological sequence of time-series data within each batch, ensuring the continuity and integrity of temporal patterns in sensor-based HAR.
Authors: Ahmed Shaaban, Zeineb Chaabouni, Maximilian Strobel, Wolfgang Furtner, Robert Weigel, Fabian Lurz
Abstract: Hand gesture recognition using radar often relies on computationally expensive fast Fourier transforms. This paper proposes an alternative approach that bypasses fast Fourier transforms using resonate-and-fire neurons. These neurons directly detect the hand in the time-domain signal, eliminating the need for fast Fourier transforms to retrieve range information. Following detection, a simple Goertzel algorithm is employed to extract five key features, eliminating the need for a second fast Fourier transform. These features are then fed into a recurrent neural network, achieving an accuracy of 98.21% for classifying five gestures. The proposed approach demonstrates competitive performance with reduced complexity compared to traditional methods
Authors: Chuheng Wu, S. Farokh Atashzar, Mohammad M. Ghassemi, Tuka Alhanai
Abstract: Surface Electromyography (sEMG) is a non-invasive signal that is used in the recognition of hand movement patterns, the diagnosis of diseases, and the robust control of prostheses. Despite the remarkable success of recent end-to-end Deep Learning approaches, they are still limited by the need for large amounts of labeled data. To alleviate the requirement for big data, researchers utilize Feature Engineering, which involves decomposing the sEMG signal into several spatial, temporal, and frequency features. In this paper, we propose utilizing a feature-imitating network (FIN) for closed-form temporal feature learning over a 300ms signal window on Ninapro DB2, and applying it to the task of 17 hand movement recognition. We implement a lightweight LSTM-FIN network to imitate four standard temporal features (entropy, root mean square, variance, simple square integral). We then explore transfer learning capabilities by applying the pre-trained LSTM-FIN for tuning to a downstream hand movement recognition task. We observed that the LSTM network can achieve up to 99\% R2 accuracy in feature reconstruction and 80\% accuracy in hand movement recognition. Our results also showed that the model can be robustly applied for both within- and cross-subject movement recognition, as well as simulated low-latency environments. Overall, our work demonstrates the potential of the FIN modeling paradigm in data-scarce scenarios for sEMG signal processing.
Authors: Nabil Ibtehaz, Masood Mortazavi
Abstract: Electrocardiogram (ECG) signals, profiling the electrical activities of the heart, are used for a plethora of diagnostic applications. However, ECG systems require multiple leads or channels of signals to capture the complete view of the cardiac system, which limits their application in smartwatches and wearables. In this work, we propose a modally reduced representation learning method for ECG signals that is capable of generating channel-agnostic, unified representations for ECG signals. Through joint optimization of reconstruction and alignment, we ensure that the embeddings of the different channels contain an amalgamation of the overall information across channels while also retaining their specific information. On an independent test dataset, we generated highly correlated channel embeddings from different ECG channels, leading to a moderate approximation of the 12-lead signals from a single-channel embedding. Our generated embeddings can work as competent features for ECG signals for downstream tasks.
Authors: Yihe Wang, Nan Huang, Taida Li, Yujun Yan, Xiang Zhang
Abstract: Medical time series data, such as Electroencephalography (EEG) and Electrocardiography (ECG), play a crucial role in healthcare, such as diagnosing brain and heart diseases. Existing methods for medical time series classification primarily rely on handcrafted biomarkers extraction and CNN-based models, with limited exploration of transformers tailored for medical time series. In this paper, we introduce Medformer, a multi-granularity patching transformer tailored specifically for medical time series classification. Our method incorporates three novel mechanisms to leverage the unique characteristics of medical time series: cross-channel patching to leverage inter-channel correlations, multi-granularity embedding for capturing features at different scales, and two-stage (intra- and inter-granularity) multi-granularity self-attention for learning features and correlations within and among granularities. We conduct extensive experiments on five public datasets under both subject-dependent and challenging subject-independent setups. Results demonstrate Medformer's superiority over 10 baselines, achieving top averaged ranking across five datasets on all six evaluation metrics. These findings underscore the significant impact of our method on healthcare applications, such as diagnosing Myocardial Infarction, Alzheimer's, and Parkinson's disease. We release the source code at \url{https://github.com/DL4mHealth/Medformer}.
Authors: Yihang Dong, Xuhang Chen, Yanyan Shen, Michael Kwok-Po Ng, Tao Qian, Shuqiang Wang
Abstract: Emotion recognition based on Electroencephalography (EEG) has gained significant attention and diversified development in fields such as neural signal processing and affective computing. However, the unique brain anatomy of individuals leads to non-negligible natural differences in EEG signals across subjects, posing challenges for cross-subject emotion recognition. While recent studies have attempted to address these issues, they still face limitations in practical effectiveness and model framework unity. Current methods often struggle to capture the complex spatial-temporal dynamics of EEG signals and fail to effectively integrate multimodal information, resulting in suboptimal performance and limited generalizability across subjects. To overcome these limitations, we develop a Pre-trained model based Multimodal Mood Reader for cross-subject emotion recognition that utilizes masked brain signal modeling and interlinked spatial-temporal attention mechanism. The model learns universal latent representations of EEG signals through pre-training on large scale dataset, and employs Interlinked spatial-temporal attention mechanism to process Differential Entropy(DE) features extracted from EEG data. Subsequently, a multi-level fusion layer is proposed to integrate the discriminative features, maximizing the advantages of features across different dimensions and modalities. Extensive experiments on public datasets demonstrate Mood Reader's superior performance in cross-subject emotion recognition tasks, outperforming state-of-the-art methods. Additionally, the model is dissected from attention perspective, providing qualitative analysis of emotion-related brain areas, offering valuable insights for affective research in neural signal processing.
Authors: Haipeng Luo, Spandan Senapati, Vatsal Sharan
Abstract: We consider the problem of online multiclass U-calibration, where a forecaster aims to make sequential distributional predictions over $K$ classes with low U-calibration error, that is, low regret with respect to all bounded proper losses simultaneously. Kleinberg et al. (2023) developed an algorithm with U-calibration error $O(K\sqrt{T})$ after $T$ rounds and raised the open question of what the optimal bound is. We resolve this question by showing that the optimal U-calibration error is $\Theta(\sqrt{KT})$ -- we start with a simple observation that the Follow-the-Perturbed-Leader algorithm of Daskalakis and Syrgkanis (2016) achieves this upper bound, followed by a matching lower bound constructed with a specific proper loss (which, as a side result, also proves the optimality of the algorithm of Daskalakis and Syrgkanis (2016) in the context of online learning against an adversary with finite choices). We also strengthen our results under natural assumptions on the loss functions, including $\Theta(\log T)$ U-calibration error for Lipschitz proper losses, $O(\log T)$ U-calibration error for a certain class of decomposable proper losses, U-calibration error bounds for proper losses with a low covering number, and others.
Authors: F\'elix Marcoccia, C\'edric Adjih, Paul M\"uhlethaler
Abstract: Most of multiple link prediction or graph generation techniques rely on the attention mechanism or on Graph Neural Networks (GNNs), which consist in leveraging node-level information exchanges in order to form proper link predictions. Such node-level interactions do not process nodes as an ordered sequence, which would imply some kind of natural ordering of the nodes: they are said to be permutation invariant mechanisms. They are well suited for graph problems, but struggle at providing a global orchestration of the predicted links, which can result in a loss of performance. Some typical issues can be the difficulty to ensure high-level properties such as global connectedness, fixed diameter or to avoid information bottleneck effects such as oversmoothing and oversquashing, which respectively consist in abundant smoothing in dense areas leading to a loss of information and a tendency to exclude isolated nodes from the message passing scheme, and often result in irrelevant, unbalanced link predictions. To tackle this problem, we hereby present Cross-Attentive Modulation (CAM) tokens, which introduce cross-attentive units used to condition node and edge-level modulations in order to enable context-aware computations that improve the global consistency of the prediction links. We will implement it on a few permutation invariant architectures, and showcase benchmarks that prove the merits of our work.
Authors: Yeoneung Kim, Gihun Kim, Insoon Yang
Abstract: We propose an approximate Thompson sampling algorithm that learns linear quadratic regulators (LQR) with an improved Bayesian regret bound of $O(\sqrt{T})$. Our method leverages Langevin dynamics with a meticulously designed preconditioner as well as a simple excitation mechanism. We show that the excitation signal induces the minimum eigenvalue of the preconditioner to grow over time, thereby accelerating the approximate posterior sampling process. Moreover, we identify nontrivial concentration properties of the approximate posteriors generated by our algorithm. These properties enable us to bound the moments of the system state and attain an $O(\sqrt{T})$ regret bound without the unrealistic restrictive assumptions on parameter sets that are often used in the literature.
Authors: Bruno Deprez, Toon Vanderschueren, Wouter Verbeke, Bart Baesens, Tim Verdonck
Abstract: Money laundering presents a pervasive challenge, burdening society by financing illegal activities. To more effectively combat and detect money laundering, the use of network information is increasingly being explored, exploiting that money laundering necessarily involves interconnected parties. This has lead to a surge in literature on network analytics (NA) for anti-money laundering (AML). The literature, however, is fragmented and a comprehensive overview of existing work is missing. This results in limited understanding of the methods that may be applied and their comparative detection power. Therefore, this paper presents an extensive and systematic review of the literature. We identify and analyse 97 papers in the Web of Science and Scopus databases, resulting in a taxonomy of approaches following the fraud analytics framework of Bockel-Rickermann et al.. Moreover, this paper presents a comprehensive experimental framework to evaluate and compare the performance of prominent NA methods in a uniform setup. The framework is applied on the publicly available Elliptic data set and implements manual feature engineering, random walk-based methods, and deep learning GNNs. We conclude from the results that network analytics increases the predictive power of the AML model with graph neural networks giving the best results. An open source implementation of the experimental framework is provided to facilitate researchers and practitioners to extend upon these results and experiment on proprietary data. As such, we aim to promote a standardised approach towards the analysis and evaluation of network analytics for AML.
Authors: Dario Izzo, Giacomo Acciarini, Francesco Biscani
Abstract: We introduce a novel neural architecture termed thermoNET, designed to represent thermospheric density in satellite orbital propagation using a reduced amount of differentiable computations. Due to the appearance of a neural network on the right-hand side of the equations of motion, the resulting satellite dynamics is governed by a NeuralODE, a neural Ordinary Differential Equation, characterized by its fully differentiable nature, allowing the derivation of variational equations (hence of the state transition matrix) and facilitating its use in connection to advanced numerical techniques such as Taylor-based numerical propagation and differential algebraic techniques. Efficient training of the network parameters occurs through two distinct approaches. In the first approach, the network undergoes training independently of spacecraft dynamics, engaging in a pure regression task against ground truth models, including JB-08 and NRLMSISE-00. In the second paradigm, network parameters are learned based on observed dynamics, adapting through ODE sensitivities. In both cases, the outcome is a flexible, compact model of the thermosphere density greatly enhancing numerical propagation efficiency while maintaining accuracy in the orbital predictions.
Authors: Conor Smith, Yixiao Chen, Ryan Levy, Yubo Yang, Miguel A. Morales, Shiwei Zhang
Abstract: The two-dimensional electron gas (2DEG) is a fundamental model, which is drawing increasing interest because of recent advances in experimental and theoretical studies of 2D materials. Current understanding of the ground state of the 2DEG relies on quantum Monte Carlo calculations, based on variational comparisons of different ansatze for different phases. We use a single variational ansatz, a general backflow-type wave function using a message-passing neural quantum state architecture, for a unified description across the entire density range. The variational optimization consistently leads to lower ground-state energies than previous best results. Transition into a Wigner crystal (WC) phase occurs automatically at rs = 37 +/- 1, a density lower than currently believed. Between the liquid and WC phases, the same ansatz and variational search strongly suggest the existence of intermediate states in a broad range of densities, with enhanced short-range nematic spin correlations.
Authors: Zhengkang Zhang
Abstract: Many machine learning models based on neural networks exhibit scaling laws: their performance scales as power laws with respect to the sizes of the model and training data set. We use large-N field theory methods to solve a model recently proposed by Maloney, Roberts and Sully which provides a simplified setting to study neural scaling laws. Our solution extends the result in this latter paper to general nonzero values of the ridge parameter, which are essential to regularize the behavior of the model. In addition to obtaining new and more precise scaling laws, we also uncover a duality transformation at the diagrams level which explains the symmetry between model and training data set sizes. The same duality underlies recent efforts to design neural networks to simulate quantum field theories.
Authors: Alexander L. Mitchell, Wolfgang Merkt, Aristotelis Papatheodorou, Ioannis Havoutis, Ingmar Posner
Abstract: The current state-of-the-art in quadruped locomotion is able to produce robust motion for terrain traversal but requires the segmentation of a desired robot trajectory into a discrete set of locomotion skills such as trot and crawl. In contrast, in this work we demonstrate the feasibility of learning a single, unified representation for quadruped locomotion enabling continuous blending between gait types and characteristics. We present Gaitor, which learns a disentangled representation of locomotion skills, thereby sharing information common to all gait types seen during training. The structure emerging in the learnt representation is interpretable in that it is found to encode phase correlations between the different gait types. These can be leveraged to produce continuous gait transitions. In addition, foot swing characteristics are disentangled and directly addressable. Together with a rudimentary terrain encoding and a learned planner operating in this structured latent representation, Gaitor is able to take motion commands including desired gait type and characteristics from a user while reacting to uneven terrain. We evaluate Gaitor in both simulated and real-world settings on the ANYmal C platform. To the best of our knowledge, this is the first work learning such a unified and interpretable latent representation for multiple gaits, resulting in on-demand continuous blending between different locomotion modes on a real quadruped robot.
Authors: Xuxing Chen, Abhishek Roy, Yifan Hu, Krishnakumar Balasubramanian
Abstract: We develop and analyze algorithms for instrumental variable regression by viewing the problem as a conditional stochastic optimization problem. In the context of least-squares instrumental variable regression, our algorithms neither require matrix inversions nor mini-batches and provides a fully online approach for performing instrumental variable regression with streaming data. When the true model is linear, we derive rates of convergence in expectation, that are of order $\mathcal{O}(\log T/T)$ and $\mathcal{O}(1/T^{1-\iota})$ for any $\iota>0$, respectively under the availability of two-sample and one-sample oracles, respectively, where $T$ is the number of iterations. Importantly, under the availability of the two-sample oracle, our procedure avoids explicitly modeling and estimating the relationship between confounder and the instrumental variables, demonstrating the benefit of the proposed approach over recent works based on reformulating the problem as minimax optimization problems. Numerical experiments are provided to corroborate the theoretical results.
Authors: Harini Suresh, Emily Tseng, Meg Young, Mary L. Gray, Emma Pierson, Karen Levy
Abstract: Growing interest and investment in the capabilities of foundation models has positioned such systems to impact a wide array of public services. Alongside these opportunities is the risk that these systems reify existing power imbalances and cause disproportionate harm to marginalized communities. Participatory approaches hold promise to instead lend agency and decision-making power to marginalized stakeholders. But existing approaches in participatory AI/ML are typically deeply grounded in context - how do we apply these approaches to foundation models, which are, by design, disconnected from context? Our paper interrogates this question. First, we examine existing attempts at incorporating participation into foundation models. We highlight the tension between participation and scale, demonstrating that it is intractable for impacted communities to meaningfully shape a foundation model that is intended to be universally applicable. In response, we develop a blueprint for participatory foundation models that identifies more local, application-oriented opportunities for meaningful participation. In addition to the "foundation" layer, our framework proposes the "subfloor'' layer, in which stakeholders develop shared technical infrastructure, norms and governance for a grounded domain, and the "surface'' layer, in which affected communities shape the use of a foundation model for a specific downstream task. The intermediate "subfloor'' layer scopes the range of potential harms to consider, and affords communities more concrete avenues for deliberation and intervention. At the same time, it avoids duplicative effort by scaling input across relevant use cases. Through three case studies in clinical care, financial services, and journalism, we illustrate how this multi-layer model can create more meaningful opportunities for participation than solely intervening at the foundation layer.
Authors: Mohamed Chaouch, Omama M. Al-Hamed
Abstract: Despite their benefits in terms of simplicity, low computational cost and data requirement, parametric machine learning algorithms, such as linear discriminant analysis, quadratic discriminant analysis or logistic regression, suffer from serious drawbacks including linearity, poor fit of features to the usually imposed normal distribution and high dimensionality. Batch kernel-based nonparametric classifier, which overcomes the linearity and normality of features constraints, represent an interesting alternative for supervised classification problem. However, it suffers from the ``curse of dimension". The problem can be alleviated by the explosive sample size in the era of big data, while large-scale data size presents some challenges in the storage of data and the calculation of the classifier. These challenges make the classical batch nonparametric classifier no longer applicable. This motivates us to develop a fast algorithm adapted to the real-time calculation of the nonparametric classifier in massive as well as streaming data frameworks. This online classifier includes two steps. First, we consider an online principle components analysis to reduce the dimension of the features with a very low computation cost. Then, a stochastic approximation algorithm is deployed to obtain a real-time calculation of the nonparametric classifier. The proposed methods are evaluated and compared to some commonly used machine learning algorithms for real-time fetal well-being monitoring. The study revealed that, in terms of accuracy, the offline (or Batch), as well as, the online classifiers are good competitors to the random forest algorithm. Moreover, we show that the online classifier gives the best trade-off accuracy/computation cost compared to the offline classifier.
Authors: Eloi Moliner, Sebastian Braun, Hannes Gamper
Abstract: Audio domain transfer is the process of modifying audio signals to match characteristics of a different domain, while retaining the original content. This paper investigates the potential of Gaussian Flow Bridges, an emerging approach in generative modeling, for this problem. The presented framework addresses the transport problem across different distributions of audio signals through the implementation of a series of two deterministic probability flows. The proposed framework facilitates manipulation of the target distribution properties through a continuous control variable, which defines a certain aspect of the target domain. Notably, this approach does not rely on paired examples for training. To address identified challenges on maintaining the speech content consistent, we recommend a training strategy that incorporates chunk-based minibatch Optimal Transport couplings of data samples and noise. Comparing our unsupervised method with established baselines, we find competitive performance in tasks of reverberation and distortion manipulation. Despite encoutering limitations, the intriguing results obtained in this study underscore potential for further exploration.
Authors: Haowen Lai, Gaoxiang Luo, Yifei Liu, Mingmin Zhao
Abstract: This paper introduces PanoRadar, a novel RF imaging system that brings RF resolution close to that of LiDAR, while providing resilience against conditions challenging for optical signals. Our LiDAR-comparable 3D imaging results enable, for the first time, a variety of visual recognition tasks at radio frequency, including surface normal estimation, semantic segmentation, and object detection. PanoRadar utilizes a rotating single-chip mmWave radar, along with a combination of novel signal processing and machine learning algorithms, to create high-resolution 3D images of the surroundings. Our system accurately estimates robot motion, allowing for coherent imaging through a dense grid of synthetic antennas. It also exploits the high azimuth resolution to enhance elevation resolution using learning-based methods. Furthermore, PanoRadar tackles 3D learning via 2D convolutions and addresses challenges due to the unique characteristics of RF signals. Our results demonstrate PanoRadar's robust performance across 12 buildings.
Authors: Dhruvit Patel, Troy Arcomano, Brian Hunt, Istvan Szunyogh, Edward Ott
Abstract: This paper explores the potential of a hybrid modeling approach that combines machine learning (ML) with conventional physics-based modeling for weather prediction beyond the medium range. It extends the work of Arcomano et al. (2022), which tested the approach for short- and medium-range weather prediction, and the work of Arcomano et al. (2023), which investigated its potential for climate modeling. The hybrid model used for the forecast experiments of the paper is based on the low-resolution, simplified parameterization atmospheric general circulation model (AGCM) SPEEDY. In addition to the hybridized prognostic variables of SPEEDY, the current version of the model has three purely ML-based prognostic variables. One of these is 6~h cumulative precipitation, another is the sea surface temperature, while the third is the heat content of the top 300 m deep layer of the ocean. The model has skill in predicting the El Ni\~no cycle and its global teleconnections with precipitation for 3-7 months depending on the season. The model captures equatorial variability of the precipitation associated with Kelvin and Rossby waves and MJO. Predictions of the precipitation in the equatorial region have skill for 15 days in the East Pacific and 11.5 days in the West Pacific. Though the model has low spatial resolution, for these tasks it has prediction skill comparable to what has been published for high-resolution, purely physics-based, conventional operational forecast models.
Authors: Mingqi Yuan, Huijiang Wang, Kai-Fung Chu, Fumiya Iida, Bo Li, Wenjun Zeng
Abstract: Advances in artificial intelligence (AI) have been propelling the evolution of human-robot interaction (HRI) technologies. However, significant challenges remain in achieving seamless interactions, particularly in tasks requiring physical contact with humans. These challenges arise from the need for accurate real-time perception of human actions, adaptive control algorithms for robots, and the effective coordination between human and robotic movements. In this paper, we propose an approach to enhancing physical HRI with a focus on dynamic robot-assisted hand-object interaction (HOI). Our methodology integrates hand pose estimation, adaptive robot control, and motion primitives to facilitate human-robot collaboration. Specifically, we employ a transformer-based algorithm to perform real-time 3D modeling of human hands from single RGB images, based on which a motion primitives model (MPM) is designed to translate human hand motions into robotic actions. The robot's action implementation is dynamically fine-tuned using the continuously updated 3D hand models. Experimental validations, including a ring-wearing task, demonstrate the system's effectiveness in adapting to real-time movements and assisting in precise task executions.
Authors: Pierre Chambon, Jean-Benoit Delbrouck, Thomas Sounack, Shih-Cheng Huang, Zhihong Chen, Maya Varma, Steven QH Truong, Chu The Chuong, Curtis P. Langlotz
Abstract: Since the release of the original CheXpert paper five years ago, CheXpert has become one of the most widely used and cited clinical AI datasets. The emergence of vision language models has sparked an increase in demands for sharing reports linked to CheXpert images, along with a growing interest among AI fairness researchers in obtaining demographic data. To address this, CheXpert Plus serves as a new collection of radiology data sources, made publicly available to enhance the scaling, performance, robustness, and fairness of models for all subsequent machine learning tasks in the field of radiology. CheXpert Plus is the largest text dataset publicly released in radiology, with a total of 36 million text tokens, including 13 million impression tokens. To the best of our knowledge, it represents the largest text de-identification effort in radiology, with almost 1 million PHI spans anonymized. It is only the second time that a large-scale English paired dataset has been released in radiology, thereby enabling, for the first time, cross-institution training at scale. All reports are paired with high-quality images in DICOM format, along with numerous image and patient metadata covering various clinical and socio-economic groups, as well as many pathology labels and RadGraph annotations. We hope this dataset will boost research for AI models that can further assist radiologists and help improve medical care. Data is available at the following URL: https://stanfordaimi.azurewebsites.net/datasets/5158c524-d3ab-4e02-96e9-6ee9efc110a1 Models are available at the following URL: https://github.com/Stanford-AIMI/chexpert-plus
URLs: https://stanfordaimi.azurewebsites.net/datasets/5158c524-d3ab-4e02-96e9-6ee9efc110a1, https://github.com/Stanford-AIMI/chexpert-plus
Authors: Bangyu Lan, Stefano Stramigioli, Kenan Niu
Abstract: Accurate bone tracking is crucial for kinematic analysis in orthopedic surgery and prosthetic robotics. Traditional methods (e.g., skin markers) are subject to soft tissue artifacts, and the bone pins used in surgery introduce the risk of additional trauma and infection. For electromyography (EMG), its inability to directly measure joint angles requires complex algorithms for kinematic estimation. To address these issues, A-mode ultrasound-based tracking has been proposed as a non-invasive and safe alternative. However, this approach suffers from limited accuracy in peak detection when processing received ultrasound signals. To build a precise and real-time bone tracking approach, this paper introduces a deep learning-based method for anatomical region recognition and bone tracking using A-mode ultrasound signals, specifically focused on the knee joint. The algorithm is capable of simultaneously performing bone tracking and identifying the anatomical region where the A-mode ultrasound transducer is placed. It contains the fully connection between all encoding and decoding layers of the cascaded U-Nets to focus only on the signal region that is most likely to have the bone peak, thus pinpointing the exact location of the peak and classifying the anatomical region of the signal. The experiment showed a 97% accuracy in the classification of the anatomical regions and a precision of around 0.5$\pm$1mm under dynamic tracking conditions for various anatomical areas surrounding the knee joint. In general, this approach shows great potential beyond the traditional method, in terms of the accuracy achieved and the recognition of the anatomical region where the ultrasound has been attached as an additional functionality.
Authors: Xinmeng Huang, Shuo Li, Edgar Dobriban, Osbert Bastani, Hamed Hassani, Dongsheng Ding
Abstract: The growing safety concerns surrounding Large Language Models (LLMs) raise an urgent need to align them with diverse human preferences to simultaneously enhance their helpfulness and safety. A promising approach is to enforce safety constraints through Reinforcement Learning from Human Feedback (RLHF). For such constrained RLHF, common Lagrangian-based primal-dual policy optimization methods are computationally expensive and often unstable. This paper presents a dualization perspective that reduces constrained alignment to an equivalent unconstrained alignment problem. We do so by pre-optimizing a smooth and convex dual function that has a closed form. This shortcut eliminates the need for cumbersome primal-dual policy iterations, thus greatly reducing the computational burden and improving training stability. Our strategy leads to two practical algorithms in model-based and preference-based scenarios (MoCAN and PeCAN, respectively). A broad range of experiments demonstrate the effectiveness of our methods.
Authors: Holden Lee, Matheau Santana-Gijzen
Abstract: We prove bounds on the variance of a function $f$ under the empirical measure of the samples obtained by the Sequential Monte Carlo (SMC) algorithm, with time complexity depending on local rather than global Markov chain mixing dynamics. SMC is a Markov Chain Monte Carlo (MCMC) method, which starts by drawing $N$ particles from a known distribution, and then, through a sequence of distributions, re-weights and re-samples the particles, at each instance applying a Markov chain for smoothing. In principle, SMC tries to alleviate problems from multi-modality. However, most theoretical guarantees for SMC are obtained by assuming global mixing time bounds, which are only efficient in the uni-modal setting. We show that bounds can be obtained in the truly multi-modal setting, with mixing times that depend only on local MCMC dynamics.
Authors: Lucas Monteiro Paes, Dennis Wei, Flavio P. Calmon
Abstract: Feature attribution methods explain black-box machine learning (ML) models by assigning importance scores to input features. These methods can be computationally expensive for large ML models. To address this challenge, there has been increasing efforts to develop amortized explainers, where a machine learning model is trained to predict feature attribution scores with only one inference. Despite their efficiency, amortized explainers can produce inaccurate predictions and misleading explanations. In this paper, we propose selective explanations, a novel feature attribution method that (i) detects when amortized explainers generate low-quality explanations and (ii) improves these explanations using a technique called explanations with initial guess. Our selective explanation method allows practitioners to specify the fraction of samples that receive explanations with initial guess, offering a principled way to bridge the gap between amortized explainers and their high-quality counterparts.
Authors: Shenghuan Sun, Gregory M. Goldgof, Alexander Schubert, Zhiqing Sun, Thomas Hartvigsen, Atul J. Butte, Ahmed Alaa
Abstract: Vision-Language Models (VLM) can support clinicians by analyzing medical images and engaging in natural language interactions to assist in diagnostic and treatment tasks. However, VLMs often exhibit "hallucinogenic" behavior, generating textual outputs not grounded in contextual multimodal information. This challenge is particularly pronounced in the medical domain, where we do not only require VLM outputs to be accurate in single interactions but also to be consistent with clinical reasoning and diagnostic pathways throughout multi-turn conversations. For this purpose, we propose a new alignment algorithm that uses symbolic representations of clinical reasoning to ground VLMs in medical knowledge. These representations are utilized to (i) generate GPT-4-guided visual instruction tuning data at scale, simulating clinician-VLM conversations with demonstrations of clinical reasoning, and (ii) create an automatic reward function that evaluates the clinical validity of VLM generations throughout clinician-VLM interactions. Our algorithm eliminates the need for human involvement in training data generation or reward model construction, reducing costs compared to standard reinforcement learning with human feedback (RLHF). We apply our alignment algorithm to develop Dr-LLaVA, a conversational VLM finetuned for analyzing bone marrow pathology slides, demonstrating strong performance in multi-turn medical conversations.
Authors: Junjie Zhang, Chenjia Bai, Haoran He, Wenke Xia, Zhigang Wang, Bin Zhao, Xiu Li, Xuelong Li
Abstract: Acquiring a multi-task imitation policy in 3D manipulation poses challenges in terms of scene understanding and action prediction. Current methods employ both 3D representation and multi-view 2D representation to predict the poses of the robot's end-effector. However, they still require a considerable amount of high-quality robot trajectories, and suffer from limited generalization in unseen tasks and inefficient execution in long-horizon reasoning. In this paper, we propose SAM-E, a novel architecture for robot manipulation by leveraging a vision-foundation model for generalizable scene understanding and sequence imitation for long-term action reasoning. Specifically, we adopt Segment Anything (SAM) pre-trained on a huge number of images and promptable masks as the foundation model for extracting task-relevant features, and employ parameter-efficient fine-tuning on robot data for a better understanding of embodied scenarios. To address long-horizon reasoning, we develop a novel multi-channel heatmap that enables the prediction of the action sequence in a single pass, notably enhancing execution efficiency. Experimental results from various instruction-following tasks demonstrate that SAM-E achieves superior performance with higher execution efficiency compared to the baselines, and also significantly improves generalization in few-shot adaptation to new tasks.
Authors: Guanhao Zhou, Yuefeng Han, Xiufan Yu
Abstract: This paper studies the prediction task of tensor-on-tensor regression in which both covariates and responses are multi-dimensional arrays (a.k.a., tensors) across time with arbitrary tensor order and data dimension. Existing methods either focused on linear models without accounting for possibly nonlinear relationships between covariates and responses, or directly employed black-box deep learning algorithms that failed to utilize the inherent tensor structure. In this work, we propose a Factor Augmented Tensor-on-Tensor Neural Network (FATTNN) that integrates tensor factor models into deep neural networks. We begin with summarizing and extracting useful predictive information (represented by the ``factor tensor'') from the complex structured tensor covariates, and then proceed with the prediction task using the estimated factor tensor as input of a temporal convolutional neural network. The proposed methods effectively handle nonlinearity between complex data structures, and improve over traditional statistical models and conventional deep learning approaches in both prediction accuracy and computational cost. By leveraging tensor factor models, our proposed methods exploit the underlying latent factor structure to enhance the prediction, and in the meantime, drastically reduce the data dimensionality that speeds up the computation. The empirical performances of our proposed methods are demonstrated via simulation studies and real-world applications to three public datasets. Numerical results show that our proposed algorithms achieve substantial increases in prediction accuracy and significant reductions in computational time compared to benchmark methods.
Authors: Sean Williams, James Huckle
Abstract: We introduce a comprehensive Linguistic Benchmark designed to evaluate the limitations of Large Language Models (LLMs) in domains such as logical reasoning, spatial intelligence, and linguistic understanding, among others. Through a series of straightforward questions, it uncovers the significant limitations of well-regarded models to perform tasks that humans manage with ease. It also highlights the potential of prompt engineering to mitigate some errors and underscores the necessity for better training methodologies. Our findings stress the importance of grounding LLMs with human reasoning and common sense, emphasising the need for human-in-the-loop for enterprise applications. We hope this work paves the way for future research to enhance the usefulness and reliability of new models.
Authors: Ryo Fujii, Masashi Hatano, Hideo Saito, Hiroki Kajita
Abstract: Surgical phase recognition has gained significant attention due to its potential to offer solutions to numerous demands of the modern operating room. However, most existing methods concentrate on minimally invasive surgery (MIS), leaving surgical phase recognition for open surgery understudied. This discrepancy is primarily attributed to the scarcity of publicly available open surgery video datasets for surgical phase recognition. To address this issue, we introduce a new egocentric open surgery video dataset for phase recognition, named EgoSurgery-Phase. This dataset comprises 15 hours of real open surgery videos spanning 9 distinct surgical phases all captured using an egocentric camera attached to the surgeon's head. In addition to video, the EgoSurgery-Phase offers eye gaze. As far as we know, it is the first real open surgery video dataset for surgical phase recognition publicly available. Furthermore, inspired by the notable success of masked autoencoders (MAEs) in video understanding tasks (e.g., action recognition), we propose a gaze-guided masked autoencoder (GGMAE). Considering the regions where surgeons' gaze focuses are often critical for surgical phase recognition (e.g., surgical field), in our GGMAE, the gaze information acts as an empirical semantic richness prior to guiding the masking process, promoting better attention to semantically rich spatial regions. GGMAE significantly improves the previous state-of-the-art recognition method (6.4% in Jaccard) and the masked autoencoder-based method (3.1% in Jaccard) on EgoSurgery-Phase. The dataset will be released at https://github.com/Fujiry0/EgoSurgery.
Authors: Ernesto Quevedo, Jorge Yero, Rachel Koerner, Pablo Rivas, Tomas Cerny
Abstract: Concerns regarding the propensity of Large Language Models (LLMs) to produce inaccurate outputs, also known as hallucinations, have escalated. Detecting them is vital for ensuring the reliability of applications relying on LLM-generated content. Current methods often demand substantial resources and rely on extensive LLMs or employ supervised learning with multidimensional features or intricate linguistic and semantic analyses difficult to reproduce and largely depend on using the same LLM that hallucinated. This paper introduces a supervised learning approach employing two simple classifiers utilizing only four numerical features derived from tokens and vocabulary probabilities obtained from other LLM evaluators, which are not necessarily the same. The method yields promising results, surpassing state-of-the-art outcomes in multiple tasks across three different benchmarks. Additionally, we provide a comprehensive examination of the strengths and weaknesses of our approach, highlighting the significance of the features utilized and the LLM employed as an evaluator. We have released our code publicly at https://github.com/Baylor-AI/HalluDetect.
Authors: Jialong Huang, Junlin Song, Penglong Lian, Mengjie Gan, Zhiheng Su, Benhao Wang, Wenji Zhu, Xiaomin Pu, Jianxiao Zou, Shicai Fan
Abstract: Due to the scarcity of fault samples and the complexity of non-linear and non-smooth characteristics data in hydroelectric units, most of the traditional hydroelectric unit fault localization methods are difficult to carry out accurate localization. To address these problems, a sparse autoencoder (SAE)-generative adversarial network (GAN)-wavelet noise reduction (WNR)- manifold-boosted deep learning (SG-WMBDL) based fault localization method for hydroelectric units is proposed. To overcome the data scarcity, a SAE is embedded into the GAN to generate more high-quality samples in the data generation module. Considering the signals involving non-linear and non-smooth characteristics, the improved WNR which combining both soft and hard thresholding and local linear embedding (LLE) are utilized to the data preprocessing module in order to reduce the noise and effectively capture the local features. In addition, to seek higher performance, the novel Adaptive Boost (AdaBoost) combined with multi deep learning is proposed to achieve accurate fault localization. The experimental results show that the SG-WMBDL can locate faults for hydroelectric units under a small number of fault samples with non-linear and non-smooth characteristics on higher precision and accuracy compared to other frontier methods, which verifies the effectiveness and practicality of the proposed method.
Authors: Ankush Gajanan Arudkar, Bernard J. E. Evans
Abstract: Accurate detection of colorectal cancer and early prevention heavily rely on precise polyp identification during gastrointestinal colonoscopy. Due to limited data, many current state-of-the-art deep learning methods for polyp segmentation often rely on post-processing of masks to reduce noise and enhance results. In this study, we propose an approach that integrates mask refinement and binary semantic segmentation, leveraging a novel collaborative training strategy that surpasses current widely-used refinement strategies. We demonstrate the superiority of our approach through comprehensive evaluation on established benchmark datasets and its successful application across various medical image segmentation architectures.
Authors: Matt Jones, Peter Chang, Kevin Murphy
Abstract: We propose a novel approach to sequential Bayesian inference based on variational Bayes. The key insight is that, in the online setting, we do not need to add the KL term to regularize to the prior (which comes from the posterior at the previous timestep); instead we can optimize just the expected log-likelihood, performing a single step of natural gradient descent starting at the prior predictive. We prove this method recovers exact Bayesian inference if the model is conjugate, and empirically outperforms other online VB methods in the non-conjugate setting, such as online learning for neural networks, especially when controlling for computational costs.
Authors: Jimmy Dani, Kalyan Nakka, Nitesh Saxena
Abstract: In this research, we introduce MIND-Crypt, a novel attack framework that uses deep learning (DL) and transfer learning (TL) to challenge the indistinguishability of block ciphers, specifically SPECK32/64 encryption algorithm in CBC mode (Cipher Block Chaining) against Known Plaintext Attacks (KPA). Our methodology includes training a DL model with ciphertexts of two messages encrypted using the same key. The selected messages have the same byte-length and differ by only one bit at the binary level. This DL model employs a residual network architecture. For the TL, we use the trained DL model as a feature extractor, and these features are then used to train a shallow machine learning, such as XGBoost. This dual strategy aims to distinguish ciphertexts of two encrypted messages, addressing traditional cryptanalysis challenges. Our findings demonstrate that the DL model achieves an accuracy of approximately 99% under consistent cryptographic conditions (Same Key or Rounds) with the SPECK32/64 cipher. However, performance degrades to random guessing levels (50%) when tested with ciphertext generated from different keys or different encryption rounds of SPECK32/64. To enhance the results, the DL model requires retraining with different keys or encryption rounds using larger datasets (10^7 samples). To overcome this limitation, we implement TL, achieving an accuracy of about 53% with just 10,000 samples, which is better than random guessing. Further training with 580,000 samples increases accuracy to nearly 99%, showing a substantial reduction in data requirements by over 94%. This shows that an attacker can utilize machine learning models to break indistinguishability by accessing pairs of plaintexts and their corresponding ciphertexts encrypted with the same key, without directly interacting with the communicating parties.
Authors: Yan Yang, Bin Gao, Ya-xiang Yuan
Abstract: Bilevel reinforcement learning (RL), which features intertwined two-level problems, has attracted growing interest recently. The inherent non-convexity of the lower-level RL problem is, however, to be an impediment to developing bilevel optimization methods. By employing the fixed point equation associated with the regularized RL, we characterize the hyper-gradient via fully first-order information, thus circumventing the assumption of lower-level convexity. This, remarkably, distinguishes our development of hyper-gradient from the general AID-based bilevel frameworks since we take advantage of the specific structure of RL problems. Moreover, we propose both model-based and model-free bilevel reinforcement learning algorithms, facilitated by access to the fully first-order hyper-gradient. Both algorithms are provable to enjoy the convergence rate $\mathcal{O}(\epsilon^{-1})$. To the best of our knowledge, this is the first time that AID-based bilevel RL gets rid of additional assumptions on the lower-level problem. In addition, numerical experiments demonstrate that the hyper-gradient indeed serves as an integration of exploitation and exploration.
Authors: Seungbeom Hong, Ilmun Kim, Jun Song
Abstract: In this work, we develop a new theory and method for sufficient dimension reduction (SDR) in single-index models, where SDR is a sub-field of supervised dimension reduction based on conditional independence. Our work is primarily motivated by the recent introduction of the Hellinger correlation as a dependency measure. Utilizing this measure, we develop a method capable of effectively detecting the dimension reduction subspace, complete with theoretical justification. Through extensive numerical experiments, we demonstrate that our proposed method significantly enhances and outperforms existing SDR methods. This improvement is largely attributed to our proposed method's deeper understanding of data dependencies and the refinement of existing SDR techniques.
Authors: Kaixuan Huang, Xudong Guo, Mengdi Wang
Abstract: Speculative decoding reduces the inference latency of a target large language model via utilizing a smaller and faster draft model. Its performance depends on a hyperparameter K -- the candidate length, i.e., the number of candidate tokens for the target model to verify in each round. However, previous methods often use simple heuristics to choose K, which may result in sub-optimal performance. We study the choice of the candidate length K and formulate it as a Markov Decision Process. We theoretically show that the optimal policy of this Markov decision process takes the form of a threshold policy, i.e., the current speculation should stop and be verified when the probability of getting a rejection exceeds a threshold value. Motivated by this theory, we propose SpecDec++, an enhanced version of speculative decoding that adaptively determines the candidate length on the fly. We augment the draft model with a trained acceptance prediction head to predict the conditional acceptance probability of the candidate tokens. SpecDec++ will stop the current speculation when the predicted probability that at least one token gets rejected exceeds a threshold. We implement SpecDec++ and apply it to the llama-2-chat 7B & 70B model pair. Our adaptive method achieves a 2.04x speedup on the Alpaca dataset (an additional 7.2% improvement over the baseline speculative decoding). On the GSM8K and HumanEval datasets, our method achieves a 2.26x speedup (9.4% improvement) and 2.23x speedup (11.1% improvement), respectively.
Authors: Shaohua Wang (Aerospace Information Research Institute, Chinese Academy of Sciences), Xing Xie (Microsoft Research Asia), Yong Li (Tsinghua University), Danhuai Guo (Beijing University of Chemical Technology), Zhi Cai (Beijing University of Technology), Yu Liu (Peking University), Yang Yue (Shenzhen University), Xiao Pan (Shijiazhuang Tiedao University), Feng Lu (Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences), Huayi Wu (Wuhan University), Zhipeng Gui (Wuhan University), Zhiming Ding (Institute of Software, Chinese Academy of Sciences), Bolong Zheng (Huazhong University of Science and Technology), Fuzheng Zhang (Kuaishou Natural Language Processing Center and Audio Center), Tao Qin (Microsoft Research Asia), Jingyuan Wang (Beijing University of Aeronautics and Astronautics), Chuang Tao (Shanghai Figure Interesting Information Technology Co., Ltd), Zhengchao Chen (Aerospace Information Research Institute, Chinese Academy of Sciences), Hao Lu (SuperMap Software Co., Ltd), Jiayi Li (Wuhan University), Hongyang Chen (Zhejiang Lab), Peng Yue (Wuhan University), Wenhao Yu (China University of Geosciences), Yao Yao (China University of Geosciences), Leilei Sun (Beijing University of Aeronautics and Astronautics), Yong Zhang (Beijing University of Technology), Longbiao Chen (Xiamen University), Xiaoping Du (Key Laboratory of Digital Earth, Chinese Academy of Sciences), Xiang Li (East China Normal University), Xueying Zhang (Nanjing Normal University), Kun Qin (Wuhan University), Zhaoya Gong (Peking University), Weihua Dong (Beijing Normal University), Xiaofeng Meng (Renmin University of China)
Abstract: This report focuses on spatial data intelligent large models, delving into the principles, methods, and cutting-edge applications of these models. It provides an in-depth discussion on the definition, development history, current status, and trends of spatial data intelligent large models, as well as the challenges they face. The report systematically elucidates the key technologies of spatial data intelligent large models and their applications in urban environments, aerospace remote sensing, geography, transportation, and other scenarios. Additionally, it summarizes the latest application cases of spatial data intelligent large models in themes such as urban development, multimodal systems, remote sensing, smart transportation, and resource environments. Finally, the report concludes with an overview and outlook on the development prospects of spatial data intelligent large models.
Authors: Zixian Guo, Ming Liu, Zhilong Ji, Jinfeng Bai, Yiwen Guo, Wangmeng Zuo
Abstract: Learning a skill generally relies on both practical experience by doer and insightful high-level guidance by instructor. Will this strategy also work well for solving complex non-convex optimization problems? Here, a common gradient-based optimizer acts like a disciplined doer, making locally optimal update at each step. Recent methods utilize large language models (LLMs) to optimize solutions for concrete problems by inferring from natural language instructions, akin to a high-level instructor. In this paper, we show that these two optimizers are complementary to each other, suggesting a collaborative optimization approach. The gradient-based optimizer and LLM-based optimizer are combined in an interleaved manner. We instruct LLMs using task descriptions and timely optimization trajectories recorded during gradient-based optimization. Inferred results from LLMs are used as restarting points for the next stage of gradient optimization. By leveraging both the locally rigorous gradient-based optimizer and the high-level deductive LLM-based optimizer, our combined optimization method consistently yields improvements over competitive baseline prompt tuning methods. Our results demonstrate the synergistic effect of conventional gradient-based optimization and the inference ability of LLMs. The code is released at https://github.com/guozix/LLM-catalyst.
Authors: Hiroaki Sasaki
Abstract: Identifiability of statistical models is a key notion in unsupervised representation learning. Recent work of nonlinear independent component analysis (ICA) employs auxiliary data and has established identifiable conditions. This paper proposes a statistical model of two latent vectors with single auxiliary data generalizing nonlinear ICA, and establishes various identifiability conditions. Unlike previous work, the two latent vectors in the proposed model can have arbitrary dimensions, and this property enables us to reveal an insightful dimensionality relation among two latent vectors and auxiliary data in identifiability conditions. Furthermore, surprisingly, we prove that the indeterminacies of the proposed model has the same as \emph{linear} ICA under certain conditions: The elements in the latent vector can be recovered up to their permutation and scales. Next, we apply the identifiability theory to a statistical model for graph data. As a result, one of the identifiability conditions includes an appealing implication: Identifiability of the statistical model could depend on the maximum value of link weights in graph data. Then, we propose a practical method for identifiable graph embedding. Finally, we numerically demonstrate that the proposed method well-recovers the latent vectors and model identifiability clearly depends on the maximum value of link weights, which supports the implication of our theoretical results
Authors: Chao Wang, Jiaxuan Zhao, Lingling Li, Licheng Jiao, Fang Liu, Shuyuan Yang
Abstract: Existing efforts are dedicated to designing many topologies and graph-aware strategies for the graph Transformer, which greatly improve the model's representation capabilities. However, manually determining the suitable Transformer architecture for a specific graph dataset or task requires extensive expert knowledge and laborious trials. This paper proposes an evolutionary graph Transformer architecture search framework (EGTAS) to automate the construction of strong graph Transformers. We build a comprehensive graph Transformer search space with the micro-level and macro-level designs. EGTAS evolves graph Transformer topologies at the macro level and graph-aware strategies at the micro level. Furthermore, a surrogate model based on generic architectural coding is proposed to directly predict the performance of graph Transformers, substantially reducing the evaluation cost of evolutionary search. We demonstrate the efficacy of EGTAS across a range of graph-level and node-level tasks, encompassing both small-scale and large-scale graph datasets. Experimental results and ablation studies show that EGTAS can construct high-performance architectures that rival state-of-the-art manual and automated baselines.
Authors: Jinliang Zheng, Jianxiong Li, Sijie Cheng, Yinan Zheng, Jiaming Li, Jihao Liu, Yu Liu, Jingjing Liu, Xianyuan Zhan
Abstract: Instruction following is crucial in contemporary LLM. However, when extended to multimodal setting, it often suffers from misalignment between specific textual instruction and targeted local region of an image. To achieve more accurate and nuanced multimodal instruction following, we introduce Instruction-guided Visual Masking (IVM), a new versatile visual grounding model that is compatible with diverse multimodal models, such as LMM and robot model. By constructing visual masks for instruction-irrelevant regions, IVM-enhanced multimodal models can effectively focus on task-relevant image regions to better align with complex instructions. Specifically, we design a visual masking data generation pipeline and create an IVM-Mix-1M dataset with 1 million image-instruction pairs. We further introduce a new learning technique, Discriminator Weighted Supervised Learning (DWSL) for preferential IVM training that prioritizes high-quality data samples. Experimental results on generic multimodal tasks such as VQA and embodied robotic control demonstrate the versatility of IVM, which as a plug-and-play tool, significantly boosts the performance of diverse multimodal models, yielding new state-of-the-art results across challenging multimodal benchmarks. Code is available at https://github.com/2toinf/IVM.
Authors: Haoqiong Bian, Dongyang Geng, Haoyang Li, Anastasia Ailamaki
Abstract: Serverless query processing has become increasingly popular due to its advantages, including automated hardware and software management, high elasticity, and pay-as-you-go pricing. For users who are not system experts, serverless query processing greatly reduces the cost of owning a data analytic system. However, it is still a significant challenge for non-expert users to transform their complex and evolving data analytic needs into proper SQL queries and select a serverless query engine that delivers satisfactory performance and price for each type of query. This paper presents PixelsDB, an open-source data analytic system that allows users who lack system or SQL expertise to explore data efficiently. It allows users to generate and debug SQL queries using a natural language interface powered by fine-tuned language models. The queries are then executed by a serverless query engine that offers varying prices for different service levels on query urgency. The service levels are natively supported by dedicated architecture design and heterogeneous resource scheduling that can apply cost-efficient resources to process non-urgent queries. We envision that the combination of a serverless paradigm, a natural-language-aided interface, and flexible service levels and prices will substantially improve the user experience in data analysis.
Authors: Dylan Zhang, Justin Wang, Francois Charton
Abstract: Instruction tuning -- tuning large language models on instruction-output pairs -- is a promising technique for making models better adapted to the real world. Yet, the key factors driving the model's capability to understand and follow instructions not seen during training remain under-explored. Our investigation begins with a series of synthetic experiments within the theoretical framework of a Turing-complete algorithm called Markov algorithm, which allows fine-grained control over the instruction-tuning data. Generalization and robustness with respect to the training distribution emerge once a diverse enough set of tasks is provided, even though very few examples are provided for each task. We extend these initial results to a real-world application scenario of code generation and find that a more diverse instruction set, extending beyond code-related tasks, improves the performance of code generation. Our observations suggest that a more diverse semantic space for instruction-tuning sets greatly improves the model's ability to follow instructions and perform tasks.
Authors: Vincent Froese, Moritz Grillo, Martin Skutella
Abstract: Neural networks with ReLU activation play a key role in modern machine learning. In view of safety-critical applications, the verification of trained networks is of great importance and necessitates a thorough understanding of essential properties of the function computed by a ReLU network, including characteristics like injectivity and surjectivity. Recently, Puthawala et al. [JMLR 2022] came up with a characterization for injectivity of a ReLU layer, which implies an exponential time algorithm. However, the exact computational complexity of deciding injectivity remained open. We answer this question by proving coNP-completeness of deciding injectivity of a ReLU layer. On the positive side, as our main result, we present a parameterized algorithm which yields fixed-parameter tractability of the problem with respect to the input dimension. In addition, we also characterize surjectivity for two-layer ReLU networks with one-dimensional output. Remarkably, the decision problem turns out to be the complement of a basic network verification task. We prove NP-hardness for surjectivity, implying a stronger hardness result than previously known for the network verification problem. Finally, we reveal interesting connections to computational convexity by formulating the surjectivity problem as a zonotope containment problem
Authors: Hao Zhao, Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion
Abstract: In-context learning (ICL) allows LLMs to learn from examples without changing their weights, which is a particularly promising capability for long-context LLMs that can potentially learn from many examples. Recently, Lin et al. (2024) proposed URIAL, a method using only three in-context examples to align base LLMs, achieving non-trivial instruction following performance. In this work, we show that, while effective, ICL alignment with URIAL still underperforms compared to instruction fine-tuning on established benchmarks such as MT-Bench and AlpacaEval 2.0 (LC), especially with more capable base LMs. Unlike for tasks such as classification, translation, or summarization, adding more ICL demonstrations for long-context LLMs does not systematically improve instruction following performance. To address this limitation, we derive a greedy selection approach for ICL examples that noticeably improves performance, yet without bridging the gap to instruction fine-tuning. Finally, we provide a series of ablation studies to better understand the reasons behind the remaining gap, and we show how some aspects of ICL depart from the existing knowledge and are specific to the instruction tuning setting. Overall, our work advances the understanding of ICL as an alignment technique. We provide our code at https://github.com/tml-epfl/icl-alignment.
Authors: Henrik Ryd\'en, Reza Moosavi, Erik G. Larsson
Abstract: In federated learning, a server must periodically broadcast a model to the agents. We propose to use multi-resolution coding and modulation (also known as non-uniform modulation) for this purpose. In the simplest instance, broadcast transmission is used, whereby all agents are targeted with one and the same transmission (typically without any particular favored beam direction), which is coded using multi-resolution coding/modulation. This enables high-SNR agents, with high path gains to the server, to receive a more accurate model than the low-SNR agents do, without consuming more downlink resources. As one implementation, we use transmission with a non-uniform 8-PSK constellation, where a high-SNR receiver (agent) can separate all 8 constellation points (hence receive 3 bits) whereas a low-SNR receiver can only separate 4 points (hence receive 2 bits). By encoding the least significant information in the third bit, the high-SNR receivers can obtain the model with higher accuracy, while the low-SNR receiver can still obtain the model although with reduced accuracy, thereby facilitating at least some basic participation of the low-SNR receiver. We show the effectiveness of our proposed scheme via experimentation using federated learning with the MNIST data-set.
Authors: Minghui Wu, Zhen Gao, Zhaocheng Wang, Dusit Niyato, George K. Karagiannidis, Sheng Chen
Abstract: Near-space airship-borne communication network is recognized to be an indispensable component of the future integrated ground-air-space network thanks to airships' advantage of long-term residency at stratospheric altitudes, but it urgently needs reliable and efficient Airship-to-X link. To improve the transmission efficiency and capacity, this paper proposes to integrate semantic communication with massive multiple-input multiple-output (MIMO) technology. Specifically, we propose a deep joint semantic coding and beamforming (JSCBF) scheme for airship-based massive MIMO image transmission network in space, in which semantics from both source and channel are fused to jointly design the semantic coding and physical layer beamforming. First, we design two semantic extraction networks to extract semantics from image source and channel state information, respectively. Then, we propose a semantic fusion network that can fuse these semantics into complex-valued semantic features for subsequent physical-layer transmission. To efficiently transmit the fused semantic features at the physical layer, we then propose the hybrid data and model-driven semantic-aware beamforming networks. At the receiver, a semantic decoding network is designed to reconstruct the transmitted images. Finally, we perform end-to-end deep learning to jointly train all the modules, using the image reconstruction quality at the receivers as a metric. The proposed deep JSCBF scheme fully combines the efficient source compressibility and robust error correction capability of semantic communication with the high spectral efficiency of massive MIMO, achieving a significant performance improvement over existing approaches.
Authors: Antonin Schrab, Ilmun Kim
Abstract: We propose two general methods for constructing robust permutation tests under data corruption. The proposed tests effectively control the non-asymptotic type I error under data corruption, and we prove their consistency in power under minimal conditions. This contributes to the practical deployment of hypothesis tests for real-world applications with potential adversarial attacks. One of our methods inherently ensures differential privacy, further broadening its applicability to private data analysis. For the two-sample and independence settings, we show that our kernel robust tests are minimax optimal, in the sense that they are guaranteed to be non-asymptotically powerful against alternatives uniformly separated from the null in the kernel MMD and HSIC metrics at some optimal rate (tight with matching lower bound). Finally, we provide publicly available implementations and empirically illustrate the practicality of our proposed tests.
Authors: Xiaoyu Wu, Jiaru Zhang, Yang Hua, Bohan Lyu, Hao Wang, Tao Song, Haibing Guan
Abstract: Few-shot fine-tuning of Diffusion Models (DMs) is a key advancement, significantly reducing training costs and enabling personalized AI applications. However, we explore the training dynamics of DMs and observe an unanticipated phenomenon: during the training process, image fidelity initially improves, then unexpectedly deteriorates with the emergence of noisy patterns, only to recover later with severe overfitting. We term the stage with generated noisy patterns as corruption stage. To understand this corruption stage, we begin by theoretically modeling the one-shot fine-tuning scenario, and then extend this modeling to more general cases. Through this modeling, we identify the primary cause of this corruption stage: a narrowed learning distribution inherent in the nature of few-shot fine-tuning. To tackle this, we apply Bayesian Neural Networks (BNNs) on DMs with variational inference to implicitly broaden the learned distribution, and present that the learning target of the BNNs can be naturally regarded as an expectation of the diffusion loss and a further regularization with the pretrained DMs. This approach is highly compatible with current few-shot fine-tuning methods in DMs and does not introduce any extra inference costs. Experimental results demonstrate that our method significantly mitigates corruption, and improves the fidelity, quality and diversity of the generated images in both object-driven and subject-driven generation tasks.
Authors: Ehud Malul, Yair Meidan, Dudu Mimran, Yuval Elovici, Asaf Shabtai
Abstract: A key challenge associated with Kubernetes configuration files (KCFs) is that they are often highly complex and error-prone, leading to security vulnerabilities and operational setbacks. Rule-based (RB) tools for KCF misconfiguration detection rely on static rule sets, making them inherently limited and unable to detect newly-discovered misconfigurations. RB tools also suffer from misdetection, since mistakes are likely when coding the detection rules. Recent methods for detecting and remediating KCF misconfigurations are limited in terms of their scalability and detection coverage, or due to the fact that they have high expertise requirements and do not offer automated remediation along with misconfiguration detection. Novel approaches that employ LLMs in their pipeline rely on API-based, general-purpose, and mainly commercial models. Thus, they pose security challenges, have inconsistent classification performance, and can be costly. In this paper, we propose GenKubeSec, a comprehensive and adaptive, LLM-based method, which, in addition to detecting a wide variety of KCF misconfigurations, also identifies the exact location of the misconfigurations and provides detailed reasoning about them, along with suggested remediation. When empirically compared with three industry-standard RB tools, GenKubeSec achieved equivalent precision (0.990) and superior recall (0.999). When a random sample of KCFs was examined by a Kubernetes security expert, GenKubeSec's explanations as to misconfiguration localization, reasoning and remediation were 100% correct, informative and useful. To facilitate further advancements in this domain, we share the unique dataset we collected, a unified misconfiguration index we developed for label standardization, our experimentation code, and GenKubeSec itself as an open-source tool.
Authors: Hossam M. Zawbaa, Wael Rashwan, Sourav Dutta, Haytham Assem
Abstract: Detecting out-of-scope user utterances is essential for task-oriented dialogues and intent classification. Current methodologies face difficulties with the unpredictable distribution of outliers and often rely on assumptions about data distributions. We present the Dual Encoder for Threshold-Based Re-Classification (DETER) to address these challenges. This end-to-end framework efficiently detects out-of-scope intents without requiring assumptions on data distributions or additional post-processing steps. The core of DETER utilizes dual text encoders, the Universal Sentence Encoder (USE) and the Transformer-based Denoising AutoEncoder (TSDAE), to generate user utterance embeddings, which are classified through a branched neural architecture. Further, DETER generates synthetic outliers using self-supervision and incorporates out-of-scope phrases from open-domain datasets. This approach ensures a comprehensive training set for out-of-scope detection. Additionally, a threshold-based re-classification mechanism refines the model's initial predictions. Evaluations on the CLINC-150, Stackoverflow, and Banking77 datasets demonstrate DETER's efficacy. Our model outperforms previous benchmarks, increasing up to 13% and 5% in F1 score for known and unknown intents on CLINC-150 and Stackoverflow, and 16% for known and 24% % for unknown intents on Banking77. The source code has been released at https://github.com/Hossam-Mohammed-tech/Intent\_Classification\_OOS.
URLs: https://github.com/Hossam-Mohammed-tech/Intent\_Classification\_OOS.
Authors: Zekai Liu, Xiaoqi Li, Hongli Peng, Wenkai Li
Abstract: The openness and transparency of Ethereum transaction data make it easy to be exploited by any entities, executing malicious attacks. The sandwich attack manipulates the Automated Market Maker (AMM) mechanism, profiting from manipulating the market price through front or after-running transactions. To identify and prevent sandwich attacks, we propose a cascade classification framework GasTrace. GasTrace analyzes various transaction features to detect malicious accounts, notably through the analysis and modeling of Gas features. In the initial classification, we utilize the Support Vector Machine (SVM) with the Radial Basis Function (RBF) kernel to generate the predicted probabilities of accounts, further constructing a detailed transaction network. Subsequently, the behavior features are captured by the Graph Attention Network (GAT) technique in the second classification. Through cascade classification, GasTrace can analyze and classify the sandwich attacks. Our experimental results demonstrate that GasTrace achieves a remarkable detection and generation capability, performing an accuracy of 96.73\% and an F1 score of 95.71\% for identifying sandwich attack accounts.
Authors: Paul D\"utting, Federico Fusco, Silvio Lattanzi, Ashkan Norouzi-Fard, Morteza Zadimoghaddam
Abstract: Maximizing monotone submodular functions under cardinality constraints is a classic optimization task with several applications in data mining and machine learning. In this paper we study this problem in a dynamic environment with consistency constraints: elements arrive in a streaming fashion and the goal is maintaining a constant approximation to the optimal solution while having a stable solution (i.e., the number of changes between two consecutive solutions is bounded). We provide algorithms in this setting with different trade-offs between consistency and approximation quality. We also complement our theoretical results with an experimental analysis showing the effectiveness of our algorithms in real-world instances.
Authors: Elisabeth Ailer, Niclas Dern, Jason Hartford, Niki Kilbertus
Abstract: Scientific hypotheses typically concern specific aspects of complex, imperfectly understood or entirely unknown mechanisms, such as the effect of gene expression levels on phenotypes or how microbial communities influence environmental health. Such queries are inherently causal (rather than purely associational), but in many settings, experiments can not be conducted directly on the target variables of interest, but are indirect. Therefore, they perturb the target variable, but do not remove potential confounding factors. If, additionally, the resulting experimental measurements are multi-dimensional and the studied mechanisms nonlinear, the query of interest is generally not identified. We develop an adaptive strategy to design indirect experiments that optimally inform a targeted query about the ground truth mechanism in terms of sequentially narrowing the gap between an upper and lower bound on the query. While the general formulation consists of a bi-level optimization procedure, we derive an efficiently estimable analytical kernel-based estimator of the bounds for the causal effect, a query of key interest, and demonstrate the efficacy of our approach in confounded, multivariate, nonlinear synthetic settings.
Authors: Minttu Alakuijala, Reginald McLean, Isaac Woungang, Nariman Farsad, Samuel Kaski, Pekka Marttinen, Kai Yuan
Abstract: Natural language is often the easiest and most convenient modality for humans to specify tasks for robots. However, learning to ground language to behavior typically requires impractical amounts of diverse, language-annotated demonstrations collected on each target robot. In this work, we aim to separate the problem of what to accomplish from how to accomplish it, as the former can benefit from substantial amounts of external observation-only data, and only the latter depends on a specific robot embodiment. To this end, we propose Video-Language Critic, a reward model that can be trained on readily available cross-embodiment data using contrastive learning and a temporal ranking objective, and use it to score behavior traces from a separate reinforcement learning actor. When trained on Open X-Embodiment data, our reward model enables 2x more sample-efficient policy training on Meta-World tasks than a sparse reward only, despite a significant domain gap. Using in-domain data but in a challenging task generalization setting on Meta-World, we further demonstrate more sample-efficient training than is possible with prior language-conditioned reward models that are either trained with binary classification, use static images, or do not leverage the temporal information present in video data.
Authors: Javier Maass Mart\'inez, Joaquin Fontbona
Abstract: We develop a Mean-Field (MF) view of the learning dynamics of overparametrized Artificial Neural Networks (NN) under data symmetric in law wrt the action of a general compact group $G$. We consider for this a class of generalized shallow NNs given by an ensemble of $N$ multi-layer units, jointly trained using stochastic gradient descent (SGD) and possibly symmetry-leveraging (SL) techniques, such as Data Augmentation (DA), Feature Averaging (FA) or Equivariant Architectures (EA). We introduce the notions of weakly and strongly invariant laws (WI and SI) on the parameter space of each single unit, corresponding, respectively, to $G$-invariant distributions, and to distributions supported on parameters fixed by the group action (which encode EA). This allows us to define symmetric models compatible with taking $N\to\infty$ and give an interpretation of the asymptotic dynamics of DA, FA and EA in terms of Wasserstein Gradient Flows describing their MF limits. When activations respect the group action, we show that, for symmetric data, DA, FA and freely-trained models obey the exact same MF dynamic, which stays in the space of WI laws and minimizes therein the population risk. We also give a counterexample to the general attainability of an optimum over SI laws. Despite this, quite remarkably, we show that the set of SI laws is also preserved by the MF dynamics even when freely trained. This sharply contrasts the finite-$N$ setting, in which EAs are generally not preserved by unconstrained SGD. We illustrate the validity of our findings as $N$ gets larger in a teacher-student experimental setting, training a student NN to learn from a WI, SI or arbitrary teacher model through various SL schemes. We last deduce a data-driven heuristic to discover the largest subspace of parameters supporting SI distributions for a problem, that could be used for designing EA with minimal generalization error.
Authors: Ziyan Wang, Meng Fang, Tristan Tomilin, Fei Fang, Yali Du
Abstract: The role of natural language constraints in Safe Multi-agent Reinforcement Learning (MARL) is crucial, yet often overlooked. While Safe MARL has vast potential, especially in fields like robotics and autonomous vehicles, its full potential is limited by the need to define constraints in pre-designed mathematical terms, which requires extensive domain expertise and reinforcement learning knowledge, hindering its broader adoption. To address this limitation and make Safe MARL more accessible and adaptable, we propose a novel approach named Safe Multi-agent Reinforcement Learning with Natural Language constraints (SMALL). Our method leverages fine-tuned language models to interpret and process free-form textual constraints, converting them into semantic embeddings that capture the essence of prohibited states and behaviours. These embeddings are then integrated into the multi-agent policy learning process, enabling agents to learn policies that minimize constraint violations while optimizing rewards. To evaluate the effectiveness of SMALL, we introduce the LaMaSafe, a multi-task benchmark designed to assess the performance of multiple agents in adhering to natural language constraints. Empirical evaluations across various environments demonstrate that SMALL achieves comparable rewards and significantly fewer constraint violations, highlighting its effectiveness in understanding and enforcing natural language constraints.
Authors: Jiacheng Miao, Qiongshi Lu
Abstract: Machine learning (ML) is playing an increasingly important role in scientific research. In conjunction with classical statistical approaches, ML-assisted analytical strategies have shown great promise in accelerating research findings. This has also opened up a whole new field of methodological research focusing on integrative approaches that leverage both ML and statistics to tackle data science challenges. One type of study that has quickly gained popularity employs ML to predict unobserved outcomes in massive samples and then uses the predicted outcomes in downstream statistical inference. However, existing methods designed to ensure the validity of this type of post-prediction inference are limited to very basic tasks such as linear regression analysis. This is because any extension of these approaches to new, more sophisticated statistical tasks requires task-specific algebraic derivations and software implementations, which ignores the massive library of existing software tools already developed for complex inference tasks and severely constrains the scope of post-prediction inference in real applications. To address this challenge, we propose a novel statistical framework for task-agnostic ML-assisted inference. It provides a post-prediction inference solution that can be easily plugged into almost any established data analysis routine. It delivers valid and efficient inference that is robust to arbitrary choices of ML models, while allowing nearly all existing analytical frameworks to be incorporated into the analysis of ML-predicted outcomes. Through extensive experiments, we showcase the validity, versatility, and superiority of our method compared to existing approaches.
Authors: Mohammad Kalbasi, MohammadAli Shaeri, Vincent Alexandre Mendez, Solaiman Shokur, Silvestro Micera, Mahsa Shoaran
Abstract: Advancements in neural engineering have enabled the development of Robotic Prosthetic Hands (RPHs) aimed at restoring hand functionality. Current commercial RPHs offer limited control through basic on/off commands. Recent progresses in machine learning enable finger movement decoding with higher degrees of freedom, yet the high computational complexity of such models limits their application in portable devices. Future RPH designs must balance portability, low power consumption, and high decoding accuracy to be practical for individuals with disabilities. To this end, we introduce a novel attractor-based neural network to realize on-chip movement decoding for next-generation portable RPHs. The proposed architecture comprises an encoder, an attention layer, an attractor network, and a refinement regressor. We tested our model on four healthy subjects and achieved a decoding accuracy of 80.6\pm3.3\%. Our proposed model is over 120 and 50 times more compact compared to state-of-the-art LSTM and CNN models, respectively, with comparable (or superior) decoding accuracy. Therefore, it exhibits minimal hardware complexity and can be effectively integrated as a System-on-Chip.
Authors: Avelina Asada Hadji-Kyriacou, Ognjen Arandjelovic
Abstract: Pre-trained Language Models (LMs) exhibit strong zero-shot and in-context learning capabilities; however, their behaviors are often difficult to control. By utilizing Reinforcement Learning from Human Feedback (RLHF), it is possible to fine-tune unsupervised LMs to follow instructions and produce outputs that reflect human preferences. Despite its benefits, RLHF has been shown to potentially harm a language model's reasoning capabilities and introduce artifacts such as hallucinations where the model may fabricate facts. To address this issue we introduce Direct Preference Heads (DPH), a fine-tuning framework that enables LMs to learn human preference signals through an auxiliary reward head without directly affecting the output distribution of the language modeling head. We perform a theoretical analysis of our objective function and find strong ties to Conservative Direct Preference Optimization (cDPO). Finally we evaluate our models on GLUE, RACE, and the GPT4All evaluation suite and demonstrate that our method produces models which achieve higher scores than those fine-tuned with Supervised Fine-Tuning (SFT) or Direct Preference Optimization (DPO) alone.
Authors: Anjum Shaik, Kristoffer Larsen, Nancy E. Lane, Chen Zhao, Kuan-Jui Su, Joyce H. Keyak, Qing Tian, Qiuying Sha, Hui Shen, Hong-Wen Deng, Weihua Zhou
Abstract: Despite advancements in medical care, hip fractures impose a significant burden on individuals and healthcare systems. This paper focuses on the prediction of hip fracture risk in older and middle-aged adults, where falls and compromised bone quality are predominant factors. We propose a novel staged model that combines advanced imaging and clinical data to improve predictive performance. By using CNNs to extract features from hip DXA images, along with clinical variables, shape measurements, and texture features, our method provides a comprehensive framework for assessing fracture risk. A staged machine learning-based model was developed using two ensemble models: Ensemble 1 (clinical variables only) and Ensemble 2 (clinical variables and DXA imaging features). This staged approach used uncertainty quantification from Ensemble 1 to decide if DXA features are necessary for further prediction. Ensemble 2 exhibited the highest performance, achieving an AUC of 0.9541, an accuracy of 0.9195, a sensitivity of 0.8078, and a specificity of 0.9427. The staged model also performed well, with an AUC of 0.8486, an accuracy of 0.8611, a sensitivity of 0.5578, and a specificity of 0.9249, outperforming Ensemble 1, which had an AUC of 0.5549, an accuracy of 0.7239, a sensitivity of 0.1956, and a specificity of 0.8343. Furthermore, the staged model suggested that 54.49% of patients did not require DXA scanning. It effectively balanced accuracy and specificity, offering a robust solution when DXA data acquisition is not always feasible. Statistical tests confirmed significant differences between the models, highlighting the advantages of the advanced modeling strategies. Our staged approach could identify individuals at risk with a high accuracy but reduce the unnecessary DXA scanning. It has great promise to guide interventions to prevent hip fractures with reduced cost and radiation.
Authors: Elena Grazia Gado, Tommaso Martorella, Luca Zunino, Paola Mejia-Domenzain, Vinitra Swamy, Jibril Frej, Tanja K\"aser
Abstract: Intelligent Tutoring Systems (ITS) enhance personalized learning by predicting student answers to provide immediate and customized instruction. However, recent research has primarily focused on the correctness of the answer rather than the student's performance on specific answer choices, limiting insights into students' thought processes and potential misconceptions. To address this gap, we present MCQStudentBert, an answer forecasting model that leverages the capabilities of Large Language Models (LLMs) to integrate contextual understanding of students' answering history along with the text of the questions and answers. By predicting the specific answer choices students are likely to make, practitioners can easily extend the model to new answer choices or remove answer choices for the same multiple-choice question (MCQ) without retraining the model. In particular, we compare MLP, LSTM, BERT, and Mistral 7B architectures to generate embeddings from students' past interactions, which are then incorporated into a finetuned BERT's answer-forecasting mechanism. We apply our pipeline to a dataset of language learning MCQ, gathered from an ITS with over 10,000 students to explore the predictive accuracy of MCQStudentBert, which incorporates student interaction patterns, in comparison to correct answer prediction and traditional mastery-learning feature-based approaches. This work opens the door to more personalized content, modularization, and granular support.
Authors: Benoit Oriol
Abstract: Multi-target linear shrinkage is an extension of the standard single-target linear shrinkage for covariance estimation. We combine several constant matrices - the targets - with the sample covariance matrix. We derive the oracle and a \textit{bona fide} multi-target linear shrinkage estimator with exact and empirical mean. In both settings, we proved its convergence towards the oracle under Kolmogorov asymptotics. Finally, we show empirically that it outperforms other standard estimators in various situations.
Authors: Navarro Miriam, Becerra \'Alvaro, Daza Roberto, Cobos Ruth, Morales Aythami, Fierrez Julian
Abstract: In this paper, we present an approach in the Multimodal Learning Analytics field. Within this approach, we have developed a tool to visualize and analyze eye movement data collected during learning sessions in online courses. The tool is named VAAD (an acronym for Visual Attention Analysis Dashboard). These eye movement data have been gathered using an eye-tracker and subsequently processed and visualized for interpretation. The purpose of the tool is to conduct a descriptive analysis of the data by facilitating its visualization, enabling the identification of differences and learning patterns among various learner populations. Additionally, it integrates a predictive module capable of anticipating learner activities during a learning session. Consequently, VAAD holds the potential to offer valuable insights into online learning behaviors from both descriptive and predictive perspectives.
Authors: Reza Arabpour, John Armstrong, Luca Galimberti, Anastasis Kratsios, Giulia Livieri
Abstract: Predicting the conditional evolution of Volterra processes with stochastic volatility is a crucial challenge in mathematical finance. While deep neural network models offer promise in approximating the conditional law of such processes, their effectiveness is hindered by the curse of dimensionality caused by the infinite dimensionality and non-smooth nature of these problems. To address this, we propose a two-step solution. Firstly, we develop a stable dimension reduction technique, projecting the law of a reasonably broad class of Volterra process onto a low-dimensional statistical manifold of non-positive sectional curvature. Next, we introduce a sequentially deep learning model tailored to the manifold's geometry, which we show can approximate the projected conditional law of the Volterra process. Our model leverages an auxiliary hypernetwork to dynamically update its internal parameters, allowing it to encode non-stationary dynamics of the Volterra process, and it can be interpreted as a gating mechanism in a mixture of expert models where each expert is specialized at a specific point in time. Our hypernetwork further allows us to achieve approximation rates that would seemingly only be possible with very large networks.
Authors: Man-Chung Yue, Yves Rychener, Daniel Kuhn, Viet Anh Nguyen
Abstract: The state-of-the-art methods for estimating high-dimensional covariance matrices all shrink the eigenvalues of the sample covariance matrix towards a data-insensitive shrinkage target. The underlying shrinkage transformation is either chosen heuristically - without compelling theoretical justification - or optimally in view of restrictive distributional assumptions. In this paper, we propose a principled approach to construct covariance estimators without imposing restrictive assumptions. That is, we study distributionally robust covariance estimation problems that minimize the worst-case Frobenius error with respect to all data distributions close to a nominal distribution, where the proximity of distributions is measured via a divergence on the space of covariance matrices. We identify mild conditions on this divergence under which the resulting minimizers represent shrinkage estimators. We show that the corresponding shrinkage transformations are intimately related to the geometrical properties of the underlying divergence. We also prove that our robust estimators are efficiently computable and asymptotically consistent and that they enjoy finite-sample performance guarantees. We exemplify our general methodology by synthesizing explicit estimators induced by the Kullback-Leibler, Fisher-Rao, and Wasserstein divergences. Numerical experiments based on synthetic and real data show that our robust estimators are competitive with state-of-the-art estimators.
Authors: Avetik Karagulyan, Egor Shulgin, Abdurakhmon Sadiev, Peter Richt\'arik
Abstract: Cross-device training is a crucial subfield of federated learning, where the number of clients can reach into the billions. Standard approaches and local methods are prone to issues such as client drift and insensitivity to data similarities. We propose a novel algorithm (SPAM) for cross-device federated learning with non-convex losses, which solves both issues. We provide sharp analysis under second-order (Hessian) similarity, a condition satisfied by a variety of machine learning problems in practice. Additionally, we extend our results to the partial participation setting, where a cohort of selected clients communicate with the server at each communication round. Our method is the first in its kind, that does not require the smoothness of the objective and provably benefits from clients having similar data.
Authors: Costas Mavromatis, George Karypis
Abstract: Knowledge Graphs (KGs) represent human-crafted factual knowledge in the form of triplets (head, relation, tail), which collectively form a graph. Question Answering over KGs (KGQA) is the task of answering natural questions grounding the reasoning to the information provided by the KG. Large Language Models (LLMs) are the state-of-the-art models for QA tasks due to their remarkable ability to understand natural language. On the other hand, Graph Neural Networks (GNNs) have been widely used for KGQA as they can handle the complex graph information stored in the KG. In this work, we introduce GNN-RAG, a novel method for combining language understanding abilities of LLMs with the reasoning abilities of GNNs in a retrieval-augmented generation (RAG) style. First, a GNN reasons over a dense KG subgraph to retrieve answer candidates for a given question. Second, the shortest paths in the KG that connect question entities and answer candidates are extracted to represent KG reasoning paths. The extracted paths are verbalized and given as input for LLM reasoning with RAG. In our GNN-RAG framework, the GNN acts as a dense subgraph reasoner to extract useful graph information, while the LLM leverages its natural language processing ability for ultimate KGQA. Furthermore, we develop a retrieval augmentation (RA) technique to further boost KGQA performance with GNN-RAG. Experimental results show that GNN-RAG achieves state-of-the-art performance in two widely used KGQA benchmarks (WebQSP and CWQ), outperforming or matching GPT-4 performance with a 7B tuned LLM. In addition, GNN-RAG excels on multi-hop and multi-entity questions outperforming competing approaches by 8.9--15.5% points at answer F1.
Authors: Wooseong Cho, Taehyun Hwang, Joongkyu Lee, Min-hwan Oh
Abstract: We study reinforcement learning with multinomial logistic (MNL) function approximation where the underlying transition probability kernel of the Markov decision processes (MDPs) is parametrized by an unknown transition core with features of state and action. For the finite horizon episodic setting with inhomogeneous state transitions, we propose provably efficient algorithms with randomized exploration having frequentist regret guarantees. For our first algorithm, $\texttt{RRL-MNL}$, we adapt optimistic sampling to ensure the optimism of the estimated value function with sufficient frequency and establish that $\texttt{RRL-MNL}$ is both statistically and computationally efficient, achieving a $\tilde{O}(\kappa^{-1} d^{\frac{3}{2}} H^{\frac{3}{2}} \sqrt{T})$ frequentist regret bound with constant-time computational cost per episode. Here, $d$ is the dimension of the transition core, $H$ is the horizon length, $T$ is the total number of steps, and $\kappa$ is a problem-dependent constant. Despite the simplicity and practicality of $\texttt{RRL-MNL}$, its regret bound scales with $\kappa^{-1}$, which is potentially large in the worst case. To improve the dependence on $\kappa^{-1}$, we propose $\texttt{ORRL-MNL}$, which estimates the value function using local gradient information of the MNL transition model. We show that its frequentist regret bound is $\tilde{O}(d^{\frac{3}{2}} H^{\frac{3}{2}} \sqrt{T} + \kappa^{-1} d^2 H^2)$. To the best of our knowledge, these are the first randomized RL algorithms for the MNL transition model that achieve both computational and statistical efficiency. Numerical experiments demonstrate the superior performance of the proposed algorithms.
Authors: Alaa Nfissi, Wassim Bouachir, Nizar Bouguila, Brian Mishara
Abstract: In speech emotion recognition (SER), using predefined features without considering their practical importance may lead to high dimensional datasets, including redundant and irrelevant information. Consequently, high-dimensional learning often results in decreasing model accuracy while increasing computational complexity. Our work underlines the importance of carefully considering and analyzing features in order to build efficient SER systems. We present a new supervised SER method based on an efficient feature engineering approach. We pay particular attention to the explainability of results to evaluate feature relevance and refine feature sets. This is performed iteratively through feature evaluation loop, using Shapley values to boost feature selection and improve overall framework performance. Our approach allows thus to balance the benefits between model performance and transparency. The proposed method outperforms human-level performance (HLP) and state-of-the-art machine learning methods in emotion recognition on the TESS dataset.
Authors: Joshua Hanson, Biliana Paskaleva, Pavel Bochev
Abstract: We demonstrate that data-driven system identification techniques can provide a basis for effective, non-intrusive model order reduction (MOR) for common circuits that are key building blocks in microelectronics. Our approach is motivated by the practical operation of these circuits and utilizes a canonical Hammerstein architecture. To demonstrate the approach we develop a parsimonious Hammerstein model for a non-linear CMOS differential amplifier. We train this model on a combination of direct current (DC) and transient Spice (Xyce) circuit simulation data using a novel sequential strategy to identify the static nonlinear and linear dynamical parts of the model. Simulation results show that the Hammerstein model is an effective surrogate for the differential amplifier circuit that accurately and efficiently reproduces its behavior over a wide range of operating points and input frequencies.
Authors: Vijay Jaisankar, Sambaran Bandyopadhyay, Kalp Vyas, Varre Chaitanya, Shwetha Somasundaram
Abstract: A poster from a long input document can be considered as a one-page easy-to-read multimodal (text and images) summary presented on a nice template with good design elements. Automatic transformation of a long document into a poster is a very less studied but challenging task. It involves content summarization of the input document followed by template generation and harmonization. In this work, we propose a novel deep submodular function which can be trained on ground truth summaries to extract multimodal content from the document and explicitly ensures good coverage, diversity and alignment of text and images. Then, we use an LLM based paraphraser and propose to generate a template with various design aspects conditioned on the input content. We show the merits of our approach through extensive automated and human evaluations.
Authors: Sanghyeon Na, Yonggyu Kim, Hyunjoon Lee
Abstract: The generation of high-quality human images through text-to-image (T2I) methods is a significant yet challenging task. Distinct from general image generation, human image synthesis must satisfy stringent criteria related to human pose, anatomy, and alignment with textual prompts, making it particularly difficult to achieve realistic results. Recent advancements in T2I generation based on diffusion models have shown promise, yet challenges remain in meeting human-specific preferences. In this paper, we introduce a novel approach tailored specifically for human image generation utilizing Direct Preference Optimization (DPO). Specifically, we introduce an efficient method for constructing a specialized DPO dataset for training human image generation models without the need for costly human feedback. We also propose a modified loss function that enhances the DPO training process by minimizing artifacts and improving image fidelity. Our method demonstrates its versatility and effectiveness in generating human images, including personalized text-to-image generation. Through comprehensive evaluations, we show that our approach significantly advances the state of human image generation, achieving superior results in terms of natural anatomies, poses, and text-image alignment.
Authors: Ayyub Alzahem, Wadii Boulila, Maha Driss, Anis Koubaa
Abstract: Addressing uncertainty in Deep Learning (DL) is essential, as it enables the development of models that can make reliable predictions and informed decisions in complex, real-world environments where data may be incomplete or ambiguous. This paper introduces a novel algorithm leveraging Dempster-Shafer Theory (DST) to integrate multiple pre-trained models to form an ensemble capable of providing more reliable and enhanced classifications. The main steps of the proposed method include feature extraction, mass function calculation, fusion, and expected utility calculation. Several experiments have been conducted on CIFAR-10 and CIFAR-100 datasets, demonstrating superior classification accuracy of the proposed DST-based method, achieving improvements of 5.4% and 8.4%, respectively, compared to the best individual pre-trained models. Results highlight the potential of DST as a robust framework for managing uncertainties related to data when applying DL in real-world scenarios.
Authors: Naoki Hiratani
Abstract: Continual learning of partially similar tasks poses a challenge for artificial neural networks, as task similarity presents both an opportunity for knowledge transfer and a risk of interference and catastrophic forgetting. However, it remains unclear how task similarity in input features and readout patterns influences knowledge transfer and forgetting, as well as how they interact with common algorithms for continual learning. Here, we develop a linear teacher-student model with latent structure and show analytically that high input feature similarity coupled with low readout similarity is catastrophic for both knowledge transfer and retention. Conversely, the opposite scenario is relatively benign. Our analysis further reveals that task-dependent activity gating improves knowledge retention at the expense of transfer, while task-dependent plasticity gating does not affect either retention or transfer performance at the over-parameterized limit. In contrast, weight regularization based on the Fisher information metric significantly improves retention, regardless of task similarity, without compromising transfer performance. Nevertheless, its diagonal approximation and regularization in the Euclidean space are much less robust against task similarity. We demonstrate consistent results in a permuted MNIST task with latent variables. Overall, this work provides insights into when continual learning is difficult and how to mitigate it.
Authors: Brian Coyle, El Amine Cherrat, Nishant Jain, Natansh Mathur, Snehal Raj, Skander Kazdaghli, Iordanis Kerenidis
Abstract: Quantum machine learning requires powerful, flexible and efficiently trainable models to be successful in solving challenging problems. In this work, we present density quantum neural networks, a learning model incorporating randomisation over a set of trainable unitaries. These models generalise quantum neural networks using parameterised quantum circuits, and allow a trade-off between expressibility and efficient trainability, particularly on quantum hardware. We demonstrate the flexibility of the formalism by applying it to two recently proposed model families. The first are commuting-block quantum neural networks (QNNs) which are efficiently trainable but may be limited in expressibility. The second are orthogonal (Hamming-weight preserving) quantum neural networks which provide well-defined and interpretable transformations on data but are challenging to train at scale on quantum devices. Density commuting QNNs improve capacity with minimal gradient complexity overhead, and density orthogonal neural networks admit a quadratic-to-constant gradient query advantage with minimal to no performance loss. We conduct numerical experiments on synthetic translationally invariant data and MNIST image data with hyperparameter optimisation to support our findings. Finally, we discuss the connection to post-variational quantum neural networks, measurement-based quantum machine learning and the dropout mechanism.
Authors: Franz Louis Cesista, Rui Aguiar, Jason Kim, Paolo Acilo
Abstract: Business Document Information Extraction (BDIE) is the problem of transforming a blob of unstructured information (raw text, scanned documents, etc.) into a structured format that downstream systems can parse and use. It has two main tasks: Key-Information Extraction (KIE) and Line Items Recognition (LIR). In this paper, we argue that BDIE is best modeled as a Tool Use problem, where the tools are these downstream systems. We then present Retrieval Augmented Structured Generation (RASG), a novel general framework for BDIE that achieves state of the art (SOTA) results on both KIE and LIR tasks on BDIE benchmarks. The contributions of this paper are threefold: (1) We show, with ablation benchmarks, that Large Language Models (LLMs) with RASG are already competitive with or surpasses current SOTA Large Multimodal Models (LMMs) without RASG on BDIE benchmarks. (2) We propose a new metric class for Line Items Recognition, General Line Items Recognition Metric (GLIRM), that is more aligned with practical BDIE use cases compared to existing metrics, such as ANLS*, DocILE, and GriTS. (3) We provide a heuristic algorithm for backcalculating bounding boxes of predicted line items and tables without the need for vision encoders. Finally, we claim that, while LMMs might sometimes offer marginal performance benefits, LLMs + RASG is oftentimes superior given real-world applications and constraints of BDIE.
Authors: Matthew Watson, Divyashree Shivakumar Sreepathihalli, Francois Chollet, Martin Gorner, Kiranbir Sodhia, Ramesh Sampath, Tirth Patel, Haifeng Jin, Neel Kovelamudi, Gabriel Rasskin, Samaneh Saadat, Luke Wood, Chen Qian, Jonathan Bischof, Ian Stenbit
Abstract: We present the Keras domain packages KerasCV and KerasNLP, extensions of the Keras API for Computer Vision and Natural Language Processing workflows, capable of running on either JAX, TensorFlow, or PyTorch. These domain packages are designed to enable fast experimentation, with a focus on ease-of-use and performance. We adopt a modular, layered design: at the library's lowest level of abstraction, we provide building blocks for creating models and data preprocessing pipelines, and at the library's highest level of abstraction, we provide pretrained ``task" models for popular architectures such as Stable Diffusion, YOLOv8, GPT2, BERT, Mistral, CLIP, Gemma, T5, etc. Task models have built-in preprocessing, pretrained weights, and can be fine-tuned on raw inputs. To enable efficient training, we support XLA compilation for all models, and run all preprocessing via a compiled graph of TensorFlow operations using the tf.data API. The libraries are fully open-source (Apache 2.0 license) and available on GitHub.
Authors: Deven Sethi, David \v{S}i\v{s}ka, Yufei Zhang
Abstract: Entropy regularization has been extensively used in policy optimization algorithms to regularize the optimization landscape and accelerate convergence; however, it comes at the cost of introducing an additional regularization bias. This work quantifies the impact of entropy regularization on the convergence of policy gradient methods for stochastic exit time control problems. We analyze a continuous-time policy mirror descent dynamics, which updates the policy based on the gradient of an entropy-regularized value function and adjusts the strength of entropy regularization as the algorithm progresses. We prove that with a fixed entropy level, the dynamics converges exponentially to the optimal solution of the regularized problem. We further show that when the entropy level decays at suitable polynomial rates, the annealed flow converges to the solution of the unregularized problem at a rate of $\mathcal O(1/S)$ for discrete action spaces and, under suitable conditions, at a rate of $\mathcal O(1/\sqrt{S})$ for general action spaces, with $S$ being the gradient flow time. This paper explains how entropy regularization improves policy optimization, even with the true gradient, from the perspective of convergence rate.
Authors: Siva Uday Sampreeth Chebolu, Franck Dernoncourt, Nedim Lipka, Thamar Solorio
Abstract: Aspect-Based Sentiment Analysis (ABSA) has experienced tremendous expansion and diversity due to various shared tasks spanning several languages and fields and organized via SemEval workshops and Germeval. Nonetheless, a few shortcomings still need to be addressed, such as the lack of low-resource language evaluations and the emphasis on sentence-level analysis. To thoroughly assess ABSA techniques in the context of complete reviews, this research presents a novel task, Review-Level Opinion Aspect Sentiment Target (ROAST). ROAST seeks to close the gap between sentence-level and text-level ABSA by identifying every ABSA constituent at the review level. We extend the available datasets to enable ROAST, addressing the drawbacks noted in previous research by incorporating low-resource languages, numerous languages, and a variety of topics. Through this effort, ABSA research will be able to cover more ground and get a deeper comprehension of the task and its practical application in a variety of languages and domains (https://github.com/RiTUAL-UH/ROAST-ABSA).
Authors: Zachary Novack, Julian McAuley, Taylor Berg-Kirkpatrick, Nicholas Bryan
Abstract: Controllable music generation methods are critical for human-centered AI-based music creation, but are currently limited by speed, quality, and control design trade-offs. Diffusion Inference-Time T-optimization (DITTO), in particular, offers state-of-the-art results, but is over 10x slower than real-time, limiting practical use. We propose Distilled Diffusion Inference-Time T -Optimization (or DITTO-2), a new method to speed up inference-time optimization-based control and unlock faster-than-real-time generation for a wide-variety of applications such as music inpainting, outpainting, intensity, melody, and musical structure control. Our method works by (1) distilling a pre-trained diffusion model for fast sampling via an efficient, modified consistency or consistency trajectory distillation process (2) performing inference-time optimization using our distilled model with one-step sampling as an efficient surrogate optimization task and (3) running a final multi-step sampling generation (decoding) using our estimated noise latents for best-quality, fast, controllable generation. Through thorough evaluation, we find our method not only speeds up generation over 10-20x, but simultaneously improves control adherence and generation quality all at once. Furthermore, we apply our approach to a new application of maximizing text adherence (CLAP score) and show we can convert an unconditional diffusion model without text inputs into a model that yields state-of-the-art text control. Sound examples can be found at https://ditto-music.github.io/ditto2/.
Authors: Shyam Sundhar Ramesh, Yifan Hu, Iason Chaimalas, Viraj Mehta, Pier Giuseppe Sessa, Haitham Bou Ammar, Ilija Bogunovic
Abstract: Adapting large language models (LLMs) for specific tasks usually involves fine-tuning through reinforcement learning with human feedback (RLHF) on preference data. While these data often come from diverse labelers' groups (e.g., different demographics, ethnicities, company teams, etc.), traditional RLHF approaches adopt a "one-size-fits-all" approach, i.e., they indiscriminately assume and optimize a single preference model, thus not being robust to unique characteristics and needs of the various groups. To address this limitation, we propose a novel Group Robust Preference Optimization (GRPO) method to align LLMs to individual groups' preferences robustly. Our approach builds upon reward-free direct preference optimization methods, but unlike previous approaches, it seeks a robust policy which maximizes the worst-case group performance. To achieve this, GRPO adaptively and sequentially weights the importance of different groups, prioritizing groups with worse cumulative loss. We theoretically study the feasibility of GRPO and analyze its convergence for the log-linear policy class. By fine-tuning LLMs with GRPO using diverse group-based global opinion data, we significantly improved performance for the worst-performing groups, reduced loss imbalances across groups, and improved probability accuracies compared to non-robust baselines.
Authors: Roberto Ceraolo, Dmitrii Kharlapenko, Am\'elie Reymond, Rada Mihalcea, Mrinmaya Sachan, Bernhard Sch\"olkopf, Zhijing Jin
Abstract: Humans have an innate drive to seek out causality. Whether fuelled by curiosity or specific goals, we constantly question why things happen, how they are interconnected, and many other related phenomena. To develop AI agents capable of addressing this natural human quest for causality, we urgently need a comprehensive dataset of natural causal questions. Unfortunately, existing datasets either contain only artificially-crafted questions that do not reflect real AI usage scenarios or have limited coverage of questions from specific sources. To address this gap, we present CausalQuest, a dataset of 13,500 naturally occurring questions sourced from social networks, search engines, and AI assistants. We formalize the definition of causal questions and establish a taxonomy for finer-grained classification. Through a combined effort of human annotators and large language models (LLMs), we carefully label the dataset. We find that 42% of the questions humans ask are indeed causal, with the majority seeking to understand the causes behind given effects. Using this dataset, we train efficient classifiers (up to 2.85B parameters) for the binary task of identifying causal questions, achieving high performance with F1 scores of up to 0.877. We conclude with a rich set of future research directions that can build upon our data and models.
Authors: Sangyun Lee, Zinan Lin, Giulia Fanti
Abstract: Diffusion models have shown great promise for image and video generation, but sampling from state-of-the-art models requires expensive numerical integration of a generative ODE. One approach for tackling this problem is rectified flows, which iteratively learn smooth ODE paths that are less susceptible to truncation error. However, rectified flows still require a relatively large number of function evaluations (NFEs). In this work, we propose improved techniques for training rectified flows, allowing them to compete with knowledge distillation methods even in the low NFE setting. Our main insight is that under realistic settings, a single iteration of the Reflow algorithm for training rectified flows is sufficient to learn nearly straight trajectories; hence, the current practice of using multiple Reflow iterations is unnecessary. We thus propose techniques to improve one-round training of rectified flows, including a U-shaped timestep distribution and LPIPS-Huber premetric. With these techniques, we improve the FID of the previous 2-rectified flow by up to 72% in the 1 NFE setting on CIFAR-10. On ImageNet 64$\times$64, our improved rectified flow outperforms the state-of-the-art distillation methods such as consistency distillation and progressive distillation in both one-step and two-step settings and rivals the performance of improved consistency training (iCT) in FID. Code is available at https://github.com/sangyun884/rfpp.
Authors: Yifeng Zhu, Arisrei Lim, Peter Stone, Yuke Zhu
Abstract: We present an object-centric approach to empower robots to learn vision-based manipulation skills from human videos. We investigate the problem of imitating robot manipulation from a single human video in the open-world setting, where a robot must learn to manipulate novel objects from one video demonstration. We introduce ORION, an algorithm that tackles the problem by extracting an object-centric manipulation plan from a single RGB-D video and deriving a policy that conditions on the extracted plan. Our method enables the robot to learn from videos captured by daily mobile devices such as an iPad and generalize the policies to deployment environments with varying visual backgrounds, camera angles, spatial layouts, and novel object instances. We systematically evaluate our method on both short-horizon and long-horizon tasks, demonstrating the efficacy of ORION in learning from a single human video in the open world. Videos can be found in the project website https://ut-austin-rpl.github.io/ORION-release.
Authors: Nicolas Dufour, Victor Besnier, Vicky Kalogeiton, David Picard
Abstract: Conditional diffusion models are powerful generative models that can leverage various types of conditional information, such as class labels, segmentation masks, or text captions. However, in many real-world scenarios, conditional information may be noisy or unreliable due to human annotation errors or weak alignment. In this paper, we propose the Coherence-Aware Diffusion (CAD), a novel method that integrates coherence in conditional information into diffusion models, allowing them to learn from noisy annotations without discarding data. We assume that each data point has an associated coherence score that reflects the quality of the conditional information. We then condition the diffusion model on both the conditional information and the coherence score. In this way, the model learns to ignore or discount the conditioning when the coherence is low. We show that CAD is theoretically sound and empirically effective on various conditional generation tasks. Moreover, we show that leveraging coherence generates realistic and diverse samples that respect conditional information better than models trained on cleaned datasets where samples with low coherence have been discarded.
Authors: Kailu Wu, Fangfu Liu, Zhihan Cai, Runjie Yan, Hanyang Wang, Yating Hu, Yueqi Duan, Kaisheng Ma
Abstract: In this work, we introduce Unique3D, a novel image-to-3D framework for efficiently generating high-quality 3D meshes from single-view images, featuring state-of-the-art generation fidelity and strong generalizability. Previous methods based on Score Distillation Sampling (SDS) can produce diversified 3D results by distilling 3D knowledge from large 2D diffusion models, but they usually suffer from long per-case optimization time with inconsistent issues. Recent works address the problem and generate better 3D results either by finetuning a multi-view diffusion model or training a fast feed-forward model. However, they still lack intricate textures and complex geometries due to inconsistency and limited generated resolution. To simultaneously achieve high fidelity, consistency, and efficiency in single image-to-3D, we propose a novel framework Unique3D that includes a multi-view diffusion model with a corresponding normal diffusion model to generate multi-view images with their normal maps, a multi-level upscale process to progressively improve the resolution of generated orthographic multi-views, as well as an instant and consistent mesh reconstruction algorithm called ISOMER, which fully integrates the color and geometric priors into mesh results. Extensive experiments demonstrate that our Unique3D significantly outperforms other image-to-3D baselines in terms of geometric and textural details.
Authors: Bingshan Hu, Zhiming Huang, Nishant A. Mehta, Nidhi Hegde
Abstract: In this paper, we study differentially private online learning problems in a stochastic environment under both bandit and full information feedback. For differentially private stochastic bandits, we propose both UCB and Thompson Sampling-based algorithms that are anytime and achieve the optimal $O \left(\sum_{j: \Delta_j>0} \frac{\ln(T)}{\min \left\{\Delta_j, \epsilon \right\}} \right)$ instance-dependent regret bound, where $T$ is the finite learning horizon, $\Delta_j$ denotes the suboptimality gap between the optimal arm and a suboptimal arm $j$, and $\epsilon$ is the required privacy parameter. For the differentially private full information setting with stochastic rewards, we show an $\Omega \left(\frac{\ln(K)}{\min \left\{\Delta_{\min}, \epsilon \right\}} \right)$ instance-dependent regret lower bound and an $\Omega\left(\sqrt{T\ln(K)} + \frac{\ln(K)}{\epsilon}\right)$ minimax lower bound, where $K$ is the total number of actions and $\Delta_{\min}$ denotes the minimum suboptimality gap among all the suboptimal actions. For the same differentially private full information setting, we also present an $\epsilon$-differentially private algorithm whose instance-dependent regret and worst-case regret match our respective lower bounds up to an extra $\log(T)$ factor.
Authors: Eva Memmel, Clara Menzen, Jetze Schuurmans, Frederiek Wesel, Kim Batselier
Abstract: For the first time, this position paper introduces a fundamental link between tensor networks (TNs) and Green AI, highlighting their synergistic potential to enhance both the inclusivity and sustainability of AI research. We argue that TNs are valuable for Green AI due to their strong mathematical backbone and inherent logarithmic compression potential. We undertake a comprehensive review of the ongoing discussions on Green AI, emphasizing the importance of sustainability and inclusivity in AI research to demonstrate the significance of establishing the link between Green AI and TNs. To support our position, we first provide a comprehensive overview of efficiency metrics proposed in Green AI literature and then evaluate examples of TNs in the fields of kernel machines and deep learning using the proposed efficiency metrics. This position paper aims to incentivize meaningful, constructive discussions by bridging fundamental principles of Green AI and TNs. We advocate for researchers to seriously evaluate the integration of TNs into their research projects, and in alignment with the link established in this paper, we support prior calls encouraging researchers to treat Green AI principles as a research priority.
Authors: Arip Asadulaev, Alexander Korotin, Vage Egiazarian, Petr Mokrov, Evgeny Burnaev
Abstract: We introduce a novel neural network-based algorithm to compute optimal transport (OT) plans for general cost functionals. In contrast to common Euclidean costs, i.e., $\ell^1$ or $\ell^2$, such functionals provide more flexibility and allow using auxiliary information, such as class labels, to construct the required transport map. Existing methods for general costs are discrete and have limitations in practice, i.e. they do not provide an out-of-sample estimation. We address the challenge of designing a continuous OT approach for general costs that generalizes to new data points in high-dimensional spaces, such as images. Additionally, we provide the theoretical error analysis for our recovered transport plans. As an application, we construct a cost functional to map data distributions while preserving the class-wise structure.
Authors: Felix Marx, Thomas Schneider, Ajith Suresh, Tobias Wehrle, Christian Weinert, Hossein Yalame
Abstract: Federated learning (FL) is an efficient approach for large-scale distributed machine learning that promises data privacy by keeping training data on client devices. However, recent research has uncovered vulnerabilities in FL, impacting both security and privacy through poisoning attacks and the potential disclosure of sensitive information in individual model updates as well as the aggregated global model. This paper explores the inadequacies of existing FL protection measures when applied independently, and the challenges of creating effective compositions. Addressing these issues, we propose WW-FL, an innovative framework that combines secure multi-party computation (MPC) with hierarchical FL to guarantee data and global model privacy. One notable feature of WW-FL is its capability to prevent malicious clients from directly poisoning model parameters, confining them to less destructive data poisoning attacks. We furthermore provide a PyTorch-based FL implementation integrated with Meta's CrypTen MPC framework to systematically measure the performance and robustness of WW-FL. Our extensive evaluation demonstrates that WW-FL is a promising solution for secure and private large-scale federated learning.
Authors: Yihao Xue, Ali Payani, Yu Yang, Baharan Mirzasoleiman
Abstract: Pretrained machine learning models need to be adapted to distribution shifts when deployed in new target environments. When obtaining labeled data from the target distribution is expensive, few-shot adaptation with only a few examples from the target distribution becomes essential. In this work, we propose MixPro, a lightweight and highly data-efficient approach for few-shot adaptation. MixPro first generates a relatively large dataset by mixing (linearly combining) pre-trained embeddings of large source data with those of the few target examples. This process preserves important features of both source and target distributions, while mitigating the specific noise in the small target data. Then, it trains a linear classifier on the mixed embeddings to effectively adapts the model to the target distribution without overfitting the small target data. Theoretically, we demonstrate the advantages of MixPro over previous methods. Our experiments, conducted across various model architectures on 8 datasets featuring different types of distribution shifts, reveal that MixPro can outperform baselines by up to 7\%, with only 2-4 target examples.
Authors: Cornelius Schr\"oder, Jakob H. Macke
Abstract: Many scientific models are composed of multiple discrete components, and scientists often make heuristic decisions about which components to include. Bayesian inference provides a mathematical framework for systematically selecting model components, but defining prior distributions over model components and developing associated inference schemes has been challenging. We approach this problem in a simulation-based inference framework: We define model priors over candidate components and, from model simulations, train neural networks to infer joint probability distributions over both model components and associated parameters. Our method, simulation-based model inference (SBMI), represents distributions over model components as a conditional mixture of multivariate binary distributions in the Grassmann formalism. SBMI can be applied to any compositional stochastic simulator without requiring likelihood evaluations. We evaluate SBMI on a simple time series model and on two scientific models from neuroscience, and show that it can discover multiple data-consistent model configurations, and that it reveals non-identifiable model components and parameters. SBMI provides a powerful tool for data-driven scientific inquiry which will allow scientists to identify essential model components and make uncertainty-informed modelling decisions.
Authors: Jos\'e Ram\'on Pareja Monturiol, David P\'erez-Garc\'ia, Alejandro Pozas-Kerstjens
Abstract: Tensor networks are factorizations of high-dimensional tensors into networks of smaller tensors. They have applications in physics and mathematics, and recently have been proposed as promising machine learning architectures. To ease the integration of tensor networks in machine learning pipelines, we introduce TensorKrowch, an open source Python library built on top of PyTorch. Providing a user-friendly interface, TensorKrowch allows users to construct any tensor network, train it, and integrate it as a layer in more intricate deep learning models. In this paper, we describe the main functionality and basic usage of TensorKrowch, and provide technical details on its building blocks and the optimizations performed to achieve efficient operation.
Authors: Siqi Liang, Jintao Huang, Junyuan Hong, Dun Zeng, Jiayu Zhou, Zenglin Xu
Abstract: Federated learning has gained popularity for distributed learning without aggregating sensitive data from clients. But meanwhile, the distributed and isolated nature of data isolation may be complicated by data quality, making it more vulnerable to noisy labels. Many efforts exist to defend against the negative impacts of noisy labels in centralized or federated settings. However, there is a lack of a benchmark that comprehensively considers the impact of noisy labels in a wide variety of typical FL settings. In this work, we serve the first standardized benchmark that can help researchers fully explore potential federated noisy settings. Also, we conduct comprehensive experiments to explore the characteristics of these data settings and unravel challenging scenarios on the federated noisy label learning, which may guide method development in the future. We highlight the 20 basic settings for more than 5 datasets proposed in our benchmark and standardized simulation pipeline for federated noisy label learning. We hope this benchmark can facilitate idea verification in federated learning with noisy labels. \texttt{FedNoisy} is available at \codeword{https://github.com/SMILELab-FL/FedNoisy}.
Authors: Tessa Han, Suraj Srinivas, Himabindu Lakkaraju
Abstract: Studying the robustness of machine learning models is important to ensure consistent model behaviour across real-world settings. To this end, adversarial robustness is a standard framework, which views robustness of predictions through a binary lens: either a worst-case adversarial misclassification exists in the local region around an input, or it does not. However, this binary perspective does not account for the degrees of vulnerability, as data points with a larger number of misclassified examples in their neighborhoods are more vulnerable. In this work, we consider a complementary framework for robustness, called average-case robustness, which measures the fraction of points in a local region that provides consistent predictions. However, computing this quantity is hard, as standard Monte Carlo approaches are inefficient especially for high-dimensional inputs. In this work, we propose the first analytical estimators for average-case robustness for multi-class classifiers. We show empirically that our estimators are accurate and efficient for standard deep learning models and demonstrate their usefulness for identifying vulnerable data points, as well as quantifying robustness bias of models. Overall, our tools provide a complementary view to robustness, improving our ability to characterize model behaviour.
Authors: Thanh Vinh Vo, Young lee, Tze-Yun Leong
Abstract: Decentralized data sources are prevalent in real-world applications, posing a formidable challenge for causal inference. These sources cannot be consolidated into a single entity owing to privacy constraints. The presence of dissimilar data distributions and missing values within them can potentially introduce bias to the causal estimands. In this article, we propose a framework to estimate causal effects from decentralized data sources. The proposed framework avoid exchanging raw data among the sources, thus contributing towards privacy-preserving causal learning. Three instances of the proposed framework are introduced to estimate causal effects across a wide range of diverse scenarios within a federated setting. (1) FedCI: a Bayesian framework based on Gaussian processes for estimating causal effects from federated observational data sources. It estimates the posterior distributions of the causal effects to compute the higher-order statistics that capture the uncertainty. (2) CausalRFF: an adaptive transfer algorithm that learns the similarities among the data sources by utilizing Random Fourier Features to disentangle the loss function into multiple components, each of which is associated with a data source. It estimates the similarities among the sources through transfer coefficients, and hence requiring no prior information about the similarity measures. (3) CausalFI: a new approach for federated causal inference from incomplete data, enabling the estimation of causal effects from multiple decentralized and incomplete data sources. It accounts for the missing data under the missing at random assumption, while also estimating higher-order statistics of the causal estimands. The proposed federated framework and its instances are an important step towards a privacy-preserving causal learning model.
Authors: Qining Zhang, Lei Ying
Abstract: This paper considers a stochastic Multi-Armed Bandit (MAB) problem with dual objectives: (i) quick identification and commitment to the optimal arm, and (ii) reward maximization throughout a sequence of $T$ consecutive rounds. Though each objective has been individually well-studied, i.e., best arm identification for (i) and regret minimization for (ii), the simultaneous realization of both objectives remains an open problem, despite its practical importance. This paper introduces \emph{Regret Optimal Best Arm Identification} (ROBAI) which aims to achieve these dual objectives. To solve ROBAI with both pre-determined stopping time and adaptive stopping time requirements, we present an algorithm called EOCP and its variants respectively, which not only achieve asymptotic optimal regret in both Gaussian and general bandits, but also commit to the optimal arm in $\mathcal{O}(\log T)$ rounds with pre-determined stopping time and $\mathcal{O}(\log^2 T)$ rounds with adaptive stopping time. We further characterize lower bounds on the commitment time (equivalent to the sample complexity) of ROBAI, showing that EOCP and its variants are sample optimal with pre-determined stopping time, and almost sample optimal with adaptive stopping time. Numerical results confirm our theoretical analysis and reveal an interesting "over-exploration" phenomenon carried by classic UCB algorithms, such that EOCP has smaller regret even though it stops exploration much earlier than UCB, i.e., $\mathcal{O}(\log T)$ versus $\mathcal{O}(T)$, which suggests over-exploration is unnecessary and potentially harmful to system performance.
Authors: Donald Martin, Jr., David Kinney
Abstract: Deep learning is a powerful set of techniques for detecting complex patterns in data. However, when the causal structure of that process is underspecified, deep learning models can be brittle, lacking robustness to shifts in the distribution of the data-generating process. In this paper, we turn to loop polarity analysis as a tool for specifying the causal structure of a data-generating process, in order to encode a more robust understanding of the relationship between system structure and system behavior within the deep learning pipeline. We use simulated epidemic data based on an SIR model to demonstrate how measuring the polarity of the different feedback loops that compose a system can lead to more robust inferences on the part of neural networks, improving the out-of-distribution performance of a deep learning model and infusing a system-dynamics-inspired approach into the machine learning development pipeline.
Authors: Cristiana Bolchini, Luca Cassano, Antonio Miele
Abstract: Machine Learning (ML) is currently being exploited in numerous applications being one of the most effective Artificial Intelligence (AI) technologies, used in diverse fields, such as vision, autonomous systems, and alike. The trend motivated a significant amount of contributions to the analysis and design of ML applications against faults affecting the underlying hardware. The authors investigate the existing body of knowledge on Deep Learning (among ML techniques) resilience against hardware faults systematically through a thoughtful review in which the strengths and weaknesses of this literature stream are presented clearly and then future avenues of research are set out. The review is based on 220 scientific articles published between January 2019 and March 2024. The authors adopt a classifying framework to interpret and highlight research similarities and peculiarities, based on several parameters, starting from the main scope of the work, the adopted fault and error models, to their reproducibility. This framework allows for a comparison of the different solutions and the identification of possible synergies. Furthermore, suggestions concerning the future direction of research are proposed in the form of open challenges to be addressed.
Authors: Seul Lee, Seanie Lee, Kenji Kawaguchi, Sung Ju Hwang
Abstract: Fragment-based drug discovery is an effective strategy for discovering drug candidates in the vast chemical space, and has been widely employed in molecular generative models. However, many existing fragment extraction methods in such models do not take the target chemical properties into account or rely on heuristic rules. Additionally, the existing fragment-based generative models cannot update the fragment vocabulary with goal-aware fragments newly discovered during the generation. To this end, we propose a molecular generative framework for drug discovery, named Goal-aware fragment Extraction, Assembly, and Modification (GEAM). GEAM consists of three modules, each responsible for goal-aware fragment extraction, fragment assembly, and fragment modification. The fragment extraction module identifies important fragments contributing to the desired target properties with the information bottleneck principle, thereby constructing an effective goal-aware fragment vocabulary. Moreover, GEAM can explore beyond the initial vocabulary with the fragment modification module, and the exploration is further enhanced through the dynamic goal-aware vocabulary update. We experimentally demonstrate that GEAM effectively discovers drug candidates through the generative cycle of the three modules in various drug discovery tasks. Our code is available at https://github.com/SeulLee05/GEAM.
Authors: Jeonghye Kim, Suyoung Lee, Woojun Kim, Youngchul Sung
Abstract: The recent success of Transformer in natural language processing has sparked its use in various domains. In offline reinforcement learning (RL), Decision Transformer (DT) is emerging as a promising model based on Transformer. However, we discovered that the attention module of DT is not appropriate to capture the inherent local dependence pattern in trajectories of RL modeled as a Markov decision process. To overcome the limitations of DT, we propose a novel action sequence predictor, named Decision ConvFormer (DC), based on the architecture of MetaFormer, which is a general structure to process multiple entities in parallel and understand the interrelationship among the multiple entities. DC employs local convolution filtering as the token mixer and can effectively capture the inherent local associations of the RL dataset. In extensive experiments, DC achieved state-of-the-art performance across various standard RL benchmarks while requiring fewer resources. Furthermore, we show that DC better understands the underlying meaning in data and exhibits enhanced generalization capability.
Authors: Yuan Xin, Michael Backes, Xiao Zhang
Abstract: We study the problem of robust learning against adversarial perturbations under cost-sensitive scenarios, where the potential harm of different types of misclassifications is encoded in a cost matrix. Existing approaches are either empirical and cannot certify robustness or suffer from inherent scalability issues. In this work, we investigate whether randomized smoothing, a scalable framework for robustness certification, can be leveraged to certify and train for cost-sensitive robustness. Built upon the notion of cost-sensitive certified radius, we first illustrate how to adapt the standard certification algorithm of randomized smoothing to produce tight robustness certificates for any binary cost matrix, and then develop a robust training method to promote certified cost-sensitive robustness while maintaining the model's overall accuracy. Through extensive experiments on image benchmarks, we demonstrate the superiority of our proposed certification algorithm and training method under various cost-sensitive scenarios. Our implementation is available as open source code at: https://github.com/TrustMLRG/CS-RS.
Authors: Weiye Zhao, Feihan Li, Yifan Sun, Rui Chen, Tianhao Wei, Changliu Liu
Abstract: In recent years, trust region on-policy reinforcement learning has achieved impressive results in addressing complex control tasks and gaming scenarios. However, contemporary state-of-the-art algorithms within this category primarily emphasize improvement in expected performance, lacking the ability to control over the worst-case performance outcomes. To address this limitation, we introduce a novel objective function, optimizing which leads to guaranteed monotonic improvement in the lower probability bound of performance with high confidence. Building upon this groundbreaking theoretical advancement, we further introduce a practical solution called Absolute Policy Optimization (APO). Our experiments demonstrate the effectiveness of our approach across challenging continuous control benchmark tasks and extend its applicability to mastering Atari games. Our findings reveal that APO as well as its efficient variation Proximal Absolute Policy Optimization (PAPO) significantly outperforms state-of-the-art policy gradient algorithms, resulting in substantial improvements in worst-case performance, as well as expected performance.
Authors: Shion Takeno, Yu Inatsu, Masayuki Karasuyama, Ichiro Takeuchi
Abstract: Among various acquisition functions (AFs) in Bayesian optimization (BO), Gaussian process upper confidence bound (GP-UCB) and Thompson sampling (TS) are well-known options with established theoretical properties regarding Bayesian cumulative regret (BCR). Recently, it has been shown that a randomized variant of GP-UCB achieves a tighter BCR bound compared with GP-UCB, which we call the tighter BCR bound for brevity. Inspired by this study, this paper first shows that TS achieves the tighter BCR bound. On the other hand, GP-UCB and TS often practically suffer from manual hyperparameter tuning and over-exploration issues, respectively. Therefore, we analyze yet another AF called a probability of improvement from the maximum of a sample path (PIMS). We show that PIMS achieves the tighter BCR bound and avoids the hyperparameter tuning, unlike GP-UCB. Furthermore, we demonstrate a wide range of experiments, focusing on the effectiveness of PIMS that mitigates the practical issues of GP-UCB and TS.
Authors: Pascal Iversen, Simon Witzke, Katharina Baum, Bernhard Y. Renard
Abstract: Explainability and uncertainty quantification are two pillars of trustable artificial intelligence. However, the reasoning behind uncertainty estimates is generally left unexplained. Identifying the drivers of uncertainty complements explanations of point predictions in recognizing model limitations and enhances trust in decisions and their communication. So far, explanations of uncertainties have been rarely studied. The few exceptions rely on Bayesian neural networks or technically intricate approaches, such as auxiliary generative models, thereby hindering their broad adoption. We present a simple approach to explain predictive aleatoric uncertainties. We estimate uncertainty as predictive variance by adapting a neural network with a Gaussian output distribution. Subsequently, we apply out-of-the-box explainers to the model's variance output. This approach can explain uncertainty influences more reliably than literature baselines, which we evaluate in a synthetic setting with a known data-generating process. We further adapt multiple metrics from conventional XAI research to uncertainty explanations. We quantify our findings with a nuanced benchmark analysis that includes real-world datasets. Finally, we apply our approach to an age regression model and discover reasonable sources of uncertainty. Overall, we explain uncertainty estimates with little modifications to the model architecture and demonstrate that our approach competes effectively with more intricate methods.
Authors: David H. Lee, Anishalakshmi V. Palaparthi, Matthew C. Fontaine, Bryon Tjanaka, Stefanos Nikolaidis
Abstract: Diversity optimization seeks to discover a set of solutions that elicit diverse features. Prior work has proposed Novelty Search (NS), which, given a current set of solutions, seeks to expand the set by finding points in areas of low density in the feature space. However, to estimate density, NS relies on a heuristic that considers the k-nearest neighbors of the search point in the feature space, which yields a weaker stability guarantee. We propose Density Descent Search (DDS), an algorithm that explores the feature space via CMA-ES on a continuous density estimate of the feature space that also provides a stronger stability guarantee. We experiment with DDS and two density estimation methods: kernel density estimation (KDE) and continuous normalizing flow (CNF). On several standard diversity optimization benchmarks, DDS outperforms NS, the recently proposed MAP-Annealing algorithm, and other state-of-the-art baselines. Additionally, we prove that DDS with KDE provides stronger stability guarantees than NS, making it more suitable for adaptive optimizers. Furthermore, we prove that NS is a special case of DDS that descends a KDE of the feature space.
Authors: Eloy Reulen, Siamak Mehrkanoon
Abstract: In recent years, data-driven modeling approaches have gained significant attention across various meteorological applications, particularly in weather forecasting. However, these methods often face challenges in handling extreme weather conditions. In response, we present the GA-SmaAt-GNet model, a novel generative adversarial framework for extreme precipitation nowcasting. This model features a unique SmaAt-GNet generator, an extension of the successful SmaAt-UNet architecture, capable of integrating precipitation masks (binarized precipitation maps) to enhance predictive accuracy. Additionally, GA-SmaAt-GNet incorporates an attention-augmented discriminator inspired by the Pix2Pix architecture. This innovative framework paves the way for generative precipitation nowcasting using multiple data sources. We evaluate the performance of SmaAt-GNet and GA-SmaAt-GNet using real-life precipitation data from the Netherlands, revealing notable improvements in overall performance and for extreme precipitation events compared to other models. Specifically, our proposed architecture demonstrates its main performance gain in summer and autumn, when precipitation intensity is typically at its peak. Furthermore, we conduct uncertainty analysis on the GA-SmaAt-GNet model and the precipitation dataset, providing insights into its predictive capabilities. Finally, we employ Grad-CAM to offer visual explanations of our model's predictions, generating activation heatmaps that highlight areas of input activation throughout the network.
Authors: Guangyi Chen, Yifan Shen, Zhenhao Chen, Xiangchen Song, Yuewen Sun, Weiran Yao, Xiao Liu, Kun Zhang
Abstract: Identifying the underlying time-delayed latent causal processes in sequential data is vital for grasping temporal dynamics and making downstream reasoning. While some recent methods can robustly identify these latent causal variables, they rely on strict assumptions about the invertible generation process from latent variables to observed data. However, these assumptions are often hard to satisfy in real-world applications containing information loss. For instance, the visual perception process translates a 3D space into 2D images, or the phenomenon of persistence of vision incorporates historical data into current perceptions. To address this challenge, we establish an identifiability theory that allows for the recovery of independent latent components even when they come from a nonlinear and non-invertible mix. Using this theory as a foundation, we propose a principled approach, CaRiNG, to learn the CAusal RepresentatIon of Non-invertible Generative temporal data with identifiability guarantees. Specifically, we utilize temporal context to recover lost latent information and apply the conditions in our theory to guide the training process. Through experiments conducted on synthetic datasets, we validate that our CaRiNG method reliably identifies the causal process, even when the generation process is non-invertible. Moreover, we demonstrate that our approach considerably improves temporal understanding and reasoning in practical applications.
Authors: Chia-Cheng Chiang, Li-Cheng Lan, Wei-Fang Sun, Chien Feng, Cho-Jui Hsieh, Chun-Yi Lee
Abstract: In this paper, we focus on single-demonstration imitation learning (IL), a practical approach for real-world applications where acquiring multiple expert demonstrations is costly or infeasible and the ground truth reward function is not available. In contrast to typical IL settings with multiple demonstrations, single-demonstration IL involves an agent having access to only one expert trajectory. We highlight the issue of sparse reward signals in this setting and propose to mitigate this issue through our proposed Transition Discriminator-based IL (TDIL) method. TDIL is an IRL method designed to address reward sparsity by introducing a denser surrogate reward function that considers environmental dynamics. This surrogate reward function encourages the agent to navigate towards states that are proximal to expert states. In practice, TDIL trains a transition discriminator to differentiate between valid and non-valid transitions in a given environment to compute the surrogate rewards. The experiments demonstrate that TDIL outperforms existing IL approaches and achieves expert-level performance in the single-demonstration IL setting across five widely adopted MuJoCo benchmarks as well as the "Adroit Door" robotic environment.
Authors: Artur Back de Luca, Kimon Fountoulakis
Abstract: The execution of graph algorithms using neural networks has recently attracted significant interest due to promising empirical progress. This motivates further understanding of how neural networks can replicate reasoning steps with relational data. In this work, we study the ability of transformer networks to simulate algorithms on graphs from a theoretical perspective. The architecture we use is a looped transformer with extra attention heads that interact with the graph. We prove by construction that this architecture can simulate individual algorithms such as Dijkstra's shortest path, Breadth- and Depth-First Search, and Kosaraju's strongly connected components, as well as multiple algorithms simultaneously. The number of parameters in the networks does not increase with the input graph size, which implies that the networks can simulate the above algorithms for any graph. Despite this property, we show a limit to simulation in our solution due to finite precision. Finally, we show a Turing Completeness result with constant width when the extra attention heads are utilized.
Authors: Tin Sum Cheng, Aurelien Lucchi, Anastasis Kratsios, David Belius
Abstract: We derive new bounds for the condition number of kernel matrices, which we then use to enhance existing non-asymptotic test error bounds for kernel ridgeless regression (KRR) in the over-parameterized regime for a fixed input dimension. For kernels with polynomial spectral decay, we recover the bound from previous work; for exponential decay, our bound is non-trivial and novel. Our contribution is two-fold: (i) we rigorously prove the phenomena of tempered overfitting and catastrophic overfitting under the sub-Gaussian design assumption, closing an existing gap in the literature; (ii) we identify that the independence of the features plays an important role in guaranteeing tempered overfitting, raising concerns about approximating KRR generalization using the Gaussian design assumption in previous literature.
Authors: Kwangjun Ahn, Zhiyu Zhang, Yunbum Kook, Yan Dai
Abstract: Despite the success of the Adam optimizer in practice, the theoretical understanding of its algorithmic components still remains limited. In particular, most existing analyses of Adam show the convergence rate that can be simply achieved by non-adative algorithms like SGD. In this work, we provide a different perspective based on online learning that underscores the importance of Adam's algorithmic components. Inspired by Cutkosky et al. (2023), we consider the framework called online learning of updates/increments, where we choose the updates/increments of an optimizer based on an online learner. With this framework, the design of a good optimizer is reduced to the design of a good online learner. Our main observation is that Adam corresponds to a principled online learning framework called Follow-the-Regularized-Leader (FTRL). Building on this observation, we study the benefits of its algorithmic components from the online learning perspective.
Authors: Reyna Abhyankar, Zijian He, Vikranth Srivatsa, Hao Zhang, Yiying Zhang
Abstract: Large language models are increasingly integrated with external environments, tools, and agents like ChatGPT plugins to extend their capability beyond language-centric tasks. However, today's LLM inference systems are designed for standalone LLMs. They treat each external interaction as the end of LLM generation and form a new request when the interaction finishes, causing unnecessary recomputation of already computed contexts, which accounts for 37-40% of total model forwarding time. This paper presents InferCept, the first LLM inference framework targeting augmented LLMs and supporting the efficient interception of LLM generation. InferCept minimizes the GPU resource waste caused by LLM interceptions and dedicates saved memory for serving more requests. InferCept improves the overall serving throughput by 1.6x-2x and completes 2x more requests per second compared to the state-of-the-art LLM inference systems.
Authors: Sangmin Lee, Abbas Mammadov, Jong Chul Ye
Abstract: Current theoretical and empirical research in neural networks suggests that complex datasets require large network architectures for thorough classification, yet the precise nature of this relationship remains unclear. This paper tackles this issue by defining upper and lower bounds for neural network widths, which are informed by the polytope structure of the dataset in question. We also delve into the application of these principles to simplicial complexes and specific manifold shapes, explaining how the requirement for network width varies in accordance with the geometric complexity of the dataset. Moreover, we develop an algorithm to investigate a converse situation where the polytope structure of a dataset can be inferred from its corresponding trained neural networks. Through our algorithm, it is established that popular datasets such as MNIST, Fashion-MNIST, and CIFAR10 can be efficiently encapsulated using no more than two polytopes with a small number of faces.
Authors: Qilong Ma, Haixu Wu, Lanxiang Xing, Shangchen Miao, Mingsheng Long
Abstract: Accurately predicting the future fluid is vital to extensive areas such as meteorology, oceanology, and aerodynamics. However, since the fluid is usually observed from an Eulerian perspective, its moving and intricate dynamics are seriously obscured and confounded in static grids, bringing thorny challenges to the prediction. This paper introduces a new Lagrangian-Eulerian combined paradigm to tackle the tanglesome fluid dynamics. Instead of solely predicting the future based on Eulerian observations, we propose DeepLag to discover hidden Lagrangian dynamics within the fluid by tracking the movements of adaptively sampled key particles. DeepLag utilizes the proposed where the Lagrangian movement of the tracked particles is inferred from Eulerian observations, and their accumulated Lagrangian dynamics information is incorporated into global Eulerian evolving features to guide future prediction respectively. Tracking key particles not only provides a transparent and interpretable clue for fluid dynamics but also makes our model free from modeling complex correlations among massive grids for better efficiency. Experimentally, DeepLag excels in three challenging fluid prediction tasks covering 2D and 3D, simulated and real-world fluids.
Authors: Cheng Zhang, Jianyi Cheng, George A. Constantinides, Yiren Zhao
Abstract: Post-training quantization of Large Language Models (LLMs) is challenging. In this work, we introduce Low-rank Quantization Error Reduction (LQER), which combines quantization and low-rank approximation to recover the model capability. LQER leverages an activation-induced scale matrix to drive the singular value distribution of quantization error towards a desirable distribution, which enables nearly-lossless W4A8 quantization on various LLMs and downstream tasks without the need for knowledge distillation, grid search, or gradient-base iterative optimization. Unlike existing methods, the computation pattern of LQER eliminates the need for specialized Scatter and Gather processes to collect high-precision weights from irregular memory locations. Our W4A8 LLMs achieve near-lossless performance on six popular downstream tasks, while using 1.36$\times$ fewer hardware resources than the leading state-of-the-art method. We open-source our framework at https://github.com/ChengZhang-98/lqer
Authors: Junhong Shen, Neil Tenenholtz, James Brian Hall, David Alvarez-Melis, Nicolo Fusi
Abstract: Large Language Models (LLMs) have demonstrated remarkable proficiency in understanding and generating natural language. However, their capabilities wane in highly specialized domains underrepresented in the pretraining corpus, such as physical and biomedical sciences. This work explores how to repurpose general LLMs into effective task solvers for specialized domains. We introduce a novel, model-agnostic framework for learning custom input tags, which are parameterized as continuous vectors appended to the LLM's embedding layer, to condition the LLM. We design two types of input tags: domain tags are used to delimit specialized representations (e.g., chemical formulas) and provide domain-relevant context; function tags are used to represent specific functions (e.g., predicting molecular properties) and compress function-solving instructions. We develop a three-stage protocol to learn these tags using auxiliary data and domain knowledge. By explicitly disentangling task domains from task functions, our method enables zero-shot generalization to unseen problems through diverse combinations of the input tags. It also boosts LLM's performance in various specialized domains, such as predicting protein or chemical properties and modeling drug-target interactions, outperforming expert models tailored to these tasks.
Authors: Reijo Jaakkola, Tomi Janhunen, Antti Kuusisto, Masood Feyzbakhsh Rankooh, Miikka Vilander
Abstract: We introduce a method for computing immediately human interpretable yet accurate classifiers from tabular data. The classifiers obtained are short Boolean formulas, computed via first discretizing the original data and then using feature selection coupled with a very fast algorithm for producing the best possible Boolean classifier for the setting. We demonstrate the approach via 13 experiments, obtaining results with accuracies comparable to ones obtained via random forests, XGBoost, and existing results for the same datasets in the literature. In most cases, the accuracy of our method is in fact similar to that of the reference methods, even though the main objective of our study is the immediate interpretability of our classifiers. We also prove a new result on the probability that the classifier we obtain from real-life data corresponds to the ideally best classifier with respect to the background distribution the data comes from.
Authors: Ingvar Ziemann, Stephen Tu, George J. Pappas, Nikolai Matni
Abstract: In this work, we study statistical learning with dependent ($\beta$-mixing) data and square loss in a hypothesis class $\mathscr{F}\subset L_{\Psi_p}$ where $\Psi_p$ is the norm $\|f\|_{\Psi_p} \triangleq \sup_{m\geq 1} m^{-1/p} \|f\|_{L^m} $ for some $p\in [2,\infty]$. Our inquiry is motivated by the search for a sharp noise interaction term, or variance proxy, in learning with dependent data. Absent any realizability assumption, typical non-asymptotic results exhibit variance proxies that are deflated multiplicatively by the mixing time of the underlying covariates process. We show that whenever the topologies of $L^2$ and $\Psi_p$ are comparable on our hypothesis class $\mathscr{F}$ -- that is, $\mathscr{F}$ is a weakly sub-Gaussian class: $\|f\|_{\Psi_p} \lesssim \|f\|_{L^2}^\eta$ for some $\eta\in (0,1]$ -- the empirical risk minimizer achieves a rate that only depends on the complexity of the class and second order statistics in its leading term. Our result holds whether the problem is realizable or not and we refer to this as a \emph{near mixing-free rate}, since direct dependence on mixing is relegated to an additive higher order term. We arrive at our result by combining the above notion of a weakly sub-Gaussian class with mixed tail generic chaining. This combination allows us to compute sharp, instance-optimal rates for a wide range of problems. Examples that satisfy our framework include sub-Gaussian linear regression, more general smoothly parameterized function classes, finite hypothesis classes, and bounded smoothness classes.
Authors: Sean Jaffe, Alexander Davydov, Deniz Lapsekili, Ambuj Singh, Francesco Bullo
Abstract: Global stability and robustness guarantees in learned dynamical systems are essential to ensure well-behavedness of the systems in the face of uncertainty. We present Extended Linearized Contracting Dynamics (ELCD), the first neural network-based dynamical system with global contractivity guarantees in arbitrary metrics. The key feature of ELCD is a parametrization of the extended linearization of the nonlinear vector field. In its most basic form, ELCD is guaranteed to be (i) globally exponentially stable, (ii) equilibrium contracting, and (iii) globally contracting with respect to some metric. To allow for contraction with respect to more general metrics in the data space, we train diffeomorphisms between the data space and a latent space and enforce contractivity in the latent space, which ensures global contractivity in the data space. We demonstrate the performance of ELCD on the high dimensional LASA, multi-link pendulum, and Rosenbrock datasets.
Authors: Theodore Papamarkou, Tolga Birdal, Michael Bronstein, Gunnar Carlsson, Justin Curry, Yue Gao, Mustafa Hajij, Roland Kwitt, Pietro Li\`o, Paolo Di Lorenzo, Vasileios Maroulas, Nina Miolane, Farzana Nasrin, Karthikeyan Natesan Ramamurthy, Bastian Rieck, Simone Scardapane, Michael T. Schaub, Petar Veli\v{c}kovi\'c, Bei Wang, Yusu Wang, Guo-Wei Wei, Ghada Zamzmi
Abstract: Topological deep learning (TDL) is a rapidly evolving field that uses topological features to understand and design deep learning models. This paper posits that TDL is the new frontier for relational learning. TDL may complement graph representation learning and geometric deep learning by incorporating topological concepts, and can thus provide a natural choice for various machine learning settings. To this end, this paper discusses open problems in TDL, ranging from practical benefits to theoretical foundations. For each problem, it outlines potential solutions and future research opportunities. At the same time, this paper serves as an invitation to the scientific community to actively participate in TDL research to unlock the potential of this emerging field.
Authors: Jie Cheng, Gang Xiong, Xingyuan Dai, Qinghai Miao, Yisheng Lv, Fei-Yue Wang
Abstract: Preference-based Reinforcement Learning (PbRL) circumvents the need for reward engineering by harnessing human preferences as the reward signal. However, current PbRL methods excessively depend on high-quality feedback from domain experts, which results in a lack of robustness. In this paper, we present RIME, a robust PbRL algorithm for effective reward learning from noisy preferences. Our method utilizes a sample selection-based discriminator to dynamically filter out noise and ensure robust training. To counteract the cumulative error stemming from incorrect selection, we suggest a warm start for the reward model, which additionally bridges the performance gap during the transition from pre-training to online training in PbRL. Our experiments on robotic manipulation and locomotion tasks demonstrate that RIME significantly enhances the robustness of the state-of-the-art PbRL method. Code is available at https://github.com/CJReinforce/RIME_ICML2024.
Authors: Shanghua Gao, Teddy Koker, Owen Queen, Thomas Hartvigsen, Theodoros Tsiligkaridis, Marinka Zitnik
Abstract: Advances in time series models are driving a shift from conventional deep learning methods to pre-trained foundational models. While pre-trained transformers and reprogrammed text-based LLMs report state-of-the-art results, the best-performing architectures vary significantly across tasks, and models often have limited scope, such as focusing only on time series forecasting. Models that unify predictive and generative time series tasks under a single framework remain challenging to achieve. We introduce UniTS, a multi-task time series model that uses task tokenization to express predictive and generative tasks within a single model. UniTS leverages a modified transformer block designed to obtain universal time series representations. This design induces transferability from a heterogeneous, multi-domain pre-training dataset-often with diverse dynamic patterns, sampling rates, and temporal scales-to many downstream datasets, which can also be diverse in task specifications and data domains. Across 38 datasets spanning human activity sensors, healthcare, engineering, and finance domains, UniTS model performs favorably against 12 forecasting models, 20 classification models, 18 anomaly detection models, and 16 imputation models, including repurposed text-based LLMs. UniTS demonstrates effective few-shot and prompt learning capabilities when evaluated on new data domains and tasks. In the conventional single-task setting, UniTS outperforms strong task-specialized time series models. The source code and datasets are available at https://github.com/mims-harvard/UniTS.
Authors: Quan Nguyen, Nishant A. Mehta
Abstract: We derive near-optimal per-action regret bounds for sleeping bandits, in which both the sets of available arms and their losses in every round are chosen by an adversary. In a setting with $K$ total arms and at most $A$ available arms in each round over $T$ rounds, the best known upper bound is $O(K\sqrt{TA\ln{K}})$, obtained indirectly via minimizing internal sleeping regrets. Compared to the minimax $\Omega(\sqrt{TA})$ lower bound, this upper bound contains an extra multiplicative factor of $K\ln{K}$. We address this gap by directly minimizing the per-action regret using generalized versions of EXP3, EXP3-IX and FTRL with Tsallis entropy, thereby obtaining near-optimal bounds of order $O(\sqrt{TA\ln{K}})$ and $O(\sqrt{T\sqrt{AK}})$. We extend our results to the setting of bandits with advice from sleeping experts, generalizing EXP4 along the way. This leads to new proofs for a number of existing adaptive and tracking regret bounds for standard non-sleeping bandits. Extending our results to the bandit version of experts that report their confidences leads to new bounds for the confidence regret that depends primarily on the sum of experts' confidences. We prove a lower bound, showing that for any minimax optimal algorithms, there exists an action whose regret is sublinear in $T$ but linear in the number of its active rounds.
Authors: Mehran Hosseini, Peyman Hosseini
Abstract: Scaled Dot Product Attention (SDPA) is the backbone of many modern deep-learning models. It is so versatile that it has been used in natural language, vision, and multi-modal domains with very little change compared to its original formulation. This paper discusses why the current formulation is inefficient by delving into the mathematical details of the attention mechanism. We propose three improvements to mitigate these inefficiencies, thereby, introducing three enhanced attention mechanisms: Optimised, Efficient, and Super Attention. Optimised and Efficient Attention have one and two matrix multiplications fewer per head, respectively, and 25% and 50% fewer parameters, respectively, than standard SDPA, but perform similarly to standard SDPA in both vision and natural language tasks. They can be used in all applications where SDPA is used while offering smaller model sizes and faster training and inference without noticeable loss in performance. Super Attention introduces a new linear transformation on the values, transforming them from the left. It outperforms standard SPDA on vision and natural language tasks by up to 17% while having one fewer matrix multiplication per head and 25% fewer parameters than standard SDPA. Consequently, it is also faster than standard SDPA. Super Attention is ideal in applications where the attention layer's context length is fixed, such as Vision Transformers. In addition to providing mathematical reasoning, we evaluate the presented attention mechanisms on several datasets including MNIST, CIFAR100, ImageNet, IMDB Movie Reviews, and Amazon Reviews datasets, as well as combined Europarl and Anki English-Spanish datasets for neural machine translation.
Authors: Suhan Cui, Prasenjit Mitra
Abstract: In the realm of big data and digital healthcare, Electronic Health Records (EHR) have become a rich source of information with the potential to improve patient care and medical research. In recent years, machine learning models have proliferated for analyzing EHR data to predict patients future health conditions. Among them, some studies advocate for multi-task learning (MTL) to jointly predict multiple target diseases for improving the prediction performance over single task learning. Nevertheless, current MTL frameworks for EHR data have significant limitations due to their heavy reliance on human experts to identify task groups for joint training and design model architectures. To reduce human intervention and improve the framework design, we propose an automated approach named AutoDP, which can search for the optimal configuration of task grouping and architectures simultaneously. To tackle the vast joint search space encompassing task combinations and architectures, we employ surrogate model-based optimization, enabling us to efficiently discover the optimal solution. Experimental results on real-world EHR data demonstrate the efficacy of the proposed AutoDP framework. It achieves significant performance improvements over both hand-crafted and automated state-of-the-art methods, also maintains a feasible search cost at the same time.
Authors: Thomas M. Sutter, Yang Meng, Andrea Agostini, Daphn\'e Chopard, Norbert Fortin, Julia E. Vogt, Bahbak Shahbaba, Stephan Mandt
Abstract: Variational Autoencoders for multimodal data hold promise for many tasks in data analysis, such as representation learning, conditional generation, and imputation. Current architectures either share the encoder output, decoder input, or both across modalities to learn a shared representation. Such architectures impose hard constraints on the model. In this work, we show that a better latent representation can be obtained by replacing these hard constraints with a soft constraint. We propose a new mixture-of-experts prior, softly guiding each modality's latent representation towards a shared aggregate posterior. This approach results in a superior latent representation and allows each encoding to preserve information better from its uncompressed original features. In extensive experiments on multiple benchmark datasets and two challenging real-world datasets, we show improved learned latent representations and imputation of missing data modalities compared to existing methods.
Authors: Yunpeng Qing, Shunyu liu, Jingyuan Cong, Kaixuan Chen, Yihe Zhou, Mingli Song
Abstract: Offline reinforcement learning endeavors to leverage offline datasets to craft effective agent policy without online interaction, which imposes proper conservative constraints with the support of behavior policies to tackle the out-of-distribution problem. However, existing works often suffer from the constraint conflict issue when offline datasets are collected from multiple behavior policies, i.e., different behavior policies may exhibit inconsistent actions with distinct returns across the state space. To remedy this issue, recent advantage-weighted methods prioritize samples with high advantage values for agent training while inevitably ignoring the diversity of behavior policy. In this paper, we introduce a novel Advantage-Aware Policy Optimization (A2PO) method to explicitly construct advantage-aware policy constraints for offline learning under mixed-quality datasets. Specifically, A2PO employs a conditional variational auto-encoder to disentangle the action distributions of intertwined behavior policies by modeling the advantage values of all training data as conditional variables. Then the agent can follow such disentangled action distribution constraints to optimize the advantage-aware policy towards high advantage values. Extensive experiments conducted on both the single-quality and mixed-quality datasets of the D4RL benchmark demonstrate that A2PO yields results superior to the counterparts. Our code will be made publicly available.
Authors: Zijian Liu, Zhengyuan Zhou
Abstract: Shuffling gradient methods are widely implemented in practice, particularly including three popular algorithms: Random Reshuffle (RR), Shuffle Once (SO), and Incremental Gradient (IG). Compared to the empirical success, the theoretical guarantee of shuffling gradient methods was not well-understood for a long time. Until recently, the convergence rates had just been established for the average iterate for convex functions and the last iterate for strongly convex problems (using squared distance as the metric). However, when using the function value gap as the convergence criterion, existing theories cannot interpret the good performance of the last iterate in different settings (e.g., constrained optimization). To bridge this gap between practice and theory, we prove the first last-iterate convergence rates for shuffling gradient methods with respect to the objective value even without strong convexity. Our new results either (nearly) match the existing last-iterate lower bounds or are as fast as the previous best upper bounds for the average iterate.
Authors: Michael Sun, Minghao Guo, Weize Yuan, Veronika Thost, Crystal Elaine Owens, Aristotle Franklin Grosz, Sharvaa Selvan, Katelyn Zhou, Hassan Mohiuddin, Benjamin J Pedretti, Zachary P Smith, Jie Chen, Wojciech Matusik
Abstract: Recent research in molecular discovery has primarily been devoted to small, drug-like molecules, leaving many similarly important applications in material design without adequate technology. These applications often rely on more complex molecular structures with fewer examples that are carefully designed using known substructures. We propose a data-efficient and interpretable model for representing and reasoning over such molecules in terms of graph grammars that explicitly describe the hierarchical design space featuring motifs to be the design basis. We present a novel representation in the form of random walks over the design space, which facilitates both molecule generation and property prediction. We demonstrate clear advantages over existing methods in terms of performance, efficiency, and synthesizability of predicted molecules, and we provide detailed insights into the method's chemical interpretability.
Authors: Mubashara Akhtar, Omar Benjelloun, Costanza Conforti, Pieter Gijsbers, Joan Giner-Miguelez, Nitisha Jain, Michael Kuchnik, Quentin Lhoest, Pierre Marcenac, Manil Maskey, Peter Mattson, Luis Oala, Pierre Ruyssen, Rajat Shinde, Elena Simperl, Goeffry Thomas, Slava Tykhonov, Joaquin Vanschoren, Jos van der Velde, Steffen Vogler, Carole-Jean Wu
Abstract: Data is a critical resource for Machine Learning (ML), yet working with data remains a key friction point. This paper introduces Croissant, a metadata format for datasets that simplifies how data is used by ML tools and frameworks. Croissant makes datasets more discoverable, portable and interoperable, thereby addressing significant challenges in ML data management and responsible AI. Croissant is already supported by several popular dataset repositories, spanning hundreds of thousands of datasets, ready to be loaded into the most popular ML frameworks.
Authors: Aarush Sinha
Abstract: In this study, we propose a multi branched network approach to predict the dynamics of a physics attractor characterized by intricate and chaotic behavior. We introduce a unique neural network architecture comprised of Radial Basis Function (RBF) layers combined with an attention mechanism designed to effectively capture nonlinear inter-dependencies inherent in the attractor's temporal evolution. Our results demonstrate successful prediction of the attractor's trajectory across 100 predictions made using a real-world dataset of 36,700 time-series observations encompassing approximately 28 minutes of activity. To further illustrate the performance of our proposed technique, we provide comprehensive visualizations depicting the attractor's original and predicted behaviors alongside quantitative measures comparing observed versus estimated outcomes. Overall, this work showcases the potential of advanced machine learning algorithms in elucidating hidden structures in complex physical systems while offering practical applications in various domains requiring accurate short-term forecasting capabilities.
Authors: Anurag Singh, Siu Lun Chau, Shahine Bouabid, Krikamol Muandet
Abstract: Out-of-distribution (OOD) generalisation is challenging because it involves not only learning from empirical data, but also deciding among various notions of generalisation, e.g., optimising the average-case risk, worst-case risk, or interpolations thereof. While this choice should in principle be made by the model operator like medical doctors, this information might not always be available at training time. The institutional separation between machine learners and model operators leads to arbitrary commitments to specific generalisation strategies by machine learners due to these deployment uncertainties. We introduce the Imprecise Domain Generalisation framework to mitigate this, featuring an imprecise risk optimisation that allows learners to stay imprecise by optimising against a continuous spectrum of generalisation strategies during training, and a model framework that allows operators to specify their generalisation preference at deployment. Supported by both theoretical and empirical evidence, our work showcases the benefits of integrating imprecision into domain generalisation.
Authors: Jaesung Choi, Pilwon Kim
Abstract: Removing noise from a signal without knowing the characteristics of the noise is a challenging task. This paper introduces a signal-noise separation method based on time series prediction. We use Reservoir Computing (RC) to extract the maximum portion of "predictable information" from a given signal. Reproducing the deterministic component of the signal using RC, we estimate the noise distribution from the difference between the original signal and reconstructed one. The method is based on a machine learning approach and requires no prior knowledge of either the deterministic signal or the noise distribution. It provides a way to identify additivity/multiplicativity of noise and to estimate the signal-to-noise ratio (SNR) indirectly. The method works successfully for combinations of various signal and noise, including chaotic signal and highly oscillating sinusoidal signal which are corrupted by non-Gaussian additive/ multiplicative noise. The separation performances are robust and notably outstanding for signals with strong noise, even for those with negative SNR.
Authors: Artur Grigorev, Adriana-Simona Mihaita Khaled Saleh, Yuming Ou
Abstract: Traffic congestion due to road incidents poses a significant challenge in urban environments, leading to increased pollution, economic losses, and traffic congestion. Efficiently managing these incidents is imperative for mitigating their adverse effects; however, the complexity of urban traffic systems and the variety of potential incidents represent a considerable obstacle. This paper introduces IncidentResponseGPT, an innovative solution designed to assist traffic management authorities by providing rapid, informed, and adaptable traffic incident response plans. By integrating a Generative AI platform with real-time traffic incident reports and operational guidelines, our system aims to streamline the decision-making process in responding to traffic incidents. The research addresses the critical challenges involved in deploying AI in traffic management, including overcoming the complexity of urban traffic networks, ensuring real-time decision-making capabilities, aligning with local laws and regulations, and securing public acceptance for AI-driven systems. Through a combination of text analysis of accident reports, validation of AI recommendations through traffic simulation, and implementation of transparent and validated AI systems, IncidentResponseGPT offers a promising approach to optimizing traffic flow and reducing congestion in the face of traffic incidents. The relevance of this work extends to traffic management authorities, emergency response teams, and municipal bodies, all integral stakeholders in urban traffic control and incident management. By proposing a novel solution to the identified challenges, this research aims to develop a framework that not only facilitates faster resolution of traffic incidents but also minimizes their overall impact on urban traffic systems.
Authors: Alessandro Montenegro, Marco Mussi, Alberto Maria Metelli, Matteo Papini
Abstract: Policy gradient (PG) methods are successful approaches to deal with continuous reinforcement learning (RL) problems. They learn stochastic parametric (hyper)policies by either exploring in the space of actions or in the space of parameters. Stochastic controllers, however, are often undesirable from a practical perspective because of their lack of robustness, safety, and traceability. In common practice, stochastic (hyper)policies are learned only to deploy their deterministic version. In this paper, we make a step towards the theoretical understanding of this practice. After introducing a novel framework for modeling this scenario, we study the global convergence to the best deterministic policy, under (weak) gradient domination assumptions. Then, we illustrate how to tune the exploration level used for learning to optimize the trade-off between the sample complexity and the performance of the deployed deterministic policy. Finally, we quantitatively compare action-based and parameter-based exploration, giving a formal guise to intuitive results.
Authors: Kevin Lange, Federico Fontana, Francesco Rossi, Mattia Varile, Giovanni Apruzzese
Abstract: Modern spacecraft are increasingly relying on machine learning (ML). However, physical equipment in space is subject to various natural hazards, such as radiation, which may inhibit the correct operation of computing devices. Despite plenty of evidence showing the damage that naturally-induced faults can cause to ML-related hardware, we observe that the effects of radiation on ML models for space applications are not well-studied. This is a problem: without understanding how ML models are affected by these natural phenomena, it is uncertain "where to start from" to develop radiation-tolerant ML software. As ML researchers, we attempt to tackle this dilemma. By partnering up with space-industry practitioners specialized in ML, we perform a reflective analysis of the state of the art. We provide factual evidence that prior work did not thoroughly examine the impact of natural hazards on ML models meant for spacecraft. Then, through a "negative result", we show that some existing open-source technologies can hardly be used by researchers to study the effects of radiation for some applications of ML in satellites. As a constructive step forward, we perform simple experiments showcasing how to leverage current frameworks to assess the robustness of practical ML models for cloud detection against radiation-induced faults. Our evaluation reveals that not all faults are as devastating as claimed by some prior work. By publicly releasing our resources, we provide a foothold -- usable by researchers without access to spacecraft -- for spearheading development of space-tolerant ML models.
Authors: Alan A. Lahoud, Erik Schaffernicht, Johannes A. Stork
Abstract: Learning latent costs of transitions on graphs from trajectories demonstrations under various contextual features is challenging but useful for path planning. Yet, existing methods either oversimplify cost assumptions or scale poorly with the number of observed trajectories. This paper introduces DataSP, a differentiable all-to-all shortest path algorithm to facilitate learning latent costs from trajectories. It allows to learn from a large number of trajectories in each learning step without additional computation. Complex latent cost functions from contextual features can be represented in the algorithm through a neural network approximation. We further propose a method to sample paths from DataSP in order to reconstruct/mimic observed paths' distributions. We prove that the inferred distribution follows the maximum entropy principle. We show that DataSP outperforms state-of-the-art differentiable combinatorial solver and classical machine learning approaches in predicting paths on graphs.
Authors: Ruixiang Sun, Hongyu Zang, Xin Li, Riashat Islam
Abstract: Visual Model-Based Reinforcement Learning (MBRL) promises to encapsulate agent's knowledge about the underlying dynamics of the environment, enabling learning a world model as a useful planner. However, top MBRL agents such as Dreamer often struggle with visual pixel-based inputs in the presence of exogenous or irrelevant noise in the observation space, due to failure to capture task-specific features while filtering out irrelevant spatio-temporal details. To tackle this problem, we apply a spatio-temporal masking strategy, a bisimulation principle, combined with latent reconstruction, to capture endogenous task-specific aspects of the environment for world models, effectively eliminating non-essential information. Joint training of representations, dynamics, and policy often leads to instabilities. To further address this issue, we develop a Hybrid Recurrent State-Space Model (HRSSM) structure, enhancing state representation robustness for effective policy learning. Our empirical evaluation demonstrates significant performance improvements over existing methods in a range of visually complex control tasks such as Maniskill \cite{gu2023maniskill2} with exogenous distractors from the Matterport environment. Our code is avaliable at https://github.com/bit1029public/HRSSM.
Authors: Federico Moiraghi, Matteo Palmonari, Davide Allavena, Federico Morando
Abstract: Classifying public tenders is a useful task for both companies that are invited to participate and for inspecting fraudulent activities. To facilitate the task for both participants and public administrations, the European Union presented a common taxonomy (Common Procurement Vocabulary, CPV) which is mandatory for tenders of certain importance; however, the contracts in which a CPV label is mandatory are the minority compared to all the Public Administrations activities. Classifying over a real-world taxonomy introduces some difficulties that can not be ignored. First of all, some fine-grained classes have an insufficient (if any) number of observations in the training set, while other classes are far more frequent (even thousands of times) than the average. To overcome those difficulties, we present a zero-shot approach, based on a pre-trained language model that relies only on label description and respects the label taxonomy. To train our proposed model, we used industrial data, which comes from contrattipubblici.org, a service by SpazioDati s.r.l. that collects public contracts stipulated in Italy in the last 25 years. Results show that the proposed model achieves better performance in classifying low-frequent classes compared to three different baselines, and is also able to predict never-seen classes.
Authors: Vladimir Malinovskii, Denis Mazur, Ivan Ilin, Denis Kuznedelev, Konstantin Burlachenko, Kai Yi, Dan Alistarh, Peter Richtarik
Abstract: There has been significant interest in "extreme" compression of large language models (LLMs), i.e., to 1-2 bits per parameter, which allows such models to be executed efficiently on resource-constrained devices. Existing work focused on improved one-shot quantization techniques and weight representations; yet, purely post-training approaches are reaching diminishing returns in terms of the accuracy-vs-bit-width trade-off. State-of-the-art quantization methods such as QuIP# and AQLM include fine-tuning (part of) the compressed parameters over a limited amount of calibration data; however, such fine-tuning techniques over compressed weights often make exclusive use of straight-through estimators (STE), whose performance is not well-understood in this setting. In this work, we question the use of STE for extreme LLM compression, showing that it can be sub-optimal, and perform a systematic study of quantization-aware fine-tuning strategies for LLMs. We propose PV-Tuning - a representation-agnostic framework that generalizes and improves upon existing fine-tuning strategies, and provides convergence guarantees in restricted cases. On the practical side, when used for 1-2 bit vector quantization, PV-Tuning outperforms prior techniques for highly-performant models such as Llama and Mistral. Using PV-Tuning, we achieve the first Pareto-optimal quantization for Llama 2 family models at 2 bits per parameter.
Authors: Yao Lai, Sungyoung Lee, Guojin Chen, Souradip Poddar, Mengkang Hu, David Z. Pan, Ping Luo
Abstract: Analog circuit design is a significant task in modern chip technology, focusing on the selection of component types, connectivity, and parameters to ensure proper circuit functionality. Despite advances made by Large Language Models (LLMs) in digital circuit design, the complexity and scarcity of data in analog circuitry pose significant challenges. To mitigate these issues, we introduce AnalogCoder, the first training-free LLM agent for designing analog circuits through Python code generation. Firstly, AnalogCoder incorporates a feedback-enhanced flow with tailored domain-specific prompts, enabling the automated and self-correcting design of analog circuits with a high success rate. Secondly, it proposes a circuit tool library to archive successful designs as reusable modular sub-circuits, simplifying composite circuit creation. Thirdly, extensive experiments on a benchmark designed to cover a wide range of analog circuit tasks show that AnalogCoder outperforms other LLM-based methods. It has successfully designed 20 circuits, 5 more than standard GPT-4o. We believe AnalogCoder can significantly improve the labor-intensive chip design process, enabling non-experts to design analog circuits efficiently.
Authors: Cong Lu, Shengran Hu, Jeff Clune
Abstract: Go-Explore is a powerful family of algorithms designed to solve hard-exploration problems, built on the principle of archiving discovered states, and iteratively returning to and exploring from the most promising states. This approach has led to superhuman performance across a wide variety of challenging problems including Atari games and robotic control, but requires manually designing heuristics to guide exploration, which is time-consuming and infeasible in general. To resolve this, we propose Intelligent Go-Explore (IGE) which greatly extends the scope of the original Go-Explore by replacing these heuristics with the intelligence and internalized human notions of interestingness captured by giant foundation models (FMs). This provides IGE with a human-like ability to instinctively identify how interesting or promising any new state is (e.g. discovering new objects, locations, or behaviors), even in complex environments where heuristics are hard to define. Moreover, IGE offers the exciting and previously impossible opportunity to recognize and capitalize on serendipitous discoveries that cannot be predicted ahead of time. We evaluate IGE on a range of language-based tasks that require search and exploration. In Game of 24, a multistep mathematical reasoning problem, IGE reaches 100% success rate 70.8% faster than the best classic graph search baseline. Next, in BabyAI-Text, a challenging partially observable gridworld, IGE exceeds the previous SOTA with orders of magnitude fewer online samples. Finally, in TextWorld, we show the unique ability of IGE to succeed in settings requiring long-horizon exploration where prior SOTA FM agents like Reflexion completely fail. Overall, IGE combines the tremendous strengths of FMs and the powerful Go-Explore algorithm, opening up a new frontier of research into creating more generally capable agents with impressive exploration capabilities.
Authors: Zhibo Wang, Peng Kuang, Zhixuan Chu, Jingyi Wang, Kui Ren
Abstract: Spurious correlations in training data significantly hinder the generalization capability of machine learning models when faced with distribution shifts in real-world scenarios. To tackle the problem, numerous debias approaches have been proposed and benchmarked on datasets intentionally designed with severe biases. However, it remains to be asked: \textit{1. Do existing benchmarks really capture biases in the real world? 2. Can existing debias methods handle biases in the real world?} To answer the questions, we revisit biased distributions in existing benchmarks and real-world datasets, and propose a fine-grained framework for analyzing dataset bias by disentangling it into the magnitude and prevalence of bias. We observe and theoretically demonstrate that existing benchmarks poorly represent real-world biases. We further introduce two novel biased distributions to bridge this gap, forming a nuanced evaluation framework for real-world debiasing. Building upon these results, we evaluate existing debias methods with our evaluation framework. Results show that existing methods are incapable of handling real-world biases. Through in-depth analysis, we propose a simple yet effective approach that can be easily applied to existing debias methods, named Debias in Destruction (DiD). Empirical results demonstrate the superiority of DiD, improving the performance of existing methods on all types of biases within the proposed evaluation framework.
Authors: Wenfei Liang, Yanan Zhao, Rui She, Yiming Li, Wee Peng Tay
Abstract: Personalized subgraph Federated Learning (FL) is a task that customizes Graph Neural Networks (GNNs) to individual client needs, accommodating diverse data distributions. However, applying hypernetworks in FL, while aiming to facilitate model personalization, often encounters challenges due to inadequate representation of client-specific characteristics. To overcome these limitations, we propose a model called FedSheafHN, using enhanced collaboration graph embedding and efficient personalized model parameter generation. Specifically, our model embeds each client's local subgraph into a server-constructed collaboration graph. We utilize sheaf diffusion in the collaboration graph to learn client representations. Our model improves the integration and interpretation of complex client characteristics. Furthermore, our model ensures the generation of personalized models through advanced hypernetworks optimized for parallel operations across clients. Empirical evaluations demonstrate that FedSheafHN outperforms existing methods in most scenarios, in terms of client model performance on various graph-structured datasets. It also has fast model convergence and effective new clients generalization.
Authors: Mohammed Nowaz Rabbani Chowdhury, Meng Wang, Kaoutar El Maghraoui, Naigang Wang, Pin-Yu Chen, Christopher Carothers
Abstract: The sparsely gated mixture of experts (MoE) architecture sends different inputs to different subnetworks, i.e., experts, through trainable routers. MoE reduces the training computation significantly for large models, but its deployment can be still memory or computation expensive for some downstream tasks. Model pruning is a popular approach to reduce inference computation, but its application in MoE architecture is largely unexplored. To the best of our knowledge, this paper provides the first provably efficient technique for pruning experts in finetuned MoE models. We theoretically prove that prioritizing the pruning of the experts with a smaller change of the routers l2 norm from the pretrained model guarantees the preservation of test accuracy, while significantly reducing the model size and the computational requirements. Although our theoretical analysis is centered on binary classification tasks on simplified MoE architecture, our expert pruning method is verified on large vision MoE models such as VMoE and E3MoE finetuned on benchmark datasets such as CIFAR10, CIFAR100, and ImageNet.
Authors: Chenhao Lu, Ruizhe Shi, Yuyao Liu, Kaizhe Hu, Simon S. Du, Huazhe Xu
Abstract: Sequential decision-making algorithms such as reinforcement learning (RL) in real-world scenarios inevitably face environments with partial observability. This paper scrutinizes the effectiveness of a popular architecture, namely Transformers, in Partially Observable Markov Decision Processes (POMDPs) and reveals its theoretical limitations. We establish that regular languages, which Transformers struggle to model, are reducible to POMDPs. This poses a significant challenge for Transformers in learning POMDP-specific inductive biases, due to their lack of inherent recurrence found in other models like RNNs. This paper casts doubt on the prevalent belief in Transformers as sequence models for RL and proposes to introduce a point-wise recurrent structure. The Deep Linear Recurrent Unit (LRU) emerges as a well-suited alternative for Partially Observable RL, with empirical results highlighting the sub-optimal performance of the Transformer and considerable strength of LRU.
Authors: Sheng Yue, Jiani Liu, Xingyuan Hua, Ju Ren, Sen Lin, Junshan Zhang, Yaoxue Zhang
Abstract: Offline Imitation Learning (IL) with imperfect demonstrations has garnered increasing attention owing to the scarcity of expert data in many real-world domains. A fundamental problem in this scenario is how to extract positive behaviors from noisy data. In general, current approaches to the problem select data building on state-action similarity to given expert demonstrations, neglecting precious information in (potentially abundant) $\textit{diverse}$ state-actions that deviate from expert ones. In this paper, we introduce a simple yet effective data selection method that identifies positive behaviors based on their resultant states -- a more informative criterion enabling explicit utilization of dynamics information and effective extraction of both expert and beneficial diverse behaviors. Further, we devise a lightweight behavior cloning algorithm capable of leveraging the expert and selected data correctly. In the experiments, we evaluate our method on a suite of complex and high-dimensional offline IL benchmarks, including continuous-control and vision-based tasks. The results demonstrate that our method achieves state-of-the-art performance, outperforming existing methods on $\textbf{20/21}$ benchmarks, typically by $\textbf{2-5x}$, while maintaining a comparable runtime to Behavior Cloning ($\texttt{BC}$).
Authors: Sheng Yue, Xingyuan Hua, Ju Ren, Sen Lin, Junshan Zhang, Yaoxue Zhang
Abstract: In this paper, we study offline-to-online Imitation Learning (IL) that pretrains an imitation policy from static demonstration data, followed by fast finetuning with minimal environmental interaction. We find the na\"ive combination of existing offline IL and online IL methods tends to behave poorly in this context, because the initial discriminator (often used in online IL) operates randomly and discordantly against the policy initialization, leading to misguided policy optimization and $\textit{unlearning}$ of pretraining knowledge. To overcome this challenge, we propose a principled offline-to-online IL method, named $\texttt{OLLIE}$, that simultaneously learns a near-expert policy initialization along with an $\textit{aligned discriminator initialization}$, which can be seamlessly integrated into online IL, achieving smooth and fast finetuning. Empirically, $\texttt{OLLIE}$ consistently and significantly outperforms the baseline methods in $\textbf{20}$ challenging tasks, from continuous control to vision-based domains, in terms of performance, demonstration efficiency, and convergence speed. This work may serve as a foundation for further exploration of pretraining and finetuning in the context of IL.
Authors: Khuong Vo
Abstract: A deep latent variable model is a powerful method for capturing complex distributions. These models assume that underlying structures, but unobserved, are present within the data. In this dissertation, we explore high-dimensional problems related to physiological monitoring using latent variable models. First, we present a novel deep state-space model to generate electrical waveforms of the heart using optically obtained signals as inputs. This can bring about clinical diagnoses of heart disease via simple assessment through wearable devices. Second, we present a brain signal modeling scheme that combines the strengths of probabilistic graphical models and deep adversarial learning. The structured representations can provide interpretability and encode inductive biases to reduce the data complexity of neural oscillations. The efficacy of the learned representations is further studied in epilepsy seizure detection formulated as an unsupervised learning problem. Third, we propose a framework for the joint modeling of physiological measures and behavior. Existing methods to combine multiple sources of brain data provided are limited. Direct analysis of the relationship between different types of physiological measures usually does not involve behavioral data. Our method can identify the unique and shared contributions of brain regions to behavior and can be used to discover new functions of brain regions. The success of these innovative computational methods would allow the translation of biomarker findings across species and provide insight into neurocognitive analysis in numerous biological studies and clinical diagnoses, as well as emerging consumer applications.
Authors: Ho Long Fung, Victor-Alexandru Darvariu, Stephen Hailes, Mirco Musolesi
Abstract: An often neglected issue in multi-agent reinforcement learning (MARL) is the potential presence of unreliable agents in the environment whose deviations from expected behavior can prevent a system from accomplishing its intended tasks. In particular, consensus is a fundamental underpinning problem of cooperative distributed multi-agent systems. Consensus requires different agents, situated in a decentralized communication network, to reach an agreement out of a set of initial proposals that they put forward. Learning-based agents should adopt a protocol that allows them to reach consensus despite having one or more unreliable agents in the system. This paper investigates the problem of unreliable agents in MARL, considering consensus as a case study. Echoing established results in the distributed systems literature, our experiments show that even a moderate fraction of such agents can greatly impact the ability of reaching consensus in a networked environment. We propose Reinforcement Learning-based Trusted Consensus (RLTC), a decentralized trust mechanism, in which agents can independently decide which neighbors to communicate with. We empirically demonstrate that our trust mechanism is able to handle unreliable agents effectively, as evidenced by higher consensus success rates.
Authors: Jared Town, Zachary Morrison, Rushikesh Kamalapurkar
Abstract: A key challenge in solving the deterministic inverse reinforcement learning (IRL) problem online and in real-time is the existence of multiple solutions. Nonuniqueness necessitates the study of the notion of equivalent solutions, i.e., solutions that result in a different cost functional but same feedback matrix, and convergence to such solutions. While offline algorithms that result in convergence to equivalent solutions have been developed in the literature, online, real-time techniques that address nonuniqueness are not available. In this paper, a regularized history stack observer that converges to approximately equivalent solutions of the IRL problem is developed. Novel data-richness conditions are developed to facilitate the analysis and simulation results are provided to demonstrate the effectiveness of the developed technique.
Authors: Joe Stacey, Marek Rei
Abstract: Knowledge distillation optimises a smaller student model to behave similarly to a larger teacher model, retaining some of the performance benefits. While this method can improve results on in-distribution examples, it does not necessarily generalise to out-of-distribution (OOD) settings. We investigate two complementary methods for improving the robustness of the resulting student models on OOD domains. The first approach augments the distillation with generated unlabelled examples that match the target distribution. The second method upsamples data points among the training set that are similar to the target distribution. When applied on the task of natural language inference (NLI), our experiments on MNLI show that distillation with these modifications outperforms previous robustness solutions. We also find that these methods improve performance on OOD domains even beyond the target domain.
Authors: Anima Singh, Trung Vu, Nikhil Mehta, Raghunandan Keshavan, Maheswaran Sathiamoorthy, Yilin Zheng, Lichan Hong, Lukasz Heldt, Li Wei, Devansh Tandon, Ed H. Chi, Xinyang Yi
Abstract: Randomly-hashed item ids are used ubiquitously in recommendation models. However, the learned representations from random hashing prevents generalization across similar items, causing problems of learning unseen and long-tail items, especially when item corpus is large, power-law distributed, and evolving dynamically. In this paper, we propose using content-derived features as a replacement for random ids. We show that simply replacing ID features with content-based embeddings can cause a drop in quality due to reduced memorization capability. To strike a good balance of memorization and generalization, we propose to use Semantic IDs -- a compact discrete item representation learned from frozen content embeddings using RQ-VAE that captures the hierarchy of concepts in items -- as a replacement for random item ids. Similar to content embeddings, the compactness of Semantic IDs poses a problem of easy adaption in recommendation models. We propose novel methods for adapting Semantic IDs in industry-scale ranking models, through hashing sub-pieces of of the Semantic-ID sequences. In particular, we find that the SentencePiece model that is commonly used in LLM tokenization outperforms manually crafted pieces such as N-grams. To the end, we evaluate our approaches in a real-world ranking model for YouTube recommendations. Our experiments demonstrate that Semantic IDs can replace the direct use of video IDs by improving the generalization ability on new and long-tail item slices without sacrificing overall model quality.
Authors: Xue Yang, Zifeng Liu, Xiaohu Tang, Rongxing Lu, Bo Liu
Abstract: With the emergence of privacy leaks in federated learning, secure aggregation protocols that mainly adopt either homomorphic encryption or threshold secret sharing have been widely developed for federated learning to protect the privacy of the local training data of each client. However, these existing protocols suffer from many shortcomings, such as the dependence on a trusted third party, the vulnerability to clients being corrupted, low efficiency, the trade-off between security and fault tolerance, etc. To solve these disadvantages, we propose an efficient and multi-private key secure aggregation scheme for federated learning. Specifically, we skillfully modify the variant ElGamal encryption technique to achieve homomorphic addition operation, which has two important advantages: 1) The server and each client can freely select public and private keys without introducing a trust third party and 2) Compared to the variant ElGamal encryption, the plaintext space is relatively large, which is more suitable for the deep model. Besides, for the high dimensional deep model parameter, we introduce a super-increasing sequence to compress multi-dimensional data into 1-D, which can greatly reduce encryption and decryption times as well as communication for ciphertext transmission. Detailed security analyses show that our proposed scheme achieves the semantic security of both individual local gradients and the aggregated result while achieving optimal robustness in tolerating both client collusion and dropped clients. Extensive simulations demonstrate that the accuracy of our scheme is almost the same as the non-private approach, while the efficiency of our scheme is much better than the state-of-the-art homomorphic encryption-based secure aggregation schemes. More importantly, the efficiency advantages of our scheme will become increasingly prominent as the number of model parameters increases.
Authors: Maria Chiara Angelini, Angelo Giorgio Cavaliere, Raffaele Marino, Federico Ricci-Tersenghi
Abstract: Is Stochastic Gradient Descent (SGD) substantially different from Metropolis Monte Carlo dynamics? This is a fundamental question at the time of understanding the most used training algorithm in the field of Machine Learning, but it received no answer until now. Here we show that in discrete optimization and inference problems, the dynamics of an SGD-like algorithm resemble very closely that of Metropolis Monte Carlo with a properly chosen temperature, which depends on the mini-batch size. This quantitative matching holds both at equilibrium and in the out-of-equilibrium regime, despite the two algorithms having fundamental differences (e.g.\ SGD does not satisfy detailed balance). Such equivalence allows us to use results about performances and limits of Monte Carlo algorithms to optimize the mini-batch size in the SGD-like algorithm and make it efficient at recovering the signal in hard inference problems.
Authors: Dennis Shen, Dogyoon Song, Peng Ding, Jasjeet S. Sekhon
Abstract: Deep learning research has uncovered the phenomenon of benign overfitting for overparameterized statistical models, which has drawn significant theoretical interest in recent years. Given its simplicity and practicality, the ordinary least squares (OLS) interpolator has become essential to gain foundational insights into this phenomenon. While properties of OLS are well established in classical, underparameterized settings, its behavior in high-dimensional, overparameterized regimes is less explored (unlike for ridge or lasso regression) though significant progress has been made of late. We contribute to this growing literature by providing fundamental algebraic and statistical results for the minimum $\ell_2$-norm OLS interpolator. In particular, we provide algebraic equivalents of (i) the leave-$k$-out residual formula, (ii) Cochran's formula, and (iii) the Frisch-Waugh-Lovell theorem in the overparameterized regime. These results aid in understanding the OLS interpolator's ability to generalize and have substantive implications for causal inference. Under the Gauss-Markov model, we present statistical results such as an extension of the Gauss-Markov theorem and an analysis of variance estimation under homoskedastic errors for the overparameterized regime. To substantiate our theoretical contributions, we conduct simulations that further explore the stochastic properties of the OLS interpolator.
Authors: Yupei Liu, Yuqi Jia, Runpeng Geng, Jinyuan Jia, Neil Zhenqiang Gong
Abstract: A prompt injection attack aims to inject malicious instruction/data into the input of an LLM-Integrated Application such that it produces results as an attacker desires. Existing works are limited to case studies. As a result, the literature lacks a systematic understanding of prompt injection attacks and their defenses. We aim to bridge the gap in this work. In particular, we propose a framework to formalize prompt injection attacks. Existing attacks are special cases in our framework. Moreover, based on our framework, we design a new attack by combining existing ones. Using our framework, we conduct a systematic evaluation on 5 prompt injection attacks and 10 defenses with 10 LLMs and 7 tasks. Our work provides a common benchmark for quantitatively evaluating future prompt injection attacks and defenses. To facilitate research on this topic, we make our platform public at https://github.com/liu00222/Open-Prompt-Injection.
Authors: Franz Nowak, Anej Svete, Li Du, Ryan Cotterell
Abstract: This work investigates the computational expressivity of language models (LMs) based on recurrent neural networks (RNNs). Siegelmann and Sontag (1992) famously showed that RNNs with rational weights and hidden states and unbounded computation time are Turing complete. However, LMs define weightings over strings in addition to just (unweighted) language membership and the analysis of the computational power of RNN LMs (RLMs) should reflect this. We extend the Turing completeness result to the probabilistic case, showing how a rationally weighted RLM with unbounded computation time can simulate any deterministic probabilistic Turing machine (PTM) with rationally weighted transitions. Since, in practice, RLMs work in real-time, processing a symbol at every time step, we treat the above result as an upper bound on the expressivity of RLMs. We also provide a lower bound by showing that under the restriction to real-time computation, such models can simulate deterministic real-time rational PTMs.
Authors: Juan Carlos Perdomo
Abstract: Algorithmic predictions are increasingly used to inform the allocations of goods and interventions in the public sphere. In these domains, predictions serve as a means to an end. They provide stakeholders with insights into likelihood of future events as a means to improve decision making quality, and enhance social welfare. However, if maximizing welfare is the ultimate goal, prediction is only a small piece of the puzzle. There are various other policy levers a social planner might pursue in order to improve bottom-line outcomes, such as expanding access to available goods, or increasing the effect sizes of interventions. Given this broad range of design decisions, a basic question to ask is: What is the relative value of prediction in algorithmic decision making? How do the improvements in welfare arising from better predictions compare to those of other policy levers? The goal of our work is to initiate the formal study of these questions. Our main results are theoretical in nature. We identify simple, sharp conditions determining the relative value of prediction vis-\`a-vis expanding access, within several statistical models that are popular amongst quantitative social scientists. Furthermore, we illustrate how these theoretical insights may be used to guide the design of algorithmic decision making systems in practice.
Authors: Yao Zhao, Zhitian Xie, Chen Liang, Chenyi Zhuang, Jinjie Gu
Abstract: As Large Language Models (LLMs) have made significant advancements across various tasks, such as question answering, translation, text summarization, and dialogue systems, the need for accuracy in information becomes crucial, especially for serious financial products serving billions of users like Alipay. However, for a real-world product serving millions of users, the inference speed of LLMs becomes a critical factor compared to a mere experimental model. Hence, this paper presents a generic framework for accelerating the inference process, resulting in a substantial increase in speed and cost reduction for our LLM-based scenarios, with lossless generation accuracy. In the traditional inference process, each token is generated sequentially by the LLM, leading to a time consumption proportional to the number of generated tokens. To enhance this process, our framework, named \textit{lookahead}, introduces a \textit{multi-branch} strategy. Instead of generating a single token at a time, we propose a Trie-based retrieval and verification mechanism to be able to accept several tokens at a forward step. Our strategy offers two distinct advantages: (1) it guarantees absolute correctness of the output, avoiding any approximation algorithms, and (2) the worst-case performance of our approach is equivalent to the conventional process. We conduct extensive experiments to demonstrate the significant improvements achieved by applying our inference acceleration framework. Our framework is widely deployed in Alipay since April 2023, and obtain remarkable 2.66x to 6.26x speedup. Our code is available at https://github.com/alipay/PainlessInferenceAcceleration.
URLs: https://github.com/alipay/PainlessInferenceAcceleration.
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: Qingyun Wang, Zixuan Zhang, Hongxiang Li, Xuan Liu, Jiawei Han, Huimin Zhao, Heng Ji
Abstract: Fine-grained few-shot entity extraction in the chemical domain faces two unique challenges. First, compared with entity extraction tasks in the general domain, sentences from chemical papers usually contain more entities. Moreover, entity extraction models usually have difficulty extracting entities of long-tailed types. In this paper, we propose Chem-FINESE, a novel sequence-to-sequence (seq2seq) based few-shot entity extraction approach, to address these two challenges. Our Chem-FINESE has two components: a seq2seq entity extractor to extract named entities from the input sentence and a seq2seq self-validation module to reconstruct the original input sentence from extracted entities. Inspired by the fact that a good entity extraction system needs to extract entities faithfully, our new self-validation module leverages entity extraction results to reconstruct the original input sentence. Besides, we design a new contrastive loss to reduce excessive copying during the extraction process. Finally, we release ChemNER+, a new fine-grained chemical entity extraction dataset that is annotated by domain experts with the ChemNER schema. Experiments in few-shot settings with both ChemNER+ and CHEMET datasets show that our newly proposed framework has contributed up to 8.26% and 6.84% absolute F1-score gains respectively.
Authors: Weihan Li, Chengrui Li, Yule Wang, Anqi Wu
Abstract: Studying the complex interactions between different brain regions is crucial in neuroscience. Various statistical methods have explored the latent communication across multiple brain regions. Two main categories are the Gaussian Process (GP) and Linear Dynamical System (LDS), each with unique strengths. The GP-based approach effectively discovers latent variables with frequency bands and communication directions. Conversely, the LDS-based approach is computationally efficient but lacks powerful expressiveness in latent representation. In this study, we merge both methodologies by creating an LDS mirroring a multi-output GP, termed Multi-Region Markovian Gaussian Process (MRM-GP). Our work establishes a connection between an LDS and a multi-output GP that explicitly models frequencies and phase delays within the latent space of neural recordings. Consequently, the model achieves a linear inference cost over time points and provides an interpretable low-dimensional representation, revealing communication directions across brain regions and separating oscillatory communications into different frequency bands.
Authors: Zhiyuan Hu, Chumin Liu, Xidong Feng, Yilun Zhao, See-Kiong Ng, Anh Tuan Luu, Junxian He, Pang Wei Koh, Bryan Hooi
Abstract: In the face of uncertainty, the ability to *seek information* is of fundamental importance. In many practical applications, such as medical diagnosis and troubleshooting, the information needed to solve the task is not initially given and has to be actively sought by asking follow-up questions (for example, a doctor asking a patient for more details about their symptoms). In this work, we introduce Uncertainty of Thoughts (UoT), an algorithm to augment large language models with the ability to actively seek information by asking effective questions. UoT combines 1) an *uncertainty-aware simulation approach* which enables the model to simulate possible future scenarios and how likely they are to occur, 2) *uncertainty-based rewards* motivated by information gain which incentivizes the model to seek information, and 3) a *reward propagation scheme* to select the optimal question to ask in a way that maximizes the expected reward. In experiments on medical diagnosis, troubleshooting, and the `20 Questions` game, UoT achieves an average performance improvement of 38.1% in the rate of successful task completion across multiple LLMs compared with direct prompting and also improves efficiency (i.e., the number of questions needed to complete the task). Our code has been released [here](https://github.com/zhiyuanhubj/UoT)
Authors: Yoad Tewel, Omri Kaduri, Rinon Gal, Yoni Kasten, Lior Wolf, Gal Chechik, Yuval Atzmon
Abstract: Text-to-image models offer a new level of creative flexibility by allowing users to guide the image generation process through natural language. However, using these models to consistently portray the same subject across diverse prompts remains challenging. Existing approaches fine-tune the model to teach it new words that describe specific user-provided subjects or add image conditioning to the model. These methods require lengthy per-subject optimization or large-scale pre-training. Moreover, they struggle to align generated images with text prompts and face difficulties in portraying multiple subjects. Here, we present ConsiStory, a training-free approach that enables consistent subject generation by sharing the internal activations of the pretrained model. We introduce a subject-driven shared attention block and correspondence-based feature injection to promote subject consistency between images. Additionally, we develop strategies to encourage layout diversity while maintaining subject consistency. We compare ConsiStory to a range of baselines, and demonstrate state-of-the-art performance on subject consistency and text alignment, without requiring a single optimization step. Finally, ConsiStory can naturally extend to multi-subject scenarios, and even enable training-free personalization for common objects.
Authors: Simone Magistri, Tomaso Trinci, Albin Soutif-Cormerais, Joost van de Weijer, Andrew D. Bagdanov
Abstract: Exemplar-Free Class Incremental Learning (EFCIL) aims to learn from a sequence of tasks without having access to previous task data. In this paper, we consider the challenging Cold Start scenario in which insufficient data is available in the first task to learn a high-quality backbone. This is especially challenging for EFCIL since it requires high plasticity, which results in feature drift which is difficult to compensate for in the exemplar-free setting. To address this problem, we propose a simple and effective approach that consolidates feature representations by regularizing drift in directions highly relevant to previous tasks and employs prototypes to reduce task-recency bias. Our method, called Elastic Feature Consolidation (EFC), exploits a tractable second-order approximation of feature drift based on an Empirical Feature Matrix (EFM). The EFM induces a pseudo-metric in feature space which we use to regularize feature drift in important directions and to update Gaussian prototypes used in a novel asymmetric cross entropy loss which effectively balances prototype rehearsal with data from new tasks. Experimental results on CIFAR-100, Tiny-ImageNet, ImageNet-Subset and ImageNet-1K demonstrate that Elastic Feature Consolidation is better able to learn new tasks by maintaining model plasticity and significantly outperform the state-of-the-art.
Authors: Syamantak Kumar, Purnamrita Sarkar
Abstract: Oja's algorithm for streaming Principal Component Analysis (PCA) for $n$ datapoints in a $d$ dimensional space achieves the same sin-squared error $O(r_\mathsf{eff}/n)$ as the offline algorithm in $O(d)$ space and $O(nd)$ time and a single pass through the datapoints. Here $r_\mathsf{eff}$ is the effective rank (ratio of the trace and the principal eigenvalue of the population covariance matrix $\Sigma$). Under this computational budget, we consider the problem of sparse PCA, where the principal eigenvector of $\Sigma$ is $s$-sparse, and $r_\mathsf{eff}$ can be large. In this setting, to our knowledge, \textit{there are no known single-pass algorithms} that achieve the minimax error bound in $O(d)$ space and $O(nd)$ time without either requiring strong initialization conditions or assuming further structure (e.g., spiked) of the covariance matrix. We show that a simple single-pass procedure that thresholds the output of Oja's algorithm (the Oja vector) can achieve the minimax error bound under some regularity conditions in $O(d)$ space and $O(nd)$ time as long as $r_\mathsf{eff}=O(n/\log n)$. We present a nontrivial and novel analysis of the entries of the unnormalized Oja vector, which involves the projection of a product of independent random matrices on a random initial vector. This is completely different from previous analyses of Oja's algorithm and matrix products, which have been done when the $r_\mathsf{eff}$ is bounded.
Authors: Siddharth Karamcheti, Suraj Nair, Ashwin Balakrishna, Percy Liang, Thomas Kollar, Dorsa Sadigh
Abstract: Visually-conditioned language models (VLMs) have seen growing adoption in applications such as visual dialogue, scene understanding, and robotic task planning; adoption that has fueled a wealth of new models such as LLaVa, InstructBLIP, and PaLI-3. Despite the volume of new releases, key design decisions around image preprocessing, architecture, and optimization are under-explored, making it challenging to understand what factors account for model performance $-$ a challenge further complicated by the lack of objective, consistent evaluations. To address these gaps, we first compile a suite of standardized evaluations spanning visual question answering, object localization, and challenge sets that probe properties such as hallucination; evaluations that provide fine-grained insight VLM capabilities. Second, we rigorously investigate VLMs along key design axes, including pretrained visual representations and training from base vs. instruct-tuned language models, amongst others. We couple our analysis with three resource contributions: (1) a unified framework for evaluating VLMs, (2) optimized, flexible training code, and (3) checkpoints for all models, including a family of VLMs at the 7-13B scale that strictly outperform InstructBLIP and LLaVa v1.5, the state-of-the-art in open VLMs.
Authors: Xudong Lu, Qi Liu, Yuhui Xu, Aojun Zhou, Siyuan Huang, Bo Zhang, Junchi Yan, Hongsheng Li
Abstract: A pivotal advancement in the progress of large language models (LLMs) is the emergence of the Mixture-of-Experts (MoE) LLMs. Compared to traditional LLMs, MoE LLMs can achieve higher performance with fewer parameters, but it is still hard to deploy them due to their immense parameter sizes. Different from previous weight pruning methods that rely on specifically designed hardware, this paper mainly aims to enhance the deployment efficiency of MoE LLMs by introducing plug-and-play expert-level sparsification techniques. Specifically, we propose, for the first time to our best knowledge, post-training approaches for task-agnostic and task-specific expert pruning and skipping of MoE LLMs, tailored to improve deployment efficiency while maintaining model performance across a wide range of tasks. Extensive experiments show that our proposed methods can simultaneously reduce model sizes and increase the inference speed, while maintaining satisfactory performance. Data and code will be available at https://github.com/Lucky-Lance/Expert_Sparsity.
Authors: Jin Yao, Eli Chien, Minxin Du, Xinyao Niu, Tianhao Wang, Zezhou Cheng, Xiang Yue
Abstract: This study investigates the concept of the `right to be forgotten' within the context of large language models (LLMs). We explore machine unlearning as a pivotal solution, with a focus on pre-trained models--a notably under-researched area. Our research delineates a comprehensive framework for machine unlearning in pre-trained LLMs, encompassing a critical analysis of seven diverse unlearning methods. Through rigorous evaluation using curated datasets from arXiv, books, and GitHub, we establish a robust benchmark for unlearning performance, demonstrating that these methods are over $10^5$ times more computationally efficient than retraining. Our results show that integrating gradient ascent with gradient descent on in-distribution data improves hyperparameter robustness. We also provide detailed guidelines for efficient hyperparameter tuning in the unlearning process. Our findings advance the discourse on ethical AI practices, offering substantive insights into the mechanics of machine unlearning for pre-trained LLMs and underscoring the potential for responsible AI development.
Authors: Muhammad Faaiz Taufiq, Jean-Francois Ton, Yang Liu
Abstract: In machine learning fairness, training models that minimize disparity across different sensitive groups often leads to diminished accuracy, a phenomenon known as the fairness-accuracy trade-off. The severity of this trade-off inherently depends on dataset characteristics such as dataset imbalances or biases and therefore, using a uniform fairness requirement across diverse datasets remains questionable. To address this, we present a computationally efficient approach to approximate the fairness-accuracy trade-off curve tailored to individual datasets, backed by rigorous statistical guarantees. By utilizing the You-Only-Train-Once (YOTO) framework, our approach mitigates the computational burden of having to train multiple models when approximating the trade-off curve. Crucially, we introduce a novel methodology for quantifying uncertainty in our estimates, thereby providing practitioners with a robust framework for auditing model fairness while avoiding false conclusions due to estimation errors. Our experiments spanning tabular (e.g., Adult), image (CelebA), and language (Jigsaw) datasets underscore that our approach not only reliably quantifies the optimum achievable trade-offs across various data modalities but also helps detect suboptimality in SOTA fairness methods.
Authors: Aonan Zhang, Chong Wang, Yi Wang, Xuanyu Zhang, Yunfei Cheng
Abstract: In this paper, we introduce an improved approach of speculative decoding aimed at enhancing the efficiency of serving large language models. Our method capitalizes on the strengths of two established techniques: the classic two-model speculative decoding approach, and the more recent single-model approach, Medusa. Drawing inspiration from Medusa, our approach adopts a single-model strategy for speculative decoding. However, our method distinguishes itself by employing a single, lightweight draft head with a recurrent dependency design, akin in essence to the small, draft model uses in classic speculative decoding, but without the complexities of the full transformer architecture. And because of the recurrent dependency, we can use beam search to swiftly filter out undesired candidates with the draft head. The outcome is a method that combines the simplicity of single-model design and avoids the need to create a data-dependent tree attention structure only for inference in Medusa. We empirically demonstrate the effectiveness of the proposed method on several popular open source language models, along with a comprehensive analysis of the trade-offs involved in adopting this approach.
Authors: Korbinian Randl, John Pavlopoulos, Aron Henriksson, Tony Lindgren
Abstract: Contaminated or adulterated food poses a substantial risk to human health. Given sets of labeled web texts for training, Machine Learning and Natural Language Processing can be applied to automatically detect such risks. We publish a dataset of 7,546 short texts describing public food recall announcements. Each text is manually labeled, on two granularity levels (coarse and fine), for food products and hazards that the recall corresponds to. We describe the dataset and benchmark naive, traditional, and Transformer models. Based on our analysis, Logistic Regression based on a tf-idf representation outperforms RoBERTa and XLM-R on classes with low support. Finally, we discuss different prompting strategies and present an LLM-in-the-loop framework, based on Conformal Prediction, which boosts the performance of the base classifier while reducing energy consumption compared to normal prompting.
Authors: Alina Petukhova, Jo\~ao P. Matos-Carvalho, Nuno Fachada
Abstract: Text clustering is an important approach for organising the growing amount of digital content, helping to structure and find hidden patterns in uncategorised data. However, the effectiveness of text clustering heavily relies on the choice of textual embeddings and clustering algorithms. We argue that recent advances in large language models (LLMs) can potentially improve this task. In this research, we investigated how different textual embeddings -- particularly those used in LLMs -- and clustering algorithms affect how text datasets are clustered. A series of experiments were conducted to assess how embeddings influence clustering results, the role played by dimensionality reduction through summarisation, and model size adjustment. Findings reveal that LLM embeddings excel at capturing subtleties in structured language, while BERT leads the lightweight options in performance. In addition, we observe that increasing model dimensionality and employing summarization techniques do not consistently lead to improvements in clustering efficiency, suggesting that these strategies require careful analysis to use in real-life models. These results highlight a complex balance between the need for refined text representation and computational feasibility in text clustering applications. This study extends traditional text clustering frameworks by incorporating embeddings from LLMs, providing a path for improved methodologies, while informing new avenues for future research in various types of textual analysis.
Authors: Mohammad Shahab Sepehri, Zalan Fabian, Mahdi Soltanolkotabi
Abstract: The landscape of computational building blocks of efficient image restoration architectures is dominated by a combination of convolutional processing and various attention mechanisms. However, convolutional filters, while efficient, are inherently local and therefore struggle with modeling long-range dependencies in images. In contrast, attention excels at capturing global interactions between arbitrary image regions, but suffers from a quadratic cost in image dimension. In this work, we propose Serpent, an efficient architecture for high-resolution image restoration that combines recent advances in state space models (SSMs) with multi-scale signal processing in its core computational block. SSMs, originally introduced for sequence modeling, can maintain a global receptive field with a favorable linear scaling in input size. We propose a novel hierarchical architecture inspired by traditional signal processing principles, that converts the input image into a collection of sequences and processes them in a multi-scale fashion. Our experimental results demonstrate that Serpent can achieve reconstruction quality on par with state-of-the-art techniques, while requiring orders of magnitude less compute (up to $150$ fold reduction in FLOPS) and a factor of up to $5\times$ less GPU memory while maintaining a compact model size. The efficiency gains achieved by Serpent are especially notable at high image resolutions.
Authors: Ningsheng Zhao, Jia Yuan Yu, Krzysztof Dzieciolowski, Trang Bui
Abstract: Shapley value attribution (SVA) is an increasingly popular explainable AI (XAI) method, which quantifies the contribution of each feature to the model's output. However, recent work has shown that most existing methods to implement SVAs have some drawbacks, resulting in biased or unreliable explanations that fail to correctly capture the true intrinsic relationships between features and model outputs. Moreover, the mechanism and consequences of these drawbacks have not been discussed systematically. In this paper, we propose a novel error theoretical analysis framework, in which the explanation errors of SVAs are decomposed into two components: observation bias and structural bias. We further clarify the underlying causes of these two biases and demonstrate that there is a trade-off between them. Based on this error analysis framework, we develop two novel concepts: over-informative and underinformative explanations. We demonstrate how these concepts can be effectively used to understand potential errors of existing SVA methods. In particular, for the widely deployed assumption-based SVAs, we find that they can easily be under-informative due to the distribution drift caused by distributional assumptions. We propose a measurement tool to quantify such a distribution drift. Finally, our experiments illustrate how different existing SVA methods can be over- or under-informative. Our work sheds light on how errors incur in the estimation of SVAs and encourages new less error-prone methods.
Authors: Patrik Reizinger, Szilvia Ujv\'ary, Anna M\'esz\'aros, Anna Kerekes, Wieland Brendel, Ferenc Husz\'ar
Abstract: The last decade has seen blossoming research in deep learning theory attempting to answer, "Why does deep learning generalize?" A powerful shift in perspective precipitated this progress: the study of overparametrized models in the interpolation regime. In this paper, we argue that another perspective shift is due, since some of the desirable qualities of LLMs are not a consequence of good statistical generalization and require a separate theoretical explanation. Our core argument relies on the observation that AR probabilistic models are inherently non-identifiable: models zero or near-zero KL divergence apart -- thus, equivalent test loss -- can exhibit markedly different behaviors. We support our position with mathematical examples and empirical observations, illustrating why non-identifiability has practical relevance through three case studies: (1) the non-identifiability of zero-shot rule extrapolation; (2) the approximate non-identifiability of in-context learning; and (3) the non-identifiability of fine-tunability. We review promising research directions focusing on LLM-relevant generalization measures, transferability, and inductive biases.
Authors: Yu Cheng, Qin Yang, Liyang Wang, Ao Xiang, Jingyu Zhang
Abstract: In the realm of globalized financial markets, commercial banks are confronted with an escalating magnitude of credit risk, thereby imposing heightened requisites upon the security of bank assets and financial stability. This study harnesses advanced neural network techniques, notably the Backpropagation (BP) neural network, to pioneer a novel model for preempting credit risk in commercial banks. The discourse initially scrutinizes conventional financial risk preemptive models, such as ARMA, ARCH, and Logistic regression models, critically analyzing their real-world applications. Subsequently, the exposition elaborates on the construction process of the BP neural network model, encompassing network architecture design, activation function selection, parameter initialization, and objective function construction. Through comparative analysis, the superiority of neural network models in preempting credit risk in commercial banks is elucidated. The experimental segment selects specific bank data, validating the model's predictive accuracy and practicality. Research findings evince that this model efficaciously enhances the foresight and precision of credit risk management.
Authors: Joris Depoortere, Johan Driesen, Johan Suykens, Hussain Syed Kazmi
Abstract: Deep learning models have gained increasing prominence in recent years in the field of solar pho-tovoltaic (PV) forecasting. One drawback of these models is that they require a lot of high-quality data to perform well. This is often infeasible in practice, due to poor measurement infrastructure in legacy systems and the rapid build-up of new solar systems across the world. This paper proposes SolNet: a novel, general-purpose, multivariate solar power forecaster, which addresses these challenges by using a two-step forecasting pipeline which incorporates transfer learning from abundant synthetic data generated from PVGIS, before fine-tuning on observational data. Using actual production data from hundreds of sites in the Netherlands, Australia and Belgium, we show that SolNet improves forecasting performance over data-scarce settings as well as baseline models. We find transfer learning benefits to be the strongest when only limited observational data is available. At the same time we provide several guidelines and considerations for transfer learning practitioners, as our results show that weather data, seasonal patterns, amount of synthetic data and possible mis-specification in source location, can have a major impact on the results. The SolNet models created in this way are applicable for any land-based solar photovoltaic system across the planet where simulated and observed data can be combined to obtain improved forecasting capabilities.
Authors: Jie Wang, March Boedihardjo, Yao Xie
Abstract: Optimal transport has been very successful for various machine learning tasks; however, it is known to suffer from the curse of dimensionality. Hence, dimensionality reduction is desirable when applied to high-dimensional data with low-dimensional structures. The kernel max-sliced (KMS) Wasserstein distance is developed for this purpose by finding an optimal nonlinear mapping that reduces data into $1$ dimensions before computing the Wasserstein distance. However, its theoretical properties have not yet been fully developed. In this paper, we provide sharp finite-sample guarantees under milder technical assumptions compared with state-of-the-art for the KMS $p$-Wasserstein distance between two empirical distributions with $n$ samples for general $p\in[1,\infty)$. Algorithm-wise, we show that computing the KMS $2$-Wasserstein distance is NP-hard, and then we further propose a semidefinite relaxation (SDR) formulation (which can be solved efficiently in polynomial time) and provide a relaxation gap for the SDP solution. We provide numerical examples to demonstrate the good performance of our scheme for high-dimensional two-sample testing.
Authors: Xiyao Wang, Jiuhai Chen, Zhaoyang Wang, Yuhang Zhou, Yiyang Zhou, Huaxiu Yao, Tianyi Zhou, Tom Goldstein, Parminder Bhatia, Furong Huang, Cao Xiao
Abstract: Large vision-language models (LVLMs) have achieved impressive results in various visual question-answering and reasoning tasks through vision instruction tuning on specific datasets. However, there is still significant room for improvement in the alignment between visual and language modalities. Previous methods to enhance this alignment typically require external models or data, heavily depending on their capabilities and quality, which inevitably sets an upper bound on performance. In this paper, we propose SIMA, a framework that enhances visual and language modality alignment through self-improvement, eliminating the needs for external models or data. SIMA leverages prompts from existing vision instruction tuning datasets to self-generate responses and employs an in-context self-critic mechanism to select response pairs for preference tuning. The key innovation is the introduction of three vision metrics during the in-context self-critic process, which can guide the LVLM in selecting responses that enhance image comprehension. Through experiments across 14 hallucination and comprehensive benchmarks, we demonstrate that SIMA not only improves model performance across all benchmarks but also achieves superior modality alignment, outperforming previous approaches.
Authors: Yuhao Chen, Zhimu Wang, Bo Wen, Farhana Zulkernine
Abstract: Unstructured text in medical notes and dialogues contains rich information. Recent advancements in Large Language Models (LLMs) have demonstrated superior performance in question answering and summarization tasks on unstructured text data, outperforming traditional text analysis approaches. However, there is a lack of scientific studies in the literature that methodically evaluate and report on the performance of different LLMs, specifically for domain-specific data such as medical chart notes. We propose an evaluation approach to analyze the performance of open-source LLMs such as Llama2 and Mistral for medical summarization tasks, using GPT-4 as an assessor. Our innovative approach to quantitative evaluation of LLMs can enable quality control, support the selection of effective LLMs for specific tasks, and advance knowledge discovery in digital health.
Authors: Cong Zhang, Derrick Goh Xin Deik, Dexun Li, Hao Zhang, Yong Liu
Abstract: The rapid advancement of neural language models has sparked a new surge of intelligent agent research. Unlike traditional agents, large language model-based agents (LLM agents) have emerged as a promising paradigm for achieving artificial general intelligence (AGI) due to their superior reasoning and generalization capabilities. Effective planning is crucial for the success of LLM agents in real-world tasks, making it a highly pursued topic in the community. Current planning methods typically translate tasks into executable action sequences. However, determining a feasible or optimal sequence for complex tasks at fine granularity, which often requires compositing long chains of heterogeneous actions, remains challenging. This paper introduces Meta-Task Planning (MTP), a zero-shot methodology for collaborative LLM-based multi-agent systems that simplifies complex task planning by decomposing it into a hierarchy of subordinate tasks, or meta-tasks. Each meta-task is then mapped into executable actions. MTP was assessed on two rigorous benchmarks, TravelPlanner and API-Bank. Notably, MTP achieved an average $\sim40\%$ success rate on TravelPlanner, significantly higher than the state-of-the-art (SOTA) baseline ($2.92\%$), and outperforming $LLM_{api}$-4 with ReAct on API-Bank by $\sim14\%$, showing the immense potential of integrating LLM with multi-agent systems.
Authors: Dibyajyoti Chakraborty, Shivam Barwey, Hong Zhang, Romit Maulik
Abstract: In this work, we provide a mathematical formulation for error propagation in flow trajectory prediction using data-driven turbulence closure modeling. Under the assumption that the predicted state of a large eddy simulation prediction must be close to that of a subsampled direct numerical simulation, we retrieve an upper bound for the prediction error when utilizing a data-driven closure model. We also demonstrate that this error is significantly affected by the time step size and the Jacobian which play a role in amplifying the initial one-step error made by using the closure. Our analysis also shows that the error propagates exponentially with rollout time and the upper bound of the system Jacobian which is itself influenced by the Jacobian of the closure formulation. These findings could enable the development of new regularization techniques for ML models based on the identified error-bound terms, improving their robustness and reducing error propagation.
Authors: Zhengyang Tang, Chenyu Huang, Xin Zheng, Shixi Hu, Zizhuo Wang, Dongdong Ge, Benyou Wang
Abstract: Large Language Models (LLMs) have emerged as powerful tools for tackling complex Operations Research (OR) problem by providing the capacity in automating optimization modeling. However, current methodologies heavily rely on prompt engineering (e.g., multi-agent cooperation) with proprietary LLMs, raising data privacy concerns that could be prohibitive in industry applications. To tackle this issue, we propose training open-source LLMs for optimization modeling. We identify four critical requirements for the training dataset of OR LLMs, design and implement OR-Instruct, a semi-automated process for creating synthetic data tailored to specific requirements. We also introduce the IndustryOR benchmark, the first industrial benchmark for testing LLMs on solving real-world OR problems. We apply the data from OR-Instruct to various open-source LLMs of 7b size (termed as ORLMs), resulting in a significantly improved capability for optimization modeling. Our best-performing ORLM achieves state-of-the-art performance on the NL4OPT, MAMO, and IndustryOR benchmarks. Our code and data are available at \url{https://github.com/Cardinal-Operations/ORLM}.
Authors: Yuka Hashimoto, Ayoub Hafid, Masahiro Ikeda, Hachem Kadri
Abstract: In this paper, we propose a new class of positive definite kernels based on the spectral truncation, which has been discussed in the fields of noncommutative geometry and $C^*$-algebra. We focus on kernels whose inputs and outputs are functions and generalize existing kernels, such as polynomial, product, and separable kernels, by introducing a truncation parameter $n$ that describes the noncommutativity of the products appearing in the kernels. When $n$ goes to infinity, the proposed kernels tend to the existing commutative kernels. If $n$ is finite, they exhibit different behavior, and the noncommutativity induces interactions along the data function domain. We show that the truncation parameter $n$ is a governing factor leading to performance enhancement: by setting an appropriate $n$, we can balance the representation power and the complexity of the representation space. The flexibility of the proposed class of kernels allows us to go beyond previous commutative kernels.
Authors: Quanqi Hu, Qi Qi, Zhaosong Lu, Tianbao Yang
Abstract: In this paper, we study a class of non-smooth non-convex problems in the form of $\min_{x}[\max_{y\in Y}\phi(x, y) - \max_{z\in Z}\psi(x, z)]$, where both $\Phi(x) = \max_{y\in Y}\phi(x, y)$ and $\Psi(x)=\max_{z\in Z}\psi(x, z)$ are weakly convex functions, and $\phi(x, y), \psi(x, z)$ are strongly concave functions in terms of $y$ and $z$, respectively. It covers two families of problems that have been studied but are missing single-loop stochastic algorithms, i.e., difference of weakly convex functions and weakly convex strongly-concave min-max problems. We propose a stochastic Moreau envelope approximate gradient method dubbed SMAG, the first single-loop algorithm for solving these problems, and provide a state-of-the-art non-asymptotic convergence rate. The key idea of the design is to compute an approximate gradient of the Moreau envelopes of $\Phi, \Psi$ using only one step of stochastic gradient update of the primal and dual variables. Empirically, we conduct experiments on positive-unlabeled (PU) learning and partial area under ROC curve (pAUC) optimization with an adversarial fairness regularizer to validate the effectiveness of our proposed algorithms.
Authors: Antonio Briola, Silvia Bartolucci, Tomaso Aste
Abstract: We introduce a novel large-scale deep learning model for Limit Order Book mid-price changes forecasting, and we name it `HLOB'. This architecture (i) exploits the information encoded by an Information Filtering Network, namely the Triangulated Maximally Filtered Graph, to unveil deeper and non-trivial dependency structures among volume levels; and (ii) guarantees deterministic design choices to handle the complexity of the underlying system by drawing inspiration from the groundbreaking class of Homological Convolutional Neural Networks. We test our model against 9 state-of-the-art deep learning alternatives on 3 real-world Limit Order Book datasets, each including 15 stocks traded on the NASDAQ exchange, and we systematically characterize the scenarios where HLOB outperforms state-of-the-art architectures. Our approach sheds new light on the spatial distribution of information in Limit Order Books and on its degradation over increasing prediction horizons, narrowing the gap between microstructural modeling and deep learning-based forecasting in high-frequency financial markets.
Authors: Ge Zhang, Scott Qu, Jiaheng Liu, Chenchen Zhang, Chenghua Lin, Chou Leuang Yu, Danny Pan, Esther Cheng, Jie Liu, Qunshu Lin, Raven Yuan, Tuney Zheng, Wei Pang, Xinrun Du, Yiming Liang, Yinghao Ma, Yizhi Li, Ziyang Ma, Bill Lin, Emmanouil Benetos, Huan Yang, Junting Zhou, Kaijing Ma, Minghao Liu, Morry Niu, Noah Wang, Quehry Que, Ruibo Liu, Sine Liu, Shawn Guo, Soren Gao, Wangchunshu Zhou, Xinyue Zhang, Yizhi Zhou, Yubo Wang, Yuelin Bai, Yuhan Zhang, Yuxiang Zhang, Zenith Wang, Zhenzhu Yang, Zijian Zhao, Jiajun Zhang, Wanli Ouyang, Wenhao Huang, Wenhu Chen
Abstract: Large Language Models (LLMs) have made great strides in recent years to achieve unprecedented performance across different tasks. However, due to commercial interest, the most competitive models like GPT, Gemini, and Claude have been gated behind proprietary interfaces without disclosing the training details. Recently, many institutions have open-sourced several strong LLMs like LLaMA-3, comparable to existing closed-source LLMs. However, only the model's weights are provided with most details (e.g., intermediate checkpoints, pre-training corpus, and training code, etc.) being undisclosed. To improve the transparency of LLMs, the research community has formed to open-source truly open LLMs (e.g., Pythia, Amber, OLMo), where more details (e.g., pre-training corpus and training code) are being provided. These models have greatly advanced the scientific study of these large models including their strengths, weaknesses, biases and risks. However, we observe that the existing truly open LLMs on reasoning, knowledge, and coding tasks are still inferior to existing state-of-the-art LLMs with similar model sizes. To this end, we open-source MAP-Neo, a highly capable and transparent bilingual language model with 7B parameters trained from scratch on 4.5T high-quality tokens. Our MAP-Neo is the first fully open-sourced bilingual LLM with comparable performance compared to existing state-of-the-art LLMs. Moreover, we open-source all details to reproduce our MAP-Neo, where the cleaned pre-training corpus, data cleaning pipeline, checkpoints, and well-optimized training/evaluation framework are provided. Finally, we hope our MAP-Neo will enhance and strengthen the open research community and inspire more innovations and creativities to facilitate the further improvements of LLMs.