Authors: Dayu Yang, Natawut Monaikul, Amanda Ding, Bozhao Tan, Kishore Mosaliganti, Giri Iyengar
Abstract: In the era of data-driven decision-making, accurate table-level representations and efficient table recommendation systems are becoming increasingly crucial for improving table management, discovery, and analysis. However, existing approaches to tabular data representation often face limitations, primarily due to their focus on cell-level tasks and the lack of high-quality training data. To address these challenges, we first formulate a clear definition of table similarity in the context of data transformation activities within data-driven enterprises. This definition serves as the foundation for synthetic data generation, which require a well-defined data generation process. Building on this, we propose a novel synthetic data generation pipeline that harnesses the code generation and data manipulation capabilities of Large Language Models (LLMs) to create a large-scale synthetic dataset tailored for table-level representation learning. Through manual validation and performance comparisons on the table recommendation task, we demonstrate that the synthetic data generated by our pipeline aligns with our proposed definition of table similarity and significantly enhances table representations, leading to improved recommendation performance.
Authors: MZ Naser, Ahmed Z Naser
Abstract: This article introduces a new symbolic regression algorithm based on the SPINEX (Similarity-based Predictions with Explainable Neighbors Exploration) family. This new algorithm (SPINEX_SymbolicRegression) adopts a similarity-based approach to identifying high-merit expressions that satisfy accuracy- and structural similarity metrics. We conducted extensive benchmarking tests comparing SPINEX_SymbolicRegression to over 180 mathematical benchmarking functions from international problem sets that span randomly generated expressions and those based on real physical phenomena. Then, we evaluated the performance of the proposed algorithm in terms of accuracy, expression similarity in terms of presence operators and variables (as compared to the actual expressions), population size, and number of generations at convergence. The results indicate that SPINEX_SymbolicRegression consistently performs well and can, in some instances, outperform leading algorithms. In addition, the algorithm's explainability capabilities are highlighted through in-depth experiments.
Authors: Yiwei Dong, Tingjin Chu, Lele Zhang, Hadi Ghaderi, Hanfang Yang
Abstract: Effective models for analysing and predicting pedestrian flow are important to ensure the safety of both pedestrians and other road users. These tools also play a key role in optimising infrastructure design and geometry and supporting the economic utility of interconnected communities. The implementation of city-wide automatic pedestrian counting systems provides researchers with invaluable data, enabling the development and training of deep learning applications that offer better insights into traffic and crowd flows. Benefiting from real-world data provided by the City of Melbourne pedestrian counting system, this study presents a pedestrian flow prediction model, as an extension of Diffusion Convolutional Grated Recurrent Unit (DCGRU) with dynamic time warping, named DCGRU-DTW. This model captures the spatial dependencies of pedestrian flow through the diffusion process and the temporal dependency captured by Gated Recurrent Unit (GRU). Through extensive numerical experiments, we demonstrate that the proposed model outperforms the classic vector autoregressive model and the original DCGRU across multiple model accuracy metrics.
Authors: Alexandru-Victor Andrei, Georg Velev, Filip-Mihai Toma, Daniel Traian Pele, Stefan Lessmann
Abstract: Energy is a critical driver of modern economic systems. Accurate energy price forecasting plays an important role in supporting decision-making at various levels, from operational purchasing decisions at individual business organizations to policy-making. A significant body of literature has looked into energy price forecasting, investigating a wide range of methods to improve accuracy and inform these critical decisions. Given the evolving landscape of forecasting techniques, the literature lacks a thorough empirical comparison that systematically contrasts these methods. This paper provides an in-depth review of the evolution of forecasting modeling frameworks, from well-established econometric models to machine learning methods, early sequence learners such LSTMs, and more recent advancements in deep learning with transformer networks, which represent the cutting edge in forecasting. We offer a detailed review of the related literature and categorize forecasting methodologies into four model families. We also explore emerging concepts like pre-training and transfer learning, which have transformed the analysis of unstructured data and hold significant promise for time series forecasting. We address a gap in the literature by performing a comprehensive empirical analysis on these four family models, using data from the EU energy markets, we conduct a large-scale empirical study, which contrasts the forecasting accuracy of different approaches, focusing especially on alternative propositions for time series transformers.
Authors: Julian B\"uchel, Giacomo Camposampiero, Athanasios Vasilopoulos, Corey Lammie, Manuel Le Gallo, Abbas Rahimi, Abu Sebastian
Abstract: Kernel functions are vital ingredients of several machine learning algorithms, but often incur significant memory and computational costs. We introduce an approach to kernel approximation in machine learning algorithms suitable for mixed-signal Analog In-Memory Computing (AIMC) architectures. Analog In-Memory Kernel Approximation addresses the performance bottlenecks of conventional kernel-based methods by executing most operations in approximate kernel methods directly in memory. The IBM HERMES Project Chip, a state-of-the-art phase-change memory based AIMC chip, is utilized for the hardware demonstration of kernel approximation. Experimental results show that our method maintains high accuracy, with less than a 1% drop in kernel-based ridge classification benchmarks and within 1% accuracy on the Long Range Arena benchmark for kernelized attention in Transformer neural networks. Compared to traditional digital accelerators, our approach is estimated to deliver superior energy efficiency and lower power consumption. These findings highlight the potential of heterogeneous AIMC architectures to enhance the efficiency and scalability of machine learning applications.
Authors: Valentyn Melnychuk, Stefan Feuerriegel, Mihaela van der Schaar
Abstract: Estimating causal quantities from observational data is crucial for understanding the safety and effectiveness of medical treatments. However, to make reliable inferences, medical practitioners require not only estimating averaged causal quantities, such as the conditional average treatment effect, but also understanding the randomness of the treatment effect as a random variable. This randomness is referred to as aleatoric uncertainty and is necessary for understanding the probability of benefit from treatment or quantiles of the treatment effect. Yet, the aleatoric uncertainty of the treatment effect has received surprisingly little attention in the causal machine learning community. To fill this gap, we aim to quantify the aleatoric uncertainty of the treatment effect at the covariate-conditional level, namely, the conditional distribution of the treatment effect (CDTE). Unlike average causal quantities, the CDTE is not point identifiable without strong additional assumptions. As a remedy, we employ partial identification to obtain sharp bounds on the CDTE and thereby quantify the aleatoric uncertainty of the treatment effect. We then develop a novel, orthogonal learner for the bounds on the CDTE, which we call AU-learner. We further show that our AU-learner has several strengths in that it satisfies Neyman-orthogonality and is doubly robust. Finally, we propose a fully-parametric deep learning instantiation of our AU-learner.
Authors: Todd Huster, Peter Lin, Razvan Stefanescu, Emmanuel Ekwedike, Ritu Chadha
Abstract: Neural networks can conceal malicious Trojan backdoors that allow a trigger to covertly change the model behavior. Detecting signs of these backdoors, particularly without access to any triggered data, is the subject of ongoing research and open challenges. In one common formulation of the problem, we are given a set of clean and poisoned models and need to predict whether a given test model is clean or poisoned. In this paper, we introduce a detector that works remarkably well across many of the existing datasets and domains. It is obtained by training a binary classifier on a large number of models' weights after performing a few different pre-processing steps including feature selection and standardization, reference model weights subtraction, and model alignment prior to detection. We evaluate this algorithm on a diverse set of Trojan detection benchmarks and domains and examine the cases where the approach is most and least effective.
Authors: Marco Wiedmann, Maniraman Periyasamy, Daniel D. Scherer
Abstract: VQC can be understood through the lens of Fourier analysis. It is already well-known that the function space represented by any circuit architecture can be described through a truncated Fourier sum. We show that the spectrum available to that truncated Fourier sum is not entirely determined by the encoding gates of the circuit, since the variational part of the circuit can constrain certain coefficients to zero, effectively removing that frequency from the spectrum. To the best of our knowledge, we give the first description of the functional dependence of the Fourier coefficients on the variational parameters as trigonometric polynomials. This allows us to provide an algorithm which computes the exact spectrum of any given circuit and the corresponding Fourier coefficients. Finally, we demonstrate that by comparing the Fourier transform of the dataset to the available spectra, it is possible to predict which \gls{VQC} out of a given list of choices will be able to best fit the data.
Authors: Alif Bin Abdul Qayyum, Susan D. Mertins, Amanda K. Paulson, Nathan M. Urban, Byung-Jun Yoon
Abstract: The data-driven drug design problem can be formulated as an optimization task of a potentially expensive black-box objective function over a huge high-dimensional and structured molecular space. The junction tree variational autoencoder (JTVAE) has been shown to be an efficient generative model that can be used for suggesting legitimate novel drug-like small molecules with improved properties. While the performance of the generative molecular design (GMD) scheme strongly depends on the initial training data, one can improve its sampling efficiency for suggesting better molecules with enhanced properties by optimizing the latent space. In this work, we propose how mechanistic models - such as pathway models described by differential equations - can be used for effective latent space optimization(LSO) of JTVAEs and other similar models for GMD. To demonstrate the potential of our proposed approach, we show how a pharmacodynamic model, assessing the therapeutic efficacy of a drug-like small molecule by predicting how it modulates a cancer pathway, can be incorporated for effective LSO of data-driven models for GMD.
Authors: Sai Surya Duvvuri, Inderjit S. Dhillon
Abstract: Transformers have had tremendous impact for several sequence related tasks, largely due to their ability to retrieve from any part of the sequence via softmax based dot-product attention. This mechanism plays a crucial role in Transformer's performance. We analyze the gradients backpropagated through the softmax operation in the attention mechanism and observe that these gradients can often be small. This poor gradient signal backpropagation can lead to inefficient learning of parameters preceeding the attention operations. To this end, we introduce a new attention mechanism called LASER, which we analytically show to admit a larger gradient signal. We show that LASER Attention can be implemented by making small modifications to existing attention implementations. We conduct experiments on autoregressive large language models (LLMs) with upto 2.2 billion parameters where we show upto 3.38% and an average of ~1% improvement over standard attention on downstream evaluations. Using LASER gives the following relative improvements in generalization performance across a variety of tasks (vision, text and speech): 4.67% accuracy in Vision Transformer (ViT) on Imagenet, 2.25% error rate in Conformer on the Librispeech speech-to-text and 0.93% fraction of incorrect predictions in BERT with 2.2 billion parameters.
Authors: Parikshit Bansal, Ali Kavis, Sujay Sanghavi
Abstract: Contrastive learning attempts to learn representations from un-labeled data; it does so via a loss function that encourages the embedding of a point to be close to that of its augmentations, and far from the embeddings of random other points. This simple idea performs remarkably well, yet it is not precisely theoretically understood why this is the case. In this paper we analyze contrastive learning (specifically, the InfoNCE loss) in a natural context: dimensionality reduction in Gaussian Mixture Models. Crucially, we define an augmentation of a data point as being another independent draw from the same underlying mixture component. We show that vanilla InfoNCE is able to find the optimal lower-dimensional subspace even when the Gaussians are not isotropic -- something that vanilla spectral techniques cannot do. We further extend our analyses to multi-modal contrastive learning algorithms (e.g., CLIP). In this setting we show that contrastive learning learns the subset of fisher-optimal subspace, effectively filtering out all the noise from the learnt representations.
Authors: Hanqing Zhu, Wenyan Cong, Guojin Chen, Shupeng Ning, Ray T. Chen, Jiaqi Gu, David Z. Pan
Abstract: Electromagnetic field simulation is central to designing, optimizing, and validating photonic devices and circuits. However, costly computation associated with numerical simulation poses a significant bottleneck, hindering scalability and turnaround time in the photonic circuit design process. Neural operators offer a promising alternative, but existing SOTA approaches, NeurOLight, struggle with predicting high-fidelity fields for real-world complicated photonic devices, with the best reported 0.38 normalized mean absolute error in NeurOLight. The inter-plays of highly complex light-matter interaction, e.g., scattering and resonance, sensitivity to local structure details, non-uniform learning complexity for full-domain simulation, and rich frequency information, contribute to the failure of existing neural PDE solvers. In this work, we boost the prediction fidelity to an unprecedented level for simulating complex photonic devices with a novel operator design driven by the above challenges. We propose a novel cross-axis factorized PACE operator with a strong long-distance modeling capacity to connect the full-domain complex field pattern with local device structures. Inspired by human learning, we further divide and conquer the simulation task for extremely hard cases into two progressively easy tasks, with a first-stage model learning an initial solution refined by a second model. On various complicated photonic device benchmarks, we demonstrate one sole PACE model is capable of achieving 73% lower error with 50% fewer parameters compared with various recent ML for PDE solvers. The two-stage setup further advances high-fidelity simulation for even more intricate cases. In terms of runtime, PACE demonstrates 154-577x and 11.8-12x simulation speedup over numerical solver using scipy or highly-optimized pardiso solver, respectively. We open sourced the code and dataset.
Authors: Kevin Tirta Wijaya, Minghao Guo, Michael Sun, Hans-Peter Seidel, Wojciech Matusik, Vahid Babaei
Abstract: Accurate property prediction is crucial for accelerating the discovery of new molecules. Although deep learning models have achieved remarkable success, their performance often relies on large amounts of labeled data that are expensive and time-consuming to obtain. Thus, there is a growing need for models that can perform well with limited experimentally-validated data. In this work, we introduce MoleVers, a versatile pretrained model designed for various types of molecular property prediction in the wild, i.e., where experimentally-validated molecular property labels are scarce. MoleVers adopts a two-stage pretraining strategy. In the first stage, the model learns molecular representations from large unlabeled datasets via masked atom prediction and dynamic denoising, a novel task enabled by a new branching encoder architecture. In the second stage, MoleVers is further pretrained using auxiliary labels obtained with inexpensive computational methods, enabling supervised learning without the need for costly experimental data. This two-stage framework allows MoleVers to learn representations that generalize effectively across various downstream datasets. We evaluate MoleVers on a new benchmark comprising 22 molecular datasets with diverse types of properties, the majority of which contain 50 or fewer training labels reflecting real-world conditions. MoleVers achieves state-of-the-art results on 20 out of the 22 datasets, and ranks second among the remaining two, highlighting its ability to bridge the gap between data-hungry models and real-world conditions where practically-useful labels are scarce.
Authors: Quinn Leng, Jacob Portes, Sam Havens, Matei Zaharia, Michael Carbin
Abstract: Retrieval Augmented Generation (RAG) has emerged as a crucial technique for enhancing the accuracy of Large Language Models (LLMs) by incorporating external information. With the advent of LLMs that support increasingly longer context lengths, there is a growing interest in understanding how these models perform in RAG scenarios. Can these new long context models improve RAG performance? This paper presents a comprehensive study of the impact of increased context length on RAG performance across 20 popular open source and commercial LLMs. We ran RAG workflows while varying the total context length from 2,000 to 128,000 tokens (and 2 million tokens when possible) on three domain-specific datasets, and report key insights on the benefits and limitations of long context in RAG applications. Our findings reveal that while retrieving more documents can improve performance, only a handful of the most recent state of the art LLMs can maintain consistent accuracy at long context above 64k tokens. We also identify distinct failure modes in long context scenarios, suggesting areas for future research.
Authors: Tanishq Kumar, Blake Bordelon, Cengiz Pehlevan, Venkatesh N. Murthy, Samuel J. Gershman
Abstract: Does learning of task-relevant representations stop when behavior stops changing? Motivated by recent theoretical advances in machine learning and the intuitive observation that human experts continue to learn from practice even after mastery, we hypothesize that task-specific representation learning can continue, even when behavior plateaus. In a novel reanalysis of recently published neural data, we find evidence for such learning in posterior piriform cortex of mice following continued training on a task, long after behavior saturates at near-ceiling performance ("overtraining"). This learning is marked by an increase in decoding accuracy from piriform neural populations and improved performance on held-out generalization tests. We demonstrate that class representations in cortex continue to separate during overtraining, so that examples that were incorrectly classified at the beginning of overtraining can abruptly be correctly classified later on, despite no changes in behavior during that time. We hypothesize this hidden yet rich learning takes the form of approximate margin maximization; we validate this and other predictions in the neural data, as well as build and interpret a simple synthetic model that recapitulates these phenomena. We conclude by showing how this model of late-time feature learning implies an explanation for the empirical puzzle of overtraining reversal in animal learning, where task-specific representations are more robust to particular task changes because the learned features can be reused.
Authors: Antoine Grosnit, Alexandre Maraval, James Doran, Giuseppe Paolo, Albert Thomas, Refinath Shahul Hameed Nabeezath Beevi, Jonas Gonzalez, Khyati Khandelwal, Ignacio Iacobacci, Abdelhakim Benechehab, Hamza Cherkaoui, Youssef Attia El-Hili, Kun Shao, Jianye Hao, Jun Yao, Balazs Kegl, Haitham Bou-Ammar, Jun Wang
Abstract: We introduce Agent K v1.0, an end-to-end autonomous data science agent designed to automate, optimise, and generalise across diverse data science tasks. Fully automated, Agent K v1.0 manages the entire data science life cycle by learning from experience. It leverages a highly flexible structured reasoning framework to enable it to dynamically process memory in a nested structure, effectively learning from accumulated experience stored to handle complex reasoning tasks. It optimises long- and short-term memory by selectively storing and retrieving key information, guiding future decisions based on environmental rewards. This iterative approach allows it to refine decisions without fine-tuning or backpropagation, achieving continuous improvement through experiential learning. We evaluate our agent's apabilities using Kaggle competitions as a case study. Following a fully automated protocol, Agent K v1.0 systematically addresses complex and multimodal data science tasks, employing Bayesian optimisation for hyperparameter tuning and feature engineering. Our new evaluation framework rigorously assesses Agent K v1.0's end-to-end capabilities to generate and send submissions starting from a Kaggle competition URL. Results demonstrate that Agent K v1.0 achieves a 92.5\% success rate across tasks, spanning tabular, computer vision, NLP, and multimodal domains. When benchmarking against 5,856 human Kaggle competitors by calculating Elo-MMR scores for each, Agent K v1.0 ranks in the top 38\%, demonstrating an overall skill level comparable to Expert-level users. Notably, its Elo-MMR score falls between the first and third quartiles of scores achieved by human Grandmasters. Furthermore, our results indicate that Agent K v1.0 has reached a performance level equivalent to Kaggle Grandmaster, with a record of 6 gold, 3 silver, and 7 bronze medals, as defined by Kaggle's progression system.
Authors: Pengju Wang, Bochao Liu, Weijia Guo, Yong Li, Shiming Ge
Abstract: Federated learning is a distributed machine learning paradigm designed to protect data privacy. However, data heterogeneity across various clients results in catastrophic forgetting, where the model rapidly forgets previous knowledge while acquiring new knowledge. To address this challenge, personalized federated learning has emerged to customize a personalized model for each client. However, the inherent limitation of this mechanism is its excessive focus on personalization, potentially hindering the generalization of those models. In this paper, we present a novel personalized federated learning method that uses global and historical models as teachers and the local model as the student to facilitate comprehensive knowledge distillation. The historical model represents the local model from the last round of client training, containing historical personalized knowledge, while the global model represents the aggregated model from the last round of server aggregation, containing global generalized knowledge. By applying knowledge distillation, we effectively transfer global generalized knowledge and historical personalized knowledge to the local model, thus mitigating catastrophic forgetting and enhancing the general performance of personalized models. Extensive experimental results demonstrate the significant advantages of our method.
Authors: Qiyuan Zhu, A. K. Qin, Hussein Dia, Adriana-Simona Mihaita, Hanna Grzybowska
Abstract: Traffic flow forecasting is a crucial task in intelligent transport systems. Deep learning offers an effective solution, capturing complex patterns in time-series traffic flow data to enable the accurate prediction. However, deep learning models are prone to overfitting the intricate details of flow data, leading to poor generalisation. Recent studies suggest that decomposition-based deep ensemble learning methods may address this issue by breaking down a time series into multiple simpler signals, upon which deep learning models are built and ensembled to generate the final prediction. However, few studies have compared the performance of decomposition-based ensemble methods with non-decomposition-based ones which directly utilise raw time-series data. This work compares several decomposition-based and non-decomposition-based deep ensemble learning methods. Experimental results on three traffic datasets demonstrate the superiority of decomposition-based ensemble methods, while also revealing their sensitivity to aggregation strategies and forecasting horizons.
Authors: Benedict Aaron Tjandra, Federico Barbero, Michael Bronstein
Abstract: Despite the successful application of Temporal Graph Networks (TGNs) for tasks such as dynamic node classification and link prediction, they still perform poorly on the task of dynamic node affinity prediction -- where the goal is to predict `how much' two nodes will interact in the future. In fact, simple heuristic approaches such as persistent forecasts and moving averages over \emph{ground-truth labels} significantly and consistently outperform TGNs. Building on this observation, we find that computing heuristics \textit{over messages} is an equally competitive approach, outperforming TGN and all current temporal graph (TG) models on dynamic node affinity prediction. In this paper, we prove that no formulation of TGN can represent persistent forecasting or moving averages over messages, and propose to enhance the expressivity of TGNs by adding source-target identification to each interaction event message. We show that this modification is required to represent persistent forecasting, moving averages, and the broader class of autoregressive models over messages. Our proposed method, TGNv2, significantly outperforms TGN and all current TG models on all Temporal Graph Benchmark (TGB) dynamic node affinity prediction datasets.
Authors: Tyler E. Korenyi-Both, Nathan J. Falkiewicz, Matthew C. Jones
Abstract: High-speed flight vehicles, which travel much faster than the speed of sound, are crucial for national defense and space exploration. However, accurately predicting their behavior under numerous, varied flight conditions is a challenge and often prohibitively expensive. The proposed approach involves creating smarter, more efficient machine learning models (also known as surrogate models or meta models) that can fuse data generated from a variety of fidelity levels -- to include engineering methods, simulation, wind tunnel, and flight test data -- to make more accurate predictions. These models are able to move the bulk of the computation from high performance computing (HPC) to single user machines (laptop, desktop, etc.). The project builds upon previous work but introduces code improvements and an informed perspective on the direction of the field. The new surrogate modeling framework is now modular and, by design, broadly applicable to many modeling problems. The new framework also has a more robust automatic hyperparameter tuning capability and abstracts away most of the pre- and post-processing tasks. The Gaussian process regression and deep neural network-based models included in the presented framework were able to model two datasets with high accuracy (R^2>0.99). The primary conclusion is that the framework is effective and has been delivered to the Air Force for integration into real-world projects. For future work, significant and immediate investment in continued research is crucial. The author recommends further testing and refining modeling methods that explicitly incorporate physical laws and are robust enough to handle simulation and test data from varying resolutions and sources, including coarse meshes, fine meshes, unstructured meshes, and limited experimental test points.
Authors: Jonas Guan, Shon Eduard Verch, Claas Voelcker, Ethan C. Jackson, Nicolas Papernot, William A. Cunningham
Abstract: A computational problem in biological reward-based learning is how credit assignment is performed in the nucleus accumbens (NAc). Much research suggests that NAc dopamine encodes temporal-difference (TD) errors for learning value predictions. However, dopamine is synchronously distributed in regionally homogeneous concentrations, which does not support explicit credit assignment (like used by backpropagation). It is unclear whether distributed errors alone are sufficient for synapses to make coordinated updates to learn complex, nonlinear reward-based learning tasks. We design a new deep Q-learning algorithm, Artificial Dopamine, to computationally demonstrate that synchronously distributed, per-layer TD errors may be sufficient to learn surprisingly complex RL tasks. We empirically evaluate our algorithm on MinAtar, the DeepMind Control Suite, and classic control tasks, and show it often achieves comparable performance to deep RL algorithms that use backpropagation.
Authors: Wenjun Wang, Jiacheng Lu, Kejia Chen, Zheng Liu, Shilong Sang
Abstract: Graph similarity computation (GSC) aims to quantify the similarity score between two graphs. Although recent GSC methods based on graph neural networks (GNNs) take advantage of intra-graph structures in message passing, few of them fully utilize the structures presented by edges to boost the representation of their connected nodes. Moreover, previous cross-graph node embedding matching lacks the perception of the overall structure of the graph pair, due to the fact that the node representations from GNNs are confined to the intra-graph structure, causing the unreasonable similarity score. Intuitively, the cross-graph structure represented in the assignment graph is helpful to rectify the inappropriate matching. Therefore, we propose a structure-enhanced graph matching network (SEGMN). Equipped with a dual embedding learning module and a structure perception matching module, SEGMN achieves structure enhancement in both embedding learning and cross-graph matching. The dual embedding learning module incorporates adjacent edge representation into each node to achieve a structure-enhanced representation. The structure perception matching module achieves cross-graph structure enhancement through assignment graph convolution. The similarity score of each cross-graph node pair can be rectified by aggregating messages from structurally relevant node pairs. Experimental results on benchmark datasets demonstrate that SEGMN outperforms the state-of-the-art GSC methods in the GED regression task, and the structure perception matching module is plug-and-play, which can further improve the performance of the baselines by up to 25%.
Authors: Diantong Li, Fengxue Zhang, Chong Liu, Yuxin Chen
Abstract: Multi-objective Bayesian optimization has been widely adopted in scientific experiment design, including drug discovery and hyperparameter optimization. In practice, regulatory or safety concerns often impose additional thresholds on certain attributes of the experimental outcomes. Previous work has primarily focused on constrained single-objective optimization tasks or active search under constraints. We propose CMOBO, a sample-efficient constrained multi-objective Bayesian optimization algorithm that balances learning of the feasible region (defined on multiple unknowns) with multi-objective optimization within the feasible region in a principled manner. We provide both theoretical justification and empirical evidence, demonstrating the efficacy of our approach on various synthetic benchmarks and real-world applications.
Authors: Hanyang Yuan, Jiarong Xu, Renhong Huang, Mingli Song, Chunping Wang, Yang Yang
Abstract: Graph neural networks (GNNs) have attracted considerable attention due to their diverse applications. However, the scarcity and quality limitations of graph data present challenges to their training process in practical settings. To facilitate the development of effective GNNs, companies and researchers often seek external collaboration. Yet, directly sharing data raises privacy concerns, motivating data owners to train GNNs on their private graphs and share the trained models. Unfortunately, these models may still inadvertently disclose sensitive properties of their training graphs (e.g., average default rate in a transaction network), leading to severe consequences for data owners. In this work, we study graph property inference attack to identify the risk of sensitive property information leakage from shared models. Existing approaches typically train numerous shadow models for developing such attack, which is computationally intensive and impractical. To address this issue, we propose an efficient graph property inference attack by leveraging model approximation techniques. Our method only requires training a small set of models on graphs, while generating a sufficient number of approximated shadow models for attacks. To enhance diversity while reducing errors in the approximated models, we apply edit distance to quantify the diversity within a group of approximated models and introduce a theoretically guaranteed criterion to evaluate each model's error. Subsequently, we propose a novel selection mechanism to ensure that the retained approximated models achieve high diversity and low error. Extensive experiments across six real-world scenarios demonstrate our method's substantial improvement, with average increases of 2.7% in attack accuracy and 4.1% in ROC-AUC, while being 6.5$\times$ faster compared to the best baseline.
Authors: Erfan Hajihashemi, Yanning Shen
Abstract: Conformal prediction is an uncertainty quantification method that constructs a prediction set for a previously unseen datum, ensuring the true label is included with a predetermined coverage probability. Adaptive conformal prediction has been developed to address data distribution shifts in dynamic environments. However, the efficiency of prediction sets varies depending on the learning model used. Employing a single fixed model may not consistently offer the best performance in dynamic environments with unknown data distribution shifts. To address this issue, we introduce a novel adaptive conformal prediction framework, where the model used for creating prediction sets is selected on the fly from multiple candidate models. The proposed algorithm is proven to achieve strongly adaptive regret over all intervals while maintaining valid coverage. Experiments on real and synthetic datasets corroborate that the proposed approach consistently yields more efficient prediction sets while maintaining valid coverage, outperforming alternative methods.
Authors: Zehao Xiao, Cees G. M. Snoek
Abstract: Machine learning algorithms have achieved remarkable success across various disciplines, use cases and applications, under the prevailing assumption that training and test samples are drawn from the same distribution. Consequently, these algorithms struggle and become brittle even when samples in the test distribution start to deviate from the ones observed during training. Domain adaptation and domain generalization have been studied extensively as approaches to address distribution shifts across test and train domains, but each has its limitations. Test-time adaptation, a recently emerging learning paradigm, combines the benefits of domain adaptation and domain generalization by training models only on source data and adapting them to target data during test-time inference. In this survey, we provide a comprehensive and systematic review on test-time adaptation, covering more than 400 recent papers. We structure our review by categorizing existing methods into five distinct categories based on what component of the method is adjusted for test-time adaptation: the model, the inference, the normalization, the sample, or the prompt, providing detailed analysis of each. We further discuss the various preparation and adaptation settings for methods within these categories, offering deeper insights into the effective deployment for the evaluation of distribution shifts and their real-world application in understanding images, video and 3D, as well as modalities beyond vision. We close the survey with an outlook on emerging research opportunities for test-time adaptation.
Authors: Long Shi, Chuanqing Tang, Huangyi Deng, Cai Xu, Lei Xing, Badong Chen
Abstract: Recently, multi-view learning has witnessed a considerable interest on the research of trusted decision-making. Previous methods are mainly inspired from an important paper published by Han et al. in 2021, which formulates a Trusted Multi-view Classification (TMC) framework that aggregates evidence from different views based on Dempster's combination rule. All these methods only consider inter-view aggregation, yet lacking exploitation of intra-view information. In this paper, we propose a generalized trusted multi-view classification framework with hierarchical opinion aggregation. This hierarchical framework includes a two-phase aggregation process: the intra-view and inter-view aggregation hierarchies. In the intra aggregation, we assume that each view is comprised of common information shared with other views, as well as its specific information. We then aggregate both the common and specific information. This aggregation phase is useful to eliminate the feature noise inherent to view itself, thereby improving the view quality. In the inter-view aggregation, we design an attention mechanism at the evidence level to facilitate opinion aggregation from different views. To the best of our knowledge, this is one of the pioneering efforts to formulate a hierarchical aggregation framework in the trusted multi-view learning domain. Extensive experiments show that our model outperforms some state-of-art trust-related baselines.
Authors: Michael Merry, Patricia Riddle, Jim Warren
Abstract: We introduce PropNEAT, a fast backpropagation implementation of NEAT that uses a bidirectional mapping of the genome graph to a layer-based architecture that preserves the NEAT genomes whilst enabling efficient GPU backpropagation. We test PropNEAT on 58 binary classification datasets from the Penn Machine Learning Benchmarks database, comparing the performance against logistic regression, dense neural networks and random forests, as well as a densely retrained variant of the final PropNEAT model. PropNEAT had the second best overall performance, behind Random Forest, though the difference between the models was not statistically significant apart from between Random Forest in comparison with logistic regression and the PropNEAT retrain models. PropNEAT was substantially faster than a naive backpropagation method, and both were substantially faster and had better performance than the original NEAT implementation. We demonstrate that the per-epoch training time for PropNEAT scales linearly with network depth, and is efficient on GPU implementations for backpropagation. This implementation could be extended to support reinforcement learning or convolutional networks, and is able to find sparser and smaller networks with potential for applications in low-power contexts.
Authors: Marlon Tobaben, Mohamed Ali Souibgui, Rub\`en Tito, Khanh Nguyen, Raouf Kerkouche, Kangsoo Jung, Joonas J\"alk\"o, Lei Kang, Andrey Barsky, Vincent Poulain d'Andecy, Aur\'elie Joseph, Aashiq Muhamed, Kevin Kuo, Virginia Smith, Yusuke Yamasaki, Takumi Fukami, Kenta Niwa, Iifan Tyou, Hiro Ishii, Rio Yokota, Ragul N, Rintu Kutum, Josep Llados, Ernest Valveny, Antti Honkela, Mario Fritz, Dimosthenis Karatzas
Abstract: The Privacy Preserving Federated Learning Document VQA (PFL-DocVQA) competition challenged the community to develop provably private and communication-efficient solutions in a federated setting for a real-life use case: invoice processing. The competition introduced a dataset of real invoice documents, along with associated questions and answers requiring information extraction and reasoning over the document images. Thereby, it brings together researchers and expertise from the document analysis, privacy, and federated learning communities. Participants fine-tuned a pre-trained, state-of-the-art Document Visual Question Answering model provided by the organizers for this new domain, mimicking a typical federated invoice processing setup. The base model is a multi-modal generative language model, and sensitive information could be exposed through either the visual or textual input modality. Participants proposed elegant solutions to reduce communication costs while maintaining a minimum utility threshold in track 1 and to protect all information from each document provider using differential privacy in track 2. The competition served as a new testbed for developing and testing private federated learning methods, simultaneously raising awareness about privacy within the document image analysis and recognition community. Ultimately, the competition analysis provides best practices and recommendations for successfully running privacy-focused federated learning challenges in the future.
Authors: Abdelmajid Essofi, Ridwan Salahuddeen, Munachiso Nwadike, Elnura Zhalieva, Kun Zhang, Eric Xing, Willie Neiswanger, Qirong Ho
Abstract: The training or fine-tuning of machine learning, vision, and language models is often implemented as a pipeline: a sequence of stages encompassing data preparation, model training and evaluation. In this paper, we exploit pipeline structures to reduce the cost of hyperparameter tuning for model training/fine-tuning, which is particularly valuable for language models given their high costs in GPU-days. We propose a "memoization-aware" Bayesian Optimization (BO) algorithm, EEIPU, that works in tandem with a pipeline caching system, allowing it to evaluate significantly more hyperparameter candidates per GPU-day than other tuning algorithms. The result is better-quality hyperparameters in the same amount of search time, or equivalently, reduced search time to reach the same hyperparameter quality. In our benchmarks on machine learning (model ensembles), vision (convolutional architecture) and language (T5 architecture) pipelines, we compare EEIPU against recent BO algorithms: EEIPU produces an average of $103\%$ more hyperparameter candidates (within the same budget), and increases the validation metric by an average of $108\%$ more than other algorithms (where the increase is measured starting from the end of warm-up iterations).
Authors: Md Abrar Jahin, M. F. Mridha, Nilanjan Dey
Abstract: Feature selection is critical for improving the performance and interpretability of machine learning models, particularly in high-dimensional spaces where complex feature interactions can reduce accuracy and increase computational demands. Existing approaches often rely on static feature subsets or manual intervention, limiting adaptability and scalability. However, dynamic, per-instance feature selection methods and model-specific interpretability in reinforcement learning remain underexplored. This study proposes a human-in-the-loop (HITL) feature selection framework integrated into a Double Deep Q-Network (DDQN) using a Kolmogorov-Arnold Network (KAN). Our novel approach leverages simulated human feedback and stochastic distribution-based sampling, specifically Beta, to iteratively refine feature subsets per data instance, improving flexibility in feature selection. The KAN-DDQN achieved notable test accuracies of 93% on MNIST and 83% on FashionMNIST, outperforming conventional MLP-DDQN models by up to 9%. The KAN-based model provided high interpretability via symbolic representation while using 4 times fewer neurons in the hidden layer than MLPs did. Comparatively, the models without feature selection achieved test accuracies of only 58% on MNIST and 64% on FashionMNIST, highlighting significant gains with our framework. Pruning and visualization further enhanced model transparency by elucidating decision pathways. These findings present a scalable, interpretable solution for feature selection that is suitable for applications requiring real-time, adaptive decision-making with minimal human oversight.
Authors: Yoni Choukroun, Shlomi Azoulay, Pavel Kisilev
Abstract: Distributed machine learning has recently become a critical paradigm for training large models on vast datasets. We examine the stochastic optimization problem for deep learning within synchronous parallel computing environments under communication constraints. While averaging distributed gradients is the most widely used method for gradient estimation, whether this is the optimal strategy remains an open question. In this work, we analyze the distributed gradient aggregation process through the lens of subspace optimization. By formulating the aggregation problem as an objective-aware subspace optimization problem, we derive an efficient weighting scheme for gradients, guided by subspace coefficients. We further introduce subspace momentum to accelerate convergence while maintaining statistical unbiasedness in the aggregation. Our method demonstrates improved performance over the ubiquitous gradient averaging on multiple MLPerf tasks while remaining extremely efficient in both communicational and computational complexity.
Authors: Shuangjie Li, Baoming Zhang, Jianqing Song, Gaoli Ruan, Chongjun Wang, Junyuan Xie
Abstract: Graph Neural Networks (GNNs) have gained considerable prominence in semi-supervised learning tasks in processing graph-structured data, primarily owing to their message-passing mechanism, which largely relies on the availability of clean labels. However, in real-world scenarios, labels on nodes of graphs are inevitably noisy and sparsely labeled, significantly degrading the performance of GNNs. Exploring robust GNNs for semi-supervised node classification in the presence of noisy and sparse labels remains a critical challenge. Therefore, we propose a novel \textbf{G}raph \textbf{N}eural \textbf{N}etwork with \textbf{C}oarse- and \textbf{F}ine-\textbf{G}rained \textbf{D}ivision for mitigating label sparsity and noise, namely GNN-CFGD. The key idea of GNN-CFGD is reducing the negative impact of noisy labels via coarse- and fine-grained division, along with graph reconstruction. Specifically, we first investigate the effectiveness of linking unlabeled nodes to cleanly labeled nodes, demonstrating that this approach is more effective in combating labeling noise than linking to potentially noisy labeled nodes. Based on this observation, we introduce a Gaussian Mixture Model (GMM) based on the memory effect to perform a coarse-grained division of the given labels into clean and noisy labels. Next, we propose a clean labels oriented link that connects unlabeled nodes to cleanly labeled nodes, aimed at mitigating label sparsity and promoting supervision propagation. Furthermore, to provide refined supervision for noisy labeled nodes and additional supervision for unlabeled nodes, we fine-grain the noisy labeled and unlabeled nodes into two candidate sets based on confidence, respectively. Extensive experiments on various datasets demonstrate the superior effectiveness and robustness of GNN-CFGD.
Authors: Yuxiao Chen, Gamze G\"ursoy, Qi Lei
Abstract: Federated Learning (FL) is designed to prevent data leakage through collaborative model training without centralized data storage. However, it remains vulnerable to gradient reconstruction attacks that recover original training data from shared gradients. To optimize the trade-off between data leakage and utility loss, we first derive a theoretical lower bound of reconstruction error (among all attackers) for the two standard methods: adding noise, and gradient pruning. We then customize these two defenses to be parameter- and model-specific and achieve the optimal trade-off between our obtained reconstruction lower bound and model utility. Experimental results validate that our methods outperform Gradient Noise and Gradient Pruning by protecting the training data better while also achieving better utility.
Authors: Yuhao He, Jinyu Tian, Xianwei Zheng, Li Dong, Yuanman Li, Leo Yu Zhang, Jiantao Zhou
Abstract: Recent studies have shown that deep learning models are very vulnerable to poisoning attacks. Many defense methods have been proposed to address this issue. However, traditional poisoning attacks are not as threatening as commonly believed. This is because they often cause differences in how the model performs on the training set compared to the validation set. Such inconsistency can alert defenders that their data has been poisoned, allowing them to take the necessary defensive actions. In this paper, we introduce a more threatening type of poisoning attack called the Deferred Poisoning Attack. This new attack allows the model to function normally during the training and validation phases but makes it very sensitive to evasion attacks or even natural noise. We achieve this by ensuring the poisoned model's loss function has a similar value as a normally trained model at each input sample but with a large local curvature. A similar model loss ensures that there is no obvious inconsistency between the training and validation accuracy, demonstrating high stealthiness. On the other hand, the large curvature implies that a small perturbation may cause a significant increase in model loss, leading to substantial performance degradation, which reflects a worse robustness. We fulfill this purpose by making the model have singular Hessian information at the optimal point via our proposed Singularization Regularization term. We have conducted both theoretical and empirical analyses of the proposed method and validated its effectiveness through experiments on image classification tasks. Furthermore, we have confirmed the hazards of this form of poisoning attack under more general scenarios using natural noise, offering a new perspective for research in the field of security.
Authors: Zihan Yu, Jingtao Ding, Yong Li
Abstract: Symbolic regression, a task discovering the formula best fitting the given data, is typically based on the heuristical search. These methods usually update candidate formulas to obtain new ones with lower prediction errors iteratively. However, since formulas with similar function shapes may have completely different symbolic forms, the prediction error does not decrease monotonously as the search approaches the target formula, causing the low recovery rate of existing methods. To solve this problem, we propose a novel search objective based on the minimum description length, which reflects the distance from the target and decreases monotonically as the search approaches the correct form of the target formula. To estimate the minimum description length of any input data, we design a neural network, MDLformer, which enables robust and scalable estimation through large-scale training. With the MDLformer's output as the search objective, we implement a symbolic regression method, SR4MDL, that can effectively recover the correct mathematical form of the formula. Extensive experiments illustrate its excellent performance in recovering formulas from data. Our method successfully recovers around 50 formulas across two benchmark datasets comprising 133 problems, outperforming state-of-the-art methods by 43.92%.
Authors: Sagar Shrestha, Xiao Fu
Abstract: Understanding identifiability of latent content and style variables from unaligned multi-domain data is essential for tasks such as domain translation and data generation. Existing works on content-style identification were often developed under somewhat stringent conditions, e.g., that all latent components are mutually independent and that the dimensions of the content and style variables are known. We introduce a new analytical framework via cross-domain \textit{latent distribution matching} (LDM), which establishes content-style identifiability under substantially more relaxed conditions. Specifically, we show that restrictive assumptions such as component-wise independence of the latent variables can be removed. Most notably, we prove that prior knowledge of the content and style dimensions is not necessary for ensuring identifiability, if sparsity constraints are properly imposed onto the learned latent representations. Bypassing the knowledge of the exact latent dimension has been a longstanding aspiration in unsupervised representation learning -- our analysis is the first to underpin its theoretical and practical viability. On the implementation side, we recast the LDM formulation into a regularized multi-domain GAN loss with coupled latent variables. We show that the reformulation is equivalent to LDM under mild conditions -- yet requiring considerably less computational resource. Experiments corroborate with our theoretical claims.
Authors: Xinnuo Xu, Minyoung Kim, Royson Lee, Brais Martinez, Timothy Hospedales
Abstract: Data point selection (DPS) is becoming a critical topic in deep learning due to the ease of acquiring uncurated training data compared to the difficulty of obtaining curated or processed data. Existing approaches to DPS are predominantly based on a bi-level optimisation (BLO) formulation, which is demanding in terms of memory and computation, and exhibits some theoretical defects regarding minibatches. Thus, we propose a novel Bayesian approach to DPS. We view the DPS problem as posterior inference in a novel Bayesian model where the posterior distributions of the instance-wise weights and the main neural network parameters are inferred under a reasonable prior and likelihood model. We employ stochastic gradient Langevin MCMC sampling to learn the main network and instance-wise weights jointly, ensuring convergence even with minibatches. Our update equation is comparable to the widely used SGD and much more efficient than existing BLO-based methods. Through controlled experiments in both the vision and language domains, we present the proof-of-concept. Additionally, we demonstrate that our method scales effectively to large language models and facilitates automated per-task optimization for instruction fine-tuning datasets.
Authors: Lawrence Stewart (SIERRA), Matthew Trager (UCLA-CS), Sujan Kumar Gonugondla (UCLA-CS), Stefano Soatto (UCLA-CS)
Abstract: Speculative decoding aims to speed up autoregressive generation of a language model by verifying in parallel the tokens generated by a smaller draft model.In this work, we explore the effectiveness of learning-free, negligible-cost draft strategies, namely $N$-grams obtained from the model weights and the context. While the predicted next token of the base model is rarely the top prediction of these simple strategies, we observe that it is often within their top-$k$ predictions for small $k$. Based on this, we show that combinations of simple strategies can achieve significant inference speedups over different tasks. The overall performance is comparable to more complex methods, yet does not require expensive preprocessing or modification of the base model, and allows for seamless `plug-and-play' integration into pipelines.
Authors: Edvin Listo Zec, Adam Breitholtz, Fredrik D. Johansson
Abstract: Federated learning enables multiple actors to collaboratively train models without sharing private data. This unlocks the potential for scaling machine learning to diverse applications. Existing algorithms for this task are well-justified when clients and the intended target domain share the same distribution of features and labels, but this assumption is often violated in real-world scenarios. One common violation is label shift, where the label distributions differ across clients or between clients and the target domain, which can significantly degrade model performance. To address this problem, we propose FedPALS, a novel model aggregation scheme that adapts to label shifts by leveraging knowledge of the target label distribution at the central server. Our approach ensures unbiased updates under stochastic gradient descent, ensuring robust generalization across clients with diverse, label-shifted data. Extensive experiments on image classification demonstrate that FedPALS consistently outperforms standard baselines by aligning model aggregation with the target domain. Our findings reveal that conventional federated learning methods suffer severely in cases of extreme client sparsity, highlighting the critical need for target-aware aggregation. FedPALS offers a principled and practical solution to mitigate label distribution mismatch, ensuring models trained in federated settings can generalize effectively to label-shifted target domains.
Authors: Chengrui Qu, Laixi Shi, Kishan Panaganti, Pengcheng You, Adam Wierman
Abstract: Online Reinforcement learning (RL) typically requires high-stakes online interaction data to learn a policy for a target task. This prompts interest in leveraging historical data to improve sample efficiency. The historical data may come from outdated or related source environments with different dynamics. It remains unclear how to effectively use such data in the target task to provably enhance learning and sample efficiency. To address this, we propose a hybrid transfer RL (HTRL) setting, where an agent learns in a target environment while accessing offline data from a source environment with shifted dynamics. We show that -- without information on the dynamics shift -- general shifted-dynamics data, even with subtle shifts, does not reduce sample complexity in the target environment. However, with prior information on the degree of the dynamics shift, we design HySRL, a transfer algorithm that achieves problem-dependent sample complexity and outperforms pure online RL. Finally, our experimental results demonstrate that HySRL surpasses state-of-the-art online RL baseline.
Authors: Kai Sandbrink, Jan P. Bauer, Alexandra M. Proca, Andrew M. Saxe, Christopher Summerfield, Ali Hummos
Abstract: Animals survive in dynamic environments changing at arbitrary timescales, but such data distribution shifts are a challenge to neural networks. To adapt to change, neural systems may change a large number of parameters, which is a slow process involving forgetting past information. In contrast, animals leverage distribution changes to segment their stream of experience into tasks and associate them with internal task abstracts. Animals can then respond flexibly by selecting the appropriate task abstraction. However, how such flexible task abstractions may arise in neural systems remains unknown. Here, we analyze a linear gated network where the weights and gates are jointly optimized via gradient descent, but with neuron-like constraints on the gates including a faster timescale, nonnegativity, and bounded activity. We observe that the weights self-organize into modules specialized for tasks or sub-tasks encountered, while the gates layer forms unique representations that switch the appropriate weight modules (task abstractions). We analytically reduce the learning dynamics to an effective eigenspace, revealing a virtuous cycle: fast adapting gates drive weight specialization by protecting previous knowledge, while weight specialization in turn increases the update rate of the gating layer. Task switching in the gating layer accelerates as a function of curriculum block size and task training, mirroring key findings in cognitive neuroscience. We show that the discovered task abstractions support generalization through both task and subtask composition, and we extend our findings to a non-linear network switching between two tasks. Overall, our work offers a theory of cognitive flexibility in animals as arising from joint gradient descent on synaptic and neural gating in a neural network architecture.
Authors: Weishuo Ma, Yanbo Wang, Xiyuan Wang, Muhan Zhang
Abstract: Various graph neural networks (GNNs) with advanced training techniques and model designs have been proposed for link prediction tasks. However, outdated baseline models may lead to an overestimation of the benefits provided by these novel approaches. To address this, we systematically investigate the potential of Graph Autoencoders (GAE) by meticulously tuning hyperparameters and utilizing the trick of orthogonal embedding and linear propagation. Our findings reveal that a well-optimized GAE can match the performance of more complex models while offering greater computational efficiency.
Authors: Kiran Purohit, Venktesh V, Raghuram Devalla, Krishna Mohan Yerragorla, Sourangshu Bhattacharya, Avishek Anand
Abstract: Answering reasoning-based complex questions over text and hybrid sources, including tables, is a challenging task. Recent advances in large language models (LLMs) have enabled in-context learning (ICL), allowing LLMs to acquire proficiency in a specific task using only a few demonstration samples (exemplars). A critical challenge in ICL is the selection of optimal exemplars, which can be either task-specific (static) or test-example-specific (dynamic). Static exemplars provide faster inference times and increased robustness across a distribution of test examples. In this paper, we propose an algorithm for static exemplar subset selection for complex reasoning tasks. We introduce EXPLORA, a novel exploration method designed to estimate the parameters of the scoring function, which evaluates exemplar subsets without incorporating confidence information. EXPLORA significantly reduces the number of LLM calls to ~11% of those required by state-of-the-art methods and achieves a substantial performance improvement of 12.24%. We open-source our code and data (https://github.com/kiranpurohit/EXPLORA).
Authors: S. Ali, A. S. Ryzhikov, D. A. Derkach, F. D. Ratnikov, V. O. Bocharnikov
Abstract: In the realm of high-energy physics, the longevity of calorimeters is paramount. Our research introduces a deep learning strategy to refine the calibration process of calorimeters used in particle physics experiments. We develop a Wasserstein GAN inspired methodology that adeptly calibrates the misalignment in calorimeter data due to aging or other factors. Leveraging the Wasserstein distance for loss calculation, this innovative approach requires a significantly lower number of events and resources to achieve high precision, minimizing absolute errors effectively. Our work extends the operational lifespan of calorimeters, thereby ensuring the accuracy and reliability of data in the long term, and is particularly beneficial for experiments where data integrity is crucial for scientific discovery.
Authors: Oliver Knitter, Dan Zhao, James Stokes, Martin Ganahl, Stefan Leichenauer, Shravan Veerapaneni
Abstract: Neural-network quantum states (NQS) has emerged as a powerful application of quantum-inspired deep learning for variational Monte Carlo methods, offering a competitive alternative to existing techniques for identifying ground states of quantum problems. A significant advancement toward improving the practical scalability of NQS has been the incorporation of autoregressive models, most recently transformers, as variational ansatze. Transformers learn sequence information with greater expressiveness than recurrent models, but at the cost of increased time complexity with respect to sequence length. We explore the use of the retentive network (RetNet), a recurrent alternative to transformers, as an ansatz for solving electronic ground state problems in $\textit{ab initio}$ quantum chemistry. Unlike transformers, RetNets overcome this time complexity bottleneck by processing data in parallel during training, and recurrently during inference. We give a simple computational cost estimate of the RetNet and directly compare it with similar estimates for transformers, establishing a clear threshold ratio of problem-to-model size past which the RetNet's time complexity outperforms that of the transformer. Though this efficiency can comes at the expense of decreased expressiveness relative to the transformer, we overcome this gap through training strategies that leverage the autoregressive structure of the model -- namely, variational neural annealing. Our findings support the RetNet as a means of improving the time complexity of NQS without sacrificing accuracy. We provide further evidence that the ablative improvements of neural annealing extend beyond the RetNet architecture, suggesting it would serve as an effective general training strategy for autoregressive NQS.
Authors: Debbie Lim, Yixian Qiu, Patrick Rebentrost, Qisheng Wang
Abstract: Logistic regression, the Support Vector Machine (SVM), and least squares are well-studied methods in the statistical and computer science community, with various practical applications. High-dimensional data arriving on a real-time basis makes the design of online learning algorithms that produce sparse solutions essential. The seminal work of \hyperlink{cite.langford2009sparse}{Langford, Li, and Zhang (2009)} developed a method to obtain sparsity via truncated gradient descent, showing a near-optimal online regret bound. Based on this method, we develop a quantum sparse online learning algorithm for logistic regression, the SVM, and least squares. Given efficient quantum access to the inputs, we show that a quadratic speedup in the time complexity with respect to the dimension of the problem is achievable, while maintaining a regret of $O(1/\sqrt{T})$, where $T$ is the number of iterations.
Authors: Khasmamad Shabanovi, Lukas Wiest, Vladimir Golkov, Daniel Cremers, Thomas Pfeil
Abstract: Post-training quantization is widely employed to reduce the computational demands of neural networks. Typically, individual substructures, such as layers or blocks of layers, are quantized with the objective of minimizing quantization errors in their pre-activations by fine-tuning the corresponding weights. Deriving this local objective from the global objective of minimizing task loss involves two key simplifications: assuming substructures are mutually independent and ignoring the knowledge of subsequent substructures as well as the task loss. In this work, we assess the effects of these simplifications on weight-only quantization of large language models. We introduce two multi-block fine-tuning strategies and compare them against the baseline of fine-tuning single transformer blocks. The first captures correlations of weights across blocks by jointly optimizing multiple quantized blocks. The second incorporates knowledge of subsequent blocks by minimizing the error in downstream pre-activations rather than focusing solely on the quantized block. Our findings indicate that the effectiveness of these methods depends on the specific network model, with no impact on some models but demonstrating significant benefits for others.
Authors: Kutay B\"olat, Simon Tindemans
Abstract: Generative modelling of multi-user datasets has become prominent in science and engineering. Generating a data point for a given user requires employing user information, and conventional generative models, including variational autoencoders (VAEs), often ignore that. This paper introduces GUIDE-VAE, a novel conditional generative model that leverages user embeddings to generate user-guided data. By allowing the model to benefit from shared patterns across users, GUIDE-VAE enhances performance in multi-user settings, even under significant data imbalance. In addition to integrating user information, GUIDE-VAE incorporates a pattern dictionary-based covariance composition (PDCC) to improve the realism of generated samples by capturing complex feature dependencies. While user embeddings drive performance gains, PDCC addresses common issues such as noise and over-smoothing typically seen in VAEs. The proposed GUIDE-VAE was evaluated on a multi-user smart meter dataset characterized by substantial data imbalance across users. Quantitative results show that GUIDE-VAE performs effectively in both synthetic data generation and missing record imputation tasks, while qualitative evaluations reveal that GUIDE-VAE produces more plausible and less noisy data. These results establish GUIDE-VAE as a promising tool for controlled, realistic data generation in multi-user datasets, with potential applications across various domains requiring user-informed modelling.
Authors: Joseph Arul Raj, Linglong Qian, Zina Ibrahim
Abstract: Secondary research use of Electronic Health Records (EHRs) is often hampered by the abundance of missing data in this valuable resource. Missingness in EHRs occurs naturally as a result of the data recording practices during routine clinical care, but handling it is crucial to the precision of medical analysis and the decision-making that follows. The literature contains a variety of imputation methodologies based on deep neural networks. Those aim to overcome the dynamic, heterogeneous and multivariate missingness patterns of EHRs, which cannot be handled by classical and statistical imputation methods. However, all existing deep imputation methods rely on end-to-end pipelines that incorporate both imputation and downstream analyses, e.g. classification. This coupling makes it difficult to assess the quality of imputation and takes away the flexibility of re-using the imputer for a different task. Furthermore, most end-to-end deep architectures tend to use complex networks to perform the downstream task, in addition to the already sophisticated deep imputation network. We, therefore ask if the high performance reported in the literature is due to the imputer or the classifier and further ask if an optimised state-of-the-art imputer is used, a simpler classifier can achieve comparable performance. This paper explores the development of a modular, deep learning-based imputation and classification pipeline, specifically built to leverage the capabilities of state-of-the-art imputation models for downstream classification tasks. Such a modular approach enables a) objective assessment of the quality of the imputer and classifier independently, and b) enables the exploration of the performance of simpler classification architectures using an optimised imputer.
Authors: Ryan Campbell, Nelson Lojo, Kesava Viswanadha, Christoffer Grondal Tryggestad, Derrick Han Sun, Sriteja Vijapurapu, August Rolfsen, Anant Sahai
Abstract: In-Context Learning (ICL) is a phenomenon where task learning occurs through a prompt sequence without the necessity of parameter updates. ICL in Multi-Headed Attention (MHA) with absolute positional embedding has been the focus of more study than other sequence model varieties. We examine implications of architectural differences between GPT-2 and LLaMa as well as LlaMa and Mamba. We extend work done by Garg et al. (2022) and Park et al. (2024) to GPT-2/LLaMa hybrid and LLaMa/Mamba hybrid models - examining the interplay between sequence transformation blocks and regressive performance in-context. We note that certain architectural changes cause degraded training efficiency/ICL accuracy by converging to suboptimal predictors or converging slower. We also find certain hybrids showing optimistic performance improvements, informing potential future ICL-focused architecture modifications. Additionally, we propose the "ICL regression score", a scalar metric describing a model's whole performance on a specific task. Compute limitations impose restrictions on our architecture-space, training duration, number of training runs, function class complexity, and benchmark complexity. To foster reproducible and extensible research, we provide a typed, modular, and extensible Python package on which we run all experiments.
Authors: Jiawei Yao, Qi Qian, Juhua Hu
Abstract: Multiple clustering aims to discover various latent structures of data from different aspects. Deep multiple clustering methods have achieved remarkable performance by exploiting complex patterns and relationships in data. However, existing works struggle to flexibly adapt to diverse user-specific needs in data grouping, which may require manual understanding of each clustering. To address these limitations, we introduce Multi-Sub, a novel end-to-end multiple clustering approach that incorporates a multi-modal subspace proxy learning framework in this work. Utilizing the synergistic capabilities of CLIP and GPT-4, Multi-Sub aligns textual prompts expressing user preferences with their corresponding visual representations. This is achieved by automatically generating proxy words from large language models that act as subspace bases, thus allowing for the customized representation of data in terms specific to the user's interests. Our method consistently outperforms existing baselines across a broad set of datasets in visual multiple clustering tasks. Our code is available at https://github.com/Alexander-Yao/Multi-Sub.
Authors: Alexandros Gkillas, Aris Lalos
Abstract: Anomaly and missing data constitute a thorny problem in industrial applications. In recent years, deep learning enabled anomaly detection has emerged as a critical direction, however the improved detection accuracy is achieved with the utilization of large neural networks, increasing their storage and computational cost. Moreover, the data collected in edge devices contain user privacy, introducing challenges that can be successfully addressed by the privacy-preserving distributed paradigm, known as federated learning (FL). This framework allows edge devices to train and exchange models increasing also the communication cost. Thus, to deal with the increased communication, processing and storage challenges of the FL based deep anomaly detection NN pruning is expected to have significant benefits towards reducing the processing, storage and communication complexity. With this focus, a novel compression-based optimization problem is proposed at the server-side of a FL paradigm that fusses the received local models broadcast and performs pruning generating a more compressed model. Experiments in the context of anomaly detection and missing value imputation demonstrate that the proposed FL scenario along with the proposed compressed-based method are able to achieve high compression rates (more than $99.7\%$) with negligible performance losses (less than $1.18\%$ ) as compared to the centralized solutions.
Authors: Themistoklis Haris
Abstract: Despite their power, Transformers face challenges with long sequences due to the quadratic complexity of self-attention. To address this limitation, methods like $k$-Nearest-Neighbor ($k$NN) attention have been introduced [Roy, Saffar, Vaswani, Grangier, 2021] enabling each token to attend to only its $k$ closest tokens. While $k$NN attention has shown empirical success in making Transformers more efficient, its exact approximation guarantees have not been theoretically analyzed. In this work, we establish a theoretical framework for $k$NN attention, reformulating self-attention as expectations over softmax distributions and leveraging lazy Gumbel sampling [Mussmann, Levy, Ermon, 2017] with $k$NN indices for efficient approximation. Building on this framework, we also propose novel sub-quadratic algorithms that approximate self-attention gradients by leveraging efficient sampling techniques, such as Markov Chain-based estimation. Finally, we demonstrate the practical effectiveness of these algorithms through empirical experiments, showcasing their benefits in both training and inference.
Authors: Nina van Tiel, Robin Zbinden, Emanuele Dalsasso, Benjamin Kellenberger, Lo\"ic Pellissier, Devis Tuia
Abstract: Species distribution models (SDMs) aim to predict the distribution of species by relating occurrence data with environmental variables. Recent applications of deep learning to SDMs have enabled new avenues, specifically the inclusion of spatial data (environmental rasters, satellite images) as model predictors, allowing the model to consider the spatial context around each species' observations. However, the appropriate spatial extent of the images is not straightforward to determine and may affect the performance of the model, as scale is recognized as an important factor in SDMs. We develop a modular structure for SDMs that allows us to test the effect of scale in both single- and multi-scale settings. Furthermore, our model enables different scales to be considered for different modalities, using a late fusion approach. Results on the GeoLifeCLEF 2023 benchmark indicate that considering multimodal data and learning multi-scale representations leads to more accurate models.
Authors: Alexandre Galashov, Michalis K. Titsias, Andr\'as Gy\"orgy, Clare Lyle, Razvan Pascanu, Yee Whye Teh, Maneesh Sahani
Abstract: Neural networks are traditionally trained under the assumption that data come from a stationary distribution. However, settings which violate this assumption are becoming more popular; examples include supervised learning under distributional shifts, reinforcement learning, continual learning and non-stationary contextual bandits. In this work we introduce a novel learning approach that automatically models and adapts to non-stationarity, via an Ornstein-Uhlenbeck process with an adaptive drift parameter. The adaptive drift tends to draw the parameters towards the initialisation distribution, so the approach can be understood as a form of soft parameter reset. We show empirically that our approach performs well in non-stationary supervised and off-policy reinforcement learning settings.
Authors: Chen Feng, Shaojie Zhuo, Xiaopeng Zhang, Ramchalam Kinattinkara Ramakrishnan, Zhaocong Yuan, Andrew Zou Li
Abstract: Continuously adapting pre-trained models to local data on resource constrained edge devices is the $\emph{last mile}$ for model deployment. However, as models increase in size and depth, backpropagation requires a large amount of memory, which becomes prohibitive for edge devices. In addition, most existing low power neural processing engines (e.g., NPUs, DSPs, MCUs, etc.) are designed as fixed-point inference accelerators, without training capabilities. Forward gradients, solely based on directional derivatives computed from two forward calls, have been recently used for model training, with substantial savings in computation and memory. However, the performance of quantized training with fixed-point forward gradients remains unclear. In this paper, we investigate the feasibility of on-device training using fixed-point forward gradients, by conducting comprehensive experiments across a variety of deep learning benchmark tasks in both vision and audio domains. We propose a series of algorithm enhancements that further reduce the memory footprint, and the accuracy gap compared to backpropagation. An empirical study on how training with forward gradients navigates in the loss landscape is further explored. Our results demonstrate that on the last mile of model customization on edge devices, training with fixed-point forward gradients is a feasible and practical approach.
Authors: Zesheng Liu, Maryam Rahnemoonfar
Abstract: Understanding spatio-temporal patterns in polar ice layers is essential for tracking changes in ice sheet balance and assessing ice dynamics. While convolutional neural networks are widely used in learning ice layer patterns from raw echogram images captured by airborne snow radar sensors, noise in the echogram images prevents researchers from getting high-quality results. Instead, we focus on geometric deep learning using graph neural networks, aiming to build a spatio-temporal graph neural network that learns from thickness information of the top ice layers and predicts for deeper layers. In this paper, we developed a novel multi-branch spatio-temporal graph neural network that used the GraphSAGE framework for spatio features learning and a temporal convolution operation to capture temporal changes, enabling different branches of the network to be more specialized and focusing on a single learning task. We found that our proposed multi-branch network can consistently outperform the current fused spatio-temporal graph neural network in both accuracy and efficiency.
Authors: Florian Wolf, Nicol\`o Botteghi, Urban Fasel, Andrea Manzoni
Abstract: Effectively controlling systems governed by Partial Differential Equations (PDEs) is crucial in several fields of Applied Sciences and Engineering. These systems usually yield significant challenges to conventional control schemes due to their nonlinear dynamics, partial observability, high-dimensionality once discretized, distributed nature, and the requirement for low-latency feedback control. Reinforcement Learning (RL), particularly Deep RL (DRL), has recently emerged as a promising control paradigm for such systems, demonstrating exceptional capabilities in managing high-dimensional, nonlinear dynamics. However, DRL faces challenges including sample inefficiency, robustness issues, and an overall lack of interpretability. To address these issues, we propose a data-efficient, interpretable, and scalable Dyna-style Model-Based RL framework for PDE control, combining the Sparse Identification of Nonlinear Dynamics with Control (SINDy-C) algorithm and an autoencoder (AE) framework for the sake of dimensionality reduction of PDE states and actions. This novel approach enables fast rollouts, reducing the need for extensive environment interactions, and provides an interpretable latent space representation of the PDE forward dynamics. We validate our method on two PDE problems describing fluid flows - namely, the 1D Burgers equation and 2D Navier-Stokes equations - comparing it against a model-free baseline, and carrying out an extensive analysis of the learned dynamics.
Authors: Guan Zhe Hong, Nishanth Dikkala, Enming Luo, Cyrus Rashtchian, Rina Panigrahy
Abstract: Large language models (LLMs) have shown amazing performance on tasks that require planning and reasoning. Motivated by this, we investigate the internal mechanisms that underpin a network's ability to perform complex logical reasoning. We first construct a synthetic propositional logic problem that serves as a concrete test-bed for network training and evaluation. Crucially, this problem demands nontrivial planning to solve, but we can train a small transformer to achieve perfect accuracy. Building on our set-up, we then pursue an understanding of precisely how a three-layer transformer, trained from scratch, solves this problem. We are able to identify certain "planning" and "reasoning" circuits in the network that necessitate cooperation between the attention blocks to implement the desired logic. To expand our findings, we then study a larger model, Mistral 7B. Using activation patching, we characterize internal components that are critical in solving our logic problem. Overall, our work systemically uncovers novel aspects of small and large transformers, and continues the study of how they plan and reason.
Authors: Ahmed Abdeljawad, Thomas Dittrich
Abstract: In this work, we consider the approximation capabilities of shallow neural networks in weighted Sobolev spaces for functions in the spectral Barron space. The existing literature already covers several cases, in which the spectral Barron space can be approximated well, i.e., without curse of dimensionality, by shallow networks and several different classes of activation function. The limitations of the existing results are mostly on the error measures that were considered, in which the results are restricted to Sobolev spaces over a bounded domain. We will here treat two cases that extend upon the existing results. Namely, we treat the case with bounded domain and Muckenhoupt weights and the case, where the domain is allowed to be unbounded and the weights are required to decay. We first present embedding results for the more general weighted Fourier-Lebesgue spaces in the weighted Sobolev spaces and then we establish asymptotic approximation rates for shallow neural networks that come without curse of dimensionality.
Authors: Nicholas Potteiger, Ankita Samaddar, Hunter Bergstrom, Xenofon Koutsoukos
Abstract: Modern network defense can benefit from the use of autonomous systems, offloading tedious and time-consuming work to agents with standard and learning-enabled components. These agents, operating on critical network infrastructure, need to be robust and trustworthy to ensure defense against adaptive cyber-attackers and, simultaneously, provide explanations for their actions and network activity. However, learning-enabled components typically use models, such as deep neural networks, that are not transparent in their high-level decision-making leading to assurance challenges. Additionally, cyber-defense agents must execute complex long-term defense tasks in a reactive manner that involve coordination of multiple interdependent subtasks. Behavior trees are known to be successful in modelling interpretable, reactive, and modular agent policies with learning-enabled components. In this paper, we develop an approach to design autonomous cyber defense agents using behavior trees with learning-enabled components, which we refer to as Evolving Behavior Trees (EBTs). We learn the structure of an EBT with a novel abstract cyber environment and optimize learning-enabled components for deployment. The learning-enabled components are optimized for adapting to various cyber-attacks and deploying security mechanisms. The learned EBT structure is evaluated in a simulated cyber environment, where it effectively mitigates threats and enhances network visibility. For deployment, we develop a software architecture for evaluating EBT-based agents in computer network defense scenarios. Our results demonstrate that the EBT-based agent is robust to adaptive cyber-attacks and provides high-level explanations for interpreting its decisions and actions.
Authors: Erik Helmut, Luca Dziarski, Niklas Funk, Boris Belousov, Jan Peters
Abstract: Contact-rich manipulation remains a major challenge in robotics. Optical tactile sensors like GelSight Mini offer a low-cost solution for contact sensing by capturing soft-body deformations of the silicone gel. However, accurately inferring shear and normal force distributions from these gel deformations has yet to be fully addressed. In this work, we propose a machine learning approach using a U-net architecture to predict force distributions directly from the sensor's raw images. Our model, trained on force distributions inferred from Finite Element Analysis (FEA), demonstrates promising accuracy in predicting normal and shear force distributions. It also shows potential for generalization across sensors of the same type and for enabling real-time application. The codebase, dataset and models are open-sourced and available at https://feats-ai.github.io .
Authors: Xiao Hu, Ziqi Chen, Daniel Adu-Ampratwum, Bo Peng, Xia Ning
Abstract: Accurate prediction of chemical reaction yields is crucial for optimizing organic synthesis, potentially reducing time and resources spent on experimentation. With the rise of artificial intelligence (AI), there is growing interest in leveraging AI-based methods to accelerate yield predictions without conducting in vitro experiments. We present log-RRIM, an innovative graph transformer-based framework designed for predicting chemical reaction yields. Our approach implements a unique local-to-global reaction representation learning strategy. This approach initially captures detailed molecule-level information and then models and aggregates intermolecular interactions, ensuring that the impact of varying-sizes molecular fragments on yield is accurately accounted for. Another key feature of log-RRIM is its integration of a cross-attention mechanism that focuses on the interplay between reagents and reaction centers. This design reflects a fundamental principle in chemical reactions: the crucial role of reagents in influencing bond-breaking and formation processes, which ultimately affect reaction yields. log-RRIM outperforms existing methods in our experiments, especially for medium to high-yielding reactions, proving its reliability as a predictor. Its advanced modeling of reactant-reagent interactions and sensitivity to small molecular fragments make it a valuable tool for reaction planning and optimization in chemical synthesis. The data and codes of log-RRIM are accessible through https://github.com/ninglab/Yield_log_RRIM.
Authors: Chenxiao Yu, Zhaotian Weng, Zheng Li, Xiyang Hu, Yue Zhao
Abstract: Can Large Language Models (LLMs) accurately predict election outcomes? While LLMs have demonstrated impressive performance in various domains, including healthcare, legal analysis, and creative tasks, their ability to forecast elections remains unknown. Election prediction poses unique challenges, such as limited voter-level data, rapidly changing political landscapes, and the need to model complex human behavior. To address these challenges, we introduce a multi-step reasoning framework designed for political analysis. Our approach is validated on real-world data from the American National Election Studies (ANES) 2016 and 2020, as well as synthetic personas generated by the leading machine learning framework, offering scalable datasets for voter behavior modeling. To capture temporal dynamics, we incorporate candidates' policy positions and biographical details, ensuring that the model adapts to evolving political contexts. Drawing on Chain of Thought prompting, our multi-step reasoning pipeline systematically integrates demographic, ideological, and time-dependent factors, enhancing the model's predictive power. Additionally, we apply our framework to predict the outcome of the 2024 U.S. presidential election in advance, demonstrating the adaptability of LLMs to unseen political data.
Authors: Katie Fankhauser, Evan Thomas, Zia Mehrabi
Abstract: High-resolution satellite-based crop yield mapping offers enormous promise for monitoring progress towards the SDGs. Across 15,000 villages in Rwanda we uncover areas that are on and off track to double productivity by 2030. This machine learning enabled analysis is used to design spatially explicit productivity targets that, if met, would simultaneously ensure national goals without leaving anyone behind.
Authors: Kikun Park, Hyerim Bae
Abstract: In ports, a variety of tasks are carried out, and scheduling these tasks is crucial due to its significant impact on productivity, making the generation of precise plans essential. This study proposes a method to solve the Quay Crane Scheduling Problem (QCSP), a representative task scheduling problem in ports known to be NP-Hard, more quickly and accurately. First, the study suggests a method to create more accurate work plans for Quay Cranes (QCs) by learning from actual port data to accurately predict the working speed of QCs. Next, a Surrogate Model is proposed by combining a Machine Learning (ML) model with a Genetic Algorithm (GA), which is widely used to solve complex optimization problems, enabling faster and more precise exploration of solutions. Unlike methods that use fixed-dimensional chromosome encoding, the proposed methodology can provide solutions for encodings of various dimensions. To validate the performance of the newly proposed methodology, comparative experiments were conducted, demonstrating faster search speeds and improved fitness scores. The method proposed in this study can be applied not only to QCSP but also to various NP-Hard problems, and it opens up possibilities for the further development of advanced search algorithms by combining heuristic algorithms with ML models.
Authors: Alec Farid, Peter Schleede, Aaron Huang, Christoffer Heckman
Abstract: We are motivated by the problem of autonomous vehicle performance validation. A key challenge is that an autonomous vehicle requires testing in every kind of driving scenario it could encounter, including rare events, to provide a strong case for safety and show there is no edge-case pathological behavior. Autonomous vehicle companies rely on potentially millions of miles driven in realistic simulation to expose the driving stack to enough miles to estimate rates and severity of collisions. To address scalability and coverage, we propose the use of a behavior foundation model, specifically a masked autoencoder (MAE), trained to reconstruct driving scenarios. We leverage the foundation model in two complementary ways: we (i) use the learned embedding space to group qualitatively similar scenarios together and (ii) fine-tune the model to label scenario difficulty based on the likelihood of a collision upon re-simulation. We use the difficulty scoring as importance weighting for the groups of scenarios. The result is an approach which can more rapidly estimate the rates and severity of collisions by prioritizing hard scenarios while ensuring exposure to every kind of driving scenario.
Authors: Zihao Li, Dongqi Fu, Hengyu Liu, Jingrui He
Abstract: Hypergraphs naturally arise when studying group relations and have been widely used in the field of machine learning. There has not been a unified formulation of hypergraphs, yet the recently proposed edge-dependent vertex weights (EDVW) modeling is one of the most generalized modeling methods of hypergraphs, i.e., most existing hypergraphs can be formulated as EDVW hypergraphs without any information loss to the best of our knowledge. However, the relevant algorithmic developments on EDVW hypergraphs remain nascent: compared to spectral graph theories, the formulations are incomplete, the spectral clustering algorithms are not well-developed, and one result regarding hypergraph Cheeger Inequality is even incorrect. To this end, deriving a unified random walk-based formulation, we propose our definitions of hypergraph Rayleigh Quotient, NCut, boundary/cut, volume, and conductance, which are consistent with the corresponding definitions on graphs. Then, we prove that the normalized hypergraph Laplacian is associated with the NCut value, which inspires our HyperClus-G algorithm for spectral clustering on EDVW hypergraphs. Finally, we prove that HyperClus-G can always find an approximately linearly optimal partitioning in terms of Both NCut and conductance. Additionally, we provide extensive experiments to validate our theoretical findings from an empirical perspective.
Authors: Shrihan Agarwal, Aleksandra \'Ciprijanovi\'c, Brian D. Nord
Abstract: Modeling strong gravitational lenses is computationally expensive for the complex data from modern and next-generation cosmic surveys. Deep learning has emerged as a promising approach for finding lenses and predicting lensing parameters, such as the Einstein radius. Mean-variance Estimators (MVEs) are a common approach for obtaining aleatoric (data) uncertainties from a neural network prediction. However, neural networks have not been demonstrated to perform well on out-of-domain target data successfully - e.g., when trained on simulated data and applied to real, observational data. In this work, we perform the first study of the efficacy of MVEs in combination with unsupervised domain adaptation (UDA) on strong lensing data. The source domain data is noiseless, and the target domain data has noise mimicking modern cosmology surveys. We find that adding UDA to MVE increases the accuracy on the target data by a factor of about two over an MVE model without UDA. Including UDA also permits much more well-calibrated aleatoric uncertainty predictions. Advancements in this approach may enable future applications of MVE models to real observational data.
Authors: Mark Humphries, Lianne C. Leddy, Quinn Downton, Meredith Legace, John McConnell, Isabella Murray, Elizabeth Spence
Abstract: This study demonstrates that Large Language Models (LLMs) can transcribe historical handwritten documents with significantly higher accuracy than specialized Handwritten Text Recognition (HTR) software, while being faster and more cost-effective. We introduce an open-source software tool called Transcription Pearl that leverages these capabilities to automatically transcribe and correct batches of handwritten documents using commercially available multimodal LLMs from OpenAI, Anthropic, and Google. In tests on a diverse corpus of 18th/19th century English language handwritten documents, LLMs achieved Character Error Rates (CER) of 5.7 to 7% and Word Error Rates (WER) of 8.9 to 15.9%, improvements of 14% and 32% respectively over specialized state-of-the-art HTR software like Transkribus. Most significantly, when LLMs were then used to correct those transcriptions as well as texts generated by conventional HTR software, they achieved near-human levels of accuracy, that is CERs as low as 1.8% and WERs of 3.5%. The LLMs also completed these tasks 50 times faster and at approximately 1/50th the cost of proprietary HTR programs. These results demonstrate that when LLMs are incorporated into software tools like Transcription Pearl, they provide an accessible, fast, and highly accurate method for mass transcription of historical handwritten documents, significantly streamlining the digitization process.
Authors: Langalibalele Lunga, Suhas Sreehari
Abstract: Machine learning models are prone to adversarial attacks, where inputs can be manipulated in order to cause misclassifications. While previous research has focused on techniques like Generative Adversarial Networks (GANs), there's limited exploration of GANs and Synthetic Minority Oversampling Technique (SMOTE) in text and image classification models to perform adversarial attacks. Our study addresses this gap by training various machine learning models and using GANs and SMOTE to generate additional data points aimed at attacking text classification models. Furthermore, we extend our investigation to face recognition models, training a Convolutional Neural Network(CNN) and subjecting it to adversarial attacks with fast gradient sign perturbations on key features identified by GradCAM, a technique used to highlight key image characteristics CNNs use in classification. Our experiments reveal a significant vulnerability in classification models. Specifically, we observe a 20 % decrease in accuracy for the top-performing text classification models post-attack, along with a 30 % decrease in facial recognition accuracy. This highlights the susceptibility of these models to manipulation of input data. Adversarial attacks not only compromise the security but also undermine the reliability of machine learning systems. By showcasing the impact of adversarial attacks on both text classification and face recognition models, our study underscores the urgent need for develop robust defenses against such vulnerabilities.
Authors: Yudi Zhang, Pei Xiao, Lu Wang, Chaoyun Zhang, Meng Fang, Yali Du, Yevgeniy Puzyrev, Randolph Yao, Si Qin, Qingwei Lin, Mykola Pechenizkiy, Dongmei Zhang, Saravan Rajmohan, Qi Zhang
Abstract: In-context learning (ICL) and Retrieval-Augmented Generation (RAG) have gained attention for their ability to enhance LLMs' reasoning by incorporating external knowledge but suffer from limited contextual window size, leading to insufficient information injection. To this end, we propose a novel framework, RuAG, to automatically distill large volumes of offline data into interpretable first-order logic rules, which are injected into LLMs to boost their reasoning capabilities. Our method begins by formulating the search process relying on LLMs' commonsense, where LLMs automatically define head and body predicates. Then, RuAG applies Monte Carlo Tree Search (MCTS) to address the combinational searching space and efficiently discover logic rules from data. The resulting logic rules are translated into natural language, allowing targeted knowledge injection and seamless integration into LLM prompts for LLM's downstream task reasoning. We evaluate our framework on public and private industrial tasks, including natural language processing, time-series, decision-making, and industrial tasks, demonstrating its effectiveness in enhancing LLM's capability over diverse tasks.
Authors: Fali Wang, Zhiwei Zhang, Xianren Zhang, Zongyu Wu, Tzuhao Mo, Qiuhao Lu, Wanjing Wang, Rui Li, Junjie Xu, Xianfeng Tang, Qi He, Yao Ma, Ming Huang, Suhang Wang
Abstract: Large language models (LLM) have demonstrated emergent abilities in text generation, question answering, and reasoning, facilitating various tasks and domains. Despite their proficiency in various tasks, LLMs like LaPM 540B and Llama-3.1 405B face limitations due to large parameter sizes and computational demands, often requiring cloud API use which raises privacy concerns, limits real-time applications on edge devices, and increases fine-tuning costs. Additionally, LLMs often underperform in specialized domains such as healthcare and law due to insufficient domain-specific knowledge, necessitating specialized models. Therefore, Small Language Models (SLMs) are increasingly favored for their low inference latency, cost-effectiveness, efficient development, and easy customization and adaptability. These models are particularly well-suited for resource-limited environments and domain knowledge acquisition, addressing LLMs' challenges and proving ideal for applications that require localized data handling for privacy, minimal inference latency for efficiency, and domain knowledge acquisition through lightweight fine-tuning. The rising demand for SLMs has spurred extensive research and development. However, a comprehensive survey investigating issues related to the definition, acquisition, application, enhancement, and reliability of SLM remains lacking, prompting us to conduct a detailed survey on these topics. The definition of SLMs varies widely, thus to standardize, we propose defining SLMs by their capability to perform specialized tasks and suitability for resource-constrained settings, setting boundaries based on the minimal size for emergent abilities and the maximum size sustainable under resource constraints. For other aspects, we provide a taxonomy of relevant models/methods and develop general frameworks for each category to enhance and utilize SLMs effectively.
Authors: Paul Badu Yakubu, Evans Owusu, Lesther Santana, Mohamed Rahouti, Abdellah Chehri, Kaiqi Xiong
Abstract: Denial of Service (DoS) attacks pose a significant threat in the realm of AI systems security, causing substantial financial losses and downtime. However, AI systems' high computational demands, dynamic behavior, and data variability make monitoring and detecting DoS attacks challenging. Nowadays, statistical and machine learning (ML)-based DoS classification and detection approaches utilize a broad range of feature selection mechanisms to select a feature subset from networking traffic datasets. Feature selection is critical in enhancing the overall model performance and attack detection accuracy while reducing the training time. In this paper, we investigate the importance of feature selection in improving ML-based detection of DoS attacks. Specifically, we explore feature contribution to the overall components in DoS traffic datasets by utilizing statistical analysis and feature engineering approaches. Our experimental findings demonstrate the usefulness of the thorough statistical analysis of DoS traffic and feature engineering in understanding the behavior of the attack and identifying the best feature selection for ML-based DoS classification and detection.
Authors: Geng Yu, Jianing Zhu, Jiangchao Yao, Bo Han
Abstract: Out-of-distribution (OOD) detection is crucial for deploying reliable machine learning models in open-world applications. Recent advances in CLIP-based OOD detection have shown promising results via regularizing prompt tuning with OOD features extracted from ID data. However, the irrelevant context mined from ID data can be spurious due to the inaccurate foreground-background decomposition, thus limiting the OOD detection performance. In this work, we propose a novel framework, namely, Self-Calibrated Tuning (SCT), to mitigate this problem for effective OOD detection with only the given few-shot ID data. Specifically, SCT introduces modulating factors respectively on the two components of the original learning objective. It adaptively directs the optimization process between the two tasks during training on data with different prediction uncertainty to calibrate the influence of OOD regularization, which is compatible with many prompt tuning based OOD detection methods. Extensive experiments and analyses have been conducted to characterize and demonstrate the effectiveness of the proposed SCT. The code is publicly available.
Authors: Zhihao Zhu, Yi Yang, Defu Lian
Abstract: Training Data Detection (TDD) is a task aimed at determining whether a specific data instance is used to train a machine learning model. In the computer security literature, TDD is also referred to as Membership Inference Attack (MIA). Given its potential to assess the risks of training data breaches, ensure copyright authentication, and verify model unlearning, TDD has garnered significant attention in recent years, leading to the development of numerous methods. Despite these advancements, there is no comprehensive benchmark to thoroughly evaluate the effectiveness of TDD methods. In this work, we introduce TDDBench, which consists of 13 datasets spanning three data modalities: image, tabular, and text. We benchmark 21 different TDD methods across four detection paradigms and evaluate their performance from five perspectives: average detection performance, best detection performance, memory consumption, and computational efficiency in both time and memory. With TDDBench, researchers can identify bottlenecks and areas for improvement in TDD algorithms, while practitioners can make informed trade-offs between effectiveness and efficiency when selecting TDD algorithms for specific use cases. Our large-scale benchmarking also reveals the generally unsatisfactory performance of TDD algorithms across different datasets. To enhance accessibility and reproducibility, we open-source TDDBench for the research community.
Authors: Jinyin Chen, Haonan Ma, Haibin Zheng
Abstract: Graph has become increasingly integral to the advancement of recommendation systems, particularly with the fast development of graph neural network(GNN). By exploring the virtue of rich node features and link information, GNN is designed to provide personalized and accurate suggestions. Meanwhile, the privacy leakage of GNN in such contexts has also captured special attention. Prior work has revealed that a malicious user can utilize auxiliary knowledge to extract sensitive link data of the target graph, integral to recommendation systems, via the decision made by the target GNN model. This poses a significant risk to the integrity and confidentiality of data used in recommendation system. Though important, previous works on GNN's privacy leakage are still challenged in three aspects, i.e., limited stealing attack scenarios, sub-optimal attack performance, and adaptation against defense. To address these issues, we propose a diffusion model based link stealing attack, named DM4Steal. It differs previous work from three critical aspects. (i) Generality: aiming at six attack scenarios with limited auxiliary knowledge, we propose a novel training strategy for diffusion models so that DM4Steal is transferable to diverse attack scenarios. (ii) Effectiveness: benefiting from the retention of semantic structure in the diffusion model during the training process, DM4Steal is capable to learn the precise topology of the target graph through the GNN decision process. (iii) Adaptation: when GNN is defensive (e.g., DP, Dropout), DM4Steal relies on the stability that comes from sampling the score model multiple times to keep performance degradation to a minimum, thus DM4Steal implements successful adaptive attack on defensive GNN.
Authors: Mohammadreza Kouchaki, Minglong Zhang, Aly S. Abdalla, Guangchen Lan, Christopher G. Brinton, Vuk Marojevic
Abstract: In the rapidly evolving landscape of 5G technology, safeguarding Radio Frequency (RF) environments against sophisticated intrusions is paramount, especially in dynamic spectrum access and management. This paper presents an enhanced experimental model that integrates a self-attention mechanism with a Recurrent Neural Network (RNN)-based autoencoder for the detection of anomalous spectral activities in 5G networks at the waveform level. Our approach, grounded in time-series analysis, processes in-phase and quadrature (I/Q) samples to identify irregularities that could indicate potential jamming attacks. The model's architecture, augmented with a self-attention layer, extends the capabilities of RNN autoencoders, enabling a more nuanced understanding of temporal dependencies and contextual relationships within the RF spectrum. Utilizing a simulated 5G Radio Access Network (RAN) test-bed constructed with srsRAN 5G and Software Defined Radios (SDRs), we generated a comprehensive stream of data that reflects real-world RF spectrum conditions and attack scenarios. The model is trained to reconstruct standard signal behavior, establishing a normative baseline against which deviations, indicative of security threats, are identified. The proposed architecture is designed to balance between detection precision and computational efficiency, so the LSTM network, enriched with self-attention, continues to optimize for minimal execution latency and power consumption. Conducted on a real-world SDR-based testbed, our results demonstrate the model's improved performance and accuracy in threat detection. Keywords: self-attention, real-time intrusion detection, RNN autoencoder, Transformer architecture, LSTM, time series anomaly detection, 5G Security, spectrum access security.
Authors: Ariel Neufeld, Philipp Schmocker
Abstract: In this paper, we solve stochastic partial differential equations (SPDEs) numerically by using (possibly random) neural networks in the truncated Wiener chaos expansion of their corresponding solution. Moreover, we provide some approximation rates for learning the solution of SPDEs with additive and/or multiplicative noise. Finally, we apply our results in numerical examples to approximate the solution of three SPDEs: the stochastic heat equation, the Heath-Jarrow-Morton equation, and the Zakai equation.
Authors: Aditya Dave, Mengchen Zhu, Dapeng Hu, Sachin Tiwari
Abstract: Corporate Greenhouse Gas (GHG) emission targets are important metrics in sustainable investing [12, 16]. To provide a comprehensive view of company emission objectives, we propose an approach to source these metrics from company public disclosures. Without automation, curating these metrics manually is a labor-intensive process that requires combing through lengthy corporate sustainability disclosures that often do not follow a standard format. Furthermore, the resulting dataset needs to be validated thoroughly by Subject Matter Experts (SMEs), further lengthening the time-to-market. We introduce the Climate Artificial Intelligence for Corporate Decarbonization Metrics Extraction (CAI) model and pipeline, a novel approach utilizing Large Language Models (LLMs) to extract and validate linked metrics from corporate disclosures. We demonstrate that the process improves data collection efficiency and accuracy by automating data curation, validation, and metric scoring from public corporate disclosures. We further show that our results are agnostic to the choice of LLMs. This framework can be applied broadly to information extraction from textual data.
Authors: Murad Mehrab Abrar, Souryadeep Mondal, Michelle Hickner
Abstract: This paper presents a Sim2Real (Simulation to Reality) approach to bridge the gap between a trained agent in a simulated environment and its real-world implementation in navigating a robot in a similar setting. Specifically, we focus on navigating a quadruped robot in a real-world grid-like environment inspired by the Gymnasium Frozen Lake -- a highly user-friendly and free Application Programming Interface (API) to develop and test Reinforcement Learning (RL) algorithms. We detail the development of a pipeline to transfer motion policies learned in the Frozen Lake simulation to a physical quadruped robot, thus enabling autonomous navigation and obstacle avoidance in a grid without relying on expensive localization and mapping sensors. The work involves training an RL agent in the Frozen Lake environment and utilizing the resulting Q-table to control a 12 Degrees-of-Freedom (DOF) quadruped robot. In addition to detailing the RL implementation, inverse kinematics-based quadruped gaits, and the transfer policy pipeline, we open-source the project on GitHub and include a demonstration video of our Sim2Real transfer approach. This work provides an accessible, straightforward, and low-cost framework for researchers, students, and hobbyists to explore and implement RL-based robot navigation in real-world grid environments.
Authors: Razvan-Gabriel Dumitru, Paul-Ioan Clotan, Vikas Yadav, Darius Peteleaza, Mihai Surdeanu
Abstract: This paper introduces a novel model compression approach through dynamic layer-specific pruning in Large Language Models (LLMs), enhancing the traditional methodology established by SliceGPT. By transitioning from constant to dynamic slicing, our method leverages the newly proposed Layer Redundancy (LR) score, which assesses how much change each layer changes its input by measuring the cosine similarity of the input to the output of the layer. We use this score to prune parts of individual layers based on redundancy in such a way that the average pruned percentage for all layers is a fixed value. We conducted extensive experiments using models like Llama3-8B and Mistral-7B on multiple datasets, evaluating different slicing bases and percentages to determine optimal configurations that balance efficiency and performance. Our findings show that our dynamic slicing approach not only maintains but, in many cases, enhances model performance compared to the baseline established by constant slicing methods. For instance, in several settings, we see performance improvements of up to 5% over the SliceGPT baseline. Additionally, a perplexity decrease by as much as 7% was observed across multiple benchmarks, validating the effectiveness of our method. The code, model weights, and datasets are open-sourced at https://github.com/RazvanDu/DynamicSlicing.
Authors: Zhiqiang Xie, Hao Kang, Ying Sheng, Tushar Krishna, Kayvon Fatahalian, Christos Kozyrakis
Abstract: With more advanced natural language understanding and reasoning capabilities, large language model (LLM)-powered agents are increasingly developed in simulated environments to perform complex tasks, interact with other agents, and exhibit emergent behaviors relevant to social science and gaming. However, current multi-agent simulations frequently suffer from inefficiencies due to the limited parallelism caused by false dependencies, resulting in performance bottlenecks. In this paper, we introduce AI Metropolis, a simulation engine that improves the efficiency of LLM agent simulations by incorporating out-of-order execution scheduling. By dynamically tracking real dependencies between agents, AI Metropolis minimizes false dependencies, enhancing parallelism and enabling efficient hardware utilization. Our evaluations demonstrate that AI Metropolis achieves speedups from 1.3x to 4.15x over standard parallel simulation with global synchronization, approaching optimal performance as the number of agents increases.
Authors: Tito Homem-de-Mello, Juan Valencia, Felipe Lagos, Guido Lagos
Abstract: The exponential growth in data availability in recent years has led to new formulations of data-driven optimization problems. One such formulation is that of stochastic optimization problems with contextual information, where the goal is to optimize the expected value of a certain function given some contextual information (also called features) that accompany the main data of interest. The contextual information then allows for a better estimation of the quantity of interest via machine learning methods, thereby leading to better solutions. Oftentimes, however, machine learning methods yield just a pointwise estimate instead of an entire distribution. In this paper we show that, when the problem to be solved is a class of two-stage stochastic programs (namely, those with fixed recourse matrix and fixed costs), under mild assumptions the problem can be solved with just one scenario. While such a scenario - which does not have be unique - is usually unknown, we present an integrated learning and optimization procedure that yields the best approximation of that scenario within the modeler's pre-specified set of parameterized forecast functions. Numerical results conducted with inventory problems from the literature (with synthetic data) as well as a bike-sharing problem with real data demonstrate that the proposed approach performs well when compared to benchmark methods from the literature.
Authors: Wei Wang, Zhichao Hou, Xiaorui Liu, Xinxia Peng
Abstract: Research on long non-coding RNAs (lncRNAs) has garnered significant attention due to their critical roles in gene regulation and disease mechanisms. However, the complexity and diversity of lncRNA sequences, along with the limited knowledge of their functional mechanisms and the regulation of their expressions, pose significant challenges to lncRNA studies. Given the tremendous success of large language models (LLMs) in capturing complex dependencies in sequential data, this study aims to systematically explore the potential and limitations of LLMs in the sequence analysis related to the transcriptional regulation of lncRNA genes. Our extensive experiments demonstrated promising performance of fine-tuned genome foundation models on progressively complex tasks. Furthermore, we conducted an insightful analysis of the critical impact of task complexity, model selection, data quality, and biological interpretability for the studies of the regulation of lncRNA gene expression.
Authors: Matteo Cacciola, Alexandre Forel, Antonio Frangioni, Andrea Lodi
Abstract: Although nearly 20 years have passed since its conception, the feasibility pump algorithm remains a widely used heuristic to find feasible primal solutions to mixed-integer linear problems. Many extensions of the initial algorithm have been proposed. Yet, its core algorithm remains centered around two key steps: solving the linear relaxation of the original problem to obtain a solution that respects the constraints, and rounding it to obtain an integer solution. This paper shows that the traditional feasibility pump and many of its follow-ups can be seen as gradient-descent algorithms with specific parameters. A central aspect of this reinterpretation is observing that the traditional algorithm differentiates the solution of the linear relaxation with respect to its cost. This reinterpretation opens many opportunities for improving the performance of the original algorithm. We study how to modify the gradient-update step as well as extending its loss function. We perform extensive experiments on MIPLIB instances and show that these modifications can substantially reduce the number of iterations needed to find a solution.
Authors: Adam R. Klivans, Konstantinos Stavropoulos, Arsen Vasilyan
Abstract: The seminal work of Linial, Mansour, and Nisan gave a quasipolynomial-time algorithm for learning constant-depth circuits ($\mathsf{AC}^0$) with respect to the uniform distribution on the hypercube. Extending their algorithm to the setting of malicious noise, where both covariates and labels can be adversarially corrupted, has remained open. Here we achieve such a result, inspired by recent work on learning with distribution shift. Our running time essentially matches their algorithm, which is known to be optimal assuming various cryptographic primitives. Our proof uses a simple outlier-removal method combined with Braverman's theorem for fooling constant-depth circuits. We attain the best possible dependence on the noise rate and succeed in the harshest possible noise model (i.e., contamination or so-called "nasty noise").
Authors: Keito Akiyama
Abstract: In recent years, learning for neural networks can be viewed as optimization in the space of probability measures. To obtain the exponential convergence to the optimizer, the regularizing term based on Shannon entropy plays an important role. Even though an entropy function heavily affects convergence results, there is almost no result on its generalization, because of the following two technical difficulties: one is the lack of sufficient condition for generalized logarithmic Sobolev inequality, and the other is the distributional dependence of the potential function within the gradient flow equation. In this paper, we establish a framework that utilizes a linearized potential function via Csisz\'{a}r type of Tsallis entropy, which is one of the generalized entropies. We also show that our new framework enable us to derive an exponential convergence result.
Authors: Debjoy Thakur
Abstract: The application of deep neural networks in geospatial data has become a trending research problem in the present day. A significant amount of statistical research has already been introduced, such as generalized least square optimization by incorporating spatial variance-covariance matrix, considering basis functions in the input nodes of the neural networks, and so on. However, for lattice data, there is no available literature about the utilization of asymptotic analysis of neural networks in regression for spatial data. This article proposes a consistent localized two-layer deep neural network-based regression for spatial data. We have proved the consistency of this deep neural network for bounded and unbounded spatial domains under a fixed sampling design of mixed-increasing spatial regions. We have proved that its asymptotic convergence rate is faster than that of \cite{zhan2024neural}'s neural network and an improved generalization of \cite{shen2023asymptotic}'s neural network structure. We empirically observe the rate of convergence of discrepancy measures between the empirical probability distribution of observed and predicted data, which will become faster for a less smooth spatial surface. We have applied our asymptotic analysis of deep neural networks to the estimation of the monthly average temperature of major cities in the USA from its satellite image. This application is an effective showcase of non-linear spatial regression. We demonstrate our methodology with simulated lattice data in various scenarios.
Authors: Qiuyu Liang, Weihua Wang, Feilong Bao, Guanglai Gao
Abstract: Hyperbolic rotation is commonly used to effectively model knowledge graphs and their inherent hierarchies. However, existing hyperbolic rotation models rely on logarithmic and exponential mappings for feature transformation. These models only project data features into hyperbolic space for rotation, limiting their ability to fully exploit the hyperbolic space. To address this problem, we propose a novel fully hyperbolic model designed for knowledge graph embedding. Instead of feature mappings, we define the model directly in hyperbolic space with the Lorentz model. Our model considers each relation in knowledge graphs as a Lorentz rotation from the head entity to the tail entity. We adopt the Lorentzian version distance as the scoring function for measuring the plausibility of triplets. Extensive results on standard knowledge graph completion benchmarks demonstrated that our model achieves competitive results with fewer parameters. In addition, our model get the state-of-the-art performance on datasets of CoDEx-s and CoDEx-m, which are more diverse and challenging than before. Our code is available at https://github.com/llqy123/FHRE.
Authors: Parand A. Alamdari, Soroush Ebadian, Ariel D. Procaccia
Abstract: We consider the challenge of AI value alignment with multiple individuals that have different reward functions and optimal policies in an underlying Markov decision process. We formalize this problem as one of policy aggregation, where the goal is to identify a desirable collective policy. We argue that an approach informed by social choice theory is especially suitable. Our key insight is that social choice methods can be reinterpreted by identifying ordinal preferences with volumes of subsets of the state-action occupancy polytope. Building on this insight, we demonstrate that a variety of methods--including approval voting, Borda count, the proportional veto core, and quantile fairness--can be practically applied to policy aggregation.
Authors: Yuqing Xiao, John Grundy, Anuradha Madugalla
Abstract: Growth of the older adult population has led to an increasing interest in technology-supported aged care. However, the area has some challenges such as a lack of caregivers and limitations in understanding the emotional, social, physical, and mental well-being needs of seniors. Furthermore, there is a gap in the understanding between developers and ageing people of their requirements. Digital health can be important in supporting older adults wellbeing, emotional requirements, and social needs. Requirements Engineering (RE) is a major software engineering field, which can help to identify, elicit and prioritize the requirements of stakeholders and ensure that the systems meet standards for performance, reliability, and usability. We carried out a systematic review of the literature on RE for older adult digital health software. This was necessary to show the representatives of the current stage of understanding the needs of older adults in aged care digital health. Using established guidelines outlined by the Kitchenham method, the PRISMA and the PICO guideline, we developed a protocol, followed by the systematic exploration of eight databases. This resulted in 69 primary studies of high relevance, which were subsequently subjected to data extraction, synthesis, and reporting. We highlight key RE processes in digital health software for ageing people. It explored the utilization of technology for older user well-being and care, and the evaluations of such solutions. The review also identified key limitations found in existing primary studies that inspire future research opportunities. The results indicate that requirement gathering and understanding have a significant variation between different studies. The differences are in the quality, depth, and techniques adopted for requirement gathering and these differences are largely due to uneven adoption of RE methods.
Authors: Jinshuai Bai, Zhongya Lin, Yizheng Wang, Jiancong Wen, Yinghua Liu, Timon Rabczuk, YuanTong Gu, Xi-Qiao Feng
Abstract: Numerical methods for contact mechanics are of great importance in engineering applications, enabling the prediction and analysis of complex surface interactions under various conditions. In this work, we propose an energy-based physics-informed neural network (PINNs) framework for solving frictionless contact problems under large deformation. Inspired by microscopic Lennard-Jones potential, a surface contact energy is used to describe the contact phenomena. To ensure the robustness of the proposed PINN framework, relaxation, gradual loading and output scaling techniques are introduced. In the numerical examples, the well-known Hertz contact benchmark problem is conducted, demonstrating the effectiveness and robustness of the proposed PINNs framework. Moreover, challenging contact problems with the consideration of geometrical and material nonlinearities are tested. It has been shown that the proposed PINNs framework provides a reliable and powerful tool for nonlinear contact mechanics. More importantly, the proposed PINNs framework exhibits competitive computational efficiency to the commercial FEM software when dealing with those complex contact problems. The codes used in this manuscript are available at https://github.com/JinshuaiBai/energy_PINN_Contact.(The code will be available after acceptance)
URLs: https://github.com/JinshuaiBai/energy_PINN_Contact.(The
Authors: Eliot Beyler (SIERRA), Francis Bach (SIERRA)
Abstract: In this paper, we derive variational inference upper-bounds on the log-partition function of pairwise Markov random fields on the Boolean hypercube, based on quantum relaxations of the Kullback-Leibler divergence. We then propose an efficient algorithm to compute these bounds based on primal-dual optimization. An improvement of these bounds through the use of ''hierarchies,'' similar to sum-of-squares (SoS) hierarchies is proposed, and we present a greedy algorithm to select among these relaxations. We carry extensive numerical experiments and compare with state-of-the-art methods for this inference problem.
Authors: Youssef Mohamed, Runjia Li, Ibrahim Said Ahmad, Kilichbek Haydarov, Philip Torr, Kenneth Ward Church, Mohamed Elhoseiny
Abstract: Research in vision and language has made considerable progress thanks to benchmarks such as COCO. COCO captions focused on unambiguous facts in English; ArtEmis introduced subjective emotions and ArtELingo introduced some multilinguality (Chinese and Arabic). However we believe there should be more multilinguality. Hence, we present ArtELingo-28, a vision-language benchmark that spans $\textbf{28}$ languages and encompasses approximately $\textbf{200,000}$ annotations ($\textbf{140}$ annotations per image). Traditionally, vision research focused on unambiguous class labels, whereas ArtELingo-28 emphasizes diversity of opinions over languages and cultures. The challenge is to build machine learning systems that assign emotional captions to images. Baseline results will be presented for three novel conditions: Zero-Shot, Few-Shot and One-vs-All Zero-Shot. We find that cross-lingual transfer is more successful for culturally-related languages. Data and code are provided at www.artelingo.org.
Authors: Daan Schouten, Giulia Nicoletti, Bas Dille, Catherine Chia, Pierpaolo Vendittelli, Megan Schuurmans, Geert Litjens, Nadieh Khalili
Abstract: Recent technological advances in healthcare have led to unprecedented growth in patient data quantity and diversity. While artificial intelligence (AI) models have shown promising results in analyzing individual data modalities, there is increasing recognition that models integrating multiple complementary data sources, so-called multimodal AI, could enhance clinical decision-making. This scoping review examines the landscape of deep learning-based multimodal AI applications across the medical domain, analyzing 432 papers published between 2018 and 2024. We provide an extensive overview of multimodal AI development across different medical disciplines, examining various architectural approaches, fusion strategies, and common application areas. Our analysis reveals that multimodal AI models consistently outperform their unimodal counterparts, with an average improvement of 6.2 percentage points in AUC. However, several challenges persist, including cross-departmental coordination, heterogeneous data characteristics, and incomplete datasets. We critically assess the technical and practical challenges in developing multimodal AI systems and discuss potential strategies for their clinical implementation, including a brief overview of commercially available multimodal AI models for clinical decision-making. Additionally, we identify key factors driving multimodal AI development and propose recommendations to accelerate the field's maturation. This review provides researchers and clinicians with a thorough understanding of the current state, challenges, and future directions of multimodal AI in medicine.
Authors: Nanxiang Zhou, Jing Dong, Yutian Li, Baoxiang Wang
Abstract: To understand the complexity of the dynamic of learning in differential games, we decompose the game into components where the dynamic is well understood. One of the possible tools is Helmholtz's theorem, which can decompose a vector field into a potential and a harmonic component. This has been shown to be effective in finite and normal-form games. However, applying Helmholtz's theorem by connecting it with the Hodge theorem on $\mathbb{R}^n$ (which is the strategy space of differential game) is non-trivial due to the non-compactness of $\mathbb{R}^n$. Bridging the dynamic-strategic disconnect through Hodge/Helmoltz's theorem in differential games is then left as an open problem \cite{letcher2019differentiable}. In this work, we provide two decompositions of differential games to answer this question: the first as an exact scalar potential part, a near vector potential part, and a non-strategic part; the second as a near scalar potential part, an exact vector potential part, and a non-strategic part. We show that scalar potential games coincide with potential games proposed by \cite{monderer1996potential}, where the gradient descent dynamic can successfully find the Nash equilibrium. For the vector potential game, we show that the individual gradient field is divergence-free, in which case the gradient descent dynamic may either be divergent or recurrent.
Authors: Tyler Clark, Mark Towers, Christine Evers, Jonathon Hare
Abstract: Rainbow Deep Q-Network (DQN) demonstrated combining multiple independent enhancements could significantly boost a reinforcement learning (RL) agent's performance. In this paper, we present "Beyond The Rainbow" (BTR), a novel algorithm that integrates six improvements from across the RL literature to Rainbow DQN, establishing a new state-of-the-art for RL using a desktop PC, with a human-normalized interquartile mean (IQM) of 7.4 on atari-60. Beyond Atari, we demonstrate BTR's capability to handle complex 3D games, successfully training agents to play Super Mario Galaxy, Mario Kart, and Mortal Kombat with minimal algorithmic changes. Designing BTR with computational efficiency in mind, agents can be trained using a desktop PC on 200 million Atari frames within 12 hours. Additionally, we conduct detailed ablation studies of each component, analzying the performance and impact using numerous measures.
Authors: Masakazu Yoshimura, Teruaki Hayashi, Yota Maeda
Abstract: An ecosystem of Transformer-based models has been established by building large models with extensive data. Parameter-efficient fine-tuning (PEFT) is a crucial technology for deploying these models to downstream tasks with minimal cost while achieving effective performance. Recently, Mamba, a State Space Model (SSM)-based model, has attracted attention as a potential alternative to Transformers. While many large-scale Mamba-based models have been proposed, efficiently adapting pre-trained Mamba-based models to downstream tasks remains unexplored. In this paper, we conduct an exploratory analysis of PEFT methods for Mamba. We investigate the effectiveness of existing PEFT methods for Transformers when applied to Mamba. We also modify these methods to better align with the Mamba architecture. Additionally, we propose new Mamba-specific PEFT methods that leverage the distinctive structure of Mamba. Our experiments indicate that PEFT performs more effectively for Mamba than Transformers. Lastly, we demonstrate how to effectively combine multiple PEFT methods and provide a framework that outperforms previous works. To ensure reproducibility, we will release the code after publication.
Authors: Qizhe Wu, Letian Zhao, Yuchen Gui, Huawen Liang Xiaotian Wang
Abstract: Graph Convolutional Networks (GCNs) are state-of-the-art deep learning models for representation learning on graphs. However, the efficient training of GCNs is hampered by constraints in memory capacity and bandwidth, compounded by the irregular data flow that results in communication bottlenecks. To address these challenges, we propose a message-passing architecture that leverages NUMA-based memory access properties and employs a parallel multicast routing algorithm based on a 4-D hypercube network within the accelerator for efficient message passing in graphs. Additionally, we have re-engineered the backpropagation algorithm specific to GCNs within our proposed accelerator. This redesign strategically mitigates the memory demands prevalent during the training phase and diminishes the computational overhead associated with the transposition of extensive matrices. Compared to the state-of-the-art HP-GNN architecture we achieved a performance improvement of $1.03\times \sim 1.81\times$.
Authors: Yuanshao Zhu, James Jianqiao Yu, Xiangyu Zhao, Xuetao Wei, Yuxuan Liang
Abstract: Human trajectory modeling is essential for deciphering movement patterns and supporting advanced applications across various domains. However, existing methods are often tailored to specific tasks and regions, resulting in limitations related to task specificity, regional dependency, and data quality sensitivity. Addressing these challenges requires a universal human trajectory foundation model capable of generalizing and scaling across diverse tasks and geographic contexts. To this end, we propose UniTraj, a Universal human Trajectory foundation model that is task-adaptive, region-independent, and highly generalizable. To further enhance performance, we construct WorldTrace, the first large-scale, high-quality, globally distributed dataset sourced from open web platforms, encompassing 2.45 million trajectories with billions of points across 70 countries. Through multiple resampling and masking strategies designed for pre-training, UniTraj effectively overcomes geographic and task constraints, adapting to heterogeneous data quality. Extensive experiments across multiple trajectory analysis tasks and real-world datasets demonstrate that UniTraj consistently outperforms existing approaches in terms of scalability and adaptability. These results underscore the potential of UniTraj as a versatile, robust solution for a wide range of trajectory analysis applications, with WorldTrace serving as an ideal but non-exclusive foundation for training.
Authors: Yizhe Huang, Xingbo Wang, Hao Liu, Fanqi Kong, Aoyang Qin, Min Tang, Xiaoxi Wang, Song-Chun Zhu, Mingjie Bi, Siyuan Qi, Xue Feng
Abstract: Traditional interactive environments limit agents' intelligence growth with fixed tasks. Recently, single-agent environments address this by generating new tasks based on agent actions, enhancing task diversity. We consider the decision-making problem in multi-agent settings, where tasks are further influenced by social connections, affecting rewards and information access. However, existing multi-agent environments lack a combination of adaptive physical surroundings and social connections, hindering the learning of intelligent behaviors. To address this, we introduce AdaSociety, a customizable multi-agent environment featuring expanding state and action spaces, alongside explicit and alterable social structures. As agents progress, the environment adaptively generates new tasks with social structures for agents to undertake. In AdaSociety, we develop three mini-games showcasing distinct social structures and tasks. Initial results demonstrate that specific social structures can promote both individual and collective benefits, though current reinforcement learning and LLM-based algorithms show limited effectiveness in leveraging social structures to enhance performance. Overall, AdaSociety serves as a valuable research platform for exploring intelligence in diverse physical and social settings. The code is available at https://github.com/bigai-ai/AdaSociety.
Authors: Feibo Jiang, Siwei Tu, Li Dong, Cunhua Pan, Jiangzhou Wang, Xiaohu You
Abstract: The rapid development of generative Artificial Intelligence (AI) continually unveils the potential of Semantic Communication (SemCom). However, current talking-face SemCom systems still encounter challenges such as low bandwidth utilization, semantic ambiguity, and diminished Quality of Experience (QoE). This study introduces a Large Generative Model-assisted Talking-face Semantic Communication (LGM-TSC) System tailored for the talking-face video communication. Firstly, we introduce a Generative Semantic Extractor (GSE) at the transmitter based on the FunASR model to convert semantically sparse talking-face videos into texts with high information density. Secondly, we establish a private Knowledge Base (KB) based on the Large Language Model (LLM) for semantic disambiguation and correction, complemented by a joint knowledge base-semantic-channel coding scheme. Finally, at the receiver, we propose a Generative Semantic Reconstructor (GSR) that utilizes BERT-VITS2 and SadTalker models to transform text back into a high-QoE talking-face video matching the user's timbre. Simulation results demonstrate the feasibility and effectiveness of the proposed LGM-TSC system.
Authors: Laura Cabello, Carmen Martin-Turrero, Uchenna Akujuobi, Anders S{\o}gaard, Carlos Bobed
Abstract: Question answering is a natural language understanding task that involves reasoning over both explicit context and unstated, relevant domain knowledge. Large language models (LLMs), which underpin most contemporary question answering systems, struggle to induce how concepts relate in specialized domains such as medicine. Existing medical LLMs are also costly to train. In this work, we present MEG, a parameter-efficient approach for medical knowledge-augmented LLMs. MEG uses a lightweight mapping network to integrate graph embeddings into the LLM, enabling it to leverage external knowledge in a cost-effective way. We evaluate our method on four popular medical multiple-choice datasets and show that LLMs greatly benefit from the factual grounding provided by knowledge graph embeddings. MEG attains an average of +10.2% accuracy over the Mistral-Instruct baseline, and +6.7% over specialized models like BioMistral. We also show results based on Llama-3. Finally, we show that MEG's performance remains robust to the choice of graph encoder.
Authors: Zhijian Zhuo, Ya Wang, Yutao Zeng, Xiaoqing Li, Xun Zhou, Jinwen Ma
Abstract: Transformers have found extensive applications across various domains due to the powerful fitting capabilities. This success can be partially attributed to their inherent nonlinearity. Thus, in addition to the ReLU function employed in the original transformer architecture, researchers have explored alternative modules such as GeLU and SwishGLU to enhance nonlinearity and thereby augment representational capacity. In this paper, we propose a novel category of polynomial composition activations (PolyCom), designed to optimize the dynamics of transformers. Theoretically, we provide a comprehensive mathematical analysis of PolyCom, highlighting its enhanced expressivity and efficacy relative to other activation functions. Notably, we demonstrate that networks incorporating PolyCom achieve the $\textbf{optimal approximation rate}$, indicating that PolyCom networks require minimal parameters to approximate general smooth functions in Sobolev spaces. We conduct empirical experiments on the pre-training configurations of large language models (LLMs), including both dense and sparse architectures. By substituting conventional activation functions with PolyCom, we enable LLMs to capture higher-order interactions within the data, thus improving performance metrics in terms of accuracy and convergence rates. Extensive experimental results demonstrate the effectiveness of our method, showing substantial improvements over other activation functions. Code is available at https://github.com/BryceZhuo/PolyCom.
Authors: Hengzhu Liu, Tianqing Zhu, Lefeng Zhang, Ping Xiong
Abstract: With the extensive use of machine learning technologies, data providers encounter increasing privacy risks. Recent legislation, such as GDPR, obligates organizations to remove requested data and its influence from a trained model. Machine unlearning is an emerging technique designed to enable machine learning models to erase users' private information. Although several efficient machine unlearning schemes have been proposed, these methods still have limitations. First, removing the contributions of partial data may lead to model performance degradation. Second, discrepancies between the original and generated unlearned models can be exploited by attackers to obtain target sample's information, resulting in additional privacy leakage risks. To address above challenges, we proposed a game-theoretic machine unlearning algorithm that simulates the competitive relationship between unlearning performance and privacy protection. This algorithm comprises unlearning and privacy modules. The unlearning module possesses a loss function composed of model distance and classification error, which is used to derive the optimal strategy. The privacy module aims to make it difficult for an attacker to infer membership information from the unlearned data, thereby reducing the privacy leakage risk during the unlearning process. Additionally, the experimental results on real-world datasets demonstrate that this game-theoretic unlearning algorithm's effectiveness and its ability to generate an unlearned model with a performance similar to that of the retrained one while mitigating extra privacy leakage risks.
Authors: R. James Cotton, Bryant A. Seamon, Richard L. Segal, Randal D. Davis, Amrita Sahu, Michelle M. McLeod, Pablo Celnik, Sharon L. Ramey
Abstract: Precision rehabilitation offers the promise of an evidence-based approach for optimizing individual rehabilitation to improve long-term functional outcomes. Emerging techniques, including those driven by artificial intelligence, are rapidly expanding our ability to quantify the different domains of function during rehabilitation, other encounters with healthcare, and in the community. While this seems poised to usher rehabilitation into the era of big data and should be a powerful driver of precision rehabilitation, our field lacks a coherent framework to utilize these data and deliver on this promise. We propose a framework that builds upon multiple existing pillars to fill this gap. Our framework aims to identify the Optimal Dynamic Treatment Regimens (ODTR), or the decision-making strategy that takes in the range of available measurements and biomarkers to identify interventions likely to maximize long-term function. This is achieved by designing and fitting causal models, which extend the Computational Neurorehabilitation framework using tools from causal inference. These causal models can learn from heterogeneous data from different silos, which must include detailed documentation of interventions, such as using the Rehabilitation Treatment Specification System. The models then serve as digital twins of patient recovery trajectories, which can be used to learn the ODTR. Our causal modeling framework also emphasizes quantitatively linking changes across levels of the functioning to ensure that interventions can be precisely selected based on careful measurement of impairments while also being selected to maximize outcomes that are meaningful to patients and stakeholders. We believe this approach can provide a unifying framework to leverage growing big rehabilitation data and AI-powered measurements to produce precision rehabilitation treatments that can improve clinical outcomes.
Authors: Harin Lee, Min-hwan Oh
Abstract: In this work, we close the fundamental gap of theory and practice by providing an improved regret bound for linear ensemble sampling. We prove that with an ensemble size logarithmic in $T$, linear ensemble sampling can achieve a frequentist regret bound of $\tilde{\mathcal{O}}(d^{3/2}\sqrt{T})$, matching state-of-the-art results for randomized linear bandit algorithms, where $d$ and $T$ are the dimension of the parameter and the time horizon respectively. Our approach introduces a general regret analysis framework for linear bandit algorithms. Additionally, we reveal a significant relationship between linear ensemble sampling and Linear Perturbed-History Exploration (LinPHE), showing that LinPHE is a special case of linear ensemble sampling when the ensemble size equals $T$. This insight allows us to derive a new regret bound of $\tilde{\mathcal{O}}(d^{3/2}\sqrt{T})$ for LinPHE, independent of the number of arms. Our contributions advance the theoretical foundation of ensemble sampling, bringing its regret bounds in line with the best known bounds for other randomized exploration algorithms.
Authors: Rolando Gonzales Martinez
Abstract: This study explores a Bayesian algorithmic approach to personalized fragrance recommendation by integrating hierarchical Relevance Vector Machines (RVM) and Jungian personality archetypes. The paper proposes a structured model that links individual scent preferences for top, middle, and base notes to personality traits derived from Jungian archetypes, such as the Hero, Caregiver, and Explorer, among others. The algorithm utilizes Bayesian updating to dynamically refine predictions as users interact with each fragrance note. This iterative process allows for the personalization of fragrance experiences based on prior data and personality assessments, leading to adaptive and interpretable recommendations. By combining psychological theory with Bayesian machine learning, this approach addresses the complexity of modeling individual preferences while capturing user-specific and population-level trends. The study highlights the potential of hierarchical Bayesian frameworks in creating customized olfactory experiences, informed by psychological and demographic factors, contributing to advancements in personalized product design and machine learning applications in sensory-based industries.
Authors: Chenrui Tie, Yue Chen, Ruihai Wu, Boxuan Dong, Zeyi Li, Chongkai Gao, Hao Dong
Abstract: Imitation learning, e.g., diffusion policy, has been proven effective in various robotic manipulation tasks. However, extensive demonstrations are required for policy robustness and generalization. To reduce the demonstration reliance, we leverage spatial symmetry and propose ET-SEED, an efficient trajectory-level SE(3) equivariant diffusion model for generating action sequences in complex robot manipulation tasks. Further, previous equivariant diffusion models require the per-step equivariance in the Markov process, making it difficult to learn policy under such strong constraints. We theoretically extend equivariant Markov kernels and simplify the condition of equivariant diffusion process, thereby significantly improving training efficiency for trajectory-level SE(3) equivariant diffusion policy in an end-to-end manner. We evaluate ET-SEED on representative robotic manipulation tasks, involving rigid body, articulated and deformable object. Experiments demonstrate superior data efficiency and manipulation proficiency of our proposed method, as well as its ability to generalize to unseen configurations with only a few demonstrations. Website: https://et-seed.github.io/
Authors: Fabio Pavirani, Jonas Van Gompel, Seyed Soroush Karimi Madahi, Bert Claessens, Chris Develder
Abstract: The growing reliance on renewable energy sources, particularly solar and wind, has introduced challenges due to their uncontrollable production. This complicates maintaining the electrical grid balance, prompting some transmission system operators in Western Europe to implement imbalance tariffs that penalize unsustainable power deviations. These tariffs create an implicit demand response framework to mitigate grid instability. Yet, several challenges limit active participation. In Belgium, for example, imbalance prices are only calculated at the end of each 15-minute settlement period, creating high risk due to price uncertainty. This risk is further amplified by the inherent volatility of imbalance prices, discouraging participation. Although transmission system operators provide minute-based price predictions, the system imbalance volatility makes accurate price predictions challenging to obtain and requires sophisticated techniques. Moreover, publishing price estimates can prompt participants to adjust their schedules, potentially affecting the system balance and the final price, adding further complexity. To address these challenges, we propose a Monte Carlo Tree Search method that publishes accurate imbalance prices while accounting for potential response actions. Our approach models the system dynamics using a neural network forecaster and a cluster of virtual batteries controlled by reinforcement learning agents. Compared to Belgium's current publication method, our technique improves price accuracy by 20.4% under ideal conditions and by 12.8% in more realistic scenarios. This research addresses an unexplored, yet crucial problem, positioning this paper as a pioneering work in analyzing the potential of more advanced imbalance price publishing techniques.
Authors: Muhammad Qasim Elahi, Mahsa Ghasemi, Murat Kocaoglu
Abstract: Causal knowledge about the relationships among decision variables and a reward variable in a bandit setting can accelerate the learning of an optimal decision. Current works often assume the causal graph is known, which may not always be available a priori. Motivated by this challenge, we focus on the causal bandit problem in scenarios where the underlying causal graph is unknown and may include latent confounders. While intervention on the parents of the reward node is optimal in the absence of latent confounders, this is not necessarily the case in general. Instead, one must consider a set of possibly optimal arms/interventions, each being a special subset of the ancestors of the reward node, making causal discovery beyond the parents of the reward node essential. For regret minimization, we identify that discovering the full causal structure is unnecessary; however, no existing work provides the necessary and sufficient components of the causal graph. We formally characterize the set of necessary and sufficient latent confounders one needs to detect or learn to ensure that all possibly optimal arms are identified correctly. We also propose a randomized algorithm for learning the causal graph with a limited number of samples, providing a sample complexity guarantee for any desired confidence level. In the causal bandit setup, we propose a two-stage approach. In the first stage, we learn the induced subgraph on ancestors of the reward, along with a necessary and sufficient subset of latent confounders, to construct the set of possibly optimal arms. The regret incurred during this phase scales polynomially with respect to the number of nodes in the causal graph. The second phase involves the application of a standard bandit algorithm, such as the UCB algorithm. We also establish a regret bound for our two-phase approach, which is sublinear in the number of rounds.
Authors: Kiran Doshi, Marco Bagatella, Stelian Coros
Abstract: The combination of behavioural cloning and neural networks has driven significant progress in robotic manipulation. As these algorithms may require a large number of demonstrations for each task of interest, they remain fundamentally inefficient in complex scenarios. This issue is aggravated when the system is treated as a black-box, ignoring its physical properties. This work characterises widespread properties of robotic manipulation, such as pose equivariance and locality. We empirically demonstrate that transformations arising from each of these properties allow neural policies trained with behavioural cloning to better generalise to out-of-distribution problem instances.
Authors: Joseph Balderas, Dong Chen, Yanbo Huang, Li Wang, Ren-Cang Li
Abstract: Crop production management is essential for optimizing yield and minimizing a field's environmental impact to crop fields, yet it remains challenging due to the complex and stochastic processes involved. Recently, researchers have turned to machine learning to address these complexities. Specifically, reinforcement learning (RL), a cutting-edge approach designed to learn optimal decision-making strategies through trial and error in dynamic environments, has emerged as a promising tool for developing adaptive crop management policies. RL models aim to optimize long-term rewards by continuously interacting with the environment, making them well-suited for tackling the uncertainties and variability inherent in crop management. Studies have shown that RL can generate crop management policies that compete with, and even outperform, expert-designed policies within simulation-based crop models. In the gym-DSSAT crop model environment, one of the most widely used simulators for crop management, proximal policy optimization (PPO) and deep Q-networks (DQN) have shown promising results. However, these methods have not yet been systematically evaluated under identical conditions. In this study, we evaluated PPO and DQN against static baseline policies across three different RL tasks, fertilization, irrigation, and mixed management, provided by the gym-DSSAT environment. To ensure a fair comparison, we used consistent default parameters, identical reward functions, and the same environment settings. Our results indicate that PPO outperforms DQN in fertilization and irrigation tasks, while DQN excels in the mixed management task. This comparative analysis provides critical insights into the strengths and limitations of each approach, advancing the development of more effective RL-based crop management strategies.
Authors: Archiki Prasad, Weizhe Yuan, Richard Yuanzhe Pang, Jing Xu, Maryam Fazel-Zarandi, Mohit Bansal, Sainbayar Sukhbaatar, Jason Weston, Jane Yu
Abstract: Self-alignment, whereby models learn to improve themselves without human annotation, is a rapidly growing research area. However, existing techniques often fail to improve complex reasoning tasks due to the difficulty of assigning correct rewards. An orthogonal approach that is known to improve correctness is self-consistency, a method applied at inference time based on multiple sampling in order to find the most consistent answer. In this work, we extend the self-consistency concept to help train models. We thus introduce self-consistency preference optimization (ScPO), which iteratively trains consistent answers to be preferred over inconsistent ones on unsupervised new problems. We show ScPO leads to large improvements over conventional reward model training on reasoning tasks such as GSM8K and MATH, closing the gap with supervised training with gold answers or preferences, and that combining ScPO with standard supervised learning improves results even further. On ZebraLogic, ScPO finetunes Llama-3 8B to be superior to Llama-3 70B, Gemma-2 27B, and Claude-3 Haiku.
Authors: Daniel P. Jeong, Saurabh Garg, Zachary C. Lipton, Michael Oberst
Abstract: Several recent works seek to develop foundation models specifically for medical applications, adapting general-purpose large language models (LLMs) and vision-language models (VLMs) via continued pretraining on publicly available biomedical corpora. These works typically claim that such domain-adaptive pretraining (DAPT) improves performance on downstream medical tasks, such as answering medical licensing exam questions. In this paper, we compare seven public "medical" LLMs and two VLMs against their corresponding base models, arriving at a different conclusion: all medical VLMs and nearly all medical LLMs fail to consistently improve over their base models in the zero-/few-shot prompting regime for medical question-answering (QA) tasks. For instance, across the tasks and model pairs we consider in the 3-shot setting, medical LLMs only outperform their base models in 12.1% of cases, reach a (statistical) tie in 49.8% of cases, and are significantly worse than their base models in the remaining 38.2% of cases. Our conclusions are based on (i) comparing each medical model head-to-head, directly against the corresponding base model; (ii) optimizing the prompts for each model separately; and (iii) accounting for statistical uncertainty in comparisons. While these basic practices are not consistently adopted in the literature, our ablations show that they substantially impact conclusions. Our findings suggest that state-of-the-art general-domain models may already exhibit strong medical knowledge and reasoning capabilities, and offer recommendations to strengthen the conclusions of future studies.
Authors: Xubo Lyu, Site Li, Seth Siriya, Ye Pu, Mo Chen
Abstract: In this paper, a novel optimal control-based baseline function is presented for the policy gradient method in deep reinforcement learning (RL). The baseline is obtained by computing the value function of an optimal control problem, which is formed to be closely associated with the RL task. In contrast to the traditional baseline aimed at variance reduction of policy gradient estimates, our work utilizes the optimal control value function to introduce a novel aspect to the role of baseline -- providing guided exploration during policy learning. This aspect is less discussed in prior works. We validate our baseline on robot learning tasks, showing its effectiveness in guided exploration, particularly in sparse reward environments.
Authors: Satya Narayan Shukla, Benjamin M. Marlin
Abstract: Irregularly sampled time series commonly occur in several domains where they present a significant challenge to standard deep learning models. In this paper, we propose a new deep learning framework for probabilistic interpolation of irregularly sampled time series that we call the Heteroscedastic Temporal Variational Autoencoder (HeTVAE). HeTVAE includes a novel input layer to encode information about input observation sparsity, a temporal VAE architecture to propagate uncertainty due to input sparsity, and a heteroscedastic output layer to enable variable uncertainty in output interpolations. Our results show that the proposed architecture is better able to reflect variable uncertainty through time due to sparse and irregular sampling than a range of baseline and traditional models, as well as recently proposed deep latent variable models that use homoscedastic output layers.
Authors: Hiroyasu Tsukamoto, Soon-Jo Chung, Jean-Jacques E. Slotine
Abstract: Contraction theory is an analytical tool to study differential dynamics of a non-autonomous (i.e., time-varying) nonlinear system under a contraction metric defined with a uniformly positive definite matrix, the existence of which results in a necessary and sufficient characterization of incremental exponential stability of multiple solution trajectories with respect to each other. By using a squared differential length as a Lyapunov-like function, its nonlinear stability analysis boils down to finding a suitable contraction metric that satisfies a stability condition expressed as a linear matrix inequality, indicating that many parallels can be drawn between well-known linear systems theory and contraction theory for nonlinear systems. Furthermore, contraction theory takes advantage of a superior robustness property of exponential stability used in conjunction with the comparison lemma. This yields much-needed safety and stability guarantees for neural network-based control and estimation schemes, without resorting to a more involved method of using uniform asymptotic stability for input-to-state stability. Such distinctive features permit systematic construction of a contraction metric via convex optimization, thereby obtaining an explicit exponential bound on the distance between a time-varying target trajectory and solution trajectories perturbed externally due to disturbances and learning errors. The objective of this paper is therefore to present a tutorial overview of contraction theory and its advantages in nonlinear stability analysis of deterministic and stochastic systems, with an emphasis on deriving formal robustness and stability guarantees for various learning-based and data-driven automatic control methods. In particular, we provide a detailed review of techniques for finding contraction metrics and associated control and estimation laws using deep neural networks.
Authors: Yadi Wei, Roni Khardon
Abstract: Traditional neural networks are simple to train but they typically produce overconfident predictions. In contrast, Bayesian neural networks provide good uncertainty quantification but optimizing them is time consuming due to the large parameter space. This paper proposes to combine the advantages of both approaches by performing Variational Inference in the Final layer Output space (VIFO), because the output space is much smaller than the parameter space. We use neural networks to learn the mean and the variance of the probabilistic output. Using the Bayesian formulation we incorporate collapsed variational inference with VIFO which significantly improves the performance in practice. On the other hand, like standard, non-Bayesian models, VIFO enjoys simple training and one can use Rademacher complexity to provide risk bounds for the model. Experiments show that VIFO provides a good tradeoff in terms of run time and uncertainty quantification, especially for out of distribution data.
Authors: Jungtaek Kim
Abstract: Bayesian optimization has attracted huge attention from diverse research areas in science and engineering, since it is capable of efficiently finding a global optimum of an expensive-to-evaluate black-box function. In general, a probabilistic regression model is widely used as a surrogate function to model an explicit distribution over function evaluations given an input to estimate and a training dataset. Beyond the probabilistic regression-based methods, density ratio estimation-based Bayesian optimization has been suggested in order to estimate a density ratio of the groups relatively close and relatively far to a global optimum. Developing this line of research further, supervised classifiers are employed to estimate a class probability for the two groups instead of a density ratio. However, the supervised classifiers used in this strategy are prone to be overconfident for known knowledge on global solution candidates. Supposing that we have access to unlabeled points, e.g., predefined fixed-size pools, we propose density ratio estimation-based Bayesian optimization with semi-supervised learning to solve this challenge. Finally, we show the empirical results of our methods and several baseline methods in two distinct scenarios with unlabeled point sampling and a fixed-size pool and analyze the validity of our proposed methods in diverse experiments.
Authors: Kenta Oono, Nontawat Charoenphakdee, Kotatsu Bito, Zhengyan Gao, Hideyoshi Igata, Masashi Yoshikawa, Yoshiaki Ota, Hiroki Okui, Kei Akita, Shoichiro Yamaguchi, Yohei Sugawara, Shin-ichi Maeda, Kunihiko Miyoshi, Yuki Saito, Koki Tsuda, Hiroshi Maruyama, Kohei Hayashi
Abstract: Identifying the relationship between healthcare attributes, lifestyles, and personality is vital for understanding and improving physical and mental well-being. Machine learning approaches are promising for modeling their relationships and offering actionable suggestions. In this paper, we propose Virtual Human Generative Model (VHGM), a machine learning model for estimating healthcare, lifestyles, and personality attributes. VHGM is a deep generative model trained with masked modeling to learn the joint distribution of attributes conditioned on known ones. Using heterogeneous tabular datasets, VHGM learns more than 2,000 attributes efficiently. We numerically evaluate the performance of VHGM and its training techniques and have deployed VHGM as a Web service, enabling various healthcare applications.
Authors: Khaled Mohammed Saifuddin, Mehmet Emin Aktas, Esra Akbas
Abstract: Hypergraphs, with their capacity to depict high-order relationships, have emerged as a significant extension of traditional graphs. Although Graph Neural Networks (GNNs) have remarkable performance in graph representation learning, their extension to hypergraphs encounters challenges due to their intricate structures. Furthermore, current hypergraph transformers, a special variant of GNN, utilize semantic feature-based self-attention, ignoring topological attributes of nodes and hyperedges. To address these challenges, we propose a Topology-guided Hypergraph Transformer Network (THTN). In this model, we first formulate a hypergraph from a graph while retaining its structural essence to learn higher-order relations within the graph. Then, we design a simple yet effective structural and spatial encoding module to incorporate the topological and spatial information of the nodes into their representation. Further, we present a structure-aware self-attention mechanism that discovers the important nodes and hyperedges from both semantic and structural viewpoints. By leveraging these two modules, THTN crafts an improved node representation, capturing both local and global topological expressions. Extensive experiments conducted on node classification tasks demonstrate that the performance of the proposed model consistently exceeds that of the existing approaches.
Authors: Marco Anisetti, Claudio A. Ardagna, Nicola Bena, Ernesto Damiani, Paolo G. Panero
Abstract: Modern applications are increasingly driven by Machine Learning (ML) models whose non-deterministic behavior is affecting the entire application life cycle from design to operation. The pervasive adoption of ML is urgently calling for approaches that guarantee a stable non-functional behavior of ML-based applications over time and across model changes. To this aim, non-functional properties of ML models, such as privacy, confidentiality, fairness, and explainability, must be monitored, verified, and maintained. Existing approaches mostly focus on i) implementing solutions for classifier selection according to the functional behavior of ML models, ii) finding new algorithmic solutions, such as continuous re-training. In this paper, we propose a multi-model approach that aims to guarantee a stable non-functional behavior of ML-based applications. An architectural and methodological approach is provided to compare multiple ML models showing similar non-functional properties and select the model supporting stable non-functional behavior over time according to (dynamic and unpredictable) contextual changes. Our approach goes beyond the state of the art by providing a solution that continuously guarantees a stable non-functional behavior of ML-based applications, is ML algorithm-agnostic, and is driven by non-functional properties assessed on the ML models themselves. It consists of a two-step process working during application operation, where model assessment verifies non-functional properties of ML models trained and selected at development time, and model substitution guarantees continuous and stable support of non-functional properties. We experimentally evaluate our solution in a real-world scenario focusing on non-functional property fairness.
Authors: Ziqi Zhang, Jingzehua Xu, Zifeng Zhuang, Hongyin Zhang, Jinxin Liu, Donglin wang, Shuai Zhang
Abstract: Proximal Policy Optimization (PPO) has been broadly applied to robotics learning, showcasing stable training performance. However, the fixed clipping bound setting may limit the performance of PPO. Specifically, there is no theoretical proof that the optimal clipping bound remains consistent throughout the entire training process. Meanwhile, previous researches suggest that a fixed clipping bound restricts the policy's ability to explore. Therefore, many past studies have aimed to dynamically adjust the PPO clipping bound to enhance PPO's performance. However, the objective of these approaches are not directly aligned with the objective of reinforcement learning (RL) tasks, which is to maximize the cumulative Return. Unlike previous clipping approaches, we propose a bi-level proximal policy optimization objective that can dynamically adjust the clipping bound to better reflect the preference (maximizing Return) of these RL tasks. Based on this bi-level proximal policy optimization paradigm, we introduce a new algorithm named Preference based Proximal Policy Optimization (Pb-PPO). Pb-PPO utilizes a multi-armed bandit approach to refelect RL preference, recommending the clipping bound for PPO that can maximizes the current Return. Therefore, Pb-PPO results in greater stability and improved performance compared to PPO with a fixed clipping bound. We test Pb-PPO on locomotion benchmarks across multiple environments, including Gym-Mujoco and legged-gym. Additionally, we validate Pb-PPO on customized navigation tasks. Meanwhile, we conducted comparisons with PPO using various fixed clipping bounds and various of clipping approaches. The experimental results indicate that Pb-PPO demonstrates superior training performance compared to PPO and its variants. Our codebase has been released at : https://github.com/stevezhangzA/pb_ppo
Authors: Siddharth Krishna Kumar
Abstract: This paper investigates the distinctions between gradient methods applied to non-differentiable functions (NGDMs) and classical gradient descents (GDs) designed for differentiable functions. First, we demonstrate significant differences in the convergence properties of NGDMs compared to GDs, challenging the applicability of the extensive neural network convergence literature based on $L-smoothness$ to non-smooth neural networks. Next, we demonstrate the paradoxical nature of NGDM solutions for $L_{1}$-regularized problems, showing that increasing the regularization penalty leads to an increase in the $L_{1}$ norm of optimal solutions in NGDMs. Consequently, we show that widely adopted $L_{1}$ penalization-based techniques for network pruning do not yield expected results. Additionally, we dispel the common belief that optimization algorithms like Adam and RMSProp perform similarly in non-differentiable contexts. Finally, we explore the Edge of Stability phenomenon, indicating its inapplicability even to Lipschitz continuous convex differentiable functions, leaving its relevance to non-convex non-differentiable neural networks inconclusive. Our analysis exposes misguided interpretations of NGDMs in widely referenced papers and texts due to an overreliance on strong smoothness assumptions, emphasizing the necessity for a nuanced understanding of foundational assumptions in the analysis of these systems.
Authors: Liwei Hu, Wenyong Wang, Yu Xiang, Stefan Sommer
Abstract: We propose to incorporate Riemannian geometric features from the geometry of aircraft wing surfaces in the prediction of coefficient of pressure (CP) on the aircraft wing. Contrary to existing approaches that treat the wing surface as a flat object, we represent the wing as a piecewise smooth manifold and calculate a set of Riemannian geometric features (Riemannian metric, connection, and curvature) over points of the wing. Combining these features in neighborhoods of points on the wing with coordinates and flight conditions gives inputs to a deep learning model that predicts CP distributions. Experimental results show that the method with incorporation of Riemannian geometric features, compared to state-of-the-art Deep Attention Network (DAN), reduces the predicted mean square error (MSE) of CP by an average of 15.00% for the DLR-F11 aircraft test set.
Authors: Adrian H\"ohl, Ivica Obadic, Miguel \'Angel Fern\'andez Torres, Hiba Najjar, Dario Oliveira, Zeynep Akata, Andreas Dengel, Xiao Xiang Zhu
Abstract: In recent years, black-box machine learning approaches have become a dominant modeling paradigm for knowledge extraction in remote sensing. Despite the potential benefits of uncovering the inner workings of these models with explainable AI, a comprehensive overview summarizing the explainable AI methods used and their objectives, findings, and challenges in remote sensing applications is still missing. In this paper, we address this gap by performing a systematic review to identify the key trends in the field and shed light on novel explainable AI approaches and emerging directions that tackle specific remote sensing challenges. We also reveal the common patterns of explanation interpretation, discuss the extracted scientific insights, and reflect on the approaches used for the evaluation of explainable AI methods. As such, our review provides a complete summary of the state-of-the-art of explainable AI in remote sensing. Further, we give a detailed outlook on the challenges and promising research directions, representing a basis for novel methodological development and a useful starting point for new researchers in the field.
Authors: Sunghyeon Woo, Baeseong Park, Byeongwook Kim, Minjung Jo, Se Jung Kwon, Dongsuk Jeon, Dongsoo Lee
Abstract: Large language models (LLMs) have achieved significant success across various domains. However, training these LLMs typically involves substantial memory and computational costs during both forward and backward propagation. While parameter-efficient fine-tuning (PEFT) considerably reduces the training memory associated with parameters, it does not address the significant computational costs and activation memory. In this paper, we propose Dropping Backward Propagation (DropBP), a novel approach designed to reduce computational costs and activation memory while maintaining accuracy. DropBP randomly drops layers during backward propagation, which is essentially equivalent to training shallow submodules generated by undropped layers and residual connections. Additionally, DropBP calculates the sensitivity of each layer to assign an appropriate drop rate, thereby stabilizing the training process. DropBP is not only applicable to full fine-tuning but can also be orthogonally integrated with all types of PEFT by dropping layers during backward propagation. Specifically, DropBP can reduce training time by 44% with comparable accuracy to the baseline, accelerate convergence to the same perplexity by 1.5x, and enable training with a sequence length 6.2x larger on a single NVIDIA-A100 GPU. Furthermore, our DropBP enabled a throughput increase of 79% on a NVIDIA A100 GPU and 117% on an Intel Gaudi2 HPU. The code is available at https://github.com/WooSunghyeon/dropbp.
Authors: Shubham Ugare, Tarun Suresh, Hangoo Kang, Sasa Misailovic, Gagandeep Singh
Abstract: LLMs are widely used in complex AI applications. These applications underscore the need for LLM outputs to adhere to a specific format, for their integration with other components in the systems. Typically the format rules e.g., for data serialization formats such as JSON, YAML, or Code in Programming Language are expressed as context-free grammar (CFG). Due to the hallucinations and unreliability of LLMs, instructing LLMs to adhere to specified syntax becomes an increasingly important challenge. We present SynCode, a novel framework for efficient and general syntactical decoding with LLMs, to address this challenge. SynCode ensures soundness and completeness with respect to the CFG of a formal language, effectively retaining valid tokens while filtering out invalid ones. SynCode uses an offline-constructed, efficient lookup table, the DFA mask store, derived from the DFA of the language's grammar for efficient generation. SynCode seamlessly integrates with any language defined by CFG, as evidenced by experiments focusing on generating JSON, Python, and Go outputs. Our experiments evaluating the effectiveness of SynCode for JSON generation demonstrate that SynCode eliminates all syntax errors and significantly outperforms state-of-the-art baselines. Furthermore, our results underscore how SynCode significantly reduces 96.07% of syntax errors in generated Python and Go code, showcasing its substantial impact on enhancing syntactical precision in LLM generation. Our code is available at https://github.com/uiuc-focal-lab/syncode
Authors: Kimon Protopapas, Anas Barakat
Abstract: Policy Mirror Descent (PMD) stands as a versatile algorithmic framework encompassing several seminal policy gradient algorithms such as natural policy gradient, with connections with state-of-the-art reinforcement learning (RL) algorithms such as TRPO and PPO. PMD can be seen as a soft Policy Iteration algorithm implementing regularized 1-step greedy policy improvement. However, 1-step greedy policies might not be the best choice and recent remarkable empirical successes in RL such as AlphaGo and AlphaZero have demonstrated that greedy approaches with respect to multiple steps outperform their 1-step counterpart. In this work, we propose a new class of PMD algorithms called $h$-PMD which incorporates multi-step greedy policy improvement with lookahead depth $h$ to the PMD update rule. To solve discounted infinite horizon Markov Decision Processes with discount factor $\gamma$, we show that $h$-PMD which generalizes the standard PMD enjoys a faster dimension-free $\gamma^h$-linear convergence rate, contingent on the computation of multi-step greedy policies. We propose an inexact version of $h$-PMD where lookahead action values are estimated. Under a generative model, we establish a sample complexity for $h$-PMD which improves over prior work. Finally, we extend our result to linear function approximation to scale to large state spaces. Under suitable assumptions, our sample complexity only involves dependence on the dimension of the feature map space instead of the state space size.
Authors: Arash Badie-Modiri, Chiara Boldrini, Lorenzo Valerio, J\'anos Kert\'esz, M\'arton Karsai
Abstract: Fully decentralised federated learning enables collaborative training of individual machine learning models on a distributed network of communicating devices while keeping the training data localised on each node. This approach avoids central coordination, enhances data privacy and eliminates the risk of a single point of failure. Our research highlights that the effectiveness of decentralised federated learning is significantly influenced by the network topology of connected devices and the learning models' initial conditions. We propose a strategy for uncoordinated initialisation of the artificial neural networks based on the distribution of eigenvector centralities of the underlying communication network, leading to a radically improved training efficiency. Additionally, our study explores the scaling behaviour and the choice of environmental parameters under our proposed initialisation strategy. This work paves the way for more efficient and scalable artificial neural network training in a distributed and uncoordinated environment, offering a deeper understanding of the intertwining roles of network structure and learning dynamics.
Authors: Silpa Vadakkeeveetil Sreelatha, Adarsh Kappiyath, Abhra Chaudhuri, Anjan Dutta
Abstract: Neural networks trained on biased datasets tend to inadvertently learn spurious correlations, hindering generalization. We formally prove that (1) samples that exhibit spurious correlations lie on a lower rank manifold relative to the ones that do not; and (2) the depth of a network acts as an implicit regularizer on the rank of the attribute subspace that is encoded in its representations. Leveraging these insights, we present DeNetDM, a novel debiasing method that uses network depth modulation as a way of developing robustness to spurious correlations. Using a training paradigm derived from Product of Experts, we create both biased and debiased branches with deep and shallow architectures and then distill knowledge to produce the target debiased model. Our method requires no bias annotations or explicit data augmentation while performing on par with approaches that require either or both. We demonstrate that DeNetDM outperforms existing debiasing techniques on both synthetic and real-world datasets by 5\%. The project page is available at https://vssilpa.github.io/denetdm/.
Authors: Jialin Chen, Jan Eric Lenssen, Aosong Feng, Weihua Hu, Matthias Fey, Leandros Tassiulas, Jure Leskovec, Rex Ying
Abstract: Time series forecasting has attracted significant attention in recent decades. Previous studies have demonstrated that the Channel-Independent (CI) strategy improves forecasting performance by treating different channels individually, while it leads to poor generalization on unseen instances and ignores potentially necessary interactions between channels. Conversely, the Channel-Dependent (CD) strategy mixes all channels with even irrelevant and indiscriminate information, which, however, results in oversmoothing issues and limits forecasting accuracy. There is a lack of channel strategy that effectively balances individual channel treatment for improved forecasting performance without overlooking essential interactions between channels. Motivated by our observation of a correlation between the time series model's performance boost against channel mixing and the intrinsic similarity on a pair of channels, we developed a novel and adaptable Channel Clustering Module (CCM). CCM dynamically groups channels characterized by intrinsic similarities and leverages cluster information instead of individual channel identities, combining the best of CD and CI worlds. Extensive experiments on real-world datasets demonstrate that CCM can (1) boost the performance of CI and CD models by an average margin of 2.4% and 7.2% on long-term and short-term forecasting, respectively; (2) enable zero-shot forecasting with mainstream time series forecasting models; (3) uncover intrinsic time series patterns among channels and improve interpretability of complex time series models.
Authors: Zeyu Yang, Han Yu, Peikun Guo, Khadija Zanna, Xiaoxue Yang, Akane Sano
Abstract: Diffusion models have emerged as a robust framework for various generative tasks, including tabular data synthesis. However, current tabular diffusion models tend to inherit bias in the training dataset and generate biased synthetic data, which may influence discriminatory actions. In this research, we introduce a novel tabular diffusion model that incorporates sensitive guidance to generate fair synthetic data with balanced joint distributions of the target label and sensitive attributes, such as sex and race. The empirical results demonstrate that our method effectively mitigates bias in training data while maintaining the quality of the generated samples. Furthermore, we provide evidence that our approach outperforms existing methods for synthesizing tabular data on fairness metrics such as demographic parity ratio and equalized odds ratio, achieving improvements of over $10\%$. Our implementation is available at https://github.com/comp-well-org/fair-tab-diffusion.
Authors: Pasan Dissanayake, Sanghamitra Dutta
Abstract: Counterfactual explanations provide ways of achieving a favorable model outcome with minimum input perturbation. However, counterfactual explanations can also be leveraged to reconstruct the model by strategically training a surrogate model to give similar predictions as the original (target) model. In this work, we analyze how model reconstruction using counterfactuals can be improved by further leveraging the fact that the counterfactuals also lie quite close to the decision boundary. Our main contribution is to derive novel theoretical relationships between the error in model reconstruction and the number of counterfactual queries required using polytope theory. Our theoretical analysis leads us to propose a strategy for model reconstruction that we call Counterfactual Clamping Attack (CCA) which trains a surrogate model using a unique loss function that treats counterfactuals differently than ordinary instances. Our approach also alleviates the related problem of decision boundary shift that arises in existing model reconstruction approaches when counterfactuals are treated as ordinary instances. Experimental results demonstrate that our strategy improves fidelity between the target and surrogate model predictions on several datasets.
Authors: Hengkang Wang, Xu Zhang, Taihui Li, Yuxiang Wan, Tiancong Chen, Ju Sun
Abstract: Pretrained diffusion models (DMs) have recently been popularly used in solving inverse problems (IPs). The existing methods mostly interleave iterative steps in the reverse diffusion process and iterative steps to bring the iterates closer to satisfying the measurement constraint. However, such interleaving methods struggle to produce final results that look like natural objects of interest (i.e., manifold feasibility) and fit the measurement (i.e., measurement feasibility), especially for nonlinear IPs. Moreover, their capabilities to deal with noisy IPs with unknown types and levels of measurement noise are unknown. In this paper, we advocate viewing the reverse process in DMs as a function and propose a novel plug-in method for solving IPs using pretrained DMs, dubbed DMPlug. DMPlug addresses the issues of manifold feasibility and measurement feasibility in a principled manner, and also shows great potential for being robust to unknown types and levels of noise. Through extensive experiments across various IP tasks, including two linear and three nonlinear IPs, we demonstrate that DMPlug consistently outperforms state-of-the-art methods, often by large margins especially for nonlinear IPs. The code is available at https://github.com/sun-umn/DMPlug.
Authors: Renato M. Silva, Greg\'orio F. Azevedo, Matheus V. V. Berto, Jean R. Rocha, Eduardo C. Fidelis, Matheus V. Nogueira, Pedro H. Lisboa, Tiago A. Almeida
Abstract: Traffic incidents involving vulnerable road users (VRUs) constitute a significant proportion of global road accidents. Advances in traffic communication ecosystems, coupled with sophisticated signal processing and machine learning techniques, have facilitated the utilization of data from diverse sensors. Despite these advancements and the availability of extensive datasets, substantial progress is required to mitigate traffic casualties. This paper provides a comprehensive survey of state-of-the-art technologies and methodologies to enhance the safety of VRUs. The study delves into the communication networks between vehicles and VRUs, emphasizing the integration of advanced sensors and the availability of relevant datasets. It explores preprocessing techniques and data fusion methods to enhance sensor data quality. Furthermore, our study assesses critical simulation environments essential for developing and testing VRU safety systems. Our research also highlights recent advances in VRU detection and classification algorithms, addressing challenges such as variable environmental conditions. Additionally, we cover cutting-edge research in predicting VRU intentions and behaviors, which is crucial for proactive collision avoidance strategies. Through this survey, we aim to provide a comprehensive understanding of the current landscape of VRU safety technologies, identifying areas of progress and areas needing further research and development.
Authors: Andrew C. Li, Zizhao Chen, Toryn Q. Klassen, Pashootan Vaezipoor, Rodrigo Toro Icarte, Sheila A. McIlraith
Abstract: Reward Machines provide an automaton-inspired structure for specifying instructions, safety constraints, and other temporally extended reward-worthy behaviour. By exposing the underlying structure of a reward function, they enable the decomposition of an RL task, leading to impressive gains in sample efficiency. Although Reward Machines and similar formal specifications have a rich history of application towards sequential decision-making problems, they critically rely on a ground-truth interpretation of the domain-specific vocabulary that forms the building blocks of the reward function--such ground-truth interpretations are elusive in the real world due in part to partial observability and noisy sensing. In this work, we explore the use of Reward Machines for Deep RL in noisy and uncertain environments. We characterize this problem as a POMDP and propose a suite of RL algorithms that exploit task structure under uncertain interpretation of the domain-specific vocabulary. Through theory and experiments, we expose pitfalls in naive approaches to this problem while simultaneously demonstrating how task structure can be successfully leveraged under noisy interpretations of the vocabulary.
Authors: Nikola Milosevic, Gesine M\"uller, Jan Huisken, Nico Scherf
Abstract: In this work, we introduce the concept of Active Representation Learning, a novel class of problems that intertwines exploration and representation learning within partially observable environments. We extend ideas from Active Simultaneous Localization and Mapping (active SLAM), and translate them to scientific discovery problems, exemplified by adaptive microscopy. We explore the need for a framework that derives exploration skills from representations that are in some sense actionable, aiming to enhance the efficiency and effectiveness of data collection and model building in the natural sciences.
Authors: Tam Thuc Do, Parham Eftekhar, Seyed Alireza Hosseini, Gene Cheung, Philip Chou
Abstract: We build interpretable and lightweight transformer-like neural networks by unrolling iterative optimization algorithms that minimize graph smoothness priors -- the quadratic graph Laplacian regularizer (GLR) and the $\ell_1$-norm graph total variation (GTV) -- subject to an interpolation constraint. The crucial insight is that a normalized signal-dependent graph learning module amounts to a variant of the basic self-attention mechanism in conventional transformers. Unlike "black-box" transformers that require learning of large key, query and value matrices to compute scaled dot products as affinities and subsequent output embeddings, resulting in huge parameter sets, our unrolled networks employ shallow CNNs to learn low-dimensional features per node to establish pairwise Mahalanobis distances and construct sparse similarity graphs. At each layer, given a learned graph, the target interpolated signal is simply a low-pass filtered output derived from the minimization of an assumed graph smoothness prior, leading to a dramatic reduction in parameter count. Experiments for two image interpolation applications verify the restoration performance, parameter efficiency and robustness to covariate shift of our graph-based unrolled networks compared to conventional transformers.
Authors: Xuehui Yu, Mhairi Dunion, Xin Li, Stefano V. Albrecht
Abstract: Meta-Reinforcement Learning (Meta-RL) agents can struggle to operate across tasks with varying environmental features that require different optimal skills (i.e., different modes of behaviour). Using context encoders based on contrastive learning to enhance the generalisability of Meta-RL agents is now widely studied but faces challenges such as the requirement for a large sample size, also referred to as the $\log$-$K$ curse. To improve RL generalisation to different tasks, we first introduce Skill-aware Mutual Information (SaMI), an optimisation objective that aids in distinguishing context embeddings according to skills, thereby equipping RL agents with the ability to identify and execute different skills across tasks. We then propose Skill-aware Noise Contrastive Estimation (SaNCE), a $K$-sample estimator used to optimise the SaMI objective. We provide a framework for equipping an RL agent with SaNCE in practice and conduct experimental validation on modified MuJoCo and Panda-gym benchmarks. We empirically find that RL agents that learn by maximising SaMI achieve substantially improved zero-shot generalisation to unseen tasks. Additionally, the context encoder trained with SaNCE demonstrates greater robustness to a reduction in the number of available samples, thus possessing the potential to overcome the $\log$-$K$ curse.
Authors: Lucas Slot, Stefan Tiegel, Manuel Wiedmer
Abstract: Rubinfeld & Vasilyan recently introduced the framework of testable learning as an extension of the classical agnostic model. It relaxes distributional assumptions which are difficult to verify by conditions that can be checked efficiently by a tester. The tester has to accept whenever the data truly satisfies the original assumptions, and the learner has to succeed whenever the tester accepts. We focus on the setting where the tester has to accept standard Gaussian data. There, it is known that basic concept classes such as halfspaces can be learned testably with the same time complexity as in the (distribution-specific) agnostic model. In this work, we ask whether there is a price to pay for testably learning more complex concept classes. In particular, we consider polynomial threshold functions (PTFs), which naturally generalize halfspaces. We show that PTFs of arbitrary constant degree can be testably learned up to excess error $\varepsilon > 0$ in time $n^{\mathrm{poly}(1/\varepsilon)}$. This qualitatively matches the best known guarantees in the agnostic model. Our results build on a connection between testable learning and fooling. In particular, we show that distributions that approximately match at least $\mathrm{poly}(1/\varepsilon)$ moments of the standard Gaussian fool constant-degree PTFs (up to error $\varepsilon$). As a secondary result, we prove that a direct approach to show testable learning (without fooling), which was successfully used for halfspaces, cannot work for PTFs.
Authors: Xiaodong Wu, Wenyi Yu, Chao Zhang, Philip Woodland
Abstract: Approximate Natural Gradient Descent (NGD) methods are an important family of optimisers for deep learning models, which use approximate Fisher information matrices to pre-condition gradients during training. The empirical Fisher (EF) method approximates the Fisher information matrix empirically by reusing the per-sample gradients collected during back-propagation. Despite its ease of implementation, the EF approximation has its theoretical and practical limitations. This paper investigates the inversely-scaled projection issue of EF, which is shown to be a major cause of its poor empirical approximation quality. An improved empirical Fisher (iEF) method is proposed to address this issue, which is motivated as a generalised NGD method from a loss reduction perspective, meanwhile retaining the practical convenience of EF. The exact iEF and EF methods are experimentally evaluated using practical deep learning setups. Optimisation experiments show that applying exact iEF directly as an optimiser provides strong convergence and generalisation. Additionally, under a novel empirical evaluation framework, the proposed iEF method shows consistently better approximation quality to exact Natural Gradient updates than both the EF and the more expensive sampled Fisher methods, meanwhile demonstrating the superior property of being robust to the choice of damping across tasks and training stages. Improving existing approximate NGD optimisers with iEF is expected to lead to better convergence and robustness. Furthermore, the iEF method also serves as a better approximation method to the Fisher information matrix itself, which enables the improvement of a variety of Fisher-based methods, not limited to the scope of optimisation.
Authors: Yongjie Duan, Vince D. Calhoun, Zhiying Long
Abstract: Dynamic functional connectivity (DFC) analysis has been widely applied to functional magnetic resonance imaging (fMRI) data to reveal time-varying dynamic changes of brain states. The sliding window method is by far the most popular DFC analysis method due to its simplicity. However, the sliding window method comes with some assumptions, namely the typically approach uses a single window which captures dynamics only within a specific frequency range. In this study, we propose a generalized approach to dynamics via a multi-dimensional random convolution (RandCon) DFC method that is able to effectively capture time-varying DFC at arbitrary time scales by extracting different local features from fMRI time series using a number of multi-dimensional random convolution kernels without the need for learning kernel weights. Compared to a standard sliding window method, multiplication of temporal derivatives (MTD) and phase synchrony methods, RandCon with the smallest kernel size (3 time points) showed notable improvements in performance on simulated data, particularly in terms of DFC temporal and spatial estimation in very short window/kernel size under different noise levels. Results from real fMRI data indicated that RandCon was more sensitive to gender differences than competing methods. Furthermore, we show that the sliding window method can be considered a special case of the proposed multi-dimensional convolution framework. The proposed method is simple and efficient significantly broadens the scope of dynamic functional connectivity research and offer theoretical and practical potential.
Authors: Dong Liu
Abstract: The conventional training approaches often face challenges in balancing the breadth of multi-task learning (MTL) with the depth of single-task learning (STL). To address this issue, we introduce the Multi-Task to Single-Task (MT2ST) framework, a groundbreaking approach that can combine the generalizability of MTL with the precision of STL. Our work include two strategies: 'Diminish' and 'Switch'. 'Diminish' Strategy will gradually reduce the influence of auxiliary tasks, while the 'Switch' strategy involves a shift from multi-tasking to single-tasking at a specific timepoint at the training process. In this paper, we propose the Multi-Task to Single-Task (MT2ST) framework, a novel approach that significantly enhances the efficiency and accuracy of word embedding training while concurrently addressing prevalent issues such as overfitting. Our empirical studies demonstrate that MT2ST can reduce training time by 67% when contrasted with single-task learning approaches, and by 13% compared to traditional multi-task learning methods. These findings underscore MT2ST's potential to be a powerful tools for word embedding training acceleration. The code implementation is can be found at: https://github.com/NoakLiu/MT2ST-Word-Embeddings-Acceleration.
URLs: https://github.com/NoakLiu/MT2ST-Word-Embeddings-Acceleration.
Authors: Azim Ospanov, Jingwei Zhang, Mohammad Jalali, Xuenan Cao, Andrej Bogdanov, Farzan Farnia
Abstract: While standard evaluation scores for generative models are mostly reference-based, a reference-dependent assessment of generative models could be generally difficult due to the unavailability of applicable reference datasets. Recently, the reference-free entropy scores, VENDI and RKE, have been proposed to evaluate the diversity of generated data. However, estimating these scores from data leads to significant computational costs for large-scale generative models. In this work, we leverage the random Fourier features framework to reduce the computational price and propose the Fourier-based Kernel Entropy Approximation (FKEA) method. We utilize FKEA's approximated eigenspectrum of the kernel matrix to efficiently estimate the mentioned entropy scores. Furthermore, we show the application of FKEA's proxy eigenvectors to reveal the method's identified modes in evaluating the diversity of produced samples. We provide a stochastic implementation of the FKEA assessment algorithm with a complexity $O(n)$ linearly growing with sample size $n$. We extensively evaluate FKEA's numerical performance in application to standard image, text, and video datasets. Our empirical results indicate the method's scalability and interpretability applied to large-scale generative models. The codebase is available at https://github.com/aziksh-ospanov/FKEA.
Authors: Simon Mataigne, Johan Mathe, Sophia Sanborn, Christopher Hillar, Nina Miolane
Abstract: An important problem in signal processing and deep learning is to achieve \textit{invariance} to nuisance factors not relevant for the task. Since many of these factors are describable as the action of a group $G$ (e.g. rotations, translations, scalings), we want methods to be $G$-invariant. The $G$-Bispectrum extracts every characteristic of a given signal up to group action: for example, the shape of an object in an image, but not its orientation. Consequently, the $G$-Bispectrum has been incorporated into deep neural network architectures as a computational primitive for $G$-invariance\textemdash akin to a pooling mechanism, but with greater selectivity and robustness. However, the computational cost of the $G$-Bispectrum ($\mathcal{O}(|G|^2)$, with $|G|$ the size of the group) has limited its widespread adoption. Here, we show that the $G$-Bispectrum computation contains redundancies that can be reduced into a \textit{selective $G$-Bispectrum} with $\mathcal{O}(|G|)$ complexity. We prove desirable mathematical properties of the selective $G$-Bispectrum and demonstrate how its integration in neural networks enhances accuracy and robustness compared to traditional approaches, while enjoying considerable speeds-up compared to the full $G$-Bispectrum.
Authors: Weiqin Chen, Sandipan Mishra, Santiago Paternain
Abstract: Offline reinforcement learning (RL) learns effective policies from a static target dataset. Despite state-of-the-art (SOTA) offline RL algorithms being promising, they highly rely on the quality of the target dataset. The performance of SOTA algorithms can degrade in scenarios with limited samples in the target dataset, which is often the case in real-world applications. To address this issue, domain adaptation that leverages auxiliary samples from related source datasets (such as simulators) can be beneficial. In this context, determining the optimal way to trade off the source and target datasets remains a critical challenge in offline RL. To the best of our knowledge, this paper proposes the first framework that theoretically and experimentally explores how the weight assigned to each dataset affects the performance of offline RL. We establish the performance bounds and convergence neighborhood of our framework, both of which depend on the selection of the weight. Furthermore, we identify the existence of an optimal weight for balancing the two datasets. All theoretical guarantees and optimal weight depend on the quality of the source dataset and the size of the target dataset. Our empirical results on the well-known Procgen Benchmark substantiate our theoretical contributions.
Authors: Nadav Cohen, Noam Razin
Abstract: These notes are based on a lecture delivered by NC on March 2021, as part of an advanced course in Princeton University on the mathematical understanding of deep learning. They present a theory (developed by NC, NR and collaborators) of linear neural networks -- a fundamental model in the study of optimization and generalization in deep learning. Practical applications born from the presented theory are also discussed. The theory is based on mathematical tools that are dynamical in nature. It showcases the potential of such tools to push the envelope of our understanding of optimization and generalization in deep learning. The text assumes familiarity with the basics of statistical learning theory. Exercises (without solutions) are included.
Authors: Hanwen Zhang, Dusit Niyato, Wei Zhang, Changyuan Zhao, Hongyang Du, Abbas Jamalipour, Sumei Sun, Yiyang Pei
Abstract: With the advancements of generative artificial intelligence (GenAI) models, their capabilities are expanding significantly beyond content generation and the models are increasingly being used across diverse applications. Particularly, GenAI shows great potential in addressing challenges in the electric vehicle (EV) ecosystem ranging from charging management to cyber-attack prevention. In this paper, we specifically consider Internet of electric vehicles (IoEV) and we categorize GenAI for IoEV into four different layers namely, EV's battery layer, individual EV layer, smart grid layer, and security layer. We introduce various GenAI techniques used in each layer of IoEV applications. Subsequently, public datasets available for training the GenAI models are summarized. Finally, we provide recommendations for future directions. This survey not only categorizes the applications of GenAI in IoEV across different layers but also serves as a valuable resource for researchers and practitioners by highlighting the design and implementation challenges within each layer. Furthermore, it provides a roadmap for future research directions, enabling the development of more robust and efficient IoEV systems through the integration of advanced GenAI techniques.
Authors: Andrei Margeloiu, Xiangjian Jiang, Nikola Simidjievski, Mateja Jamnik
Abstract: Data collection is often difficult in critical fields such as medicine, physics, and chemistry. As a result, classification methods usually perform poorly with these small datasets, leading to weak predictive performance. Increasing the training set with additional synthetic data, similar to data augmentation in images, is commonly believed to improve downstream classification performance. However, current tabular generative methods that learn either the joint distribution $ p(\mathbf{x}, y) $ or the class-conditional distribution $ p(\mathbf{x} \mid y) $ often overfit on small datasets, resulting in poor-quality synthetic data, usually worsening classification performance compared to using real data alone. To solve these challenges, we introduce TabEBM, a novel class-conditional generative method using Energy-Based Models (EBMs). Unlike existing methods that use a shared model to approximate all class-conditional densities, our key innovation is to create distinct EBM generative models for each class, each modelling its class-specific data distribution individually. This approach creates robust energy landscapes, even in ambiguous class distributions. Our experiments show that TabEBM generates synthetic data with higher quality and better statistical fidelity than existing methods. When used for data augmentation, our synthetic data consistently improves the classification performance across diverse datasets of various sizes, especially small ones. Code is available at https://github.com/andreimargeloiu/TabEBM.
Authors: Ivi Chatzi, Nina Corvelo Benz, Eleni Straitouri, Stratis Tsirtsis, Manuel Gomez-Rodriguez
Abstract: "Sure, I am happy to generate a story for you: Captain Lyra stood at the helm of her trusty ship, the Maelstrom's Fury, gazing out at the endless sea. [...] Lyra's eyes welled up with tears as she realized the bitter truth - she had sacrificed everything for fleeting riches, and lost the love of her crew, her family, and herself." Although this story, generated by a large language model, is captivating, one may wonder -- how would the story have unfolded if the model had chosen "Captain Maeve" as the protagonist instead? We cannot know. State-of-the-art large language models are stateless -- they maintain no internal memory or state. Given a prompt, they generate a sequence of tokens as an output using an autoregressive process. As a consequence, they cannot reason about counterfactual alternatives to tokens they have generated in the past. In this work, our goal is to enhance them with this functionality. To this end, we develop a causal model of token generation that builds upon the Gumbel-Max structural causal model. Our model allows any large language model to perform counterfactual token generation at almost no cost in comparison with vanilla token generation, it is embarrassingly simple to implement, and it does not require any fine-tuning nor prompt engineering. We implement our model on Llama 3 8B-Instruct and Ministral-8B-Instruct and conduct a qualitative and a quantitative analysis of counterfactually generated text. We conclude with a demonstrative application of counterfactual token generation for bias detection, unveiling interesting insights about the model of the world constructed by large language models.
Authors: Cooper Lorsung, Amir Barati Farimani
Abstract: Solving Partial Differential Equations (PDEs) is ubiquitous in science and engineering. Computational complexity and difficulty in writing numerical solvers has motivated the development of machine learning techniques to generate solutions quickly. Many existing methods are purely data driven, relying solely on numerical solution fields, rather than known system information such as boundary conditions and governing equations. However, the recent rise in popularity of Large Language Models (LLMs) has enabled easy integration of text in multimodal machine learning models. In this work, we use pretrained LLMs to integrate various amounts known system information into PDE learning. Our multimodal approach significantly outperforms our baseline model, FactFormer, in both next-step prediction and autoregressive rollout performance on the 2D Heat, Burgers, Navier-Stokes, and Shallow Water equations. Further analysis shows that pretrained LLMs provide highly structured latent space that is consistent with the amount of system information provided through text.
Authors: Yan Scholten, Stephan G\"unnemann, Leo Schwinn
Abstract: Comprehensive evaluation of Large Language Models (LLMs) is an open research problem. Existing evaluations rely on deterministic point estimates generated via greedy decoding. However, we find that deterministic evaluations fail to capture the whole output distribution of a model, yielding inaccurate estimations of model capabilities. This is particularly problematic in critical contexts such as unlearning and alignment, where precise model evaluations are crucial. To remedy this, we introduce the first formal probabilistic evaluation framework in LLMs. Namely, we derive novel metrics with high-probability guarantees concerning the output distribution of a model. Our metrics are application-independent and allow practitioners to make more reliable estimates about model capabilities before deployment. Through a case study focused on unlearning, we reveal that deterministic evaluations falsely indicate successful unlearning, whereas our probabilistic evaluations demonstrate that most if not all of the supposedly unlearned information remains accessible in these models. Additionally, we propose a novel unlearning loss based on entropy optimization and adaptive temperature scaling, which significantly improves unlearning in probabilistic settings on recent benchmarks. Our proposed shift from point estimates to probabilistic evaluations of output distributions represents an important step toward comprehensive evaluations of LLMs. Code available at https://github.com/yascho/probabilistic-unlearning.
Authors: Yong Liu, Guo Qin, Xiangdong Huang, Jianmin Wang, Mingsheng Long
Abstract: We present Timer-XL, a generative Transformer for unified time series forecasting. To uniformly predict 1D and 2D time series, we generalize next token prediction, predominantly adopted for causal generation of 1D sequences, to multivariate next token prediction. The proposed paradigm uniformly formulates various forecasting scenarios as a long-context generation problem. We opt for the generative Transformer, which can capture global-range and causal dependencies while providing contextual flexibility, to implement unified forecasting on univariate series characterized by non-stationarity, multivariate time series with complicated dynamics and correlations, and covariate-informed contexts that include both endogenous and exogenous variables. Technically, we propose a universal TimeAttention to facilitate generative Transformers on time series, which can effectively capture fine-grained intra- and inter-series dependencies of flattened time series tokens (patches) and is further strengthened by position embeddings in both temporal and variable dimensions. Timer-XL achieves state-of-the-art performance across challenging forecasting benchmarks through a unified approach. As a large time series model, it demonstrates notable model transferability by large-scale pre-training, as well as contextual flexibility in token lengths, positioning it as a one-for-all forecaster.
Authors: Shuhe Wang, Guoyin Wang, Yizhong Wang, Jiwei Li, Eduard Hovy, Chen Guo
Abstract: Packing, initially utilized in the pre-training phase, is an optimization technique designed to maximize hardware resource efficiency by combining different training sequences to fit the model's maximum input length. Although it has demonstrated effectiveness during pre-training, there remains a lack of comprehensive analysis for the supervised fine-tuning (SFT) stage on the following points: (1) whether packing can effectively enhance training efficiency while maintaining performance, (2) the suitable size of the model and dataset for fine-tuning with the packing method, and (3) whether packing unrelated or related training samples might cause the model to either excessively disregard or over-rely on the context. In this paper, we perform extensive comparisons between SFT methods using padding and packing, covering SFT datasets ranging from 69K to 1.2M and models from 8B to 70B. This provides the first comprehensive analysis of the advantages and limitations of packing versus padding, as well as practical considerations for implementing packing in various training scenarios. Our analysis covers various benchmarks, including knowledge, reasoning, and coding, as well as GPT-based evaluations, time efficiency, and other fine-tuning parameters. We also open-source our code for fine-tuning and evaluation and provide checkpoints fine-tuned on datasets of different sizes, aiming to advance future research on packing methods. Code is available at: https://github.com/ShuheWang1998/Packing-Analysis?tab=readme-ov-file.
URLs: https://github.com/ShuheWang1998/Packing-Analysis?tab=readme-ov-file.
Authors: Haolin Wang, Xuefeng Liu, Jianwei Niu, Wenkai Guo, Shaojie Tang
Abstract: Federated learning is a distributed machine learning paradigm designed to protect user data privacy, which has been successfully implemented across various scenarios. In traditional federated learning, the entire parameter set of local models is updated and averaged in each training round. Although this full network update method maximizes knowledge acquisition and sharing for each model layer, it prevents the layers of the global model from cooperating effectively to complete the tasks of each client, a challenge we refer to as layer mismatch. This mismatch problem recurs after every parameter averaging, consequently slowing down model convergence and degrading overall performance. To address the layer mismatch issue, we introduce the FedPart method, which restricts model updates to either a single layer or a few layers during each communication round. Furthermore, to maintain the efficiency of knowledge acquisition and sharing, we develop several strategies to select trainable layers in each round, including sequential updating and multi-round cycle training. Through both theoretical analysis and experiments, our findings demonstrate that the FedPart method significantly surpasses conventional full network update strategies in terms of convergence speed and accuracy, while also reducing communication and computational overheads.
Authors: Khiem Le, Nitesh V. Chawla
Abstract: Molecule optimization is a critical task in drug discovery to optimize desired properties of a given molecule through chemical modification. Despite Large Language Models (LLMs) holding the potential to efficiently simulate this task by using natural language to direct the optimization, straightforwardly utilizing shows limited performance. In this work, we facilitate utilizing LLMs in an iterative paradigm by proposing a simple yet highly effective domain feedback provider, namely $\text{Re}^3$DF. In detail, $\text{Re}^3$DF harnesses an external toolkit, RDKit, to handle the molecule hallucination, if the modified molecule is chemically invalid. Otherwise, its desired properties are computed and compared to the original one, establishing reliable domain feedback with correct direction and distance towards the objective, followed by a retrieved example, to explicitly guide the LLM to refine the modified molecule. We conduct experiments across both single- and multi-property objectives with 2 thresholds, where $\text{Re}^3$DF shows significant improvements. Particularly, for 20 single-property objectives, $\text{Re}^3$DF enhances Hit ratio by 16.95% and 20.76% under loose and strict thresholds, respectively. For 32 multi-property objectives, $\text{Re}^3$DF enhances Hit ratio by 6.04% and 5.25%.
Authors: Thomas Robert, Mher Safaryan, Ionut-Vlad Modoranu, Dan Alistarh
Abstract: We introduce LDAdam, a memory-efficient optimizer for training large models, that performs adaptive optimization steps within lower dimensional subspaces, while consistently exploring the full parameter space during training. This strategy keeps the optimizer's memory footprint to a fraction of the model size. LDAdam relies on a new projection-aware update rule for the optimizer states that allows for transitioning between subspaces, i.e., estimation of the statistics of the projected gradients. To mitigate the errors due to low-rank projection, LDAdam integrates a new generalized error feedback mechanism, which explicitly accounts for both gradient and optimizer state compression. We prove the convergence of LDAdam under standard assumptions, and show that LDAdam allows for accurate and efficient fine-tuning and pre-training of language models.
Authors: Yiqing Guo, Karel Mokany, Shaun R. Levick, Jinyan Yang, Peyman Moghadam
Abstract: Earth observation data have shown promise in predicting species richness of vascular plants ($\alpha$-diversity), but extending this approach to large spatial scales is challenging because geographically distant regions may exhibit different compositions of plant species ($\beta$-diversity), resulting in a location-dependent relationship between richness and spectral measurements. In order to handle such geolocation dependency, we propose Spatioformer, where a novel geolocation encoder is coupled with the transformer model to encode geolocation context into remote sensing imagery. The Spatioformer model compares favourably to state-of-the-art models in richness predictions on a large-scale ground-truth richness dataset (HAVPlot) that consists of 68,170 in-situ richness samples covering diverse landscapes across Australia. The results demonstrate that geolocational information is advantageous in predicting species richness from satellite observations over large spatial scales. With Spatioformer, plant species richness maps over Australia are compiled from Landsat archive for the years from 2015 to 2023. The richness maps produced in this study reveal the spatiotemporal dynamics of plant species richness in Australia, providing supporting evidence to inform effective planning and policy development for plant diversity conservation. Regions of high richness prediction uncertainties are identified, highlighting the need for future in-situ surveys to be conducted in these areas to enhance the prediction accuracy.
Authors: Zheng-An Chen, Tao Luo, GuiHong Wang
Abstract: The multi-stage phenomenon in the training loss curves of neural networks has been widely observed, reflecting the non-linearity and complexity inherent in the training process. In this work, we investigate the training dynamics of neural networks (NNs), with particular emphasis on the small initialization regime, identifying three distinct stages observed in the loss curve during training: the initial plateau stage, the initial descent stage, and the secondary plateau stage. Through rigorous analysis, we reveal the underlying challenges contributing to slow training during the plateau stages. While the proof and estimate for the emergence of the initial plateau were established in our previous work, the behaviors of the initial descent and secondary plateau stages had not been explored before. Here, we provide a more detailed proof for the initial plateau, followed by a comprehensive analysis of the initial descent stage dynamics. Furthermore, we examine the factors facilitating the network's ability to overcome the prolonged secondary plateau, supported by both experimental evidence and heuristic reasoning. Finally, to clarify the link between global training trends and local parameter adjustments, we use the Wasserstein distance to track the fine-scale evolution of weight amplitude distribution.
Authors: Zhuan Shi, Yifei Song, Xiaoli Tang, Lingjuan Lyu, Boi Faltings
Abstract: Generative art using Diffusion models has achieved remarkable performance in image generation and text-to-image tasks. However, the increasing demand for training data in generative art raises significant concerns about copyright infringement, as models can produce images highly similar to copyrighted works. Existing solutions attempt to mitigate this by perturbing Diffusion models to reduce the likelihood of generating such images, but this often compromises model performance. Another approach focuses on economically compensating data holders for their contributions, yet it fails to address copyright loss adequately. Our approach begin with the introduction of a novel copyright metric grounded in copyright law and court precedents on infringement. We then employ the TRAK method to estimate the contribution of data holders. To accommodate the continuous data collection process, we divide the training into multiple rounds. Finally, We designed a hierarchical budget allocation method based on reinforcement learning to determine the budget for each round and the remuneration of the data holder based on the data holder's contribution and copyright loss in each round. Extensive experiments across three datasets show that our method outperforms all eight benchmarks, demonstrating its effectiveness in optimizing budget distribution in a copyright-aware manner. To the best of our knowledge, this is the first technical work that introduces to incentive contributors and protect their copyrights by compensating them.
Authors: Tu Trinh, Mohamad H. Danesh, Nguyen X. Khanh, Benjamin Plaut
Abstract: While reinforcement learning (RL) agents often perform well during training, they can struggle with distribution shift in real-world deployments. One particularly severe risk of distribution shift is goal misgeneralization, where the agent learns a proxy goal that coincides with the true goal during training but not during deployment. In this paper, we explore whether allowing an agent to ask for help from a supervisor in unfamiliar situations can mitigate this issue. We focus on agents trained with PPO in the CoinRun environment, a setting known to exhibit goal misgeneralization. We evaluate multiple methods for determining when the agent should request help and find that asking for help consistently improves performance. However, we also find that methods based on the agent's internal state fail to proactively request help, instead waiting until mistakes have already occurred. Further investigation suggests that the agent's internal state does not represent the coin at all, highlighting the importance of learning nuanced representations, the risks of ignoring everything not immediately relevant to reward, and the necessity of developing ask-for-help strategies tailored to the agent's training algorithm.
Authors: Hamidreza Eivazi, Andr\'e Hebenbrock, Raphael Ginster, Steffen Bl\"omeke, Stefan Wittek, Christoph Herrmann, Thomas S. Spengler, Thomas Turek, Andreas Rausch
Abstract: Battery degradation remains a critical challenge in the pursuit of green technologies and sustainable energy solutions. Despite significant research efforts, predicting battery capacity loss accurately remains a formidable task due to its complex nature, influenced by both aging and cycling behaviors. To address this challenge, we introduce a novel general-purpose model for battery degradation prediction and synthesis, DiffBatt. Leveraging an innovative combination of conditional and unconditional diffusion models with classifier-free guidance and transformer architecture, DiffBatt achieves high expressivity and scalability. DiffBatt operates as a probabilistic model to capture uncertainty in aging behaviors and a generative model to simulate battery degradation. The performance of the model excels in prediction tasks while also enabling the generation of synthetic degradation curves, facilitating enhanced model training by data augmentation. In the remaining useful life prediction task, DiffBatt provides accurate results with a mean RMSE of 196 cycles across all datasets, outperforming all other models and demonstrating superior generalizability. This work represents an important step towards developing foundational models for battery degradation.
Authors: Heiko Hoffmann
Abstract: Scalar variables, e.g., the orientation of a shape in an image, are commonly predicted using a single output neuron in a neural network. In contrast, the mammalian cortex represents variables with a population of neurons. In this population code, each neuron is most active at its preferred value and shows partial activity for other values. Here, we investigate the benefit of using a population code for the output layer of a neural network. We compare population codes against single-neuron outputs and one-hot vectors. First, we show theoretically and in experiments with synthetic data that population codes improve robustness to input noise in networks of stacked linear layers. Second, we demonstrate the benefit of using population codes to encode ambiguous outputs, such as the pose of symmetric objects. Using the T-LESS dataset of feature-less real-world objects, we show that population codes improve the accuracy of predicting 3D object orientation from image input.
Authors: Luke Marks, Alasdair Paren, David Krueger, Fazl Barez
Abstract: Sparse Autoencoders (SAEs) have shown promise in improving the interpretability of neural network activations, but can learn features that are not features of the input, limiting their effectiveness. We propose \textsc{Mutual Feature Regularization} \textbf{(MFR)}, a regularization technique for improving feature learning by encouraging SAEs trained in parallel to learn similar features. We motivate \textsc{MFR} by showing that features learned by multiple SAEs are more likely to correlate with features of the input. By training on synthetic data with known features of the input, we show that \textsc{MFR} can help SAEs learn those features, as we can directly compare the features learned by the SAE with the input features for the synthetic data. We then scale \textsc{MFR} to SAEs that are trained to denoise electroencephalography (EEG) data and SAEs that are trained to reconstruct GPT-2 Small activations. We show that \textsc{MFR} can improve the reconstruction loss of SAEs by up to 21.21\% on GPT-2 Small, and 6.67\% on EEG data. Our results suggest that the similarity between features learned by different SAEs can be leveraged to improve SAE training, thereby enhancing performance and the usefulness of SAEs for model interpretability.
Authors: Vu Khanh Quy, Nguyen Minh Quy, Tran Thi Hoai, Shaba Shaon, Md Raihan Uddin, Tien Nguyen, Dinh C. Nguyen, Aryan Kaushik, Periklis Chatzimisios
Abstract: 6G wireless networks are expected to provide seamless and data-based connections that cover space-air-ground and underwater networks. As a core partition of future 6G networks, Space-Air-Ground Integrated Networks (SAGIN) have been envisioned to provide countless real-time intelligent applications. To realize this, promoting AI techniques into SAGIN is an inevitable trend. Due to the distributed and heterogeneous architecture of SAGIN, federated learning (FL) and then quantum FL are emerging AI model training techniques for enabling future privacy-enhanced and computation-efficient SAGINs. In this work, we explore the vision of using FL/QFL in SAGINs. We present a few representative applications enabled by the integration of FL and QFL in SAGINs. A case study of QFL over UAV networks is also given, showing the merit of quantum-enabled training approach over the conventional FL benchmark. Research challenges along with standardization for QFL adoption in future SAGINs are also highlighted.
Authors: Md Raihan Uddin, Ratun Rahman, Dinh C. Nguyen
Abstract: Smart metering networks are increasingly susceptible to cyber threats, where false data injection (FDI) appears as a critical attack. Data-driven-based machine learning (ML) methods have shown immense benefits in detecting FDI attacks via data learning and prediction abilities. Literature works have mostly focused on centralized learning and deploying FDI attack detection models at the control center, which requires data collection from local utilities like meters and transformers. However, this data sharing may raise privacy concerns due to the potential disclosure of household information like energy usage patterns. This paper proposes a new privacy-preserved FDI attack detection by developing an efficient federated learning (FL) framework in the smart meter network with edge computing. Distributed edge servers located at the network edge run an ML-based FDI attack detection model and share the trained model with the grid operator, aiming to build a strong FDI attack detection model without data sharing. Simulation results demonstrate the efficiency of our proposed FL method over the conventional method without collaboration.
Authors: Peng Tang, Jiacheng Liu, Xiaofeng Hou, Yifei Pu, Jing Wang, Pheng-Ann Heng, Chao Li, Minyi Guo
Abstract: The Mixture-of-Experts (MoE) architecture has demonstrated significant advantages in the era of Large Language Models (LLMs), offering enhanced capabilities with reduced inference costs. However, deploying MoE-based LLMs on memoryconstrained edge devices remains challenging due to their substantial memory requirements. While existing expertoffloading methods alleviate the memory requirements, they often incur significant expert-loading costs or compromise model accuracy. We present HOBBIT, a mixed precision expert offloading system to enable flexible and efficient MoE inference. Our key insight is that dynamically replacing less critical cache-miss experts with low precision versions can substantially reduce expert-loading latency while preserving model accuracy. HOBBIT introduces three innovative techniques that map the natural hierarchy of MoE computation: (1) a token-level dynamic expert loading mechanism, (2) a layer-level adaptive expert prefetching technique, and (3) a sequence-level multidimensional expert caching policy. These innovations fully leverage the benefits of mixedprecision expert inference. By implementing HOBBIT on top of the renowned LLM inference framework Llama.cpp, we evaluate its performance across different edge devices with representative MoE models. The results demonstrate that HOBBIT achieves up to a 9.93x speedup in decoding compared to state-of-the-art MoE offloading systems.
Authors: Gjergji Kasneci, Enkelejda Kasneci
Abstract: Feature engineering is crucial for optimizing machine learning model performance, particularly in tabular data classification tasks. Leveraging advancements in natural language processing, this study presents a systematic approach to enrich tabular datasets with features derived from large language model embeddings. Through a comprehensive ablation study on diverse datasets, we assess the impact of RoBERTa and GPT-2 embeddings on ensemble classifiers, including Random Forest, XGBoost, and CatBoost. Results indicate that integrating embeddings with traditional numerical and categorical features often enhances predictive performance, especially on datasets with class imbalance or limited features and samples, such as UCI Adult, Heart Disease, Titanic, and Pima Indian Diabetes, with improvements particularly notable in XGBoost and CatBoost classifiers. Additionally, feature importance analysis reveals that LLM-derived features frequently rank among the most impactful for the predictions. This study provides a structured approach to embedding-based feature enrichment and illustrates its benefits in ensemble learning for tabular data.
Authors: Mohammad Zbeeb, Mohammad Ghorayeb, Mariam Salman
Abstract: Artificial Intelligence (AI) research often aims to develop models that can generalize reliably across complex datasets, yet this remains challenging in fields where data is scarce, intricate, or inaccessible. This paper introduces a novel approach that leverages three generative models of varying complexity to synthesize one of the most demanding structured datasets: Malicious Network Traffic. Our approach uniquely transforms numerical data into text, re-framing data generation as a language modeling task, which not only enhances data regularization but also significantly improves generalization and the quality of the synthetic data. Extensive statistical analyses demonstrate that our method surpasses state-of-the-art generative models in producing high-fidelity synthetic data. Additionally, we conduct a comprehensive study on synthetic data applications, effectiveness, and evaluation strategies, offering valuable insights into its role across various domains. Our code and pre-trained models are openly accessible at Github, enabling further exploration and application of our methodology. Index Terms: Data synthesis, machine learning, traffic generation, privacy preserving data, generative models.
Authors: Aofeng Su, Aowen Wang, Chao Ye, Chen Zhou, Ga Zhang, Guangcheng Zhu, Haobo Wang, Haokai Xu, Hao Chen, Haoze Li, Haoxuan Lan, Jiaming Tian, Jing Yuan, Junbo Zhao, Junlin Zhou, Kaizhe Shou, Liangyu Zha, Lin Long, Liyao Li, Pengzuo Wu, Qi Zhang, Qingyi Huang, Saisai Yang, Tao Zhang, Wentao Ye, Wufang Zhu, Xiaomeng Hu, Xijun Gu, Xinjie Sun, Xiang Li, Yuhang Yang, Zhiqing Xiao
Abstract: The emergence of models like GPTs, Claude, LLaMA, and Qwen has reshaped AI applications, presenting vast new opportunities across industries. Yet, the integration of tabular data remains notably underdeveloped, despite its foundational role in numerous real-world domains. This gap is critical for three main reasons. First, database or data warehouse data integration is essential for advanced applications; second, the vast and largely untapped resource of tabular data offers immense potential for analysis; and third, the business intelligence domain specifically demands adaptable, precise solutions that many current LLMs may struggle to provide. In response, we introduce TableGPT2, a model rigorously pre-trained and fine-tuned with over 593.8K tables and 2.36M high-quality query-table-output tuples, a scale of table-related data unprecedented in prior research. This extensive training enables TableGPT2 to excel in table-centric tasks while maintaining strong general language and coding abilities. One of TableGPT2's key innovations is its novel table encoder, specifically designed to capture schema-level and cell-level information. This encoder strengthens the model's ability to handle ambiguous queries, missing column names, and irregular tables commonly encountered in real-world applications. Similar to visual language models, this pioneering approach integrates with the decoder to form a robust large multimodal model. We believe the results are compelling: over 23 benchmarking metrics, TableGPT2 achieves an average performance improvement of 35.20% in the 7B model and 49.32% in the 72B model over prior benchmark-neutral LLMs, with robust general-purpose capabilities intact.
Authors: Dake Bu, Wei Huang, Andi Han, Atsushi Nitanda, Taiji Suzuki, Qingfu Zhang, Hau-San Wong
Abstract: Transformer-based large language models (LLMs) have displayed remarkable creative prowess and emergence capabilities. Existing empirical studies have revealed a strong connection between these LLMs' impressive emergence abilities and their in-context learning (ICL) capacity, allowing them to solve new tasks using only task-specific prompts without further fine-tuning. On the other hand, existing empirical and theoretical studies also show that there is a linear regularity of the multi-concept encoded semantic representation behind transformer-based LLMs. However, existing theoretical work fail to build up an understanding of the connection between this regularity and the innovative power of ICL. Additionally, prior work often focuses on simplified, unrealistic scenarios involving linear transformers or unrealistic loss functions, and they achieve only linear or sub-linear convergence rates. In contrast, this work provides a fine-grained mathematical analysis to show how transformers leverage the multi-concept semantics of words to enable powerful ICL and excellent out-of-distribution ICL abilities, offering insights into how transformers innovate solutions for certain unseen tasks encoded with multiple cross-concept semantics. Inspired by empirical studies on the linear latent geometry of LLMs, the analysis is based on a concept-based low-noise sparse coding prompt model. Leveraging advanced techniques, this work showcases the exponential 0-1 loss convergence over the highly non-convex training dynamics, which pioneeringly incorporates the challenges of softmax self-attention, ReLU-activated MLPs, and cross-entropy loss. Empirical simulations corroborate the theoretical findings.
Authors: Qixun Wang, Yifei Wang, Yisen Wang, Xianghua Ying
Abstract: Enhancing node-level Out-Of-Distribution (OOD) generalization on graphs remains a crucial area of research. In this paper, we develop a Structural Causal Model (SCM) to theoretically dissect the performance of two prominent invariant learning methods -- Invariant Risk Minimization (IRM) and Variance-Risk Extrapolation (VREx) -- in node-level OOD settings. Our analysis reveals a critical limitation: due to the lack of class-conditional invariance constraints, these methods may struggle to accurately identify the structure of the predictive invariant ego-graph and consequently rely on spurious features. To address this, we propose Cross-environment Intra-class Alignment (CIA), which explicitly eliminates spurious features by aligning cross-environment representations conditioned on the same class, bypassing the need for explicit knowledge of the causal pattern structure. To adapt CIA to node-level OOD scenarios where environment labels are hard to obtain, we further propose CIA-LRA (Localized Reweighting Alignment) that leverages the distribution of neighboring labels to selectively align node representations, effectively distinguishing and preserving invariant features while removing spurious ones, all without relying on environment labels. We theoretically prove CIA-LRA's effectiveness by deriving an OOD generalization error bound based on PAC-Bayesian analysis. Experiments on graph OOD benchmarks validate the superiority of CIA and CIA-LRA, marking a significant advancement in node-level OOD generalization. The codes are available at https://github.com/NOVAglow646/NeurIPS24-Invariant-Learning-on-Graphs.
URLs: https://github.com/NOVAglow646/NeurIPS24-Invariant-Learning-on-Graphs.
Authors: Adrien LeCoz, St\'ephane Herbin, Faouzi Adjed
Abstract: For classification models based on neural networks, the maximum predicted class probability is often used as a confidence score. This score rarely predicts well the probability of making a correct prediction and requires a post-processing calibration step. However, many confidence calibration methods fail for problems with many classes. To address this issue, we transform the problem of calibrating a multiclass classifier into calibrating a single surrogate binary classifier. This approach allows for more efficient use of standard calibration methods. We evaluate our approach on numerous neural networks used for image or text classification and show that it significantly enhances existing calibration methods.
Authors: Luca Zhou, Daniele Solombrino, Donato Crisostomi, Maria Sofia Bucarelli, Fabrizio Silvestri, Emanuele Rodol\`a
Abstract: Model merging has recently emerged as a cost-efficient paradigm for multi-task learning. Among current approaches, task arithmetic stands out for its simplicity and effectiveness. In this paper, we motivate the effectiveness of task vectors by linking them to multi-task gradients. We show that in a single-epoch scenario, task vectors are mathematically equivalent to the gradients obtained via gradient descent in a multi-task setting, and still approximate these gradients in subsequent epochs. Furthermore, we show that task vectors perform optimally when equality is maintained, and their effectiveness is largely driven by the first epoch's gradient. Building on this insight, we propose viewing model merging as a single step in an iterative process that Alternates between Tuning and Merging (ATM). This method acts as a bridge between model merging and multi-task gradient descent, achieving state-of-the-art results with the same data and computational requirements. We extensively evaluate ATM across diverse settings, achieving up to 20% higher accuracy in computer vision and NLP tasks, compared to the best baselines. Finally, we provide both empirical and theoretical support for its effectiveness, demonstrating increased orthogonality between task vectors and proving that ATM minimizes an upper bound on the loss obtained by jointly finetuning all tasks.
Authors: Nasib Ullah, Erik Schultheis, Mike Lasby, Yani Ioannou, Rohit Babbar
Abstract: In recent years, Dynamic Sparse Training (DST) has emerged as an alternative to post-training pruning for generating efficient models. In principle, DST allows for a more memory efficient training process, as it maintains sparsity throughout the entire training run. However, current DST implementations fail to capitalize on this in practice. Because sparse matrix multiplication is much less efficient than dense matrix multiplication on GPUs, most implementations simulate sparsity by masking weights. In this paper, we leverage recent advances in semi-structured sparse training to apply DST in the domain of classification with large output spaces, where memory-efficiency is paramount. With a label space of possibly millions of candidates, the classification layer alone will consume several gigabytes of memory. Switching from a dense to a fixed fan-in sparse layer updated with sparse evolutionary training (SET); however, severely hampers training convergence, especially at the largest label spaces. We find that poor gradient flow from the sparse classifier to the dense text encoder make it difficult to learn good input representations. By employing an intermediate layer or adding an auxiliary training objective, we recover most of the generalisation performance of the dense model. Overall, we demonstrate the applicability and practical benefits of DST in a challenging domain -- characterized by a highly skewed label distribution that differs substantially from typical DST benchmark datasets -- which enables end-to-end training with millions of labels on commodity hardware.
Authors: Shan Zhao, Zhaiyu Chen, Zhitong Xiong, Yilei Shi, Sudipan Saha, Xiao Xiang Zhu
Abstract: Earth Observation (EO) data analysis has been significantly revolutionized by deep learning (DL), with applications typically limited to grid-like data structures. Graph Neural Networks (GNNs) emerge as an important innovation, propelling DL into the non-Euclidean domain. Naturally, GNNs can effectively tackle the challenges posed by diverse modalities, multiple sensors, and the heterogeneous nature of EO data. To introduce GNNs in the related domains, our review begins by offering fundamental knowledge on GNNs. Then, we summarize the generic problems in EO, to which GNNs can offer potential solutions. Following this, we explore a broad spectrum of GNNs' applications to scientific problems in Earth systems, covering areas such as weather and climate analysis, disaster management, air quality monitoring, agriculture, land cover classification, hydrological process modeling, and urban modeling. The rationale behind adopting GNNs in these fields is explained, alongside methodologies for organizing graphs and designing favorable architectures for various tasks. Furthermore, we highlight methodological challenges of implementing GNNs in these domains and possible solutions that could guide future research. While acknowledging that GNNs are not a universal solution, we conclude the paper by comparing them with other popular architectures like transformers and analyzing their potential synergies.
Authors: Mat\'ias Pizarro, Dorothea Kolossa, Asja Fischer
Abstract: In the past few years, it has been shown that deep learning systems are highly vulnerable under attacks with adversarial examples. Neural-network-based automatic speech recognition (ASR) systems are no exception. Targeted and untargeted attacks can modify an audio input signal in such a way that humans still recognise the same words, while ASR systems are steered to predict a different transcription. In this paper, we propose a defense mechanism against targeted adversarial attacks consisting in removing fast-changing features from the audio signals, either by applying slow feature analysis, a low-pass filter, or both, before feeding the input to the ASR system. We perform an empirical analysis of hybrid ASR models trained on data pre-processed in such a way. While the resulting models perform quite well on benign data, they are significantly more robust against targeted adversarial attacks: Our final, proposed model shows a performance on clean data similar to the baseline model, while being more than four times more robust.
Authors: Jinbao Zhu, Hengxuan Tang, Songze Li, Yijia Chang
Abstract: We consider the problem of evaluating arbitrary multivariate polynomials over a massive dataset containing multiple inputs, on a distributed computing system with a master node and multiple worker nodes. Generalized Lagrange Coded Computing (GLCC) codes are proposed to simultaneously provide resiliency against stragglers who do not return computation results in time, security against adversarial workers who deliberately modify results for their benefit, and information-theoretic privacy of the dataset amidst possible collusion of workers. GLCC codes are constructed by first partitioning the dataset into multiple groups, then encoding the dataset using carefully designed interpolating polynomials, and sharing multiple encoded data points to each worker, such that interference computation results across groups can be eliminated at the master. Particularly, GLCC codes include the state-of-the-art Lagrange Coded Computing (LCC) codes as a special case, and exhibit a more flexible tradeoff between communication and computation overheads in optimizing system efficiency. Furthermore, we apply GLCC to distributed training of machine learning models, and demonstrate that GLCC codes achieve a speedup of up to $2.5\text{--}3.9\times$ over LCC codes in training time, across experiments for training image classifiers on different datasets, model architectures, and straggler patterns.
Authors: Benjamin Gess, Sebastian Kassing
Abstract: We prove explicit bounds on the exponential rate of convergence for the momentum stochastic gradient descent scheme (MSGD) for arbitrary, fixed hyperparameters (learning rate, friction parameter) and its continuous-in-time counterpart in the context of non-convex optimization. In the small step-size regime and in the case of flat minima or large noise intensities, these bounds prove faster convergence of MSGD compared to plain stochastic gradient descent (SGD). The results are shown for objective functions satisfying a local Polyak-Lojasiewicz inequality and under assumptions on the variance of MSGD that are satisfied in overparametrized settings. Moreover, we analyze the optimal choice of the friction parameter and show that the MSGD process almost surely converges to a local minimum.
Authors: Yanguang Chen, Wenzhi Gao, Dongdong Ge, Yinyu Ye
Abstract: In this paper, we propose a Pre-trained Mixed Integer Optimization framework (PreMIO) that accelerates online mixed integer program (MIP) solving with offline datasets and machine learning models. Our method is based on a data-driven multi-variable cardinality branching procedure that splits the MIP feasible region using hyperplanes chosen by the concentration inequalities. Unlike most previous ML+MIP approaches that either require complicated implementation or suffer from a lack of theoretical justification, our method is simple, flexible, provable, and explainable. Numerical experiments on both classical OR benchmark datasets and real-life instances validate the efficiency of our proposed method.
Authors: Moritz Haas, David Holzm\"uller, Ulrike von Luxburg, Ingo Steinwart
Abstract: The success of over-parameterized neural networks trained to near-zero training error has caused great interest in the phenomenon of benign overfitting, where estimators are statistically consistent even though they interpolate noisy training data. While benign overfitting in fixed dimension has been established for some learning methods, current literature suggests that for regression with typical kernel methods and wide neural networks, benign overfitting requires a high-dimensional setting where the dimension grows with the sample size. In this paper, we show that the smoothness of the estimators, and not the dimension, is the key: benign overfitting is possible if and only if the estimator's derivatives are large enough. We generalize existing inconsistency results to non-interpolating models and more kernels to show that benign overfitting with moderate derivatives is impossible in fixed dimension. Conversely, we show that rate-optimal benign overfitting is possible for regression with a sequence of spiky-smooth kernels with large derivatives. Using neural tangent kernels, we translate our results to wide neural networks. We prove that while infinite-width networks do not overfit benignly with the ReLU activation, this can be fixed by adding small high-frequency fluctuations to the activation function. Our experiments verify that such neural networks, while overfitting, can indeed generalize well even on low-dimensional data sets.
Authors: Mohammed Rayyan Sheriff, Peyman Mohajerin Esfahani
Abstract: This article focuses on a class of distributionally robust optimization (DRO) problems where, unlike the growing body of the literature, the objective function is potentially nonlinear in the distribution. Existing methods to optimize nonlinear functions in probability space use the Frechet derivatives, which present theoretical and computational challenges. Motivated by this, we propose an alternative notion for the derivative and corresponding smoothness based on Gateaux (G)-derivative for generic risk measures. These concepts are explained via three running risk measure examples of variance, entropic risk, and risk on finite support sets. We then propose a G-derivative-based Frank-Wolfe (FW) algorithm for generic nonlinear optimization problems in probability spaces and establish its convergence under the proposed notion of smoothness in a completely norm-independent manner. We use the set-up of the FW algorithm to devise a methodology to compute a saddle point of the nonlinear DRO problem. Finally, we validate our theoretical results on two cases of the $entropic$ and $variance$ risk measures in the context of portfolio selection problems. In particular, we analyze their regularity conditions and "sufficient statistic", compute the respective FW-oracle in various settings, and confirm the theoretical outcomes through numerical validation.
Authors: Hiroshi Kera, Yuki Ishihara, Yuta Kambe, Tristan Vaccon, Kazuhiro Yokoyama
Abstract: Solving a polynomial system, or computing an associated Gr\"obner basis, has been a fundamental task in computational algebra. However, it is also known for its notorious doubly exponential time complexity in the number of variables in the worst case. This paper is the first to address the learning of Gr\"obner basis computation with Transformers. The training requires many pairs of a polynomial system and the associated Gr\"obner basis, raising two novel algebraic problems: random generation of Gr\"obner bases and transforming them into non-Gr\"obner ones, termed as backward Gr\"obner problem. We resolve these problems with 0-dimensional radical ideals, the ideals appearing in various applications. Further, we propose a hybrid input embedding to handle coefficient tokens with continuity bias and avoid the growth of the vocabulary set. The experiments show that our dataset generation method is a few orders of magnitude faster than a naive approach, overcoming a crucial challenge in learning to compute Gr\"obner bases, and Gr\"obner computation is learnable in a particular class.
Authors: Alex J. Chan, Jos\'e Luis Redondo Garc\'ia, Fabrizio Silvestri, Colm O'Donnell, Konstantina Palla
Abstract: Content moderation on a global scale must navigate a complex array of local cultural distinctions, which can hinder effective enforcement. While global policies aim for consistency and broad applicability, they often miss the subtleties of regional language interpretation, cultural beliefs, and local legislation. This work introduces a flexible framework that enhances foundation language models with cultural knowledge. Our approach involves fine-tuning encoder-decoder models on media-diet data to capture cultural nuances, and applies a continued training regime to effectively integrate these models into a content moderation pipeline. We evaluate this framework in a case study of an online podcast platform with content spanning various regions. The results show that our culturally adapted models improve the accuracy of local violation detection and offer explanations that align more closely with regional cultural norms. Our findings reinforce the need for an adaptable content moderation approach that remains flexible in response to the diverse cultural landscapes it operates in and represents a step towards a more equitable and culturally sensitive framework for content moderation, demonstrating what is achievable in this domain.
Authors: Ying Wang, Yanlai Yang, Mengye Ren
Abstract: In this paper we introduce LifelongMemory, a new framework for accessing long-form egocentric videographic memory through natural language question answering and retrieval. LifelongMemory generates concise video activity descriptions of the camera wearer and leverages the zero-shot capabilities of pretrained large language models to perform reasoning over long-form video context. Furthermore, LifelongMemory uses a confidence and explanation module to produce confident, high-quality, and interpretable answers. Our approach achieves state-of-the-art performance on the EgoSchema benchmark for question answering and is highly competitive on the natural language query (NLQ) challenge of Ego4D. Code is available at https://github.com/agentic-learning-ai-lab/lifelong-memory.
URLs: https://github.com/agentic-learning-ai-lab/lifelong-memory.
Authors: Justyna P. Zwolak, Jacob M. Taylor, Reed W. Andrews, Jared Benson, Garnett W. Bryant, Donovan Buterakos, Anasua Chatterjee, Sankar Das Sarma, Mark A. Eriksson, Eli\v{s}ka Greplov\'a, Michael J. Gullans, Fabian Hader, Tyler J. Kovach, Pranav S. Mundada, Mick Ramsey, Torbj{\o}rn Rasmussen, Brandon Severin, Anthony Sigillito, Brennan Undseth, Brian Weber
Abstract: Gate-defined quantum dots are a promising candidate system for realizing scalable, coupled qubit systems and serving as a fundamental building block for quantum computers. However, present-day quantum dot devices suffer from imperfections that must be accounted for, which hinders the characterization, tuning, and operation process. Moreover, with an increasing number of quantum dot qubits, the relevant parameter space grows sufficiently to make heuristic control infeasible. Thus, it is imperative that reliable and scalable autonomous tuning approaches are developed. This meeting report outlines current challenges in automating quantum dot device tuning and operation with a particular focus on datasets, benchmarking, and standardization. We also present insights and ideas put forward by the quantum dot community on how to overcome them. We aim to provide guidance and inspiration to researchers invested in automation efforts.
Authors: Syamantak Kumar, Purnamrita Sarkar, Peter Bickel, Derek Bean
Abstract: Independent Component Analysis (ICA) was introduced in the 1980's as a model for Blind Source Separation (BSS), which refers to the process of recovering the sources underlying a mixture of signals, with little knowledge about the source signals or the mixing process. While there are many sophisticated algorithms for estimation, different methods have different shortcomings. In this paper, we develop a nonparametric score to adaptively pick the right algorithm for ICA with arbitrary Gaussian noise. The novelty of this score stems from the fact that it just assumes a finite second moment of the data and uses the characteristic function to evaluate the quality of the estimated mixing matrix without any knowledge of the parameters of the noise distribution. In addition, we propose some new contrast functions and algorithms that enjoy the same fast computability as existing algorithms like FASTICA and JADE but work in domains where the former may fail. While these also may have weaknesses, our proposed diagnostic, as shown by our simulations, can remedy them. Finally, we propose a theoretical framework to analyze the local and global convergence properties of our algorithms.
Authors: Dimitrios Sinodinos, Narges Armanfard
Abstract: Multitask learning (MTL) has become prominent for its ability to predict multiple tasks jointly, achieving better per-task performance with fewer parameters than single-task learning. Recently, decoder-focused architectures have significantly improved multitask performance by refining task predictions using features from related tasks. However, most refinement methods struggle to efficiently capture both local and long-range dependencies between task-specific representations and cross-task patterns. In this paper, we introduce the Cross-Task Affinity Learning (CTAL) module, a lightweight framework that enhances task refinement in multitask networks. CTAL effectively captures local and long-range cross-task interactions by optimizing task affinity matrices for parameter-efficient grouped convolutions without concern for information loss. Our results demonstrate state-of-the-art MTL performance for both CNN and transformer backbones, using significantly fewer parameters than single-task learning. Our code is publicly available at https://github.com/Armanfard-Lab/EMA-Net.
Authors: Wenzhi Gao, Qi Deng
Abstract: This paper considers stochastic weakly convex optimization without the standard Lipschitz continuity assumption. Based on new adaptive regularization (stepsize) strategies, we show that a wide class of stochastic algorithms, including the stochastic subgradient method, preserve the $\mathcal{O} ( 1 / \sqrt{K})$ convergence rate with constant failure rate. Our analyses rest on rather weak assumptions: the Lipschitz parameter can be either bounded by a general growth function of $\|x\|$ or locally estimated through independent random samples.
Authors: Haoxuan Chen, Lexing Ying
Abstract: Sampling from a multimodal distribution is a fundamental and challenging problem in computational science and statistics. Among various approaches proposed for this task, one popular method is Annealed Importance Sampling (AIS). In this paper, we propose an ensemble-based version of AIS by combining it with population-based Monte Carlo methods to improve its efficiency. By keeping track of an ensemble instead of a single particle along some continuation path between the starting distribution and the target distribution, we take advantage of the interaction within the ensemble to encourage the exploration of undiscovered modes. Specifically, our main idea is to utilize either the snooker algorithm or the genetic algorithm used in Evolutionary Monte Carlo. We discuss how the proposed algorithm can be implemented and derive a partial differential equation governing the evolution of the ensemble under the continuous time and mean-field limit. We also test the efficiency of the proposed algorithm on various continuous and discrete distributions.
Authors: Goitom Ybrah Hailu, Hadush Hailu, Shishay Welay
Abstract: University students often spend a considerable amount of time seeking answers to common questions from administrators or teachers. This can become tedious for both parties, leading to a need for a solution. In response, this paper proposes a chatbot model that utilizes natural language processing and deep learning techniques to answer frequently asked questions (FAQs) in the Amharic language. Chatbots are computer programs that simulate human conversation through the use of artificial intelligence (AI), acting as a virtual assistant to handle questions and other tasks. The proposed chatbot program employs tokenization, normalization, stop word removal, and stemming to analyze and categorize Amharic input sentences. Three machine learning model algorithms were used to classify tokens and retrieve appropriate responses: Support Vector Machine (SVM), Multinomial Na\"ive Bayes, and deep neural networks implemented through TensorFlow, Keras, and NLTK. The deep learning model achieved the best results with 91.55% accuracy and a validation loss of 0.3548 using an Adam optimizer and SoftMax activation function. The chatbot model was integrated with Facebook Messenger and deployed on a Heroku server for 24-hour accessibility. The experimental results demonstrate that the chatbot framework achieved its objectives and effectively addressed challenges such as Amharic Fidel variation, morphological variation, and lexical gaps. Future research could explore the integration of Amharic WordNet to narrow the lexical gap and support more complex questions.
Authors: Thomas D Swinburne, Danny Perez
Abstract: Bayesian regression determines model parameters by minimizing the expected loss, an upper bound to the true generalization error. However, the loss ignores misspecification, where models are imperfect. Parameter uncertainties from Bayesian regression are thus significantly underestimated and vanish in the large data limit. This is particularly problematic when building models of low-noise, or near-deterministic, calculations, as the main source of uncertainty is neglected. We analyze the generalization error of misspecified, near-deterministic surrogate models, a regime of broad relevance in science and engineering. We show posterior distributions must cover every training point to avoid a divergent generalization error and design an ansatz that respects this constraint, which for linear models incurs minimal overhead. This is demonstrated on model problems before application to thousand dimensional datasets in atomistic machine learning. Our efficient misspecification-aware scheme gives accurate prediction and bounding of test errors where existing schemes fail, allowing this important source of uncertainty to be incorporated in computational workflows.
Authors: Luis Kaiser, Richard Tsai, Christian Klingenberg
Abstract: In a variety of scientific and engineering domains, the need for high-fidelity and efficient solutions for high-frequency wave propagation holds great significance. Recent advances in wave modeling use sufficiently accurate fine solver outputs to train a neural network that enhances the accuracy of a fast but inaccurate coarse solver. In this paper we build upon the work of Nguyen and Tsai (2023) and present a novel unified system that integrates a numerical solver with a deep learning component into an end-to-end framework. In the proposed setting, we investigate refinements to the network architecture and data generation algorithm. A stable and fast solver further allows the use of Parareal, a parallel-in-time algorithm to correct high-frequency wave components. Our results show that the cohesive structure improves performance without sacrificing speed, and demonstrate the importance of temporal dynamics, as well as Parareal, for accurate wave propagation.
Authors: Zehang Weng, Haofei Lu, Danica Kragic, Jens Lundell
Abstract: We introduce DexDiffuser, a novel dexterous grasping method that generates, evaluates, and refines grasps on partial object point clouds. DexDiffuser includes the conditional diffusion-based grasp sampler DexSampler and the dexterous grasp evaluator DexEvaluator. DexSampler generates high-quality grasps conditioned on object point clouds by iterative denoising of randomly sampled grasps. We also introduce two grasp refinement strategies: Evaluator-Guided Diffusion (EGD) and Evaluator-based Sampling Refinement (ESR). The experiment results demonstrate that DexDiffuser consistently outperforms the state-of-the-art multi-finger grasp generation method FFHNet with an, on average, 9.12% and 19.44% higher grasp success rate in simulation and real robot experiments, respectively. Supplementary materials are available at https://yulihn.github.io/DexDiffuser_page/
Authors: Jonathan Evertz, Merlin Chlosta, Lea Sch\"onherr, Thorsten Eisenhofer
Abstract: Large Language Models (LLMs) are increasingly augmented with external tools and commercial services into LLM-integrated systems. While these interfaces can significantly enhance the capabilities of the models, they also introduce a new attack surface. Manipulated integrations, for example, can exploit the model and compromise sensitive data accessed through other interfaces. While previous work primarily focused on attacks targeting a model's alignment or the leakage of training data, the security of data that is only available during inference has escaped scrutiny so far. In this work, we demonstrate the vulnerabilities associated with external components and introduce a systematic approach to evaluate confidentiality risks in LLM-integrated systems. We identify two specific attack scenarios unique to these systems and formalize these into a tool-robustness framework designed to measure a model's ability to protect sensitive information. Our findings show that all examined models are highly vulnerable to confidentiality attacks, with the risk increasing significantly when models are used together with external tools.
Authors: Syamantak Kumar, Purnamrita Sarkar
Abstract: Oja's algorithm for Streaming Principal Component Analysis (PCA) for $n$ data-points 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. 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: Bo Liu, Grace Li Zhang, Xunzhao Yin, Ulf Schlichtmann, Bing Li
Abstract: Deep neural networks (DNNs) have achieved great breakthroughs in many fields such as image classification and natural language processing. However, the execution of DNNs needs to conduct massive numbers of multiply-accumulate (MAC) operations on hardware and thus incurs a large power consumption. To address this challenge, we propose a novel digital MAC design based on encoding. In this new design, the multipliers are replaced by simple logic gates to represent the results with a wide bit representation. The outputs of the new multipliers are added by bit-wise weighted accumulation and the accumulation results are compatible with existing computing platforms accelerating neural networks. Since the multiplication function is replaced by a simple logic representation, the critical paths in the resulting circuits become much shorter. Correspondingly, pipelining stages and intermediate registers used to store partial sums in the MAC array can be reduced, leading to a significantly smaller area as well as better power efficiency. The proposed design has been synthesized and verified by ResNet18- Cifar10, ResNet20-Cifar100, ResNet50-ImageNet, MobileNetV2-Cifar10, MobileNetV2-Cifar100, and EfficientNetB0-ImageNet. The experimental results confirmed the reduction of circuit area by up to 48.79% and the reduction of power consumption of executing DNNs by up to 64.41%, while the accuracy of the neural networks can still be well maintained. The open source code of this work can be found on GitHub with link https://github.com/Bo-Liu-TUM/EncodingNet/.
Authors: Behzad Shayegh, Yuqiao Wen, Lili Mou
Abstract: We address unsupervised discontinuous constituency parsing, where we observe a high variance in the performance of the only previous model in the literature. We propose to build an ensemble of different runs of the existing discontinuous parser by averaging the predicted trees, to stabilize and boost performance. To begin with, we provide comprehensive computational complexity analysis (in terms of P and NP-complete) for tree averaging under different setups of binarity and continuity. We then develop an efficient exact algorithm to tackle the task, which runs in a reasonable time for all samples in our experiments. Results on three datasets show our method outperforms all baselines in all metrics; we also provide in-depth analyses of our approach.
Authors: Jannes Nys, Gabriel Pescia, Alessandro Sinibaldi, Giuseppe Carleo
Abstract: Understanding the real-time evolution of many-electron quantum systems is essential for studying dynamical properties in condensed matter, quantum chemistry, and complex materials, yet it poses a significant theoretical and computational challenge. Our work introduces a variational approach for fermionic time-dependent wave functions, surpassing mean-field approximations by accurately capturing many-body correlations. Therefore, we employ time-dependent Jastrow factors and backflow transformations, which are enhanced through neural networks parameterizations. To compute the optimal time-dependent parameters, we utilize the time-dependent variational Monte Carlo technique and a new method based on Taylor-root expansions of the propagator, enhancing the accuracy of our simulations. The approach is demonstrated in three distinct systems. In all cases, we show clear signatures of many-body correlations in the dynamics. The results showcase the ability of our variational approach to accurately capture the time evolution, providing insight into the quantum dynamics of interacting electronic systems, beyond the capabilities of mean-field.
Authors: Lena Strobl, Dana Angluin, David Chiang, Jonathan Rawski, Ashish Sabharwal
Abstract: We study the sequence-to-sequence mapping capacity of transformers by relating them to finite transducers, and find that they can express surprisingly large classes of transductions. We do so using variants of RASP, a programming language designed to help people "think like transformers," as an intermediate representation. We extend the existing Boolean variant B-RASP to sequence-to-sequence functions and show that it computes exactly the first-order rational functions (such as string rotation). Then, we introduce two new extensions. B-RASP[pos] enables calculations on positions (such as copying the first half of a string) and contains all first-order regular functions. S-RASP adds prefix sum, which enables additional arithmetic operations (such as squaring a string) and contains all first-order polyregular functions. Finally, we show that masked average-hard attention transformers can simulate S-RASP.
Authors: Tuomas Kynk\"a\"anniemi, Miika Aittala, Tero Karras, Samuli Laine, Timo Aila, Jaakko Lehtinen
Abstract: Guidance is a crucial technique for extracting the best performance out of image-generating diffusion models. Traditionally, a constant guidance weight has been applied throughout the sampling chain of an image. We show that guidance is clearly harmful toward the beginning of the chain (high noise levels), largely unnecessary toward the end (low noise levels), and only beneficial in the middle. We thus restrict it to a specific range of noise levels, improving both the inference speed and result quality. This limited guidance interval improves the record FID in ImageNet-512 significantly, from 1.81 to 1.40. We show that it is quantitatively and qualitatively beneficial across different sampler parameters, network architectures, and datasets, including the large-scale setting of Stable Diffusion XL. We thus suggest exposing the guidance interval as a hyperparameter in all diffusion models that use guidance.
Authors: Puze Liu, Haitham Bou-Ammar, Jan Peters, Davide Tateo
Abstract: Integrating learning-based techniques, especially reinforcement learning, into robotics is promising for solving complex problems in unstructured environments. However, most existing approaches are trained in well-tuned simulators and subsequently deployed on real robots without online fine-tuning. In this setting, extensive engineering is required to mitigate the sim-to-real gap, which can be challenging for complex systems. Instead, learning with real-world interaction data offers a promising alternative: it not only eliminates the need for a fine-tuned simulator but also applies to a broader range of tasks where accurate modeling is unfeasible. One major problem for on-robot reinforcement learning is ensuring safety, as uncontrolled exploration can cause catastrophic damage to the robot or the environment. Indeed, safety specifications, often represented as constraints, can be complex and non-linear, making safety challenging to guarantee in learning systems. In this paper, we show how we can impose complex safety constraints on learning-based robotics systems in a principled manner, both from theoretical and practical points of view. Our approach is based on the concept of the Constraint Manifold, representing the set of safe robot configurations. Exploiting differential geometry techniques, i.e., the tangent space, we can construct a safe action space, allowing learning agents to sample arbitrary actions while ensuring safety. We demonstrate the method's effectiveness in a real-world Robot Air Hockey task, showing that our method can handle high-dimensional tasks with complex constraints. Videos of the real robot experiments are available on the project website (https://puzeliu.github.io/TRO-ATACOM).
Authors: Piersilvio De Bartolomeis, Javier Abad, Konstantin Donhauser, Fanny Yang
Abstract: Randomized trials are considered the gold standard for making informed decisions in medicine, yet they often lack generalizability to the patient populations in clinical practice. Observational studies, on the other hand, cover a broader patient population but are prone to various biases. Thus, before using an observational study for decision-making, it is crucial to benchmark its treatment effect estimates against those derived from a randomized trial. We propose a novel strategy to benchmark observational studies beyond the average treatment effect. First, we design a statistical test for the null hypothesis that the treatment effects estimated from the two studies, conditioned on a set of relevant features, differ up to some tolerance. We then estimate an asymptotically valid lower bound on the maximum bias strength for any subgroup in the observational study. Finally, we validate our benchmarking strategy in a real-world setting and show that it leads to conclusions that align with established medical knowledge.
Authors: Niclas F\"uhrling, Kengo Ando, Giuseppe Thadeu Freitas de Abreu, David Gonz\'alez G., Osvaldo Gonsa
Abstract: We consider a novel algorithm, for the completion of partially observed low-rank matrices in a structured setting where each entry can be chosen from a finite discrete alphabet set, such as in common recommender systems. The proposed low-rank matrix completion (MC) method is an improved variation of state-of-the-art (SotA) discrete aware matrix completion method which we previously proposed, in which discreteness is enforced by an $\ell_0$-norm regularizer, not by replaced with the $\ell_1$-norm, but instead approximated by a continuous and differentiable function normalized via fractional programming (FP) under a proximal gradient (PG) framework. Simulation results demonstrate the superior performance of the new method compared to the SotA techniques as well as the earlier $\ell_1$-norm-based discrete-aware matrix completion approach.
Authors: Nastaran Okati, Sergio Hernan Garrido Mejia, William Roy Orchard, Patrick Bl\"obaum, Dominik Janzing
Abstract: Recent work conceptualized root cause analysis (RCA) of anomalies via quantitative contribution analysis using causal counterfactuals in structural causal models (SCMs).The framework comes with three practical challenges: (1) it requires the causal directed acyclic graph (DAG), together with an SCM, (2) it is statistically ill-posed since it probes regression models in regions of low probability density, (3) it relies on Shapley values which are computationally expensive to find. In this paper, we propose simplified, efficient methods of root cause analysis when the task is to identify a unique root cause instead of quantitative contribution analysis. Our proposed methods run in linear order of SCM nodes and they require only the causal DAG without counterfactuals. Furthermore, for those use cases where the causal DAG is unknown, we justify the heuristic of identifying root causes as the variables with the highest anomaly score. To this end, we prove that anomalies with small scores are unlikely to cause those with large scores and show upper bounds for the likelihood of causal pathways with non-monotonic anomaly scores.
Authors: Tim Tsz-Kit Lau, Weijian Li, Chenwei Xu, Han Liu, Mladen Kolar
Abstract: Modern deep neural networks often require distributed training with many workers due to their large size. As the number of workers increases, communication overheads become the main bottleneck in data-parallel minibatch stochastic gradient methods with per-iteration gradient synchronization. Local gradient methods like Local SGD reduce communication by only synchronizing model parameters and/or gradients after several local steps. Despite an understanding of their convergence and the importance of batch sizes for training efficiency and generalization, optimal batch sizes for local gradient methods are difficult to determine. We introduce adaptive batch size strategies for local gradient methods that increase batch sizes adaptively to reduce minibatch gradient variance. We provide convergence guarantees under homogeneous data conditions and support our claims with image classification and language modeling experiments, demonstrating the effectiveness of our strategies for both training efficiency and generalization.
Authors: Walter Simoncini, Spyros Gidaris, Andrei Bursuc, Yuki M. Asano
Abstract: This paper introduces FUNGI, Features from UNsupervised GradIents, a method to enhance the features of transformer encoders by leveraging self-supervised gradients. Our method is simple: given any pretrained model, we first compute gradients from various self-supervised objectives for each input. These gradients are projected to a lower dimension and then concatenated with the model's output embedding. The resulting features are evaluated on k-nearest neighbor classification over 11 datasets from vision, 5 from natural language processing, and 2 from audio. Across backbones spanning various sizes and pretraining strategies, FUNGI features provide consistent performance improvements over the embeddings. We also show that using FUNGI features can benefit linear classification, clustering and image retrieval, and that they significantly improve the retrieval-based in-context scene understanding abilities of pretrained models, for example improving upon DINO by +17% for semantic segmentation - without any training.
Authors: Silviu Pitis, Ziang Xiao, Nicolas Le Roux, Alessandro Sordoni
Abstract: While finetuning language models from pairwise preferences has proven remarkably effective, the underspecified nature of natural language presents critical challenges. Direct preference feedback is uninterpretable, difficult to provide where multidimensional criteria may apply, and often inconsistent, either because it is based on incomplete instructions or provided by diverse principals. To address these challenges, we consider the two-step preference modeling procedure that first resolves the under-specification by selecting a context, and then evaluates preference with respect to the chosen context. We decompose reward modeling error according to these two steps, which suggests that supervising context in addition to context-specific preference may be a viable approach to aligning models with diverse human preferences. For this to work, the ability of models to evaluate context-specific preference is critical. To this end, we contribute context-conditioned preference datasets and accompanying experiments that investigate the ability of language models to evaluate context-specific preference. We use our datasets to (1) show that existing preference models benefit from, but fail to fully consider, added context, (2) finetune a context-aware reward model with context-specific performance exceeding that of GPT-4 and Llama 3 70B on tested datasets, and (3) investigate the value of context-aware preference modeling.
Authors: Carlo Alberto Barbano, Matteo Brunello, Benoit Dufumier, Marco Grangetto
Abstract: Deep Learning (DL) in neuroimaging has become increasingly relevant for detecting neurological conditions and neurodegenerative disorders. One of the most predominant biomarkers in neuroimaging is represented by brain age, which has been shown to be a good indicator for different conditions, such as Alzheimer's Disease. Using brain age for pretraining DL models in transfer learning settings has also recently shown promising results, especially when dealing with data scarcity of different conditions. On the other hand, anatomical information of brain MRIs (e.g. cortical thickness) can provide important information for learning good representations that can be transferred to many downstream tasks. In this work, we propose AnatCL, an anatomical foundation model for brain MRIs that i.) leverages anatomical information with a weakly contrastive learning approach and ii.) achieves state-of-the-art performances in many different downstream tasks. To validate our approach we consider 12 different downstream tasks for diagnosis classification, and prediction of 10 different clinical assessment scores. Pretrained models can be found at https://github.com/EIDOSLAB/AnatCL.
Authors: Karla Pizzi, Mat\'ias Pizarro, Asja Fischer
Abstract: In this study, we investigate if noise-augmented training can concurrently improve adversarial robustness in automatic speech recognition (ASR) systems. We conduct a comparative analysis of the adversarial robustness of four different state-of-the-art ASR architectures, where each of the ASR architectures is trained under three different augmentation conditions: one subject to background noise, speed variations, and reverberations, another subject to speed variations only, and a third without any form of data augmentation. The results demonstrate that noise augmentation not only improves model performance on noisy speech but also the model's robustness to adversarial attacks.
Authors: Seyed Mohammad Azimi-Abarghouyi, Lav R. Varshney
Abstract: This paper introduces a federated learning framework that enables over-the-air computation via digital communications, using a new joint source-channel coding scheme. Without relying on channel state information at devices, this scheme employs lattice codes to both quantize model parameters and exploit interference from the devices. We propose a novel receiver structure at the server, designed to reliably decode an integer combination of the quantized model parameters as a lattice point for the purpose of aggregation. We present a mathematical approach to derive a convergence bound for the proposed scheme and offer design remarks. In this context, we suggest an aggregation metric and a corresponding algorithm to determine effective integer coefficients for the aggregation in each communication round. Our results illustrate that, regardless of channel dynamics and data heterogeneity, our scheme consistently delivers superior learning accuracy across various parameters and markedly surpasses other over-the-air methodologies.
Authors: Eliot Tron, Rita Fioresi, Nicolas Couellan, St\'ephane Puechmorel
Abstract: The purpose of this paper is to employ the language of Cartan moving frames to study the geometry of the data manifolds and its Riemannian structure, via the data information metric and its curvature at data points. Using this framework and through experiments, explanations on the response of a neural network are given by pointing out the output classes that are easily reachable from a given input. This emphasizes how the proposed mathematical relationship between the output of the network and the geometry of its inputs can be exploited as an explainable artificial intelligence tool.
Authors: Hamed Sajadinia, Ali Aghdaei, Zhuo Feng
Abstract: State-of-the-art hypergraph partitioners utilize a multilevel paradigm to construct progressively coarser hypergraphs across multiple layers, guiding cut refinements at each level of the hierarchy. Traditionally, these partitioners employ heuristic methods for coarsening and do not consider the structural features of hypergraphs. In this work, we introduce a multilevel spectral framework, SHyPar, for partitioning large-scale hypergraphs by leveraging hyperedge effective resistances and flow-based community detection techniques. Inspired by the latest theoretical spectral clustering frameworks, such as HyperEF and HyperSF, SHyPar aims to decompose large hypergraphs into multiple subgraphs with few inter-partition hyperedges (cut size). A key component of SHyPar is a flow-based local clustering scheme for hypergraph coarsening, which incorporates a max-flow-based algorithm to produce clusters with substantially improved conductance. Additionally, SHyPar utilizes an effective resistance-based rating function for merging nodes that are strongly connected (coupled). Compared with existing state-of-the-art hypergraph partitioning methods, our extensive experimental results on real-world VLSI designs demonstrate that SHyPar can more effectively partition hypergraphs, achieving state-of-the-art solution quality.
Authors: Zaixi Zhang, Ruofan Jin, Kaidi Fu, Le Cong, Marinka Zitnik, Mengdi Wang
Abstract: Protein structure is key to understanding protein function and is essential for progress in bioengineering, drug discovery, and molecular biology. Recently, with the incorporation of generative AI, the power and accuracy of computational protein structure prediction/design have been improved significantly. However, ethical concerns such as copyright protection and harmful content generation (biosecurity) pose challenges to the wide implementation of protein generative models. Here, we investigate whether it is possible to embed watermarks into protein generative models and their outputs for copyright authentication and the tracking of generated structures. As a proof of concept, we propose a two-stage method FoldMark as a generalized watermarking strategy for protein generative models. FoldMark first pretrain watermark encoder and decoder, which can minorly adjust protein structures to embed user-specific information and faithfully recover the information from the encoded structure. In the second step, protein generative models are fine-tuned with watermark Low-Rank Adaptation (LoRA) modules to preserve generation quality while learning to generate watermarked structures with high recovery rates. Extensive experiments are conducted on open-source protein structure prediction models (e.g., ESMFold and MultiFlow) and de novo structure design models (e.g., FrameDiff and FoldFlow) and we demonstrate that our method is effective across all these generative models. Meanwhile, our watermarking framework only exerts a negligible impact on the original protein structure quality and is robust under potential post-processing and adaptive attacks.
Authors: Julia Nakhleh, Joseph Shenouda, Robert D. Nowak
Abstract: This paper studies the properties of solutions to multi-task shallow ReLU neural network learning problems, wherein the network is trained to fit a dataset with minimal sum of squared weights. Remarkably, the solutions learned for each individual task resemble those obtained by solving a kernel method, revealing a novel connection between neural networks and kernel methods. It is known that single-task neural network training problems are equivalent to minimum norm interpolation problem in a non-Hilbertian Banach space, and that the solutions of such problems are generally non-unique. In contrast, we prove that the solutions to univariate-input, multi-task neural network interpolation problems are almost always unique, and coincide with the solution to a minimum-norm interpolation problem in a Sobolev (Reproducing Kernel) Hilbert Space. We also demonstrate a similar phenomenon in the multivariate-input case; specifically, we show that neural network learning problems with large numbers of diverse tasks are approximately equivalent to an $\ell^2$ (Hilbert space) minimization problem over a fixed kernel determined by the optimal neurons.
Authors: Yehe Liu, Alexander Krull, Hector Basevi, Ales Leonardis, Michael W. Jenkins
Abstract: Quanta image sensors, such as SPAD arrays, are an emerging sensor technology, producing 1-bit arrays representing photon detection events over exposures as short as a few nanoseconds. In practice, raw data are post-processed using heavy spatiotemporal binning to create more useful and interpretable images at the cost of degrading spatiotemporal resolution. In this work, we propose bit2bit, a new method for reconstructing high-quality image stacks at the original spatiotemporal resolution from sparse binary quanta image data. Inspired by recent work on Poisson denoising, we developed an algorithm that creates a dense image sequence from sparse binary photon data by predicting the photon arrival location probability distribution. However, due to the binary nature of the data, we show that the assumption of a Poisson distribution is inadequate. Instead, we model the process with a Bernoulli lattice process from the truncated Poisson. This leads to the proposal of a novel self-supervised solution based on a masked loss function. We evaluate our method using both simulated and real data. On simulated data from a conventional video, we achieve 34.35 mean PSNR with extremely photon-sparse binary input (<0.06 photons per pixel per frame). We also present a novel dataset containing a wide range of real SPAD high-speed videos under various challenging imaging conditions. The scenes cover strong/weak ambient light, strong motion, ultra-fast events, etc., which will be made available to the community, on which we demonstrate the promise of our approach. Both reconstruction quality and throughput substantially surpass the state-of-the-art methods (e.g., Quanta Burst Photography (QBP)). Our approach significantly enhances the visualization and usability of the data, enabling the application of existing analysis techniques.
Authors: Zhili Feng, Tanya Marwah, Nicolo Fusi, David Alvarez-Melis, Lester Mackey
Abstract: Modern large language models use a fixed tokenizer to effectively compress text drawn from a source domain. However, applying the same tokenizer to a new target domain often leads to inferior compression, more costly inference, and reduced semantic alignment. To address this deficiency, we introduce Sparse Sinkhorn Token Translation (S2T2). S2T2 trains a tailored tokenizer for the target domain and learns to translate between target and source tokens, enabling more effective reuse of the pre-trained next-source-token predictor. In our experiments with finetuned English language models, S2T2 improves both the perplexity and the compression of out-of-domain protein sequences, outperforming direct finetuning with either the source or target tokenizer. In addition, we find that token translations learned for smaller, less expensive models can be directly transferred to larger, more powerful models to reap the benefits of S2T2 at lower cost.
Authors: Erik M. Lintunen, Nadia M. Ady, Christian Guckelsberger
Abstract: Non-uniform goal selection has the potential to improve the reinforcement learning (RL) of skills over uniform-random selection. In this paper, we introduce a method for learning a goal-selection policy in intrinsically-motivated goal-conditioned RL: "Diversity Progress" (DP). The learner forms a curriculum based on observed improvement in discriminability over its set of goals. Our proposed method is applicable to the class of discriminability-motivated agents, where the intrinsic reward is computed as a function of the agent's certainty of following the true goal being pursued. This reward can motivate the agent to learn a set of diverse skills without extrinsic rewards. We demonstrate empirically that a DP-motivated agent can learn a set of distinguishable skills faster than previous approaches, and do so without suffering from a collapse of the goal distribution -- a known issue with some prior approaches. We end with plans to take this proof-of-concept forward.
Authors: Wenzhi Gao, Ya-Chi Chu, Yinyu Ye, Madeleine Udell
Abstract: We introduce a framework to accelerate the convergence of gradient-based methods with online learning. The framework learns to scale the gradient at each iteration through an online learning algorithm and provably accelerates gradient-based methods asymptotically. In contrast with previous literature, where convergence is established based on worst-case analysis, our framework provides a strong convergence guarantee with respect to the optimal scaling matrix for the iteration trajectory. For smooth strongly convex optimization, our results provide an $O(\kappa^\star \log(1/\varepsilon)$) complexity result, where $\kappa^\star$ is the condition number achievable by the optimal preconditioner, improving on the previous $O(\sqrt{n}\kappa^\star \log(1/\varepsilon))$ result. In particular, a variant of our method achieves superlinear convergence on convex quadratics. For smooth convex optimization, we show for the first time that the widely-used hypergradient descent heuristic improves on the convergence of gradient descent.
Authors: Yingzhen Yang, Ping Li
Abstract: We study nonparametric regression by an over-parameterized two-layer neural network trained by gradient descent (GD) in this paper. We show that, if the neural network is trained by GD with early stopping, then the trained network renders a sharp rate of the nonparametric regression risk of $\cO(\eps_n^2)$, which is the same rate as that for the classical kernel regression trained by GD with early stopping, where $\eps_n$ is the critical population rate of the Neural Tangent Kernel (NTK) associated with the network and $n$ is the size of the training data. It is remarked that our result does not require distributional assumptions on the training data, in a strong contrast with many existing results which rely on specific distributions such as the spherical uniform data distribution or distributions satisfying certain restrictive conditions. The rate $\cO(\eps_n^2)$ is known to be minimax optimal for specific cases, such as the case that the NTK has a polynomial eigenvalue decay rate which happens under certain distributional assumptions. Our result formally fills the gap between training a classical kernel regression model and training an over-parameterized but finite-width neural network by GD for nonparametric regression without distributional assumptions. We also provide confirmative answers to certain open questions or address particular concerns in the literature of training over-parameterized neural networks by GD with early stopping for nonparametric regression, including the characterization of the stopping time, the lower bound for the network width, and the constant learning rate used in GD.
Authors: Pourya Jafarzadeh, Amir Mohammad Rostami, Padideh Choobdar
Abstract: Speech is the most natural way of expressing ourselves as humans. Identifying emotion from speech is a nontrivial task due to the ambiguous definition of emotion itself. Speaker Emotion Recognition (SER) is essential for understanding human emotional behavior. The SER task is challenging due to the variety of speakers, background noise, complexity of emotions, and speaking styles. It has many applications in education, healthcare, customer service, and Human-Computer Interaction (HCI). Previously, conventional machine learning methods such as SVM, HMM, and KNN have been used for the SER task. In recent years, deep learning methods have become popular, with convolutional neural networks and recurrent neural networks being used for SER tasks. The input of these methods is mostly spectrograms and hand-crafted features. In this work, we study the use of self-supervised transformer-based models, Wav2Vec2 and HuBERT, to determine the emotion of speakers from their voice. The models automatically extract features from raw audio signals, which are then used for the classification task. The proposed solution is evaluated on reputable datasets, including RAVDESS, SHEMO, SAVEE, AESDD, and Emo-DB. The results show the effectiveness of the proposed method on different datasets. Moreover, the model has been used for real-world applications like call center conversations, and the results demonstrate that the model accurately predicts emotions.