Authors: Su Hyeong Lee, Sidharth Sharma, Manzil Zaheer, Tian Li
Abstract: Adaptive optimization plays a pivotal role in federated learning, where simultaneous server and client-side adaptivity have been shown to be essential for maximizing its performance. However, the scalability of jointly adaptive systems is often constrained by limited resources in communication and memory. In this paper, we introduce a class of efficient adaptive algorithms, named $FedAda^2$, designed specifically for large-scale, cross-device federated environments. $FedAda^2$ optimizes communication efficiency by avoiding the transfer of preconditioners between the server and clients. At the same time, it leverages memory-efficient adaptive optimizers on the client-side to reduce on-device memory consumption. Theoretically, we demonstrate that $FedAda^2$ achieves the same convergence rates for general, non-convex objectives as its more resource-intensive counterparts that directly integrate joint adaptivity. Empirically, we showcase the benefits of joint adaptivity and the effectiveness of $FedAda^2$ on both image and text datasets.
Authors: Wei Ai, Jianbin Li, Ze Wang, Jiayi Du, Tao Meng, Yuntao Shou, Keqin Li
Abstract: Graph contrastive learning (GCL) has been widely applied to text classification tasks due to its ability to generate self-supervised signals from unlabeled data, thus facilitating model training. However, existing GCL-based text classification methods often suffer from negative sampling bias, where similar nodes are incorrectly paired as negative pairs. This can lead to over-clustering, where instances of the same class are divided into different clusters. To address the over-clustering issue, we propose an innovative GCL-based method of graph contrastive learning via cluster-refined negative sampling for semi-supervised text classification, namely ClusterText. Firstly, we combine the pre-trained model Bert with graph neural networks to learn text representations. Secondly, we introduce a clustering refinement strategy, which clusters the learned text representations to obtain pseudo labels. For each text node, its negative sample set is drawn from different clusters. Additionally, we propose a self-correction mechanism to mitigate the loss of true negative samples caused by clustering inconsistency. By calculating the Euclidean distance between each text node and other nodes within the same cluster, distant nodes are still selected as negative samples. Our proposed ClusterText demonstrates good scalable computing, as it can effectively extract important information from from a large amount of data. Experimental results demonstrate the superiority of ClusterText in text classification tasks.
Authors: Abdelmonem Elrefaey, Rong Pan
Abstract: This paper presents a novel Integer Programming (IP) approach for discovering the Markov Equivalent Class (MEC) of Bayesian Networks (BNs) through observational data. The MEC-IP algorithm utilizes a unique clique-focusing strategy and Extended Maximal Spanning Graphs (EMSG) to streamline the search for MEC, thus overcoming the computational limitations inherent in other existing algorithms. Our numerical results show that not only a remarkable reduction in computational time is achieved by our algorithm but also an improvement in causal discovery accuracy is seen across diverse datasets. These findings underscore this new algorithm's potential as a powerful tool for researchers and practitioners in causal discovery and BNSL, offering a significant leap forward toward the efficient and accurate analysis of complex data structures.
Authors: Nithin Somasekharan, Shaowu Pan
Abstract: Representation learning for high-dimensional, complex physical systems aims to identify a low-dimensional intrinsic latent space, which is crucial for reduced-order modeling and modal analysis. To overcome the well-known Kolmogorov barrier, deep autoencoders (AEs) have been introduced in recent years, but they often suffer from poor convergence behavior as the rank of the latent space increases. To address this issue, we propose the learnable weighted hybrid autoencoder, a hybrid approach that combines the strengths of singular value decomposition (SVD) with deep autoencoders through a learnable weighted framework. We find that the introduction of learnable weighting parameters is essential - without them, the resulting model would either collapse into a standard POD or fail to exhibit the desired convergence behavior. Additionally, we empirically find that our trained model has a sharpness thousands of times smaller compared to other models. Our experiments on classical chaotic PDE systems, including the 1D Kuramoto-Sivashinsky and forced isotropic turbulence datasets, demonstrate that our approach significantly improves generalization performance compared to several competing methods, paving the way for robust representation learning of high-dimensional, complex physical systems.
Authors: Alessandro Londei, Matteo Benati, Denise Lanzieri, Vittorio Loreto
Abstract: Incorporating novelties into deep learning systems remains a challenging problem. Introducing new information to a machine learning system can interfere with previously stored data and potentially alter the global model paradigm, especially when dealing with non-stationary sources. In such cases, traditional approaches based on validation error minimization offer limited advantages. To address this, we propose a training algorithm inspired by Stuart Kauffman's notion of the Adjacent Possible. This novel training methodology explores new data spaces during the learning phase. It predisposes the neural network to smoothly accept and integrate data sequences with different statistical characteristics than expected. The maximum distance compatible with such inclusion depends on a specific parameter: the sampling temperature used in the explorative phase of the present method. This algorithm, called Dreaming Learning, anticipates potential regime shifts over time, enhancing the neural network's responsiveness to non-stationary events that alter statistical properties. To assess the advantages of this approach, we apply this methodology to unexpected statistical changes in Markov chains and non-stationary dynamics in textual sequences. We demonstrated its ability to improve the auto-correlation of generated textual sequences by $\sim 29\%$ and enhance the velocity of loss convergence by $\sim 100\%$ in the case of a paradigm shift in Markov chains.
Authors: Junwei Ma, Valentin Thomas, Rasa Hosseinzadeh, Hamidreza Kamkari, Alex Labach, Jesse C. Cresswell, Keyvan Golestan, Guangwei Yu, Maksims Volkovs, Anthony L. Caterini
Abstract: The challenges faced by neural networks on tabular data are well-documented and have hampered the progress of tabular foundation models. Techniques leveraging in-context learning (ICL) have shown promise here, allowing for dynamic adaptation to unseen data. ICL can provide predictions for entirely new datasets without further training or hyperparameter tuning, therefore providing very fast inference when encountering a novel task. However, scaling ICL for tabular data remains an issue: approaches based on large language models cannot efficiently process numeric tables, and tabular-specific techniques have not been able to effectively harness the power of real data to improve performance and generalization. We are able to overcome these challenges by training tabular-specific ICL-based architectures on real data with self-supervised learning and retrieval, combining the best of both worlds. Our resulting model -- the Tabular Discriminative Pre-trained Transformer (TabDPT) -- achieves state-of-the-art performance on the CC18 (classification) and CTR23 (regression) benchmarks with no task-specific fine-tuning, demonstrating the adapatability and speed of ICL once the model is pre-trained. TabDPT also demonstrates strong scaling as both model size and amount of available data increase, pointing towards future improvements simply through the curation of larger tabular pre-training datasets and training larger models.
Authors: Elyas Obbad, Iddah Mlauzi, Brando Miranda, Rylan Schaeffer, Kamal Obbad, Suhana Bedi, Sanmi Koyejo
Abstract: Data selection is crucial for optimizing language model (LM) performance on specific tasks, yet most existing methods fail to effectively consider the target task distribution. Current approaches either ignore task-specific requirements entirely or rely on approximations that fail to capture the nuanced patterns needed for tasks like Autoformalization or code generation. Methods that do consider the target distribution often rely on simplistic, sometimes noisy, representations, like hashed n-gram features, which can lead to collisions and introduce noise. We introduce ZIP-FIT, a data selection framework that uses gzip compression to directly measure alignment between potential training data and the target task distribution. In extensive evaluations on Autoformalization and Python code generation, ZIP-FIT significantly outperforms leading baselines like DSIR and D4. Models trained on ZIP-FIT-selected data achieve their lowest cross-entropy loss up to 85.1\% faster than baselines, demonstrating that better task alignment leads to more efficient learning. In addition, ZIP-FIT performs selection up to 65.8\% faster than DSIR and two orders of magnitude faster than D4. Notably, ZIP-FIT shows that smaller, well-aligned datasets often outperform larger but less targeted ones, demonstrating that a small amount of higher quality data is superior to a large amount of lower quality data. Our results imply that task-aware data selection is crucial for efficient domain adaptation, and that compression offers a principled way to measure task alignment. By showing that targeted data selection can dramatically improve task-specific performance, our work provides new insights into the relationship between data quality, task alignment, and model learning efficiency.
Authors: Rana Shahout, Cong Liang, Shiji Xin, Qianru Lao, Yong Cui, Minlan Yu, Michael Mitzenmacher
Abstract: Augmented Large Language Models (LLMs) enhance the capabilities of standalone LLMs by integrating external data sources through API calls. In interactive LLM applications, efficient scheduling is crucial for maintaining low request completion times, directly impacting user engagement. However, these augmentations introduce scheduling challenges due to the need to manage limited memory for cached information (KV caches). As a result, traditional size-based scheduling algorithms, such as Shortest Job First (SJF), become less effective at minimizing completion times. Existing work focuses only on handling requests during API calls by preserving, discarding, or swapping memory without considering how to schedule requests with API calls. In this paper, we propose LAMPS, a novel LLM inference framework for augmented LLMs. LAMPS minimizes request completion time through a unified scheduling approach that considers the total length of requests and their handling strategies during API calls. Recognizing that LLM inference is memory-bound, our approach ranks requests based on their consumption of memory over time, which depends on both the output sizes and how a request is managed during its API calls. To implement our scheduling, LAMPS predicts the strategy that minimizes memory waste of a request during its API calls, aligning with but improving upon existing approaches. We also propose starvation prevention techniques and optimizations to mitigate the overhead of our scheduling. We implement LAMPS on top of vLLM and evaluate its performance against baseline LLM inference systems, demonstrating improvements in end-to-end latency by 27%-85% and reductions in TTFT by 4%-96% compared to the existing augmented-LLM system, with even greater gains over vLLM.
Authors: Michael Noukhovitch, Shengyi Huang, Sophie Xhonneux, Arian Hosseini, Rishabh Agarwal, Aaron Courville
Abstract: The dominant paradigm for RLHF is online and on-policy RL: synchronously generating from the large language model (LLM) policy, labelling with a reward model, and learning using feedback on the LLM's own outputs. While performant, this paradigm is computationally inefficient. Inspired by classical deep RL literature, we propose separating generation and learning in RLHF. This enables asynchronous generation of new samples while simultaneously training on old samples, leading to faster training and more compute-optimal scaling. However, asynchronous training relies on an underexplored regime, online but off-policy RLHF: learning on samples from previous iterations of our model. To understand the challenges in this regime, we investigate a fundamental question: how much off-policyness can we tolerate for asynchronous training to speed up learning but maintain performance? Among several RLHF algorithms we tested, we find that online DPO is most robust to off-policy data, and robustness increases with the scale of the policy model. We study further compute optimizations for asynchronous RLHF but find that they come at a performance cost, giving rise to a trade-off. Finally, we verify the scalability of asynchronous RLHF by training LLaMA 3.1 8B on an instruction-following task 40% faster than a synchronous run while matching final performance.
Authors: Priscilla Canizares, Davide Murari, Carola-Bibiane Sch\"onlieb, Ferdia Sherry, Zakhar Shumaylov
Abstract: Hamilton's equations of motion form a fundamental framework in various branches of physics, including astronomy, quantum mechanics, particle physics, and climate science. Classical numerical solvers are typically employed to compute the time evolution of these systems. However, when the system spans multiple spatial and temporal scales numerical errors can accumulate, leading to reduced accuracy. To address the challenges of evolving such systems over long timescales, we propose SympFlow, a novel neural network-based symplectic integrator, which is the composition of a sequence of exact flow maps of parametrised time-dependent Hamiltonian functions. This architecture allows for a backward error analysis: we can identify an underlying Hamiltonian function of the architecture and use it to define a Hamiltonian matching objective function, which we use for training. In numerical experiments, we show that SympFlow exhibits promising results, with qualitative energy conservation behaviour similar to that of time-stepping symplectic integrators.
Authors: Srihari Kamesh Kompella, Kemal Davaslioglu, Yalin E. Sagduyu, Sastry Kompella
Abstract: Radio frequency (RF) communication has been an important part of civil and military communication for decades. With the increasing complexity of wireless environments and the growing number of devices sharing the spectrum, it has become critical to efficiently manage and classify the signals that populate these frequencies. In such scenarios, the accurate classification of wireless signals is essential for effective spectrum management, signal interception, and interference mitigation. However, the classification of wireless RF signals often faces challenges due to the limited availability of labeled training data, especially under low signal-to-noise ratio (SNR) conditions. To address these challenges, this paper proposes the use of a Vector-Quantized Variational Autoencoder (VQ-VAE) to augment training data, thereby enhancing the performance of a baseline wireless classifier. The VQ-VAE model generates high-fidelity synthetic RF signals, increasing the diversity and fidelity of the training dataset by capturing the complex variations inherent in RF communication signals. Our experimental results show that incorporating VQ-VAE-generated data significantly improves the classification accuracy of the baseline model, particularly in low SNR conditions. This augmentation leads to better generalization and robustness of the classifier, overcoming the constraints imposed by limited real-world data. By improving RF signal classification, the proposed approach enhances the efficacy of wireless communication in both civil and tactical settings, ensuring reliable and secure operations. This advancement supports critical decision-making and operational readiness in environments where communication fidelity is essential.
Authors: Kexin Feng, Theodora Chaspari
Abstract: This study investigates explainable machine learning algorithms for identifying depression from speech. Grounded in evidence from speech production that depression affects motor control and vowel generation, pre-trained vowel-based embeddings, that integrate semantically meaningful linguistic units, are used. Following that, an ensemble learning approach decomposes the problem into constituent parts characterized by specific depression symptoms and severity levels. Two methods are explored: a "bottom-up" approach with 8 models predicting individual Patient Health Questionnaire-8 (PHQ-8) item scores, and a "top-down" approach using a Mixture of Experts (MoE) with a router module for assessing depression severity. Both methods depict performance comparable to state-of-the-art baselines, demonstrating robustness and reduced susceptibility to dataset mean/median values. System explainability benefits are discussed highlighting their potential to assist clinicians in depression diagnosis and screening.
Authors: Qinsi Wang, Saeed Vahidian, Hancheng Ye, Jianyang Gu, Jianyi Zhang, Yiran Chen
Abstract: Large language models (LLMs) with billions of parameters have sparked a new wave of exciting AI applications. However, their high computational costs and memory demands during inference pose significant challenges. Adaptive sparse activation inference, which activates only a small number of neurons for each token, offers a novel way to accelerate model inference without degrading performance, showing great potential for resource-constrained hardware devices. Nevertheless, existing methods predict activated neurons based on individual tokens with additional MLP, which involve frequent changes in activation maps and resource calls, limiting the acceleration benefits of sparse activation. In this paper, we introduce CoreInfer, an MLP-free adaptive sparse activation inference method based on sentence-level prediction. Specifically, we propose the concept of sentence-wise core neurons, which refers to the subset of neurons most critical for a given sentence, and empirically demonstrate its effectiveness. To determine the core neurons, we explore the correlation between core neurons and the sentence's semantics. Remarkably, we discovered that core neurons exhibit both stability and similarity in relation to the sentence's semantics -- an insight overlooked by previous studies. Building on this finding, we further design two semantic-based methods for predicting core neurons to fit different input scenarios. In CoreInfer, the core neurons are determined during the pre-filling stage and fixed during the encoding stage, enabling zero-cost sparse inference. We evaluated the model generalization and task generalization of CoreInfer across various models and tasks. Notably, on an NVIDIA TITAN XP GPU, CoreInfer achieved a 10.33 times and 2.72 times speedup compared to the Huggingface implementation and PowerInfer, respectively.
Authors: Andreas L{\o}vendahl Eefsen, Nicholas Erup Larsen, Oliver Glozmann Bork Hansen, Thor H{\o}jhus Avenstrup
Abstract: Accurate time series forecasting is a highly valuable endeavour with applications across many industries. Despite recent deep learning advancements, increased model complexity, and larger model sizes, many state-of-the-art models often perform worse or on par with simpler models. One of those cases is a recently proposed model, FITS, claiming competitive performance with significantly reduced parameter counts. By training a one-layer neural network in the complex frequency domain, we are able to replicate these results. Our experiments on a wide range of real-world datasets further reveal that FITS especially excels at capturing periodic and seasonal patterns, but struggles with trending, non-periodic, or random-resembling behavior. With our two novel hybrid approaches, where we attempt to remedy the weaknesses of FITS by combining it with DLinear, we achieve the best results of any known open-source model on multivariate regression and promising results in multiple/linear regression on price datasets, on top of vastly improving upon what FITS achieves as a standalone model.
Authors: Wenhao Liang, Chang Dong, Liangwei Zheng, Zhengyang Li, Wei Zhang, Weitong Chen
Abstract: Uncertainty is a fundamental aspect of real-world scenarios, where perfect information is rarely available. Humans naturally develop complex internal models to navigate incomplete data and effectively respond to unforeseen or partially observed events. In machine learning, Focal Loss is commonly used to reduce misclassification rates by emphasizing hard-to-classify samples. However, it does not guarantee well-calibrated predicted probabilities and may result in models that are overconfident or underconfident. High calibration error indicates a misalignment between predicted probabilities and actual outcomes, affecting model reliability. This research introduces a novel loss function called Focal Calibration Loss (FCL), designed to improve probability calibration while retaining the advantages of Focal Loss in handling difficult samples. By minimizing the Euclidean norm through a strictly proper loss, FCL penalizes the instance-wise calibration error and constrains bounds. We provide theoretical validation for proposed method and apply it to calibrate CheXNet for potential deployment in web-based health-care systems. Extensive evaluations on various models and datasets demonstrate that our method achieves SOTA performance in both calibration and accuracy metrics.
Authors: Jong-Ik Park, Srinivasa Pranav, Jos\'e M. F. Moura, Carlee Joe-Wong
Abstract: Foundation models are now a major focus of leading technology organizations due to their ability to generalize across diverse tasks. Existing approaches for adapting foundation models to new applications often rely on Federated Learning (FL) and disclose the foundation model weights to clients when using it to initialize the global model. While these methods ensure client data privacy, they compromise model and information security. In this paper, we introduce Federated Learning Aggregation Biased by a Foundation Model (FedBaF), a novel method for dynamically integrating pre-trained foundation model weights during the FL aggregation phase. Unlike conventional methods, FedBaF preserves the confidentiality of the foundation model while still leveraging its power to train more accurate models, especially in non-IID and adversarial scenarios. Our comprehensive experiments use Pre-ResNet and foundation models like Vision Transformer to demonstrate that FedBaF not only matches, but often surpasses the test accuracy of traditional weight initialization methods by up to 11.4\% in IID and up to 15.8\% in non-IID settings. Additionally, FedBaF applied to a Transformer-based language model significantly reduced perplexity by up to 39.2\%.
Authors: Mahdi Saki, Rasool Keshavarz, Daniel Franklin, Mehran Abolhasan, Justin Lipman, Negin Shariati
Abstract: This review explores the most recent advancements in transformer-based data fusion techniques in agricultural remote sensing (RS), with a particular focus on soil analysis. Utilizing a systematic, data-driven approach, we demonstrate that transformers have significantly outperformed conventional deep learning and machine learning methods since 2022, achieving prediction performance between 92% and 97%. The review is specifically focused on soil analysis, due to the importance of soil condition in optimizing crop productivity and ensuring sustainable farming practices. Transformer-based models have shown remarkable capabilities in handling complex multivariate soil data, improving the accuracy of soil moisture prediction, soil element analysis, and other soil-related applications. This systematic review primarily focuses on 1) analysing research trends and patterns in the literature, both chronologically and technically, and 2) conducting a comparative analysis of data fusion approaches, considering factors such as data types, techniques, and RS applications. Finally, we propose a roadmap for implementing data fusion methods in agricultural RS.
Authors: Chenlan Wang, Gaojian Huang, Yue Luo
Abstract: This study explored how lifestyle, personal background, and family history contribute to the risk of developing Alcohol Use Disorder (AUD). Survey data from the All of Us Program was utilized to extract information on AUD status, lifestyle, personal background, and family history for 6,016 participants. Key determinants of AUD were identified using decision trees including annual income, recreational drug use, length of residence, sex/gender, marital status, education level, and family history of AUD. Data visualization and Chi-Square Tests of Independence were then used to assess associations between identified factors and AUD. Afterwards, machine learning techniques including decision trees, random forests, and Naive Bayes were applied to predict an individual's likelihood of developing AUD. Random forests were found to achieve the highest accuracy (82%), compared to Decision Trees and Naive Bayes. Findings from this study can offer insights that help parents, healthcare professionals, and educators develop strategies to reduce AUD risk, enabling early intervention and targeted prevention efforts.
Authors: Runzhen Xue, Hao Wu, Mingyu Yan, Ziheng Xiao, Xiaochun Ye, Dongrui Fan
Abstract: Design space exploration (DSE) enables architects to systematically evaluate various design options, guiding decisions on the most suitable configurations to meet specific objectives such as optimizing performance, power, and area. However, the growing complexity of modern CPUs has dramatically increased the number of micro-architectural parameters and expanded the overall design space, making DSE more challenging and time-consuming. Existing DSE frameworks struggle in large-scale design spaces due to inaccurate models and limited insights into parameter impact, hindering efficient identification of optimal micro-architectures within tight timeframes. In this work, we introduce AttentionDSE. Its key idea is to use the attention mechanism to establish a direct mapping of micro-architectural parameters to their contributions to predicted performance. This approach enhances both the prediction accuracy and interpretability of the performance model. Furthermore, the weights are dynamically adjusted, enabling the model to respond to design changes and effectively pinpoint the key micro-architectural parameters/components responsible for performance bottlenecks. Thus, AttentionDSE accurately, purposefully, and rapidly discovers optimal designs. Experiments on SPEC 2017 demonstrate that AttentionDSE significantly reduces exploration time by over 80\% and achieves 3.9\% improvement in Pareto Hypervolume compared to state-of-the-art DSE frameworks while maintaining superior prediction accuracy and efficiency with an increasing number of parameters.
Authors: Chen Gong, Zhenzhe Zheng, Fan Wu, Xiaofeng Jia, Guihai Chen
Abstract: In modern mobile applications, users frequently encounter various new contexts, necessitating on-device continual learning (CL) to ensure consistent model performance. While existing research predominantly focused on developing lightweight CL frameworks, we identify that data scarcity is a critical bottleneck for on-device CL. In this work, we explore the potential of leveraging abundant cloud-side data to enrich scarce on-device data, and propose a private, efficient and effective data enrichment framework Delta. Specifically, Delta first introduces a directory dataset to decompose the data enrichment problem into device-side and cloud-side sub-problems without sharing sensitive data. Next, Delta proposes a soft data matching strategy to effectively solve the device-side sub-problem with sparse user data, and an optimal data sampling scheme for cloud server to retrieve the most suitable dataset for enrichment with low computational complexity. Further, Delta refines the data sampling scheme by jointly considering the impact of enriched data on both new and past contexts, mitigating the catastrophic forgetting issue from a new aspect. Comprehensive experiments across four typical mobile computing tasks with varied data modalities demonstrate that Delta could enhance the overall model accuracy by an average of 15.1%, 12.4%, 1.1% and 5.6% for visual, IMU, audio and textual tasks compared with few-shot CL, and consistently reduce the communication costs by over 90% compared to federated CL.
Authors: Robert Dilworth, Charan Gudla
Abstract: This paper explores the application of Positive-Unlabeled (PU) learning for enhanced Distributed Denial-of-Service (DDoS) detection in cloud environments. Utilizing the $\texttt{BCCC-cPacket-Cloud-DDoS-2024}$ dataset, we implement PU learning with four machine learning algorithms: XGBoost, Random Forest, Support Vector Machine, and Na\"{i}ve Bayes. Our results demonstrate the superior performance of ensemble methods, with XGBoost and Random Forest achieving $F_{1}$ scores exceeding 98%. We quantify the efficacy of each approach using metrics including $F_{1}$ score, ROC AUC, Recall, and Precision. This study bridges the gap between PU learning and cloud-based anomaly detection, providing a foundation for addressing Context-Aware DDoS Detection in multi-cloud environments. Our findings highlight the potential of PU learning in scenarios with limited labeled data, offering valuable insights for developing more robust and adaptive cloud security mechanisms.
Authors: Andrew Lowy, Daogao Liu, Hilal Asi
Abstract: We study private stochastic convex optimization (SCO) under user-level differential privacy (DP) constraints. In this setting, there are $n$ users (e.g., cell phones), each possessing $m$ data items (e.g., text messages), and we need to protect the privacy of each user's entire collection of data items. Existing algorithms for user-level DP SCO are impractical in many large-scale machine learning scenarios because: (i) they make restrictive assumptions on the smoothness parameter of the loss function and require the number of users to grow polynomially with the dimension of the parameter space; or (ii) they are prohibitively slow, requiring at least $(mn)^{3/2}$ gradient computations for smooth losses and $(mn)^3$ computations for non-smooth losses. To address these limitations, we provide novel user-level DP algorithms with state-of-the-art excess risk and runtime guarantees, without stringent assumptions. First, we develop a linear-time algorithm with state-of-the-art excess risk (for a non-trivial linear-time algorithm) under a mild smoothness assumption. Our second algorithm applies to arbitrary smooth losses and achieves optimal excess risk in $\approx (mn)^{9/8}$ gradient computations. Third, for non-smooth loss functions, we obtain optimal excess risk in $n^{11/8} m^{5/4}$ gradient computations. Moreover, our algorithms do not require the number of users to grow polynomially with the dimension.
Authors: Seyed Ali Alavi Bajestan, Mark Pitt, Donald S. Williamson
Abstract: Carrying conversations in multi-sound environments is one of the more challenging tasks, since the sounds overlap across time and frequency making it difficult to understand a single sound source. One proposed approach to help isolate an attended speech source is through decoding the electroencephalogram (EEG) and identifying the attended audio source using statistical or machine learning techniques. However, the limited amount of data in comparison to other machine learning problems and the distributional shift between different EEG recordings emphasizes the need for a self supervised approach that works with limited data to achieve a more robust solution. In this paper, we propose a method based on self supervised learning to minimize the difference between the latent representations of an attended speech signal and the corresponding EEG signal. This network is further finetuned for the auditory attention classification task. We compare our results with previously published methods and achieve state-of-the-art performance on the validation set.
Authors: Kaifeng Jin, Ignavier Ng, Kun Zhang, Biwei Huang
Abstract: Recent advances in differentiable structure learning have framed the combinatorial problem of learning directed acyclic graphs as a continuous optimization problem. Various aspects, including data standardization, have been studied to identify factors that influence the empirical performance of these methods. In this work, we investigate critical limitations in differentiable structure learning methods, focusing on settings where the true structure can be identified up to Markov equivalence classes, particularly in the linear Gaussian case. While Ng et al. (2024) highlighted potential non-convexity issues in this setting, we demonstrate and explain why the use of $\ell_1$-penalized likelihood in such cases is fundamentally inconsistent, even if the global optimum of the optimization problem can be found. To resolve this limitation, we develop a hybrid differentiable structure learning method based on $\ell_0$-penalized likelihood with hard acyclicity constraint, where the $\ell_0$ penalty can be approximated by different techniques including Gumbel-Softmax. Specifically, we first estimate the underlying moral graph, and use it to restrict the search space of the optimization problem, which helps alleviate the non-convexity issue. Experimental results show that the proposed method enhances empirical performance both before and after data standardization, providing a more reliable path for future advancements in differentiable structure learning, especially for learning Markov equivalence classes.
Authors: Sijia Xia, Michael K. Ng, Xiongjun Zhang
Abstract: In this paper, we study the problem of low-rank tensor learning, where only a few of training samples are observed and the underlying tensor has a low-rank structure. The existing methods are based on the sum of nuclear norms of unfolding matrices of a tensor, which may be suboptimal. In order to explore the low-rankness of the underlying tensor effectively, we propose a nonconvex model based on transformed tensor nuclear norm for low-rank tensor learning. Specifically, a family of nonconvex functions are employed onto the singular values of all frontal slices of a tensor in the transformed domain to characterize the low-rankness of the underlying tensor. An error bound between the stationary point of the nonconvex model and the underlying tensor is established under restricted strong convexity on the loss function (such as least squares loss and logistic regression) and suitable regularity conditions on the nonconvex penalty function. By reformulating the nonconvex function into the difference of two convex functions, a proximal majorization-minimization (PMM) algorithm is designed to solve the resulting model. Then the global convergence and convergence rate of PMM are established under very mild conditions. Numerical experiments are conducted on tensor completion and binary classification to demonstrate the effectiveness of the proposed method over other state-of-the-art methods.
Authors: Maryam Aliakbarpour, Syomantak Chaudhuri, Thomas A. Courtade, Alireza Fallah, Michael I. Jordan
Abstract: Local Differential Privacy (LDP) offers strong privacy guarantees without requiring users to trust external parties. However, LDP applies uniform protection to all data features, including less sensitive ones, which degrades performance of downstream tasks. To overcome this limitation, we propose a Bayesian framework, Bayesian Coordinate Differential Privacy (BCDP), that enables feature-specific privacy quantification. This more nuanced approach complements LDP by adjusting privacy protection according to the sensitivity of each feature, enabling improved performance of downstream tasks without compromising privacy. We characterize the properties of BCDP and articulate its connections with standard non-Bayesian privacy frameworks. We further apply our BCDP framework to the problems of private mean estimation and ordinary least-squares regression. The BCDP-based approach obtains improved accuracy compared to a purely LDP-based approach, without compromising on privacy.
Authors: Zizhao Wang, Jiaheng Hu, Caleb Chuck, Stephen Chen, Roberto Mart\'in-Mart\'in, Amy Zhang, Scott Niekum, Peter Stone
Abstract: Unsupervised skill discovery carries the promise that an intelligent agent can learn reusable skills through autonomous, reward-free environment interaction. Existing unsupervised skill discovery methods learn skills by encouraging distinguishable behaviors that cover diverse states. However, in complex environments with many state factors (e.g., household environments with many objects), learning skills that cover all possible states is impossible, and naively encouraging state diversity often leads to simple skills that are not ideal for solving downstream tasks. This work introduces Skill Discovery from Local Dependencies (Skild), which leverages state factorization as a natural inductive bias to guide the skill learning process. The key intuition guiding Skild is that skills that induce diverse interactions between state factors are often more valuable for solving downstream tasks. To this end, Skild develops a novel skill learning objective that explicitly encourages the mastering of skills that effectively induce different interactions within an environment. We evaluate Skild in several domains with challenging, long-horizon sparse reward tasks including a realistic simulated household robot domain, where Skild successfully learns skills with clear semantic meaning and shows superior performance compared to existing unsupervised reinforcement learning methods that only maximize state coverage.
Authors: Shrenik Zinage, Ilias Bilionis, Peter Meckl
Abstract: The stringent regulatory requirements on nitrogen oxides (NOx) emissions from diesel compression ignition engines require accurate and reliable models for real-time monitoring and diagnostics. Although traditional methods such as physical sensors and virtual engine control module (ECM) sensors provide essential data, they are only used for estimation. Ubiquitous literature primarily focuses on deterministic models with little emphasis on capturing the uncertainties due to sensors. The lack of probabilistic frameworks restricts the applicability of these models for robust diagnostics. The objective of this paper is to develop and validate a probabilistic model to predict engine-out NOx emissions using Gaussian process regression. Our approach is as follows. We employ three variants of Gaussian process models: the first with a standard radial basis function kernel with input window, the second incorporating a deep kernel using convolutional neural networks to capture temporal dependencies, and the third enriching the deep kernel with a causal graph derived via graph convolutional networks. The causal graph embeds physics knowledge into the learning process. All models are compared against a virtual ECM sensor using both quantitative and qualitative metrics. We conclude that our model provides an improvement in predictive performance when using an input window and a deep kernel structure. Even more compelling is the further enhancement achieved by the incorporation of a causal graph into the deep kernel. These findings are corroborated across different validation datasets.
Authors: Anjali N. Albert, Patrick Flaherty, Aaron Schein
Abstract: We consider the problem of developing interpretable and computationally efficient matrix decomposition methods for matrices whose entries have bounded support. Such matrices are found in large-scale DNA methylation studies and many other settings. Our approach decomposes the data matrix into a Tucker representation wherein the number of columns in the constituent factor matrices is not constrained. We derive a computationally efficient sampling algorithm to solve for the Tucker decomposition. We evaluate the performance of our method using three criteria: predictability, computability, and stability. Empirical results show that our method has similar performance as other state-of-the-art approaches in terms of held-out prediction and computational complexity, but has significantly better performance in terms of stability to changes in hyper-parameters. The improved stability results in higher confidence in the results in applications where the constituent factors are used to generate and test scientific hypotheses such as DNA methylation analysis of cancer samples.
Authors: Fulu Li
Abstract: In this paper, we give an in-depth analysis on the mathematical problem formulations and the probabilistic optimization explorations for some of the key components in Transformer model [33] in the field of generative AI. We explore and discuss some potential further enhancement for current state of the art methods for some key underlying technologies of generative AI models from algorithmic and probabilistic optimization perspective. In particular, we present an optimal solution for sub-word encoding (SWE) based on similar initial settings as that of byte-pair encoding (BPE) algorithm in [9] with similar objectives as that of WordPiece approach in [28, 31] to maximize the likelihood of the training data. We also present cross entropy optimization method to optimize hyperparameters for word2vec model [17]. In addition, we propose a factored combination of rotary positional encoding (RoPE) [32] and attention with linear biases (ALiBi) [23] with a harmonic series. We also present a probabilistic FlashAttention [6, 7] (PrFlashAttention) method with a probability distribution over block distances in the matrix to decide which block is likely to participate in a given round of attention computation while maintaining the lower triangle shape of the tensor for autoregressive language models by re-shaping the tensors. Finally, we present staircase adaptive quantization (SAQ) of key-value (KV) cache for multi-query attention (MQA) based on the framework presented in [16] to have gradual quantization degradation while achieving reasonable model quality and cost savings.
Authors: Boxuan Zhang, Jianing Zhu, Zengmao Wang, Tongliang Liu, Bo Du, Bo Han
Abstract: Out-of-distribution (OOD) detection aims to identify OOD inputs from unknown classes, which is important for the reliable deployment of machine learning models in the open world. Various scoring functions are proposed to distinguish it from in-distribution (ID) data. However, existing methods generally focus on excavating the discriminative information from a single input, which implicitly limits its representation dimension. In this work, we introduce a novel perspective, i.e., employing different common corruptions on the input space, to expand that. We reveal an interesting phenomenon termed confidence mutation, where the confidence of OOD data can decrease significantly under the corruptions, while the ID data shows a higher confidence expectation considering the resistance of semantic features. Based on that, we formalize a new scoring method, namely, Confidence aVerage (CoVer), which can capture the dynamic differences by simply averaging the scores obtained from different corrupted inputs and the original ones, making the OOD and ID distributions more separable in detection tasks. Extensive experiments and analyses have been conducted to understand and verify the effectiveness of CoVer. The code is publicly available at: https://github.com/tmlr-group/CoVer.
Authors: Junbao Chen, Jingfeng Xue, Yong Wang, Zhenyan Liu, Lu Huang
Abstract: Data heterogeneity is one of the key challenges in federated learning, and many efforts have been devoted to tackling this problem. However, distributed concept drift with data heterogeneity, where clients may additionally experience different concept drifts, is a largely unexplored area. In this work, we focus on real drift, where the conditional distribution $P(Y|X)$ changes. We first study how distributed concept drift affects the model training and find that local classifier plays a critical role in drift adaptation. Moreover, to address data heterogeneity, we study the feature alignment under distributed concept drift, and find two factors that are crucial for feature alignment: the conditional distribution $P(Y|X)$ and the degree of data heterogeneity. Motivated by the above findings, we propose FedCCFA, a federated learning framework with classifier clustering and feature alignment. To enhance collaboration under distributed concept drift, FedCCFA clusters local classifiers at class-level and generates clustered feature anchors according to the clustering results. Assisted by these anchors, FedCCFA adaptively aligns clients' feature spaces based on the entropy of label distribution $P(Y)$, alleviating the inconsistency in feature space. Our results demonstrate that FedCCFA significantly outperforms existing methods under various concept drift settings. Code is available at https://github.com/Chen-Junbao/FedCCFA.
Authors: Jiashun Cheng, Zinan Zheng, Yang Liu, Jianheng Tang, Hongwei Wang, Yu Rong, Jia Li, Fugee Tsung
Abstract: Graph Anomaly Detection (GAD) is a challenging and practical research topic where Graph Neural Networks (GNNs) have recently shown promising results. The effectiveness of existing GNNs in GAD has been mainly attributed to the simultaneous learning of node representations and the classifier in an end-to-end manner. Meanwhile, graph pre-training, the two-stage learning paradigm such as DGI and GraphMAE, has shown potential in leveraging unlabeled graph data to enhance downstream tasks, yet its impact on GAD remains under-explored. In this work, we show that graph pre-training models are strong graph anomaly detectors. Specifically, we demonstrate that pre-training is highly competitive, markedly outperforming the state-of-the-art end-to-end training models when faced with limited supervision. To understand this phenomenon, we further uncover pre-training enhances the detection of distant, under-represented, unlabeled anomalies that go beyond 2-hop neighborhoods of known anomalies, shedding light on its superior performance against end-to-end models. Moreover, we extend our examination to the potential of pre-training in graph-level anomaly detection. We envision this work to stimulate a re-evaluation of pre-training's role in GAD and offer valuable insights for future research.
Authors: Yifei Yang, Zouying Cao, Qiguang Chen, Libo Qin, Dongjie Yang, Hai Zhao, Zhi Chen
Abstract: The development of large language models (LLMs) has significantly expanded model sizes, resulting in substantial GPU memory requirements during inference. The key and value storage of the attention map in the KV (key-value) cache accounts for more than 80\% of this memory consumption. Nowadays, most existing KV cache compression methods focus on intra-layer compression within a single Transformer layer but few works consider layer-wise compression. In this paper, we propose a plug-and-play method called \textit{KVSharer}, which shares the KV cache between layers to achieve layer-wise compression. Rather than intuitively sharing based on higher similarity, we discover a counterintuitive phenomenon: sharing dissimilar KV caches better preserves the model performance. Experiments show that \textit{KVSharer} can reduce KV cache computation by 30\%, thereby lowering memory consumption without significantly impacting model performance and it can also achieve at least 1.3 times generation acceleration. Additionally, we verify that \textit{KVSharer} is compatible with existing intra-layer KV cache compression methods, and combining both can further save memory.
Authors: Yejing Huo, Guoheng Huang, Lianglun Cheng, Jianbin He, Xuhang Chen, Xiaochen Yuan, Guo Zhong, Chi-Man Pun
Abstract: Accurate prediction of mortality in nasopharyngeal carcinoma (NPC), a complex malignancy particularly challenging in advanced stages, is crucial for optimizing treatment strategies and improving patient outcomes. However, this predictive process is often compromised by the high-dimensional and heterogeneous nature of NPC-related data, coupled with the pervasive issue of incomplete multi-modal data, manifesting as missing radiological images or incomplete diagnostic reports. Traditional machine learning approaches suffer significant performance degradation when faced with such incomplete data, as they fail to effectively handle the high-dimensionality and intricate correlations across modalities. Even advanced multi-modal learning techniques like Transformers struggle to maintain robust performance in the presence of missing modalities, as they lack specialized mechanisms to adaptively integrate and align the diverse data types, while also capturing nuanced patterns and contextual relationships within the complex NPC data. To address these problem, we introduce IMAN: an adaptive network for robust NPC mortality prediction with missing modalities.
Authors: David Khachaturov, Robert Mullins
Abstract: Quantifying robustness in a single measure for the purposes of model selection, development of adversarial training methods, and anticipating trends has so far been elusive. The simplest metric to consider is the number of trainable parameters in a model but this has previously been shown to be insufficient at explaining robustness properties. A variety of other metrics, such as ones based on boundary thickness and gradient flatness have been proposed but have been shown to be inadequate proxies for robustness. In this work, we investigate the relationship between a model's effective dimensionality, which can be thought of as model complexity, and its robustness properties. We run experiments on commercial-scale models that are often used in real-world environments such as YOLO and ResNet. We reveal a near-linear inverse relationship between effective dimensionality and adversarial robustness, that is models with a lower dimensionality exhibit better robustness. We investigate the effect of a variety of adversarial training methods on effective dimensionality and find the same inverse linear relationship present, suggesting that effective dimensionality can serve as a useful criterion for model selection and robustness evaluation, providing a more nuanced and effective metric than parameter count or previously-tested measures.
Authors: Zhenqian Shen, Mingyang Zhou, Yongqi Zhang, Quanming Yao
Abstract: Predicting drug-drug interaction (DDI) plays an important role in pharmacology and healthcare for identifying potential adverse interactions and beneficial combination therapies between drug pairs. Recently, a flurry of graph learning methods have been introduced to predict drug-drug interactions. However, evaluating existing methods has several limitations, such as the absence of a unified comparison framework for DDI prediction methods, lack of assessments in meaningful real-world scenarios, and insufficient exploration of side information usage. In order to address these unresolved limitations in the literature, we propose a DDI prediction benchmark on graph learning. We first conduct unified evaluation comparison among existing methods. To meet realistic scenarios, we further evaluate the performance of different methods in settings with new drugs involved and examine the performance across different DDI types. Component analysis is conducted on the biomedical network to better utilize side information. Through this work, we hope to provide more insights for the problem of DDI prediction. Our implementation and data is open-sourced at https://anonymous.4open.science/r/DDI-Benchmark-ACD9/.
URLs: https://anonymous.4open.science/r/DDI-Benchmark-ACD9/.
Authors: Anup Shirgaonkar, Nikhil Pandey, Nazmiye Ceren Abay, Tolga Aktas, Vijay Aski
Abstract: Leading open-source large language models (LLMs) such as Llama-3.1-Instruct-405B are extremely capable at generating text, answering questions, and solving a variety of natural language understanding tasks. However, they incur higher inference cost and latency compared to smaller LLMs. Knowledge distillation provides a way to use outputs from these large, capable teacher models to train smaller student models which can be used for inference at lower cost and latency, while retaining comparable accuracy. We investigate the efficacy of distillation using the Llama-3.1-405B-Instruct teacher and the smaller Llama-3.1-8B-Instruct and Llama-3.1-70B-Instruct student models. Contributions of this work include (a) We evaluate the generalizability of distillation with the above Llama-3.1 teacher-student pairs across different tasks and datasets (b) We show that using synthetic data during distillation significantly improves the accuracy of 8B and 70B models, and when used with reasoning chains, even matches or surpasses the zero-shot accuracy of 405B model on some datasets (c) We empirically show that distillation enables 8B and 70B models to internalize 405B's reasoning ability by using only standard fine-tuning (without customizing any loss function). This allows cost and latency-efficient student model inference. (d) We show pitfalls in evaluation of distillation, and present task-specific evaluation, including both human and LLM-grading, and ground-truth based traditional accuracy benchmarks. This methodical study brings out the fundamental importance of synthetic data quality in knowledge distillation, and of combining multiple, task-specific ways of accuracy and quality evaluation in assessing the effectiveness of distillation.
Authors: Jinrui Zhang
Abstract: In this article, an encoder was trained to obtain the inner structure of the original data by obtain a differential equations. A decoder was trained to resample the original data domain, to generate new data that obey the differential structure of the original data using the physics-informed neural network.
Authors: Tianze Wang, Maryam Honari-Jahromi, Styliani Katsarou, Olga Mikheeva, Theodoros Panagiotakopoulos, Oleg Smirnov, Lele Cao, Sahar Asadi
Abstract: This pilot study explores the application of language models (LMs) to model game event sequences, treating them as a customized natural language. We investigate a popular mobile game, transforming raw event data into textual sequences and pretraining a Longformer model on this data. Our approach captures the rich and nuanced interactions within game sessions, effectively identifying meaningful player segments. The results demonstrate the potential of self-supervised LMs in enhancing game design and personalization without relying on ground-truth labels.
Authors: Yuhua Liao, Zetian Wang, Peng Wei, Qiangqiang Nie, Zhenhua Zhang
Abstract: Deep learning and pre-trained models have shown great success in time series forecasting. However, in the tourism industry, time series data often exhibit a leading time property, presenting a 2D structure. This introduces unique challenges for forecasting in this sector. In this study, we propose a novel modelling paradigm, TripCast, which treats trip time series as 2D data and learns representations through masking and reconstruction processes. Pre-trained on large-scale real-world data, TripCast notably outperforms other state-of-the-art baselines in in-domain forecasting scenarios and demonstrates strong scalability and transferability in out-domain forecasting scenarios.
Authors: Hemanth Saratchandran, Jianqiao Zheng, Yiping Ji, Wenbo Zhang, Simon Lucey
Abstract: This paper challenges the conventional belief that softmax attention in transformers is effective primarily because it generates a probability distribution for attention allocation. Instead, we theoretically show that its success lies in its ability to implicitly regularize the Frobenius norm of the attention matrix during training. We then explore alternative activations that regularize the Frobenius norm of the attention matrix, demonstrating that certain polynomial activations can achieve this effect, making them suitable for attention-based architectures. Empirical results indicate these activations perform comparably or better than softmax across various computer vision and language tasks, suggesting new possibilities for attention mechanisms beyond softmax.
Authors: Liyu Zhang, Haochi Wu, Xu Wan, Quan Kong, Ruilong Deng, Mingyang Sun
Abstract: The offline-to-online (O2O) paradigm in reinforcement learning (RL) utilizes pre-trained models on offline datasets for subsequent online fine-tuning. However, conventional O2O RL algorithms typically require maintaining and retraining the large offline datasets to mitigate the effects of out-of-distribution (OOD) data, which limits their efficiency in exploiting online samples. To address this challenge, we introduce a new paradigm called SAMG: State-Action-Conditional Offline-to-Online Reinforcement Learning with Offline Model Guidance. In particular, rather than directly training on offline data, SAMG freezes the pre-trained offline critic to provide offline values for each state-action pair to deliver compact offline information. This framework eliminates the need for retraining with offline data by freezing and leveraging these values of the offline model. These are then incorporated with the online target critic using a Bellman equation weighted by a policy state-action-aware coefficient. This coefficient, derived from a conditional variational auto-encoder (C-VAE), aims to capture the reliability of the offline data on a state-action level. SAMG could be easily integrated with existing Q-function based O2O RL algorithms. Theoretical analysis shows good optimality and lower estimation error of SAMG. Empirical evaluations demonstrate that SAMG outperforms four state-of-the-art O2O RL algorithms in the D4RL benchmark.
Authors: Jinxu Lin, Linwei Tao, Minjing Dong, Chang Xu
Abstract: As diffusion models become increasingly popular, the misuse of copyrighted and private images has emerged as a major concern. One promising solution to mitigate this issue is identifying the contribution of specific training samples in generative models, a process known as data attribution. Existing data attribution methods for diffusion models typically quantify the contribution of a training sample by evaluating the change in diffusion loss when the sample is included or excluded from the training process. However, we argue that the direct usage of diffusion loss cannot represent such a contribution accurately due to the calculation of diffusion loss. Specifically, these approaches measure the divergence between predicted and ground truth distributions, which leads to an indirect comparison between the predicted distributions and cannot represent the variances between model behaviors. To address these issues, we aim to measure the direct comparison between predicted distributions with an attribution score to analyse the training sample importance, which is achieved by Diffusion Attribution Score (DAS). Underpinned by rigorous theoretical analysis, we elucidate the effectiveness of DAS. Additionally, we explore strategies to accelerate DAS calculations, facilitating its application to large-scale diffusion models. Our extensive experiments across various datasets and diffusion models demonstrate that DAS significantly surpasses previous benchmarks in terms of the linear data-modelling score, establishing new state-of-the-art performance.
Authors: Woosung Koh, Jang Han Yoon, MinHyung Lee, Youngjin Song, Jaegwan Cho, Jaehyun Kang, Taehyeon Kim, Se-young Yun, Youngjae Yu, Bongshin Lee
Abstract: Generating high-quality charts with Large Language Models presents significant challenges due to limited data and the high cost of scaling through human curation. Instruction, data, and code triplets are scarce and expensive to manually curate as their creation demands technical expertise. To address this scalability issue, we introduce a reference-free automatic feedback generator, which eliminates the need for costly human intervention. Our novel framework, $C^2$, consists of (1) an automatic feedback provider (ChartAF) and (2) a diverse, reference-free dataset (ChartUIE-8K). Quantitative results are compelling: in our first experiment, 74% of respondents strongly preferred, and 10% preferred, the results after feedback. The second post-feedback experiment demonstrates that ChartAF outperforms nine baselines. Moreover, ChartUIE-8K significantly improves data diversity by increasing queries, datasets, and chart types by 5982%, 1936%, and 91%, respectively, over benchmarks. Finally, an LLM user study revealed that 94% of participants preferred ChartUIE-8K's queries, with 93% deeming them aligned with real-world use cases. Core contributions are available as open-source at an anonymized project site, with ample qualitative examples.
Authors: Torbj{\o}rn Smith, Olav Egeland
Abstract: This paper presents a new method for learning dissipative Hamiltonian dynamics from a limited and noisy dataset. The method uses the Helmholtz decomposition to learn a vector field as the sum of a symplectic and a dissipative vector field. The two vector fields are learned using two reproducing kernel Hilbert spaces, defined by a symplectic and a curl-free kernel, where the kernels are specialized to enforce odd symmetry. Random Fourier features are used to approximate the kernels to reduce the dimension of the optimization problem. The performance of the method is validated in simulations for two dissipative Hamiltonian systems, and it is shown that the method improves predictive accuracy significantly compared to a method where a Gaussian separable kernel is used.
Authors: Anton Raskovalov, Nikita Gabdullin, Ilya Androsov
Abstract: This paper presents neural networks for network intrusion detection systems (NIDS), that operate on flow data preprocessed with a time window. It requires only eleven features which do not rely on deep packet inspection and can be found in most NIDS datasets and easily obtained from conventional flow collectors. The time window aggregates information with respect to hosts facilitating the identification of flow signatures that are missed by other aggregation methods. Several network architectures are studied and the use of Kalmogorov-Arnold Network (KAN)-inspired trainable activation functions that help to achieve higher accuracy with simpler network structure is proposed. The reported training accuracy exceeds 99% for the proposed method with as little as twenty neural network input features. This work also studies the generalization capability of NIDS, a crucial aspect that has not been adequately addressed in the previous studies. The generalization experiments are conducted using CICIDS2017 dataset and a custom dataset collected as part of this study. It is shown that the performance metrics decline significantly when changing datasets, and the reduction in performance metrics can be attributed to the difference in signatures of the same type flows in different datasets, which in turn can be attributed to the differences between the underlying networks. It is shown that the generalization accuracy of some neural networks can be very unstable and sensitive to random initialization parameters, and neural networks with fewer parameters and well-tuned activations are more stable and achieve higher accuracy.
Authors: Linus Bao, Emily Jin, Michael Bronstein, \.Ismail \.Ilkan Ceylan, Matthias Lanzinger
Abstract: Graph Transformers are popular neural networks that extend the well-known Transformer architecture to the graph domain. These architectures operate by applying self-attention on graph nodes and incorporating graph structure through the use of positional encodings (e.g., Laplacian positional encoding) or structural encodings (e.g., random-walk structural encoding). The quality of such encodings is critical, since they provide the necessary $\textit{graph inductive biases}$ to condition the model on graph structure. In this work, we propose $\textit{motif structural encoding}$ (MoSE) as a flexible and powerful structural encoding framework based on counting graph homomorphisms. Theoretically, we compare the expressive power of MoSE to random-walk structural encoding and relate both encodings to the expressive power of standard message passing neural networks. Empirically, we observe that MoSE outperforms other well-known positional and structural encodings across a range of architectures, and it achieves state-of-the-art performance on widely studied molecular property prediction datasets.
Authors: Xiaoyu Tao, Tingyue Pan, Mingyue Cheng, Yucong Luo
Abstract: Leveraging large language models (LLMs) has garnered increasing attention and introduced novel perspectives in time series classification. However, existing approaches often overlook the crucial dynamic temporal information inherent in time series data and face challenges in aligning this data with textual semantics. To address these limitations, we propose HiTime, a hierarchical multi-modal model that seamlessly integrates temporal information into LLMs for multivariate time series classification (MTSC). Our model employs a hierarchical feature encoder to capture diverse aspects of time series data through both data-specific and task-specific embeddings. To facilitate semantic space alignment between time series and text, we introduce a dual-view contrastive alignment module that bridges the gap between modalities. Additionally, we adopt a hybrid prompting strategy to fine-tune the pre-trained LLM in a parameter-efficient manner. By effectively incorporating dynamic temporal features and ensuring semantic alignment, HiTime enables LLMs to process continuous time series data and achieves state-of-the-art classification performance through text generation. Extensive experiments on benchmark datasets demonstrate that HiTime significantly enhances time series classification accuracy compared to most competitive baseline methods. Our findings highlight the potential of integrating temporal features into LLMs, paving the way for advanced time series analysis. The code is publicly available for further research and validation. Our codes are publicly available1.
Authors: Peizhuang Cong, Qizhi Chen, Haochen Zhao, Tong Yang
Abstract: The advanced capabilities of Large Language Models (LLMs) have inspired the development of various interactive web services or applications, such as ChatGPT, which offer query inference services for users. Unlike traditional DNN model, the inference of LLM entails different iterations of forward computation for different queries, which result in efficiency challenges for existing run-to-completion batch-wise inference. Hence, some methods refine batch-wise inference to iteration-level by duplicating all nonlinear layers of LLM. However, this approach not only increases resource usage but also introduces idle computations to the batch due to the prefilling of newly added queries. Therefore, we propose BATON, an efficient batch-wise LLM inference scheme by dynamically adjusting processing batch, which can achieve near-zero idle computations without incurring additional resource consumption. To do so, BATON 1) shapes the vectors involved in the inference of the newly inserted query and processing batch to align dimensions and generates a new attention mask based on vector shaping to ensure inference correctness, which enables query inserting without consuming additional resource; 2) embeds prefilled Keys and Values of the new query into the KV_Cache of the processing batch by leveraging the prefilling and decoding separation mechanism, eliminating idle computations to the batch introduced by the prefilling process of the new query. Experimental results show that compared to the state-of-the-art solution Orca, BATON improves query processing by up to 1.75 times.
Authors: Alba Carballo-Castro, Sonia Laguna, Moritz Vandenhirtz, Julia E. Vogt
Abstract: Concept-based machine learning methods have increasingly gained importance due to the growing interest in making neural networks interpretable. However, concept annotations are generally challenging to obtain, making it crucial to leverage all their prior knowledge. By creating concept-enriched models that incorporate concept information into existing architectures, we exploit their interpretable capabilities to the fullest extent. In particular, we propose Concept-Guided Conditional Diffusion, which can generate visual representations of concepts, and Concept-Guided Prototype Networks, which can create a concept prototype dataset and leverage it to perform interpretable concept prediction. These results open up new lines of research by exploiting pre-existing information in the quest for rendering machine learning more human-understandable.
Authors: Jingwei Liu, Ling Yang, Hongyan Li, Shenda Hong
Abstract: While time series diffusion models have received considerable focus from many recent works, the performance of existing models remains highly unstable. Factors limiting time series diffusion models include insufficient time series datasets and the absence of guidance. To address these limitations, we propose a Retrieval- Augmented Time series Diffusion model (RATD). The framework of RATD consists of two parts: an embedding-based retrieval process and a reference-guided diffusion model. In the first part, RATD retrieves the time series that are most relevant to historical time series from the database as references. The references are utilized to guide the denoising process in the second part. Our approach allows leveraging meaningful samples within the database to aid in sampling, thus maximizing the utilization of datasets. Meanwhile, this reference-guided mechanism also compensates for the deficiencies of existing time series diffusion models in terms of guidance. Experiments and visualizations on multiple datasets demonstrate the effectiveness of our approach, particularly in complicated prediction tasks.
Authors: Steffen Schotth\"ofer, Emanuele Zangrando, Gianluca Ceruti, Francesco Tudisco, Jonas Kusch
Abstract: Low-Rank Adaptation (LoRA) has become a widely used method for parameter-efficient fine-tuning of large-scale, pre-trained neural networks. However, LoRA and its extensions face several challenges, including the need for rank adaptivity, robustness, and computational efficiency during the fine-tuning process. We introduce GeoLoRA, a novel approach that addresses these limitations by leveraging dynamical low-rank approximation theory. GeoLoRA requires only a single backpropagation pass over the small-rank adapters, significantly reducing computational cost as compared to similar dynamical low-rank training methods and making it faster than popular baselines such as AdaLoRA. This allows GeoLoRA to efficiently adapt the allocated parameter budget across the model, achieving smaller low-rank adapters compared to heuristic methods like AdaLoRA and LoRA, while maintaining critical convergence, descent, and error-bound theoretical guarantees. The resulting method is not only more efficient but also more robust to varying hyperparameter settings. We demonstrate the effectiveness of GeoLoRA on several state-of-the-art benchmarks, showing that it outperforms existing methods in both accuracy and computational efficiency.
Authors: Haoxuan Kuang, Kunxiang Deng, Linlin You, Jun Li
Abstract: Electric vehicle charging demand prediction is important for vacant charging pile recommendation and charging infrastructure planning, thus facilitating vehicle electrification and green energy development. The performance of previous spatio-temporal studies is still far from satisfactory because the traditional graphs are difficult to model non-pairwise spatial relationships and multivariate temporal features are not adequately taken into account. To tackle these issues, we propose an attention-based heterogeneous multivariate data fusion approach (AHMDF) for citywide electric vehicle charging demand prediction, which incorporates geo-based clustered hypergraph and multivariate gated Transformer to considers both static and dynamic influences. To learn non-pairwise relationships, we cluster service areas by the types and numbers of points of interest in the areas and develop attentive hypergraph networks accordingly. Graph attention mechanisms are used for information propagation between neighboring areas. Additionally, we improve the Transformer encoder utilizing gated mechanisms so that it can selectively learn dynamic auxiliary information and temporal features. Experiments on an electric vehicle charging benchmark dataset demonstrate the effectiveness of our proposed approach compared with a broad range of competing baselines. Furthermore, we demonstrate the impact of dynamic influences on prediction results in different areas of the city and the effectiveness of our clustering method.
Authors: Ankit Singh Rawat, Veeranjaneyulu Sadhanala, Afshin Rostamizadeh, Ayan Chakrabarti, Wittawat Jitkrittum, Vladimir Feinberg, Seungyeon Kim, Hrayr Harutyunyan, Nikunj Saunshi, Zachary Nado, Rakesh Shivanna, Sashank J. Reddi, Aditya Krishna Menon, Rohan Anil, Sanjiv Kumar
Abstract: A primary challenge in large language model (LLM) development is their onerous pre-training cost. Typically, such pre-training involves optimizing a self-supervised objective (such as next-token prediction) over a large corpus. This paper explores a promising paradigm to improve LLM pre-training efficiency and quality by suitably leveraging a small language model (SLM). In particular, this paradigm relies on an SLM to both (1) provide soft labels as additional training supervision, and (2) select a small subset of valuable ("informative" and "hard") training examples. Put together, this enables an effective transfer of the SLM's predictive distribution to the LLM, while prioritizing specific regions of the training data distribution. Empirically, this leads to reduced LLM training time compared to standard training, while improving the overall quality. Theoretically, we develop a statistical framework to systematically study the utility of SLMs in enabling efficient training of high-quality LLMs. In particular, our framework characterizes how the SLM's seemingly low-quality supervision can enhance the training of a much more capable LLM. Furthermore, it also highlights the need for an adaptive utilization of such supervision, by striking a balance between the bias and variance introduced by the SLM-provided soft labels. We corroborate our theoretical framework by improving the pre-training of an LLM with 2.8B parameters by utilizing a smaller LM with 1.5B parameters on the Pile dataset.
Authors: Zhihan Huang, Yuting Wei, Yuxin Chen
Abstract: The denoising diffusion probabilistic model (DDPM) has emerged as a mainstream generative model in generative AI. While sharp convergence guarantees have been established for the DDPM, the iteration complexity is, in general, proportional to the ambient data dimension, resulting in overly conservative theory that fails to explain its practical efficiency. This has motivated the recent work Li and Yan (2024a) to investigate how the DDPM can achieve sampling speed-ups through automatic exploitation of intrinsic low dimensionality of data. We strengthen this prior work by demonstrating, in some sense, optimal adaptivity to unknown low dimensionality. For a broad class of data distributions with intrinsic dimension $k$, we prove that the iteration complexity of the DDPM scales nearly linearly with $k$, which is optimal when using KL divergence to measure distributional discrepancy. Our theory is established based on a key observation: the DDPM update rule is equivalent to running a suitably parameterized SDE upon discretization, where the nonlinear component of the drift term is intrinsically low-dimensional.
Authors: Bal\'azs Gyenes, Nikolai Franke, Philipp Becker, Gerhard Neumann
Abstract: Perceiving the environment via cameras is crucial for Reinforcement Learning (RL) in robotics. While images are a convenient form of representation, they often complicate extracting important geometric details, especially with varying geometries or deformable objects. In contrast, point clouds naturally represent this geometry and easily integrate color and positional data from multiple camera views. However, while deep learning on point clouds has seen many recent successes, RL on point clouds is under-researched, with only the simplest encoder architecture considered in the literature. We introduce PointPatchRL (PPRL), a method for RL on point clouds that builds on the common paradigm of dividing point clouds into overlapping patches, tokenizing them, and processing the tokens with transformers. PPRL provides significant improvements compared with other point-cloud processing architectures previously used for RL. We then complement PPRL with masked reconstruction for representation learning and show that our method outperforms strong model-free and model-based baselines on image observations in complex manipulation tasks containing deformable objects and variations in target object geometry. Videos and code are available at https://alrhub.github.io/pprl-website
Authors: Zheyuan Zhang
Abstract: Substantial research on deep learning-based emergent communication uses the referential game framework, specifically the Lewis signaling game, however we argue that successful communication in this game typically only need one or two effective symbols (i.e. message length) because of a sampling pitfall in the training data. To address this issue, we provide a theoretical analysis and introduce a combinatorial algorithm SolveMinSym (SMS) to determine the minimum number of symbols for successful communication min(|M|) in the Lewis signaling game. We use SMS algorithm to create datasets with different min(|M|) to empirically show that higher min(|M|) for the training data increases the number of effective symbols in the emergent language.
Authors: Gabriel D\'iaz Ramos, Toros Arikan, Richard G. Baraniuk
Abstract: The Obstacle Avoiding Rectilinear Steiner Minimum Tree (OARSMT) problem, which seeks the shortest interconnection of a given number of terminals in a rectilinear plane while avoiding obstacles, is a critical task in integrated circuit design, network optimization, and robot path planning. Since OARSMT is NP-hard, exact algorithms scale poorly with the number of terminals, leading practical solvers to sacrifice accuracy for large problems. We propose MazeNet, a deep learning-based method that learns to solve the OARSMT from data. MazeNet reframes OARSMT as a maze-solving task that can be addressed with a recurrent convolutional neural network (RCNN). A key hallmark of MazeNet is its scalability: we only need to train the RCNN blocks on mazes with a small number of terminals; larger mazes can be solved by replicating the same pre-trained blocks to create a larger network. Across a wide range of experiments, MazeNet achieves perfect OARSMT-solving accuracy, significantly reduces runtime compared to classical exact algorithms, and can handle more terminals than state-of-the-art approximate algorithms.
Authors: Shreeyash Gowaikar, Hugo Berard, Rashid Mushkani, Shin Koseki
Abstract: As AI systems, particularly generative models, increasingly influence decision-making, ensuring that they are able to fairly represent diverse human preferences becomes crucial. This paper introduces a novel framework for evaluating epistemic fairness in preference learning models inspired by economic theories of inequality and Rawlsian justice. We propose metrics adapted from the Gini Coefficient, Atkinson Index, and Kuznets Ratio to quantify fairness in these models. We validate our approach using two datasets: a custom visual preference dataset (AI-EDI-Space) and the Jester Jokes dataset. Our analysis reveals variations in model performance across users, highlighting potential epistemic injustices. We explore pre-processing and in-processing techniques to mitigate these inequalities, demonstrating a complex relationship between model efficiency and fairness. This work contributes to AI ethics by providing a framework for evaluating and improving epistemic fairness in preference learning models, offering insights for developing more inclusive AI systems in contexts where diverse human preferences are crucial.
Authors: Udvas Das, Debabrota Basu
Abstract: Pure exploration in bandits models multiple real-world problems, such as tuning hyper-parameters or conducting user studies, where different safety, resource, and fairness constraints on the decision space naturally appear. We study these problems as pure exploration in multi-armed bandits with unknown linear constraints, where the aim is to identify an $r$$\textit{-good feasible policy}$. First, we propose a Lagrangian relaxation of the sample complexity lower bound for pure exploration under constraints. We show how this lower bound evolves with the sequential estimation of constraints. Second, we leverage the Lagrangian lower bound and the properties of convex optimisation to propose two computationally efficient extensions of Track-and-Stop and Gamified Explorer, namely LATS and LAGEX. To this end, we propose a constraint-adaptive stopping rule, and while tracking the lower bound, use pessimistic estimate of the feasible set at each step. We show that these algorithms achieve asymptotically optimal sample complexity upper bounds up to constraint-dependent constants. Finally, we conduct numerical experiments with different reward distributions and constraints that validate efficient performance of LAGEX and LATS with respect to baselines.
Authors: I-Cheng Lin, Osman Yagan, Carlee Joe-Wong
Abstract: Federated learning has recently gained popularity as a framework for distributed clients to collaboratively train a machine learning model using local data. While traditional federated learning relies on a central server for model aggregation, recent advancements adopt a decentralized framework, enabling direct model exchange between clients and eliminating the single point of failure. However, existing decentralized frameworks often assume all clients train a shared model. Personalizing each client's model can enhance performance, especially with heterogeneous client data distributions. We propose FedSPD, an efficient personalized federated learning algorithm for the decentralized setting, and show that it learns accurate models even in low-connectivity networks. To provide theoretical guarantees on convergence, we introduce a clustering-based framework that enables consensus on models for distinct data clusters while personalizing to unique mixtures of these clusters at different clients. This flexibility, allowing selective model updates based on data distribution, substantially reduces communication costs compared to prior work on personalized federated learning in decentralized settings. Experimental results on real-world datasets show that FedSPD outperforms multiple decentralized variants of personalized federated learning algorithms, especially in scenarios with low-connectivity networks.
Authors: Katharina Friedl, No\'emie Jaquier, Jens Lundell, Tamim Asfour, Danica Kragic
Abstract: By incorporating physical consistency as inductive bias, deep neural networks display increased generalization capabilities and data efficiency in learning nonlinear dynamic models. However, the complexity of these models generally increases with the system dimensionality, requiring larger datasets, more complex deep networks, and significant computational effort. We propose a novel geometric network architecture to learn physically-consistent reduced-order dynamic parameters that accurately describe the original high-dimensional system behavior. This is achieved by building on recent advances in model-order reduction and by adopting a Riemannian perspective to jointly learn a structure-preserving latent space and the associated low-dimensional dynamics. Our approach enables accurate long-term predictions of the high-dimensional dynamics of rigid and deformable systems with increased data efficiency by inferring interpretable and physically plausible reduced Lagrangian models.
Authors: Zhaofeng Si, Shu Hu, Kaiyi Ji, Siwei Lyu
Abstract: Meta-learning is a general approach to equip machine learning models with the ability to handle few-shot scenarios when dealing with many tasks. Most existing meta-learning methods work based on the assumption that all tasks are of equal importance. However, real-world applications often present heterogeneous tasks characterized by varying difficulty levels, noise in training samples, or being distinctively different from most other tasks. In this paper, we introduce a novel meta-learning method designed to effectively manage such heterogeneous tasks by employing rank-based task-level learning objectives, Heterogeneous Tasks Robust Meta-learning (HeTRoM). HeTRoM is proficient in handling heterogeneous tasks, and it prevents easy tasks from overwhelming the meta-learner. The approach allows for an efficient iterative optimization algorithm based on bi-level optimization, which is then improved by integrating statistical guidance. Our experimental results demonstrate that our method provides flexibility, enabling users to adapt to diverse task settings and enhancing the meta-learner's overall performance.
Authors: Sicong Huang, Roozbeh Jafari, Bobak J. Mortazavi
Abstract: Continuous arterial blood pressure (ABP) monitoring is invasive but essential for hemodynamic monitoring. Recent techniques have reconstructed ABP non-invasively using pulsatile signals but produced inaccurate systolic and diastolic blood pressure (SBP and DBP) values and were sensitive to individual variability. ArterialNet integrates generalized pulsatile-to-ABP signal translation and personalized feature extraction using hybrid loss functions and regularization. We validated ArterialNet using the MIMIC-III dataset and achieved a root mean square error (RMSE) of 5.41 mmHg, with at least a 58% lower standard deviation. ArterialNet reconstructed ABP with an RMSE of 7.99 mmHg in remote health scenarios. ArterialNet achieved superior performance in ABP reconstruction and SBP and DBP estimations, with significantly reduced subject variance, demonstrating its potential in remote health settings. We also ablated ArterialNet architecture to investigate the contributions of each component and evaluated its translational impact and robustness by conducting a series of ablations on data quality and availability.
Authors: Shinjan Ghosh, Amit Chakraborty, Georgia Olympia Brikis, Biswadip Dey
Abstract: Computational fluid dynamics (CFD) solvers employing two-equation eddy viscosity models are the industry standard for simulating turbulent flows using the Reynolds-averaged Navier-Stokes (RANS) formulation. While these methods are computationally less expensive than direct numerical simulations, they can still incur significant computational costs to achieve the desired accuracy. In this context, physics-informed neural networks (PINNs) offer a promising approach for developing parametric surrogate models that leverage both existing, but limited CFD solutions and the governing differential equations to predict simulation outcomes in a computationally efficient, differentiable, and near real-time manner. In this work, we build upon the previously proposed RANS-PINN framework, which only focused on predicting flow over a cylinder. To investigate the efficacy of RANS-PINN as a viable approach to building parametric surrogate models, we investigate its accuracy in predicting relevant turbulent flow variables for both internal and external flows. To ensure training convergence with a more complex loss function, we adopt a novel sampling approach that exploits the domain geometry to ensure a proper balance among the contributions from various regions within the solution domain. The effectiveness of this framework is then demonstrated for two scenarios that represent a broad class of internal and external flow problems.
Authors: Elias J\"a\"asaari, Ville Hyv\"onen, Teemu Roos
Abstract: Approximate nearest neighbor (ANN) search is a key component in many modern machine learning pipelines; recent use cases include retrieval-augmented generation (RAG) and vector databases. Clustering-based ANN algorithms, that use score computation methods based on product quantization (PQ), are often used in industrial-scale applications due to their scalability and suitability for distributed and disk-based implementations. However, they have slower query times than the leading graph-based ANN algorithms. In this work, we propose a new supervised score computation method based on the observation that inner product approximation is a multivariate (multi-output) regression problem that can be solved efficiently by reduced-rank regression. Our experiments show that on modern high-dimensional data sets, the proposed reduced-rank regression (RRR) method is superior to PQ in both query latency and memory usage. We also introduce LoRANN, a clustering-based ANN library that leverages the proposed score computation method. LoRANN is competitive with the leading graph-based algorithms and outperforms the state-of-the-art GPU ANN methods on high-dimensional data sets.
Authors: Dylan Wilson
Abstract: In this paper, I will introduce a new form of regression, that can adjust overfitting and underfitting through, "distance-based regression." Overfitting often results in finding false patterns causing inaccurate results, so by having a new approach that minimizes overfitting, more accurate predictions can be derived. Then I will proceed with a test of my regression form and show additional ways to optimize the regression. Finally, I will apply my new technique to a specific data set to demonstrate its practical value.
Authors: Han Wang, Eduardo P\'erez, Iris A. M. Huijben, Hans van Gorp, Ruud van Sloun, Florian R\"omer
Abstract: Multidimensional data acquisition often requires extensive time and poses significant challenges for hardware and software regarding data storage and processing. Rather than designing a single compression matrix as in conventional compressed sensing, structured compressed sensing yields dimension-specific compression matrices, reducing the number of optimizable parameters. Recent advances in machine learning (ML) have enabled task-based supervised learning of subsampling matrices, albeit at the expense of complex downstream models. Additionally, the sampling resource allocation across dimensions is often determined in advance through heuristics. To address these challenges, we introduce Structured COmpressed Sensing with Automatic Resource Allocation (SCOSARA) with an information theory-based unsupervised learning strategy. SCOSARA adaptively distributes samples across sampling dimensions while maximizing Fisher information content. Using ultrasound localization as a case study, we compare SCOSARA to state-of-the-art ML-based and greedy search algorithms. Simulation results demonstrate that SCOSARA can produce high-quality subsampling matrices that achieve lower Cram\'er-Rao Bound values than the baselines. In addition, SCOSARA outperforms other ML-based algorithms in terms of the number of trainable parameters, computational complexity, and memory requirements while automatically choosing the number of samples per axis.
Authors: Fu-Yun Wang, Zhengyang Geng, Hongsheng Li
Abstract: Diffusion models achieve superior generation quality but suffer from slow generation speed due to the iterative nature of denoising. In contrast, consistency models, a new generative family, achieve competitive performance with significantly faster sampling. These models are trained either through consistency distillation, which leverages pretrained diffusion models, or consistency training/tuning directly from raw data. In this work, we propose a novel framework for understanding consistency models by modeling the denoising process of the diffusion model as a Markov Decision Process (MDP) and framing consistency model training as the value estimation through Temporal Difference~(TD) Learning. More importantly, this framework allows us to analyze the limitations of current consistency training/tuning strategies. Built upon Easy Consistency Tuning (ECT), we propose Stable Consistency Tuning (SCT), which incorporates variance-reduced learning using the score identity. SCT leads to significant performance improvements on benchmarks such as CIFAR-10 and ImageNet-64. On ImageNet-64, SCT achieves 1-step FID 2.42 and 2-step FID 1.55, a new SoTA for consistency models.
Authors: Andrew Robert Williams, Arjun Ashok, \'Etienne Marcotte, Valentina Zantedeschi, Jithendaraa Subramanian, Roland Riachi, James Requeima, Alexandre Lacoste, Irina Rish, Nicolas Chapados, Alexandre Drouin
Abstract: Forecasting is a critical task in decision making across various domains. While numerical data provides a foundation, it often lacks crucial context necessary for accurate predictions. Human forecasters frequently rely on additional information, such as background knowledge or constraints, which can be efficiently communicated through natural language. However, the ability of existing forecasting models to effectively integrate this textual information remains an open question. To address this, we introduce "Context is Key" (CiK), a time series forecasting benchmark that pairs numerical data with diverse types of carefully crafted textual context, requiring models to integrate both modalities. We evaluate a range of approaches, including statistical models, time series foundation models, and LLM-based forecasters, and propose a simple yet effective LLM prompting method that outperforms all other tested methods on our benchmark. Our experiments highlight the importance of incorporating contextual information, demonstrate surprising performance when using LLM-based forecasting models, and also reveal some of their critical shortcomings. By presenting this benchmark, we aim to advance multimodal forecasting, promoting models that are both accurate and accessible to decision-makers with varied technical expertise. The benchmark can be visualized at https://servicenow.github.io/context-is-key-forecasting/v0/ .
URLs: https://servicenow.github.io/context-is-key-forecasting/v0/
Authors: Bingcong Li, Liang Zhang, Aryan Mokhtari, Niao He
Abstract: This work revisits the classical low-rank matrix factorization problem and unveils the critical role of initialization in shaping convergence rates for such nonconvex and nonsmooth optimization. We introduce Nystrom initialization, which significantly improves the global convergence of Scaled Gradient Descent (ScaledGD) in both symmetric and asymmetric matrix factorization tasks. Specifically, we prove that ScaledGD with Nystrom initialization achieves quadratic convergence in cases where only linear rates were previously known. Furthermore, we extend this initialization to low-rank adapters (LoRA) commonly used for finetuning foundation models. Our approach, NoRA, i.e., LoRA with Nystrom initialization, demonstrates superior performance across various downstream tasks and model scales, from 1B to 7B parameters, in large language and diffusion models.
Authors: David Ortiz-Perez, Manuel Benavent-Lledo, Jose Garcia-Rodriguez, David Tom\'as, M. Flores Vizcaya-Moreno
Abstract: Cognitive decline is a natural part of aging, often resulting in reduced cognitive abilities. In some cases, however, this decline is more pronounced, typically due to disorders such as Alzheimer's disease. Early detection of anomalous cognitive decline is crucial, as it can facilitate timely professional intervention. While medical data can help in this detection, it often involves invasive procedures. An alternative approach is to employ non-intrusive techniques such as speech or handwriting analysis, which do not necessarily affect daily activities. This survey reviews the most relevant methodologies that use deep learning techniques to automate the cognitive decline estimation task, including audio, text, and visual processing. We discuss the key features and advantages of each modality and methodology, including state-of-the-art approaches like Transformer architecture and foundation models. In addition, we present works that integrate different modalities to develop multimodal models. We also highlight the most significant datasets and the quantitative results from studies using these resources. From this review, several conclusions emerge. In most cases, the textual modality achieves the best results and is the most relevant for detecting cognitive decline. Moreover, combining various approaches from individual modalities into a multimodal model consistently enhances performance across nearly all scenarios.
Authors: Xueping Li, Haowen Xu, Jose Tupayachi, Olufemi Omitaomu, Xudong Wang
Abstract: Effective monitoring of freight transportation is essential for advancing sustainable, low-carbon economies. Traditional methods relying on single-modal data and discrete simulations fall short in optimizing intermodal systems holistically. These systems involve interconnected processes that affect shipping time, costs, emissions, and socio-economic factors. Developing digital twins for real-time awareness, predictive analytics, and urban logistics optimization requires extensive efforts in knowledge discovery, data integration, and multi-domain simulation. Recent advancements in generative AI offer new opportunities to streamline digital twin development by automating knowledge discovery and data integration, generating innovative simulation and optimization solutions. These models extend digital twins' capabilities by promoting autonomous workflows for data engineering, analytics, and software development. This paper proposes an innovative paradigm that leverages generative AI to enhance digital twins for urban research and operations. Using freight decarbonization as a case study, we propose a conceptual framework employing transformer-based language models to enhance an urban digital twin through foundation models. We share preliminary results and our vision for more intelligent, autonomous, and general-purpose digital twins for optimizing integrated freight systems from multimodal to synchromodal paradigms.
Authors: Benny Wei-Yun Hsu, Yu-Ming Chen, Yuan-Han Yang, Vincent S. Tseng
Abstract: Behavioral and Psychological Symptoms of Dementia (BPSD) impact dementia care substantially, affecting both patients and caregivers. Effective management and early detection of BPSD are crucial to reduce the stress and burden on caregivers and healthcare systems. Despite the advancements in machine learning for dementia prediction, there is a considerable gap in utilizing these methods for BPSD prediction. This study aims to fill this gap by presenting a novel personalized framework for BPSD prediction, utilizing physiological signals from smart wearable devices. Our personalized fine-grained BPSD prediction method accurately predicts BPSD occurrences by extracting individual behavioral patterns, while the generalized models identify diverse patterns and differentiate between various BPSD symptoms. Detailed comparisons between the proposed personalized method and conventional generalized methods reveals substantial improvements across all performance metrics, including a 16.0% increase in AUC. These results demonstrate the potential of our proposed method in advancing dementia care by enabling proactive interventions and improving patient outcomes in real-world scenarios. To the best of our knowledge, this is the first study that leverages physiological signals from smart wearable devices to predict BPSD, marking a significant stride in dementia care research.
Authors: Xiangqian Zhu, Mengnan Shi, Xuexin Yu, Chang Liu, Xiaocong Lian, Jintao Fei, Jiangying Luo, Xin Jin, Ping Zhang, Xiangyang Ji
Abstract: Atrial fibrillation is a commonly encountered clinical arrhythmia associated with stroke and increased mortality. Since professional medical knowledge is required for annotation, exploiting a large corpus of ECGs to develop accurate supervised learning-based atrial fibrillation algorithms remains challenging. Self-supervised learning (SSL) is a promising recipe for generalized ECG representation learning, eliminating the dependence on expensive labeling. However, without well-designed incorporations of knowledge related to atrial fibrillation, existing SSL approaches typically suffer from unsatisfactory capture of robust ECG representations. In this paper, we propose an inter-intra period-aware ECG representation learning approach. Considering ECGs of atrial fibrillation patients exhibit the irregularity in RR intervals and the absence of P-waves, we develop specific pre-training tasks for interperiod and intraperiod representations, aiming to learn the single-period stable morphology representation while retaining crucial interperiod features. After further fine-tuning, our approach demonstrates remarkable AUC performances on the BTCH dataset, \textit{i.e.}, 0.953/0.996 for paroxysmal/persistent atrial fibrillation detection. On commonly used benchmarks of CinC2017 and CPSC2021, the generalization capability and effectiveness of our methodology are substantiated with competitive results.
Authors: Nayoung Choi, Youngjune Lee, Gyu-Hwung Cho, Haeyu Jeong, Jungmin Kong, Saehun Kim, Keunchan Park, Jaeho Choi, Sarah Cho, Inchang Jeong, Gyohee Nam, Sunghoon Han, Wonil Yang
Abstract: Large Language Models (LLMs) excel at understanding the semantic relationships between queries and documents, even with lengthy and complex long-tail queries. These queries are challenging for feedback-based rankings due to sparse user engagement and limited feedback, making LLMs' ranking ability highly valuable. However, the large size and slow inference of LLMs necessitate the development of smaller, more efficient models (sLLMs). Recently, integrating ranking label generation into distillation techniques has become crucial, but existing methods underutilize LLMs' capabilities and are cumbersome. Our research, RRADistill: Re-Ranking Ability Distillation, propose an efficient label generation pipeline and novel sLLM training methods for both encoder and decoder models. We introduce an encoder-based method using a Term Control Layer to capture term matching signals and a decoder-based model with a ranking layer for enhanced understanding. A/B testing on a Korean-based search platform, validates the effectiveness of our approach in improving re-ranking for long-tail queries.
Authors: Guilherme Thomaz, Denis Maua
Abstract: Mutual funds aim to generate returns above market averages. While predicting their future portfolio allocations can bring economic advantages, the task remains challenging and largely unexplored. To fill that gap, this work frames mutual fund portfolio prediction as a Next Novel Basket Recommendation (NNBR) task, focusing on predicting novel items in a fund's next portfolio. We create a comprehensive benchmark dataset using publicly available data and evaluate the performance of various recommender system models on the NNBR task. Our findings reveal that predicting novel items in mutual fund portfolios is inherently more challenging than predicting the entire portfolio or only repeated items. While state-of-the-art NBR models are outperformed by simple heuristics when considering both novel and repeated items together, autoencoder-based approaches demonstrate superior performance in predicting only new items. The insights gained from this study highlight the importance of considering domain-specific characteristics when applying recommender systems to mutual fund portfolio prediction. The performance gap between predicting the entire portfolio or repeated items and predicting novel items underscores the complexity of the NNBR task in this domain and the need for continued research to develop more robust and adaptable models for this critical financial application.
Authors: Junxiao Shen, Khadija Khaldi, Enmin Zhou, Hemant Bhaskar Surale, Amy Karlson
Abstract: Text entry with word-gesture keyboards (WGK) is emerging as a popular method and becoming a key interaction for Extended Reality (XR). However, the diversity of interaction modes, keyboard sizes, and visual feedback in these environments introduces divergent word-gesture trajectory data patterns, thus leading to complexity in decoding trajectories into text. Template-matching decoding methods, such as SHARK^2, are commonly used for these WGK systems because they are easy to implement and configure. However, these methods are susceptible to decoding inaccuracies for noisy trajectories. While conventional neural-network-based decoders (neural decoders) trained on word-gesture trajectory data have been proposed to improve accuracy, they have their own limitations: they require extensive data for training and deep-learning expertise for implementation. To address these challenges, we propose a novel solution that combines ease of implementation with high decoding accuracy: a generalizable neural decoder enabled by pre-training on large-scale coarsely discretized word-gesture trajectories. This approach produces a ready-to-use WGK decoder that is generalizable across mid-air and on-surface WGK systems in augmented reality (AR) and virtual reality (VR), which is evident by a robust average Top-4 accuracy of 90.4% on four diverse datasets. It significantly outperforms SHARK^2 with a 37.2% enhancement and surpasses the conventional neural decoder by 7.4%. Moreover, the Pre-trained Neural Decoder's size is only 4 MB after quantization, without sacrificing accuracy, and it can operate in real-time, executing in just 97 milliseconds on Quest 3.
Authors: Yuzhi Xu, Haowei Ni, Qinhui Gao, Chia-Hua Chang, Yanran Huo, Fanyu Zhao, Shiyu Hu, Wei Xia, Yike Zhang, Radu Grovu, Min He, John. Z. H. Zhang, Yuanqing Wang
Abstract: Computational molecular design -- the endeavor to design molecules, with various missions, aided by machine learning and molecular dynamics approaches, has been widely applied to create valuable new molecular entities, from small molecule therapeutics to protein biologics. In the small data regime, physics-based approaches model the interaction between the molecule being designed and proteins of key physiological functions, providing structural insights into the mechanism. When abundant data has been collected, a quantitative structure-activity relationship (QSAR) can be more directly constructed from experimental data, from which machine learning can distill key insights to guide the design of the next round of experiment design. Machine learning methodologies can also facilitate physical modeling, from improving the accuracy of force fields and extending them to unseen chemical spaces, to more directly enhancing the sampling on the conformational spaces. We argue that these techniques are mature enough to be applied to not just extend the longevity of life, but the beauty it manifests. In this perspective, we review the current frontiers in the research \& development of skin care products, as well as the statistical and physical toolbox applicable to addressing the challenges in this industry. Feasible interdisciplinary research projects are proposed to harness the power of machine learning tools to design innovative, effective, and inexpensive skin care products.
Authors: Yiye Wang, Wenming Zheng, Yang Li, Hao Yang
Abstract: Graph neural networks (GNNs) are becoming increasingly popular for EEG-based depression detection. However, previous GNN-based methods fail to sufficiently consider the characteristics of depression, thus limiting their performance. Firstly, studies in neuroscience indicate that depression patients exhibit both common and individualized brain abnormal patterns. Previous GNN-based approaches typically focus either on fixed graph connections to capture common abnormal brain patterns or on adaptive connections to capture individualized patterns, which is inadequate for depression detection. Secondly, brain network exhibits a hierarchical structure, which includes the arrangement from channel-level graph to region-level graph. This hierarchical structure varies among individuals and contains significant information relevant to detecting depression. Nonetheless, previous GNN-based methods overlook these individualized hierarchical information. To address these issues, we propose a Hybrid GNN (HGNN) that merges a Common Graph Neural Network (CGNN) branch utilizing fixed connection and an Individualized Graph Neural Network (IGNN) branch employing adaptive connections. The two branches capture common and individualized depression patterns respectively, complementing each other. Furthermore, we enhance the IGNN branch with a Graph Pooling and Unpooling Module (GPUM) to extract individualized hierarchical information. Extensive experiments on two public datasets show that our model achieves state-of-the-art performance.
Authors: Jose B. Castro, Cheryl Rogers, Camile Sothe, Dominic Cyr, Alemu Gonsamo
Abstract: Accurate forest canopy height estimation is essential for evaluating aboveground biomass and carbon stock dynamics, supporting ecosystem monitoring services like timber provisioning, climate change mitigation, and biodiversity conservation. However, despite advancements in spaceborne LiDAR technology, data for northern high latitudes remain limited due to orbital and sampling constraints. This study introduces a methodology for generating spatially continuous, high-resolution canopy height and uncertainty estimates using Deep Learning Regression models. We integrate multi-source, multi-seasonal satellite data from Sentinel-1, Landsat, and ALOS-PALSAR-2, with spaceborne GEDI LiDAR as reference data. Our approach was tested in Ontario, Canada, and validated with airborne LiDAR, demonstrating strong performance. The best results were achieved by incorporating seasonal Sentinel-1 and Landsat features alongside PALSAR data, yielding an R-square of 0.72, RMSE of 3.43 m, and bias of 2.44 m. Using seasonal data instead of summer-only data improved variability by 10%, reduced error by 0.45 m, and decreased bias by 1 m. The deep learning model's weighting strategy notably reduced errors in tall canopy height estimates compared to a recent global model, though it overestimated lower canopy heights. Uncertainty maps highlighted greater uncertainty near forest edges, where GEDI measurements are prone to errors and SAR data may encounter backscatter issues like foreshortening, layover, and shadow. This study enhances canopy height estimation techniques in areas lacking spaceborne LiDAR coverage, providing essential tools for forestry, environmental monitoring, and carbon stock estimation.
Authors: Kshitij Jain, Jingru Xie, Kevin Regan, Cheng Chen, Jie Han, Steve Li, Zhuoshu Li, Todd Phillips, Myles Sussman, Matt Troup, Angel Yu, Jia Zhuo
Abstract: Large recommendation models (LRMs) are fundamental to the multi-billion dollar online advertising industry, processing massive datasets of hundreds of billions of examples before transitioning to continuous online training to adapt to rapidly changing user behavior. The massive scale of data directly impacts both computational costs and the speed at which new methods can be evaluated (R&D velocity). This paper presents actionable principles and high-level frameworks to guide practitioners in optimizing training data requirements. These strategies have been successfully deployed in Google's largest Ads CTR prediction models and are broadly applicable beyond LRMs. We outline the concept of data convergence, describe methods to accelerate this convergence, and finally, detail how to optimally balance training data volume with model size.
Authors: Rui Du, Kai Zhao, Jinlong Hou, Qiang Zhang, Peter Zhang
Abstract: Coordination among connected and autonomous vehicles (CAVs) is advancing due to developments in control and communication technologies. However, much of the current work is based on oversimplified and unrealistic task-specific assumptions, which may introduce vulnerabilities. This is critical because CAVs not only interact with their environment but are also integral parts of it. Insufficient exploration can result in policies that carry latent risks, highlighting the need for methods that explore the environment both extensively and efficiently. This work introduces OPTIMA, a novel distributed reinforcement learning framework for cooperative autonomous vehicle tasks. OPTIMA alternates between thorough data sampling from environmental interactions and multi-agent reinforcement learning algorithms to optimize CAV cooperation, emphasizing both safety and efficiency. Our goal is to improve the generality and performance of CAVs in highly complex and crowded scenarios. Furthermore, the industrial-scale distributed training system easily adapts to different algorithms, reward functions, and strategies.
Authors: Zihan Wu, Zhaoke Huang, Hong Yan
Abstract: Co-clustering simultaneously clusters rows and columns, revealing more fine-grained groups. However, existing co-clustering methods suffer from poor scalability and cannot handle large-scale data. This paper presents a novel and scalable co-clustering method designed to uncover intricate patterns in high-dimensional, large-scale datasets. Specifically, we first propose a large matrix partitioning algorithm that partitions a large matrix into smaller submatrices, enabling parallel co-clustering. This method employs a probabilistic model to optimize the configuration of submatrices, balancing the computational efficiency and depth of analysis. Additionally, we propose a hierarchical co-cluster merging algorithm that efficiently identifies and merges co-clusters from these submatrices, enhancing the robustness and reliability of the process. Extensive evaluations validate the effectiveness and efficiency of our method. Experimental results demonstrate a significant reduction in computation time, with an approximate 83% decrease for dense matrices and up to 30% for sparse matrices.
Authors: Nguyen Quang Hieu, Minh Nguyen, Dinh Thai Hoang, Diep N. Nguyen, Eryk Dutkiewicz
Abstract: This paper introduces a novel lossless compression method for compressing geometric attributes of point cloud data with bits-back coding. Our method specializes in using a deep learning-based probabilistic model to estimate the Shannon's entropy of the point cloud information, i.e., geometric attributes of the 3D floating points. Once the entropy of the point cloud dataset is estimated with a convolutional variational autoencoder (CVAE), we use the learned CVAE model to compress the geometric attributes of the point clouds with the bits-back coding technique. The novelty of our method with bits-back coding specializes in utilizing the learned latent variable model of the CVAE to compress the point cloud data. By using bits-back coding, we can capture the potential correlation between the data points, such as similar spatial features like shapes and scattering regions, into the lower-dimensional latent space to further reduce the compression ratio. The main insight of our method is that we can achieve a competitive compression ratio as conventional deep learning-based approaches, while significantly reducing the overhead cost of storage and/or communicating the compression codec, making our approach more applicable in practical scenarios. Throughout comprehensive evaluations, we found that the cost for the overhead is significantly small, compared to the reduction of the compression ratio when compressing large point cloud datasets. Experiment results show that our proposed approach can achieve a compression ratio of 1.56 bit-per-point on average, which is significantly lower than the baseline approach such as Google's Draco with a compression ratio of 1.83 bit-per-point.
Authors: Mohammadjavad Maleki, Sobhan Zahiri
Abstract: The physicochemical properties of chemical compounds have great importance in several areas, including pharmaceuticals, environmental and separation science. Among these are physicochemical properties such as the octanol-water partition coefficient, which has been considered an important index pointing out lipophilicity and hydrophilicity. It affects drug absorption and membrane permeability. Following Lipinski's rule of five, logP was identified as one of the key determinants of the stability of chemical entities and, as such, needed state-of-the-art methods for measuring lipophilicity. This paper presents a deep-learning model, OWPCP, developed to compute logP using Morgan fingerprints and MACCS keys as input features. It uses the interconnection of such molecular representations with logP values extracted from 26,254 compounds. The dataset was prepared to contain a wide range of chemical structures with differing molecular weights and polar surface area. Hyperparameter optimization was conducted using the Keras Tuner alongside the Hyperband algorithm to enhance the performance. OWPCP demonstrated outstanding performance compared to current computational methods, achieving an MAE=0.247 on the test set and outperforming all previous DL models. Remarkably, while one of the most accurate recent models is based on experimental data on retention time to make predictions, OWPCP manages computing logP efficiently without depending on these factors, being, therefore, very useful during early-stage drug discovery. Our model outperforms the best model, which leverages Retention Time, and our model does not require any experimental data. Further validation of the model performance was done across different functional groups, and it showed very high accuracy, especially for compounds that contain aliphatic OH groups. The results have indicated that OWPCP provides a reliable prediction of logP.
Authors: Anas H. Blasi, Mohammad Awis Al Lababede, Mohammed A. Alsuwaiket
Abstract: Mosques are worship places of Allah and must be preserved clean, immaculate, provide all the comforts of the worshippers in them. The prophet's mosque in Medina/ Saudi Arabia is one of the most important mosques for Muslims. It occupies second place after the sacred mosque in Mecca/ Saudi Arabia, which is in constant overcrowding by all Muslims to visit the prophet Mohammad's tomb. This paper aims to propose a smart dome model to preserve the fresh air and allow the sunlight to enter the mosque using artificial intelligence techniques. The proposed model controls domes movements based on the weather conditions and the overcrowding rates in the mosque. The data have been collected from two different resources, the first one from the database of Saudi Arabia weather's history, and the other from Shanghai Technology Database. Congested Scene Recognition Network (CSRNet) and Fuzzy techniques have applied using Python programming language to control the domes to be opened and closed for a specific time to renew the air inside the mosque. Also, this model consists of several parts that are connected for controlling the mechanism of opening/closing domes according to weather data and the situation of crowding in the mosque. Finally, the main goal of this paper has been achieved, and the proposed model has worked efficiently and specifies the exact duration time to keep the domes open automatically for a few minutes for each hour head.
Authors: Jiacong Zhou, Xianyun Wang, Jun Yu
Abstract: Aligning large language models with human preferences improves interaction quality and safety by ensuring outputs better reflect human values. A promising strategy involves Reinforcement Learning from Human Feedback (RLHF), starting with collecting and ranking responses generated by a supervised fine-tuning model to refine alignment. Current methods (DPO) focus on learning from pairwise preference data, categorizing responses into preferred and less preferred pairs, and optimizing by maximizing pairwise margins. Recent studies have uncovered a substantial discrepancy between the theoretical aspirations of preference learning and its real-world results. Current preference alignment techniques underperform expectations, with ranking accuracies below $60\%$ on standard datasets. This suggests existing methods inadequately capture ideal preference relationships within sequences. To address this challenge, this paper introduces \underline{D}irect \underline{R}anking \underline{P}reference \underline{O}ptimization (DRPO), a novel method that views human preference alignment as a Learning-to-Rank (LTR) task. DRPO leverages NDCG, a widely used LTR metric, to optimize the ranking of responses within lists based on preference data, thereby enhancing ranking accuracies. Due to the nondifferentiability of NDCG, we propose diffNDCG loss, a differentiable approximation facilitated by a sorting network to simulate NDCG. Furthermore, to improve the quality of generated response, we propose a novel margin-based Adaptive Rank Policy Score. Extensive experiments have shown that DRPO outperforms existing baseline methods, enhancing the quality of the generated responses.
Authors: Yongheng Sun, Yueh Z. Lee, Genevieve A. Woodard, Hongtu Zhu, Chunfeng Lian, Mingxia Liu
Abstract: Radiology report generation is crucial in medical imaging,but the manual annotation process by physicians is time-consuming and labor-intensive, necessitating the develop-ment of automatic report generation methods. Existingresearch predominantly utilizes Transformers to generateradiology reports, which can be computationally intensive,limiting their use in real applications. In this work, we presentR2Gen-Mamba, a novel automatic radiology report genera-tion method that leverages the efficient sequence processingof the Mamba with the contextual benefits of Transformerarchitectures. Due to lower computational complexity ofMamba, R2Gen-Mamba not only enhances training and in-ference efficiency but also produces high-quality reports.Experimental results on two benchmark datasets with morethan 210,000 X-ray image-report pairs demonstrate the ef-fectiveness of R2Gen-Mamba regarding report quality andcomputational efficiency compared with several state-of-the-art methods. The source code can be accessed online.
Authors: Jieyu Lu, Zhangde Song, Qiyuan Zhao, Yuanqi Du, Yirui Cao, Haojun Jia, Chenru Duan
Abstract: Designing functional transition metal complexes (TMCs) faces challenges due to the vast search space of metals and ligands, requiring efficient optimization strategies. Traditional genetic algorithms (GAs) are commonly used, employing random mutations and crossovers driven by explicit mathematical objectives to explore this space. Transferring knowledge between different GA tasks, however, is difficult. We integrate large language models (LLMs) into the evolutionary optimization framework (LLM-EO) and apply it in both single- and multi-objective optimization for TMCs. We find that LLM-EO surpasses traditional GAs by leveraging the chemical knowledge of LLMs gained during their extensive pretraining. Remarkably, without supervised fine-tuning, LLMs utilize the full historical data from optimization processes, outperforming those focusing only on top-performing TMCs. LLM-EO successfully identifies eight of the top-20 TMCs with the largest HOMO-LUMO gaps by proposing only 200 candidates out of a 1.37 million TMCs space. Through prompt engineering using natural language, LLM-EO introduces unparalleled flexibility into multi-objective optimizations, thereby circumventing the necessity for intricate mathematical formulations. As generative models, LLMs can suggest new ligands and TMCs with unique properties by merging both internal knowledge and external chemistry data, thus combining the benefits of efficient optimization and molecular generation. With increasing potential of LLMs as pretrained foundational models and new post-training inference strategies, we foresee broad applications of LLM-based evolutionary optimization in chemistry and materials design.
Authors: Shrey Vishen, Jatin Sarabu, Chinmay Bharathulwar, Rithwick Lakshmanan, Vishnu Srinivas
Abstract: We present a novel method for diffusion-guided frameworks for view-consistent super-resolution (SR) in neural rendering. Our approach leverages existing 2D SR models in conjunction with advanced techniques such as Variational Score Distilling (VSD) and a LoRA fine-tuning helper, with spatial training to significantly boost the quality and consistency of upscaled 2D images compared to the previous methods in the literature, such as Renoised Score Distillation (RSD) proposed in DiSR-NeRF (1), or SDS proposed in DreamFusion. The VSD score facilitates precise fine-tuning of SR models, resulting in high-quality, view-consistent images. To address the common challenge of inconsistencies among independent SR 2D images, we integrate Iterative 3D Synchronization (I3DS) from the DiSR-NeRF framework. Our quantitative benchmarks and qualitative results on the LLFF dataset demonstrate the superior performance of our system compared to existing methods such as DiSR-NeRF.
Authors: Mayank Nagda, Phil Ostheimer, Sophie Fellenz
Abstract: Topic models are a popular approach for extracting semantic information from large document collections. However, recent studies suggest that the topics generated by these models often do not align well with human intentions. While metadata such as labels and authorship information is available, it has not yet been effectively incorporated into neural topic models. To address this gap, we introduce FANToM, a novel method for aligning neural topic models with both labels and authorship information. FANToM allows for the inclusion of this metadata when available, producing interpretable topics and author distributions for each topic. Our approach demonstrates greater expressiveness than conventional topic models by learning the alignment between labels, topics, and authors. Experimental results show that FANToM improves upon existing models in terms of both topic quality and alignment. Additionally, it identifies author interests and similarities.
Authors: Nathan Phelps, Daniel J. Lizotte, Douglas G. Woolford
Abstract: When modelling data where the response is dichotomous and highly imbalanced, response-based sampling where a subset of the majority class is retained (i.e., undersampling) is often used to create more balanced training datasets prior to modelling. However, the models fit to this undersampled data, which we refer to as base models, generate predictions that are severely biased. There are several calibration methods that can be used to combat this bias, one of which is Platt's scaling. Here, a logistic regression model is used to model the relationship between the base model's original predictions and the response. Despite its popularity for calibrating models after undersampling, Platt's scaling was not designed for this purpose. Our work presents what we believe is the first detailed study focused on the validity of using Platt's scaling to calibrate models after undersampling. We show analytically, as well as via a simulation study and a case study, that Platt's scaling should not be used for calibration after undersampling without critical thought. If Platt's scaling would have been able to successfully calibrate the base model had it been trained on the entire dataset (i.e., without undersampling), then Platt's scaling might be appropriate for calibration after undersampling. If this is not the case, we recommend a modified version of Platt's scaling that fits a logistic generalized additive model to the logit of the base model's predictions, as it is both theoretically motivated and performed well across the settings considered in our study.
Authors: Weiliang Luo
Abstract: We present Music102, an advanced model built upon the Music101 prototype, aimed at enhancing chord progression accompaniment through a D12-equivariant transformer. Inspired by group theory and symbolic music structures, Music102 leverages musical symmetry--such as transposition and reflection operations--integrating these properties into the transformer architecture. By encoding prior music knowledge, the model maintains equivariance across both melody and chord sequences. The POP909 dataset was employed to train and evaluate Music102, revealing significant improvements over Music101 in both weighted loss and exact accuracy metrics, despite using fewer parameters. This work showcases the adaptability of self-attention mechanisms and layer normalization to the discrete musical domain, addressing challenges in computational music analysis. With its stable and flexible neural framework, Music102 sets the stage for further exploration in equivariant music generation and computational composition tools, bridging mathematical theory with practical music performance.
Authors: Nicholas Walker
Abstract: Causal decoder-only transformer models used for generative language modelling, such as Generative Pre-trained Transformers (GPT), are trained to predict the next token in a sequence based only on its previous tokens. Despite this simple training objective, they have proved to be powerful AI tools. However, only predicting the next token results in top layer embedding vectors that are highly token-focused. There may be benefits in generating embedding vectors at each token position that better capture the overall meaning of longer sequences of future text. Recent studies matching brain scans with deep language models suggest that humans also predict upcoming words when listening or reading but consider multiple future tokens rather than just one. This research investigates a new pretraining method called Future Token Prediction (FTP). In FTP, a large transformer encoder generates top layer embedding vectors for each token position, which, instead of being passed to a language head, are linearly and expansively projected to a pseudo-sequence, which is cross attended to by a small transformer decoder to predict the next N tokens forward from that position in the sequence. The top layer embedding vectors from FTP models exhibit distinct properties compared to those from standard GPT models, varying smoothly along a text sequence as measured by cosine similarity between adjacent tokens. Text generated by FTP models show improved topic coherence compared to standard GPT-like models trained with the same prediction perplexity for the next single token. The vectors are shown to better represent the topic of text based on the results of text classification examples. On a toy, but complex, coding problem, FTP networks produce significantly better results than GPT networks.
Authors: G\'erard Ben Arous, C\'edric Gerbelot, Vanessa Piccolo
Abstract: We study the dynamics in high dimensions of online stochastic gradient descent for the multi-spiked tensor model. This multi-index model arises from the tensor principal component analysis (PCA) problem with multiple spikes, where the goal is to estimate $r$ unknown signal vectors within the $N$-dimensional unit sphere through maximum likelihood estimation from noisy observations of a $p$-tensor. We determine the number of samples and the conditions on the signal-to-noise ratios (SNRs) required to efficiently recover the unknown spikes from natural random initializations. We show that full recovery of all spikes is possible provided a number of sample scaling as $N^{p-2}$, matching the algorithmic threshold identified in the rank-one case [Ben Arous, Gheissari, Jagannath 2020, 2021]. Our results are obtained through a detailed analysis of a low-dimensional system that describes the evolution of the correlations between the estimators and the spikes, while controlling the noise in the dynamics. We find that the spikes are recovered sequentially in a process we term "sequential elimination": once a correlation exceeds a critical threshold, all correlations sharing a row or column index become sufficiently small, allowing the next correlation to grow and become macroscopic. The order in which correlations become macroscopic depends on their initial values and the corresponding SNRs, leading to either exact recovery or recovery of a permutation of the spikes. In the matrix case, when $p=2$, if the SNRs are sufficiently separated, we achieve exact recovery of the spikes, whereas equal SNRs lead to recovery of the subspace spanned by the spikes.
Authors: Jiantao Wu, Shentong Mo, Zhenhua Feng, Sara Atito, Josef Kitler, Muhammad Awais
Abstract: Contrastive learning, a prominent approach to representation learning, traditionally assumes positive pairs are closely related samples (the same image or class) and negative pairs are distinct samples. We challenge this assumption by proposing to learn from arbitrary pairs, allowing any pair of samples to be positive within our framework.The primary challenge of the proposed approach lies in applying contrastive learning to disparate pairs which are semantically distant. Motivated by the discovery that SimCLR can separate given arbitrary pairs (e.g., garter snake and table lamp) in a subspace, we propose a feature filter in the condition of class pairs that creates the requisite subspaces by gate vectors selectively activating or deactivating dimensions. This filter can be optimized through gradient descent within a conventional contrastive learning mechanism. We present Hydra, a universal contrastive learning framework for visual representations that extends conventional contrastive learning to accommodate arbitrary pairs. Our approach is validated using IN1K, where 1K diverse classes compose 500,500 pairs, most of them being distinct. Surprisingly, Hydra achieves superior performance in this challenging setting. Additional benefits include the prevention of dimensional collapse and the discovery of class relationships. Our work highlights the value of learning common features of arbitrary pairs and potentially broadens the applicability of contrastive learning techniques on the sample pairs with weak relationships.
Authors: Farshad Jafari, Farzad Didehvar, Amin Gheibi
Abstract: The present paper investigated automatic melody construction for Persian lyrics as an input. It was assumed that there is a phonological correlation between the lyric syllables and the melody in a song. A seq2seq neural network was developed to investigate this assumption, trained on parallel syllable and note sequences in Persian songs to suggest a pleasant melody for a new sequence of syllables. More than 100 pieces of Persian music were collected and converted from the printed version to the digital format due to the lack of a dataset on Persian digital music. Finally, 14 new lyrics were given to the model as input, and the suggested melodies were performed and recorded by music experts to evaluate the trained model. The evaluation was conducted using an audio questionnaire, which more than 170 persons answered. According to the answers about the pleasantness of melody, the system outputs scored an average of 3.005 from 5, while the human-made melodies for the same lyrics obtained an average score of 4.078.
Authors: Nasrin Azimi, Danial Mohammad Rezaei
Abstract: Grading and quality control of Piarom dates, a premium and high-value variety cultivated predominantly in Iran, present significant challenges due to the complexity and variability of defects, as well as the absence of specialized automated systems tailored to this fruit. Traditional manual inspection methods are labor intensive, time consuming, and prone to human error, while existing AI-based sorting solutions are insufficient for addressing the nuanced characteristics of Piarom dates. In this study, we propose an innovative deep learning framework designed specifically for the real-time detection, classification, and grading of Piarom dates. Leveraging a custom dataset comprising over 9,900 high-resolution images annotated across 11 distinct defect categories, our framework integrates state-of-the-art object detection algorithms and Convolutional Neural Networks (CNNs) to achieve high precision in defect identification. Furthermore, we employ advanced segmentation techniques to estimate the area and weight of each date, thereby optimizing the grading process according to industry standards. Experimental results demonstrate that our system significantly outperforms existing methods in terms of accuracy and computational efficiency, making it highly suitable for industrial applications requiring real-time processing. This work not only provides a robust and scalable solution for automating quality control in the Piarom date industry but also contributes to the broader field of AI-driven food inspection technologies, with potential applications across various agricultural products.
Authors: Samuele Poppi, Zheng-Xin Yong, Yifei He, Bobbie Chern, Han Zhao, Aobo Yang, Jianfeng Chi
Abstract: Recent advancements in Large Language Models (LLMs) have sparked widespread concerns about their safety. Recent work demonstrates that safety alignment of LLMs can be easily removed by fine-tuning with a few adversarially chosen instruction-following examples, i.e., fine-tuning attacks. We take a further step to understand fine-tuning attacks in multilingual LLMs. We first discover cross-lingual generalization of fine-tuning attacks: using a few adversarially chosen instruction-following examples in one language, multilingual LLMs can also be easily compromised (e.g., multilingual LLMs fail to refuse harmful prompts in other languages). Motivated by this finding, we hypothesize that safety-related information is language-agnostic and propose a new method termed Safety Information Localization (SIL) to identify the safety-related information in the model parameter space. Through SIL, we validate this hypothesis and find that only changing 20% of weight parameters in fine-tuning attacks can break safety alignment across all languages. Furthermore, we provide evidence to the alternative pathways hypothesis for why freezing safety-related parameters does not prevent fine-tuning attacks, and we demonstrate that our attack vector can still jailbreak LLMs adapted to new languages.
Authors: Jiri Mekyska, Zoltan Galaz, Katarina Safarova, Vojtech Zvoncak, Lukas Cunek, Tomas Urbanek, Jana Marie Havigerova, Jirina Bednarova, Jan Mucha, Michal Gavenciak, Zdenek Smekal, Marcos Faundez-Zanuy
Abstract: Even though the computerised assessment of developmental dysgraphia (DD) based on online handwriting processing has increasing popularity, most of the solutions are based on a setup, where a child writes on a paper fixed to a digitizing tablet that is connected to a computer. Although this approach enables the standard way of writing using an inking pen, it is difficult to be administered by children themselves. The main goal of this study is thus to explore, whether the quantitative analysis of online handwriting recorded via a display screen tablet could sufficiently support the assessment of DD as well. For the purpose of this study, we enrolled 144 children (attending the 3rd and 4th class of a primary school), whose handwriting proficiency was assessed by a special education counsellor, and who assessed themselves by the Handwriting Proficiency Screening Questionnaires for Children (HPSQ C). Using machine learning models based on a gradient-boosting algorithm, we were able to support the DD diagnosis with up to 83.6% accuracy. The HPSQ C total score was estimated with a minimum error equal to 10.34 %. Children with DD spent significantly higher time in-air, they had a higher number of pen elevations, a bigger height of on-surface strokes, a lower in-air tempo, and a higher variation in the angular velocity. Although this study shows a promising impact of DD assessment via display tablets, it also accents the fact that modelling of subjective scores is challenging and a complex and data-driven quantification of DD manifestations is needed.
Authors: Ashish Khisti, M. Reza Ebrahimi, Hassan Dbouk, Arash Behboodi, Roland Memisevic, Christos Louizos
Abstract: We consider multi-draft speculative sampling, where the proposal sequences are sampled independently from different draft models. At each step, a token-level draft selection scheme takes a list of valid tokens as input and produces an output token whose distribution matches that of the target model. Previous works have demonstrated that the optimal scheme (which maximizes the probability of accepting one of the input tokens) can be cast as a solution to a linear program. In this work we show that the optimal scheme can be decomposed into a two-step solution: in the first step an importance sampling (IS) type scheme is used to select one intermediate token; in the second step (single-draft) speculative sampling is applied to generate the output token. For the case of two identical draft models we further 1) establish a necessary and sufficient condition on the distributions of the target and draft models for the acceptance probability to equal one and 2) provide an explicit expression for the optimal acceptance probability. Our theoretical analysis also motives a new class of token-level selection scheme based on weighted importance sampling. Our experimental results demonstrate consistent improvements in the achievable block efficiency and token rates over baseline schemes in a number of scenarios.
Authors: Melissa Adrian, Jake A. Soloff, Rebecca Willett
Abstract: Model selection is the process of choosing from a class of candidate models given data. For instance, methods such as the LASSO and sparse identification of nonlinear dynamics (SINDy) formulate model selection as finding a sparse solution to a linear system of equations determined by training data. However, absent strong assumptions, such methods are highly unstable: if a single data point is removed from the training set, a different model may be selected. This paper presents a new approach to stabilizing model selection that leverages a combination of bagging and an "inflated" argmax operation. Our method selects a small collection of models that all fit the data, and it is stable in that, with high probability, the removal of any training point will result in a collection of selected models that overlaps with the original collection. In addition to developing theoretical guarantees, we illustrate this method in (a) a simulation in which strongly correlated covariates make standard LASSO model selection highly unstable and (b) a Lotka-Volterra model selection problem focused on identifying how competition in an ecosystem influences species' abundances. In both settings, the proposed method yields stable and compact collections of selected models, outperforming a variety of benchmarks.
Authors: Shrenik Bhansali, Alwin Jin, Tyler Lizzo, Larry Heck
Abstract: Large language models (LLMs) are essential in natural language processing (NLP) but are costly in data collection, pre-training, fine-tuning, and inference. Task-specific small language models (SLMs) offer a cheaper alternative but lack robustness and generalization. This paper proposes LEGO, a novel technique to extract SLMs from an LLM and recombine them. Using state-of-the-art LLM pruning strategies, we can create task- and user-specific SLM building blocks that are efficient for fine-tuning and inference while also preserving user data privacy. LEGO utilizes Federated Learning and a novel aggregation scheme for the LLM reconstruction, maintaining robustness without high costs and preserving user data privacy. We experimentally demonstrate the versatility of LEGO, showing its ability to enable model heterogeneity and mitigate the effects of data heterogeneity while maintaining LLM robustness.
Authors: Muqsit Azeem, Debraj Chakraborty, Sudeep Kanav, Jan Kretinsky, Mohammadsadegh Mohagheghi, Stefanie Mohr, Maximilian Weininger
Abstract: Despite the advances in probabilistic model checking, the scalability of the verification methods remains limited. In particular, the state space often becomes extremely large when instantiating parameterized Markov decision processes (MDPs) even with moderate values. Synthesizing policies for such \emph{huge} MDPs is beyond the reach of available tools. We propose a learning-based approach to obtain a reasonable policy for such huge MDPs. The idea is to generalize optimal policies obtained by model-checking small instances to larger ones using decision-tree learning. Consequently, our method bypasses the need for explicit state-space exploration of large models, providing a practical solution to the state-space explosion problem. We demonstrate the efficacy of our approach by performing extensive experimentation on the relevant models from the quantitative verification benchmark set. The experimental results indicate that our policies perform well, even when the size of the model is orders of magnitude beyond the reach of state-of-the-art analysis tools.
Authors: Solmaz Seyed Monir, Dongfang Zhao
Abstract: The proliferation of fake news on digital platforms has underscored the need for robust and scalable detection mechanisms. Traditional methods often fall short in handling large and diverse datasets due to limitations in scalability and accuracy. In this paper, we propose NexusIndex, a novel framework and model that enhances fake news detection by integrating advanced language models, an innovative FAISSNexusIndex layer, and attention mechanisms. Our approach leverages multi-model embeddings to capture rich contextual and semantic nuances, significantly improving text interpretation and classification accuracy. By transforming articles into high-dimensional embeddings and indexing them efficiently, NexusIndex facilitates rapid similarity searches across extensive collections of news articles. The FAISSNexusIndex layer further optimizes this process, enabling real-time detection and enhancing the system's scalability and performance. Our experimental results demonstrate that NexusIndex outperforms state-of-the-art methods in efficiency and accuracy across diverse datasets.
Authors: Myeonghoon Ryu, Hongseok Oh, Suji Lee, Han Park
Abstract: In this study, we introduce Unified Microphone Conversion, a unified generative framework to enhance the resilience of sound event classification systems against device variability. Building on the limitations of previous works, we condition the generator network with frequency response information to achieve many-to-many device mapping. This approach overcomes the inherent limitation of CycleGAN, requiring separate models for each device pair. Our framework leverages the strengths of CycleGAN for unpaired training to simulate device characteristics in audio recordings and significantly extends its scalability by integrating frequency response related information via Feature-wise Linear Modulation. The experiment results show that our method outperforms the state-of-the-art method by 2.6% and reducing variability by 0.8% in macro-average F1 score.
Authors: Fengchen Liu, Jordan Jung, Wei Feinstein, Jeff DAmbrogia, Gary Jung
Abstract: This paper introduces a novel approach to enhancing closed-domain Question Answering (QA) systems, focusing on the specific needs of the Lawrence Berkeley National Laboratory (LBL) Science Information Technology (ScienceIT) domain. Utilizing a rich dataset derived from the ScienceIT documentation, our study embarks on a detailed comparison of two fine-tuned large language models and five retrieval-augmented generation (RAG) models. Through data processing techniques, we transform the documentation into structured context-question-answer triples, leveraging the latest Large Language Models (AWS Bedrock, GCP PaLM2, Meta LLaMA2, OpenAI GPT-4, Google Gemini-Pro) for data-driven insights. Additionally, we introduce the Aggregated Knowledge Model (AKM), which synthesizes responses from the seven models mentioned above using K-means clustering to select the most representative answers. The evaluation of these models across multiple metrics offers a comprehensive look into their effectiveness and suitability for the LBL ScienceIT environment. The results demonstrate the potential benefits of integrating fine-tuning and retrieval-augmented strategies, highlighting significant performance improvements achieved with the AKM. The insights gained from this study can be applied to develop specialized QA systems tailored to specific domains.
Authors: Sudhanshu Agrawal, Wonseok Jeon, Mingu Lee
Abstract: Speculative decoding is a powerful technique that attempts to circumvent the autoregressive constraint of modern Large Language Models (LLMs). The aim of speculative decoding techniques is to improve the average inference time of a large, target model without sacrificing its accuracy, by using a more efficient draft model to propose draft tokens which are then verified in parallel. The number of draft tokens produced in each drafting round is referred to as the draft length and is often a static hyperparameter chosen based on the acceptance rate statistics of the draft tokens. However, setting a static draft length can negatively impact performance, especially in scenarios where drafting is expensive and there is a high variance in the number of tokens accepted. Adaptive Entropy-based Draft Length (AdaEDL) is a simple, training and parameter-free criteria which allows for early stopping of the token drafting process by approximating a lower bound on the expected acceptance probability of the drafted token based on the currently observed entropy of the drafted logits. We show that AdaEDL consistently outperforms static draft-length speculative decoding by 10%-57% as well as other training-free draft-stopping techniques by upto 10% in a variety of settings and datasets. At the same time, we show that AdaEDL is more robust than these techniques and preserves performance in high-sampling-temperature scenarios. Since it is training-free, in contrast to techniques that rely on the training of dataset-specific draft-stopping predictors, AdaEDL can seamlessly be integrated into a variety of pre-existing LLM systems.
Authors: Dae Yon Hwang, Bilal Taha, Harshit Pande, Yaroslav Nechaev
Abstract: Despite the recent advancements in information retrieval (IR), zero-shot IR remains a significant challenge, especially when dealing with new domains, languages, and newly-released use cases that lack historical query traffic from existing users. For such cases, it is common to use query augmentations followed by fine-tuning pre-trained models on the document data paired with synthetic queries. In this work, we propose a novel Universal Document Linking (UDL) algorithm, which links similar documents to enhance synthetic query generation across multiple datasets with different characteristics. UDL leverages entropy for the choice of similarity models and named entity recognition (NER) for the link decision of documents using similarity scores. Our empirical studies demonstrate the effectiveness and universality of the UDL across diverse datasets and IR models, surpassing state-of-the-art methods in zero-shot cases. The developed code for reproducibility is included in https://github.com/eoduself/UDL
Authors: Jiarui Lu, Xiaoyin Chen, Stephen Zhewen Lu, Chence Shi, Hongyu Guo, Yoshua Bengio, Jian Tang
Abstract: Proteins adopt multiple structural conformations to perform their diverse biological functions, and understanding these conformations is crucial for advancing drug discovery. Traditional physics-based simulation methods often struggle with sampling equilibrium conformations and are computationally expensive. Recently, deep generative models have shown promise in generating protein conformations as a more efficient alternative. However, these methods predominantly rely on the diffusion process within a 3D geometric space, which typically centers around the vicinity of metastable states and is often inefficient in terms of runtime. In this paper, we introduce Structure Language Modeling (SLM) as a novel framework for efficient protein conformation generation. Specifically, the protein structures are first encoded into a compact latent space using a discrete variational auto-encoder, followed by conditional language modeling that effectively captures sequence-specific conformation distributions. This enables a more efficient and interpretable exploration of diverse ensemble modes compared to existing methods. Based on this general framework, we instantiate SLM with various popular LM architectures as well as proposing the ESMDiff, a novel BERT-like structure language model fine-tuned from ESM3 with masked diffusion. We verify our approach in various scenarios, including the equilibrium dynamics of BPTI, conformational change pairs, and intrinsically disordered proteins. SLM provides a highly efficient solution, offering a 20-100x speedup than existing methods in generating diverse conformations, shedding light on promising avenues for future research.
Authors: Zhisheng Lin, Yifu Liu, Zhiling Luo, Jinyang Gao, Yu Li
Abstract: The improvement in translating natural language to structured query language (SQL) can be attributed to the advancements in large language models (LLMs). Open-source LLMs, tailored for specific database dialects such as MySQL, have shown great performance. However, cloud service providers are looking for a unified database manager service (e.g., Cosmos DB from Azure, Amazon Aurora from AWS, Lindorm from AlibabaCloud) that can support multiple dialects. This requirement has led to the concept of multi-dialect query generation, which presents challenges to LLMs. These challenges include syntactic differences among dialects and imbalanced data distribution across multiple dialects. To tackle these challenges, we propose MoMQ, a novel Mixture-of-Experts-based multi-dialect query generation framework across both relational and non-relational databases. MoMQ employs a dialect expert group for each dialect and a multi-level routing strategy to handle dialect-specific knowledge, reducing interference during query generation. Additionally, a shared expert group is introduced to address data imbalance, facilitating the transfer of common knowledge from high-resource dialects to low-resource ones. Furthermore, we have developed a high-quality multi-dialect query generation benchmark that covers relational and non-relational databases such as MySQL, PostgreSQL, Cypher for Neo4j, and nGQL for NebulaGraph. Extensive experiments have shown that MoMQ performs effectively and robustly even in resource-imbalanced scenarios.
Authors: Maarten Buyl, Alexander Rogiers, Sander Noels, Iris Dominguez-Catena, Edith Heiter, Raphael Romero, Iman Johary, Alexandru-Cristian Mara, Jefrey Lijffijt, Tijl De Bie
Abstract: Large language models (LLMs) are trained on vast amounts of data to generate natural language, enabling them to perform tasks like text summarization and question answering. These models have become popular in artificial intelligence (AI) assistants like ChatGPT and already play an influential role in how humans access information. However, the behavior of LLMs varies depending on their design, training, and use. In this paper, we uncover notable diversity in the ideological stance exhibited across different LLMs and languages in which they are accessed. We do this by prompting a diverse panel of popular LLMs to describe a large number of prominent and controversial personalities from recent world history, both in English and in Chinese. By identifying and analyzing moral assessments reflected in the generated descriptions, we find consistent normative differences between how the same LLM responds in Chinese compared to English. Similarly, we identify normative disagreements between Western and non-Western LLMs about prominent actors in geopolitical conflicts. Furthermore, popularly hypothesized disparities in political goals among Western models are reflected in significant normative differences related to inclusion, social inequality, and political scandals. Our results show that the ideological stance of an LLM often reflects the worldview of its creators. This raises important concerns around technological and regulatory efforts with the stated aim of making LLMs ideologically `unbiased', and it poses risks for political instrumentalization.
Authors: Aman Sagar, Preeti Mehta, Monika Shrivastva, Suchi Kumari
Abstract: This paper presents a deep learning framework for the multi-class classification of gastrointestinal abnormalities in Video Capsule Endoscopy (VCE) frames. The aim is to automate the identification of ten GI abnormality classes, including angioectasia, bleeding, and ulcers, thereby reducing the diagnostic burden on gastroenterologists. Utilizing an ensemble of DenseNet and ResNet architectures, the proposed model achieves an overall accuracy of 94\% across a well-structured dataset. Precision scores range from 0.56 for erythema to 1.00 for worms, with recall rates peaking at 98% for normal findings. This study emphasizes the importance of robust data preprocessing techniques, including normalization and augmentation, in enhancing model performance. The contributions of this work lie in developing an effective AI-driven tool that streamlines the diagnostic process in gastroenterology, ultimately improving patient care and clinical outcomes.
Authors: Hai Siong Tan, Kuancheng Wang, Rafe Mcbeth
Abstract: In this work, we examine the effectiveness of an uncertainty quantification framework known as Evidential Deep Learning applied in the context of biomedical image segmentation. This class of models involves assigning Dirichlet distributions as priors for segmentation labels, and enables a few distinct definitions of model uncertainties. Using the cardiac and prostate MRI images available in the Medical Segmentation Decathlon for validation, we found that Evidential Deep Learning models with U-Net backbones generally yielded superior correlations between prediction errors and uncertainties relative to the conventional baseline equipped with Shannon entropy measure, Monte-Carlo Dropout and Deep Ensemble methods. We also examined these models' effectiveness in active learning, finding that relative to the standard Shannon entropy-based sampling, they yielded higher point-biserial uncertainty-error correlations while attaining similar performances in Dice-Sorensen coefficients. These superior features of EDL models render them well-suited for segmentation tasks that warrant a critical sensitivity in detecting large model errors.
Authors: Lachlan Mares, Stefan Podgorski, Ian Reid
Abstract: This work presents the experiments and solution outline for our teams winning submission in the Learn To Race Autonomous Racing Virtual Challenge 2022 hosted by AIcrowd. The objective of the Learn-to-Race competition is to push the boundary of autonomous technology, with a focus on achieving the safety benefits of autonomous driving. In the description the competition is framed as a reinforcement learning (RL) challenge. We focused our initial efforts on implementation of Soft Actor Critic (SAC) variants. Our goal was to learn non-trivial control of the race car exclusively from visual and geometric features, directly mapping pixels to control actions. We made suitable modifications to the default reward policy aiming to promote smooth steering and acceleration control. The framework for the competition provided real time simulation, meaning a single episode (learning experience) is measured in minutes. Instead of pursuing parallelisation of episodes we opted to explore a more traditional approach in which the visual perception was processed (via learned operators) and fed into rule-based controllers. Such a system, while not as academically "attractive" as a pixels-to-actions approach, results in a system that requires less training, is more explainable, generalises better and is easily tuned and ultimately out-performed all other agents in the competition by a large margin.
Authors: Chung-En Sun, Xiaodong Liu, Weiwei Yang, Tsui-Wei Weng, Hao Cheng, Aidan San, Michel Galley, Jianfeng Gao
Abstract: Recent research has shown that Large Language Models (LLMs) are vulnerable to automated jailbreak attacks, where adversarial suffixes crafted by algorithms appended to harmful queries bypass safety alignment and trigger unintended responses. Current methods for generating these suffixes are computationally expensive and have low Attack Success Rates (ASR), especially against well-aligned models like Llama2 and Llama3. To overcome these limitations, we introduce ADV-LLM, an iterative self-tuning process that crafts adversarial LLMs with enhanced jailbreak ability. Our framework significantly reduces the computational cost of generating adversarial suffixes while achieving nearly 100\% ASR on various open-source LLMs. Moreover, it exhibits strong attack transferability to closed-source models, achieving 99% ASR on GPT-3.5 and 49% ASR on GPT-4, despite being optimized solely on Llama3. Beyond improving jailbreak ability, ADV-LLM provides valuable insights for future safety alignment research through its ability to generate large datasets for studying LLM safety. Our code is available at: https://github.com/SunChungEn/ADV-LLM
Authors: Sergio Burdisso, Srikanth Madikeri, Petr Motlicek
Abstract: Efficiently deriving structured workflows from unannotated dialogs remains an underexplored and formidable challenge in computational linguistics. Automating this process could significantly accelerate the manual design of workflows in new domains and enable the grounding of large language models in domain-specific flowcharts, enhancing transparency and controllability. In this paper, we introduce Dialog2Flow (D2F) embeddings, which differ from conventional sentence embeddings by mapping utterances to a latent space where they are grouped according to their communicative and informative functions (i.e., the actions they represent). D2F allows for modeling dialogs as continuous trajectories in a latent space with distinct action-related regions. By clustering D2F embeddings, the latent space is quantized, and dialogs can be converted into sequences of region/action IDs, facilitating the extraction of the underlying workflow. To pre-train D2F, we build a comprehensive dataset by unifying twenty task-oriented dialog datasets with normalized per-turn action annotations. We also introduce a novel soft contrastive loss that leverages the semantic information of these actions to guide the representation learning process, showing superior performance compared to standard supervised contrastive loss. Evaluation against various sentence embeddings, including dialog-specific ones, demonstrates that D2F yields superior qualitative and quantitative results across diverse domains.
Authors: Jan V\'avra (Vienna University of Economics and Business, Paris-Lodron University of Salzburg), Bettina Gr\"un (Vienna University of Economics and Business), Paul Hofmarcher (Paris-Lodron University of Salzburg)
Abstract: The world is evolving and so is the vocabulary used to discuss topics in speech. Analysing political speech data from more than 30 years requires the use of flexible topic models to uncover the latent topics and their change in prevalence over time as well as the change in the vocabulary of the topics. We propose the temporal Poisson factorisation (TPF) model as an extension to the Poisson factorisation model to model sparse count data matrices obtained based on the bag-of-words assumption from text documents with time stamps. We discuss and empirically compare different model specifications for the time-varying latent variables consisting either of a flexible auto-regressive structure of order one or a random walk. Estimation is based on variational inference where we consider a combination of coordinate ascent updates with automatic differentiation using batching of documents. Suitable variational families are proposed to ease inference. We compare results obtained using independent univariate variational distributions for the time-varying latent variables to those obtained with a multivariate variant. We discuss in detail the results of the TPF model when analysing speeches from 18 sessions in the U.S. Senate (1981-2016).
Authors: Martin Mirchev, Andreea Costea, Abhishek Kr Singh, Abhik Roychoudhury
Abstract: With the advent of AI-based coding engines, it is possible to convert natural language requirements to executable code in standard programming languages. However, AI-generated code can be unreliable, and the natural language requirements driving this code may be ambiguous. In other words, the intent may not be accurately captured in the code generated from AI-coding engines like Copilot. The goal of our work is to discover the programmer intent, while generating code which conforms to the intent and a proof of this conformance. Our approach to intent discovery is powered by a novel repair engine called program-proof co-evolution, where the object of repair is a tuple (code, logical specification, test) generated by an LLM from the same natural language description. The program and the specification capture the initial operational and declarative description of intent, while the test represents a concrete, albeit partial, understanding of the intent. Our objective is to achieve consistency between the program, the specification, and the test by incrementally refining our understanding of the user intent. Reaching consistency through this repair process provides us with a formal, logical description of the intent, which is then translated back into natural language for the developer's inspection. The resultant intent description is now unambiguous, though expressed in natural language. We demonstrate how the unambiguous intent discovered through our approach increases the percentage of verifiable auto-generated programs on a recently proposed dataset in the Dafny programming language.
Authors: Tanya Chowdhury, James Allan
Abstract: Transformer networks, especially those with performance on par with GPT models, are renowned for their powerful feature extraction capabilities. However, the nature and correlation of these features with human-engineered ones remain unclear. In this study, we delve into the mechanistic workings of state-of-the-art, fine-tuning-based passage-reranking transformer networks. Our approach involves a probing-based, layer-by-layer analysis of neurons within ranking LLMs to identify individual or groups of known human-engineered and semantic features within the network's activations. We explore a wide range of features, including lexical, document structure, query-document interaction, advanced semantic, interaction-based, and LLM-specific features, to gain a deeper understanding of the underlying mechanisms that drive ranking decisions in LLMs. Our results reveal a set of features that are prominently represented in LLM activations, as well as others that are notably absent. Additionally, we observe distinct behaviors of LLMs when processing low versus high relevance queries and when encountering out-of-distribution query and document sets. By examining these features within activations, we aim to enhance the interpretability and performance of LLMs in ranking tasks. Our findings provide valuable insights for the development of more effective and transparent ranking models, with significant implications for the broader information retrieval community. All scripts and code necessary to replicate our findings are made available.
Authors: Marian Longa, Jo\~ao F. Henriques
Abstract: Learning interpretable representations of visual data is an important challenge, to make machines' decisions understandable to humans and to improve generalisation outside of the training distribution. To this end, we propose a deep learning framework where one can specify nonlinear priors for videos (e.g. of Newtonian physics) that allow the model to learn interpretable latent variables and use these to generate videos of hypothetical scenarios not observed at training time. We do this by extending the Variational Auto-Encoder (VAE) prior from a simple isotropic Gaussian to an arbitrary nonlinear temporal Additive Noise Model (ANM), which can describe a large number of processes (e.g. Newtonian physics). We propose a novel linearization method that constructs a Gaussian Mixture Model (GMM) approximating the prior, and derive a numerically stable Monte Carlo estimate of the KL divergence between the posterior and prior GMMs. We validate the method on different real-world physics videos including a pendulum, a mass on a spring, a falling object and a pulsar (rotating neutron star). We specify a physical prior for each experiment and show that the correct variables are learned. Once a model is trained, we intervene on it to change different physical variables (such as oscillation amplitude or adding air drag) to generate physically correct videos of hypothetical scenarios that were not observed previously.
Authors: Daniel Ma\^itre, Vishal S. Ngairangbam, Michael Spannowsky
Abstract: The Matrix-Element Method (MEM) has long been a cornerstone of data analysis in high-energy physics. It leverages theoretical knowledge of parton-level processes and symmetries to evaluate the likelihood of observed events. In parallel, the advent of geometric deep learning has enabled neural network architectures that incorporate known symmetries directly into their design, leading to more efficient learning. This paper presents a novel approach that combines MEM-inspired symmetry considerations with equivariant neural network design for particle physics analysis. Even though Lorentz invariance and permutation invariance overall reconstructed objects are the largest and most natural symmetry in the input domain, we find that they are sub-optimal in most practical search scenarios. We propose a longitudinal boost-equivariant message-passing neural network architecture that preserves relevant discrete symmetries. We present numerical studies demonstrating MEM-inspired architectures achieve new state-of-the-art performance in distinguishing di-Higgs decays to four bottom quarks from the QCD background, with enhanced sample and parameter efficiencies. This synergy between MEM and equivariant deep learning opens new directions for physics-informed architecture design, promising more powerful tools for probing physics beyond the Standard Model.
Authors: Yejing Xie, Richard Zanibbi, Harold Mouch\`ere
Abstract: In this paper, we present a novel approach to Handwritten Mathematical Expression Recognition (HMER) by leveraging graph-based modeling techniques. We introduce an End-to-end model with an Edge-weighted Graph Attention Mechanism (EGAT), designed to perform simultaneous node and edge classification. This model effectively integrates node and edge features, facilitating the prediction of symbol classes and their relationships within mathematical expressions. Additionally, we propose a stroke-level Graph Modeling method for both local (LGM) and global (GGM) information, which applies an end-to-end model to Online HMER tasks, transforming the recognition problem into node and edge classification tasks in graph structure. By capturing both local and global graph features, our method ensures comprehensive understanding of the expression structure. Through the combination of these components, our system demonstrates superior performance in symbol detection, relation classification, and expression-level recognition.
Authors: Chien Van Nguyen, Huy Huu Nguyen, Thang M. Pham, Ruiyi Zhang, Hanieh Deilamsalehy, Puneet Mathur, Ryan A. Rossi, Trung Bui, Viet Dac Lai, Franck Dernoncourt, Thien Huu Nguyen
Abstract: Efficient long-context language modeling remains a significant challenge in Natural Language Processing (NLP). While Transformers dominate language tasks, they struggle with long sequences due to quadratic computational complexity in training and linearly scaling memory costs during inference. Recent State Space Models (SSMs) such as Mamba offer alternatives with constant memory usage, but they underperform in tasks requiring extensive in-context retrieval. We introduce Taipan, a novel hybrid architecture that combines Mamba-2 with Selective Attention Layers (SALs). These SALs identify tokens requiring long-range interactions, remove less important features, and then augment their representations using the attention module. This approach balances Mamba's efficiency with Transformer-like performance in memory-intensive tasks. By constraining the attention budget, Taipan extends accurate predictions to context lengths of up to 1 million tokens while preserving computational efficiency. Our experiments demonstrate Taipan's superior performance across various scales and tasks, offering a promising solution for efficient long-context language modeling.
Authors: Yibo Miao, Bofei Gao, Shanghaoran Quan, Junyang Lin, Daoguang Zan, Jiaheng Liu, Jian Yang, Tianyu Liu, Zhijie Deng
Abstract: The last year has witnessed the rapid progress of large language models (LLMs) across diverse domains. Among them, CodeLLMs have garnered particular attention because they can not only assist in completing various programming tasks but also represent the decision-making and logical reasoning capabilities of LLMs. However, current CodeLLMs mainly focus on pre-training and supervised fine-tuning scenarios, leaving the alignment stage, which is important for post-training LLMs, under-explored. This work first identifies that the commonly used PPO algorithm may be suboptimal for the alignment of CodeLLM because the involved reward rules are routinely coarse-grained and potentially flawed. We then advocate addressing this using the DPO algorithm. Based on only preference data pairs, DPO can render the model rank data automatically, giving rise to a fine-grained rewarding pattern more robust than human intervention. We also contribute a pipeline for collecting preference pairs for DPO on CodeLLMs. Studies show that our method significantly improves the performance of existing CodeLLMs on benchmarks such as MBPP and HumanEval.
Authors: Hawau Olamide Toyin, Hao Li, Hanan Aldarmaki
Abstract: Speech recognition and speech synthesis models are typically trained separately, each with its own set of learning objectives, training data, and model parameters, resulting in two distinct large networks. We propose a parameter-efficient approach to learning ASR and TTS jointly via a multi-task learning objective and shared parameters. Our evaluation demonstrates that the performance of our multi-task model is comparable to that of individually trained models while significantly saving computational and memory costs ($\sim$50\% reduction in the total number of parameters required for the two tasks combined). We experiment with English as a resource-rich language, and Arabic as a relatively low-resource language due to shortage of TTS data. Our models are trained with publicly available data, and both the training code and model checkpoints are openly available for further research.
Authors: Wonhyung Choi, Inkyung Ahn
Abstract: Understanding species dynamics in heterogeneous environments is essential for ecosystem studies. Traditional models assumed homogeneous habitats, but recent approaches include spatial and temporal variability, highlighting species migration. We adopt starvation-driven diffusion (SDD) models as nonlinear diffusion to describe species dispersal based on local resource conditions, showing advantages for species survival. However, accurate prediction remains challenging due to model simplifications. This study uses multi-agent reinforcement learning (MARL) with deep Q-networks (DQN) to simulate single species and predator-prey interactions, incorporating SDD-type rewards. Our simulations reveal evolutionary dispersal strategies, providing insights into species dispersal mechanisms and validating traditional mathematical models.
Authors: David Thulke, Yingbo Gao, Rricha Jalota, Christian Dugast, Hermann Ney
Abstract: This paper explores the rapid development of a telephone call summarization system utilizing large language models (LLMs). Our approach involves initial experiments with prompting existing LLMs to generate summaries of telephone conversations, followed by the creation of a tailored synthetic training dataset utilizing stronger frontier models. We place special focus on the diversity of the generated data and on the ability to control the length of the generated summaries to meet various use-case specific requirements. The effectiveness of our method is evaluated using two state-of-the-art LLM-as-a-judge-based evaluation techniques to ensure the quality and relevance of the summaries. Our results show that fine-tuned Llama-2-7B-based summarization model performs on-par with GPT-4 in terms of factual accuracy, completeness and conciseness. Our findings demonstrate the potential for quickly bootstrapping a practical and efficient call summarization system.
Authors: Sanjay Singh, Amaresh Chakrabarti
Abstract: This paper proposes a framework for assessing the novelty of design problems using the SAPPhIRE model of causality. The novelty of a problem is measured as its minimum distance from the problems in a reference problem database. The distance is calculated by comparing the current problem and each reference past problem at the various levels of abstraction in the SAPPhIRE ontology. The basis for comparison is textual similarity. To demonstrate the applicability of the proposed framework, The current set of problems associated with an artifact, as collected from its stakeholders, were compared with the past set of problems, as collected from patents and other web sources, to assess the novelty of the current set. This approach is aimed at providing a better understanding of the degree of novelty of any given set of current problems by comparing them to similar problems available from historical records. Since manual assessment, the current mode of such assessments as reported in the literature, is a tedious process, to reduce time complexity and to afford better applicability for larger sets of problem statements, an automated assessment is proposed and used in this paper.
Authors: Alexander Shurakov, Margarita Ershova, Abdukodir Khakimov, Anatoliy Prikhodko, Evgeny Mokrov, Vyacheslav Begishev, Galina Chulkova, Yevgeni Koucheryavy, Gregory Gol'tsman
Abstract: Beam tracking is an essential functionality of millimeter wave (mmWave, 30-100 GHz) and sub-terahertz (sub-THz, 100-300 GHz) 5G/6G systems. It operates by performing antenna sweeping at both base station (BS) and user equipment (UE) sides using the Synchronization Signal Blocks (SSB). The optimal frequency of beam tracking events is not specified by 3GPP standards and heavily depends on the micromobility properties of the applications currently utilized by the user. In absence of explicit signalling for the type of application at the air interface, in this paper, we propose a way to remotely detect it at the BS side based on the received signal strength pattern. To this aim, we first perform a multi-stage measurement campaign at 156 GHz, belonging to the sub-THz band, to obtain the received signal strength traces of popular smartphone applications. Then, we proceed applying conventional statistical Mann-Whitney tests and various machine learning (ML) based classification techniques to discriminate applications remotely. Our results show that Mann-Whitney test can be used to differentiate between fast and slow application classes with a confidence of 0.95 inducing class detection delay on the order of 1 s after application initialization. With the same time budget, random forest classifiers can differentiate between applications with fast and slow micromobility with 80% accuracy using received signal strength metric only. The accuracy of detecting a specific application however is lower, reaching 60%. By utilizing the proposed technique one can estimate the optimal values of the beam tracking intervals without adding additional signalling to the air interface.
Authors: Esteban Garces Arias, Hannah Blocher, Julian Rodemann, Meimingwei Li, Christian Heumann, Matthias A{\ss}enmacher
Abstract: Open-ended text generation has become a prominent task in natural language processing due to the rise of powerful (large) language models. However, evaluating the quality of these models and the employed decoding strategies remains challenging because of trade-offs among widely used metrics such as coherence, diversity, and perplexity. Decoding methods often excel in some metrics while underperforming in others, complicating the establishment of a clear ranking. In this paper, we present novel ranking strategies within this multicriteria framework. Specifically, we employ benchmarking approaches based on partial orderings and present a new summary metric designed to balance existing automatic indicators, providing a more holistic evaluation of text generation quality. Furthermore, we discuss the alignment of these approaches with human judgments. Our experiments demonstrate that the proposed methods offer a robust way to compare decoding strategies, exhibit similarities with human preferences, and serve as valuable tools in guiding model selection for open-ended text generation tasks. Finally, we suggest future directions for improving evaluation methodologies in text generation. Our codebase, datasets, and models are publicly available.
Authors: Michael Schopf-Kuester, Zorah L\"ahner, Michael Moeller
Abstract: This work addresses the problem of \textit{shape completion}, i.e., the task of restoring incomplete shapes by predicting their missing parts. While previous works have often predicted the fractured and restored shape in one step, we approach the task by separately predicting the fractured and newly restored parts, but ensuring these predictions are interconnected. We use a decoder network motivated by related work on the prediction of signed distance functions (DeepSDF). In particular, our representation allows us to consider test-time-training, i.e., finetuning network parameters to match the given incomplete shape more accurately during inference. While previous works often have difficulties with artifacts around the fracture boundary, we demonstrate that our overfitting to the fractured parts leads to significant improvements in the restoration of eight different shape categories of the ShapeNet data set in terms of their chamfer distances.
Authors: Vasiliki Papanikou, Panagiotis Papadakos, Theodora Karamanidou, Thanos G. Stavropoulos, Evaggelia Pitoura, Panayiotis Tsaparas
Abstract: In this paper, we present a comprehensive survey on the pervasive issue of medical misinformation in social networks from the perspective of information technology. The survey aims at providing a systematic review of related research and helping researchers and practitioners navigate through this fast-changing field. Specifically, we first present manual and automatic approaches for fact-checking. We then explore fake news detection methods, using content, propagation features, or source features, as well as mitigation approaches for countering the spread of misinformation. We also provide a detailed list of several datasets on health misinformation and of publicly available tools. We conclude the survey with a discussion on the open challenges and future research directions in the battle against health misinformation.
Authors: G\'abor Hidy, Bence Bakos, Andr\'as Luk\'acs
Abstract: In medical image segmentation tasks, the scarcity of labeled training data poses a significant challenge when training deep neural networks. When using U-Net-style architectures, it is common practice to address this problem by pretraining the encoder part on a large general-purpose dataset like ImageNet. However, these methods are resource-intensive and do not guarantee improved performance on the downstream task. In this paper we investigate a variety of training setups on medical image segmentation datasets, using ImageNet-pretrained models. By examining over 300 combinations of models, datasets, and training methods, we find that shorter pretraining often leads to better results on the downstream task, providing additional proof to the well-known fact that the accuracy of the model on ImageNet is a poor indicator for downstream performance. As our main contribution, we introduce a novel transferability metric, based on contrastive learning, that measures how robustly a pretrained model is able to represent the target data. In contrast to other transferability scores, our method is applicable to the case of transferring from ImageNet classification to medical image segmentation. We apply our robustness score by measuring it throughout the pretraining phase to indicate when the model weights are optimal for downstream transfer. This reduces pretraining time and improves results on the target task.
Authors: Stefan Brandst\"atter, Philipp Seeb\"ock, Christoph F\"urb\"ock, Svitlana Pochepnia, Helmut Prosch, Georg Langs
Abstract: 2D to 3D registration is essential in tasks such as diagnosis, surgical navigation, environmental understanding, navigation in robotics, autonomous systems, or augmented reality. In medical imaging, the aim is often to place a 2D image in a 3D volumetric observation to w. Current approaches for rigid single slice in volume registration are limited by requirements such as pose initialization, stacks of adjacent slices, or reliable anatomical landmarks. Here, we propose a self-supervised 2D/3D registration approach to match a single 2D slice to the corresponding 3D volume. The method works in data without anatomical priors such as images of tumors. It addresses the dimensionality disparity and establishes correspondences between 2D in-plane and 3D out-of-plane rotation-equivariant features by using group equivariant CNNs. These rotation-equivariant features are extracted from the 2D query slice and aligned with their 3D counterparts. Results demonstrate the robustness of the proposed slice-in-volume registration on the NSCLC-Radiomics CT and KIRBY21 MRI datasets, attaining an absolute median angle error of less than 2 degrees and a mean-matching feature accuracy of 89% at a tolerance of 3 pixels.
Authors: Md. Khairul Islam, Andrew Wang, Tianhao Wang, Yangfeng Ji, Judy Fox, Jieyu Zhao
Abstract: Differential privacy (DP) is applied when fine-tuning pre-trained large language models (LLMs) to limit leakage of training examples. While most DP research has focused on improving a model's privacy-utility tradeoff, some find that DP can be unfair to or biased against underrepresented groups. In this work, we show the impact of DP on bias in LLMs through empirical analysis. Differentially private training can increase the model bias against protected groups w.r.t AUC-based bias metrics. DP makes it more difficult for the model to differentiate between the positive and negative examples from the protected groups and other groups in the rest of the population. Our results also show that the impact of DP on bias is not only affected by the privacy protection level but also the underlying distribution of the dataset.
Authors: Chung-Yiu Yau, Haoming Liu, Hoi-To Wai
Abstract: Stochastic decentralized optimization algorithms often suffer from issues such as synchronization overhead and intermittent communication. This paper proposes a $\underline{\rm F}$ully $\underline{\rm S}$tochastic $\underline{\rm P}$rimal $\underline{\rm D}$ual gradient $\underline{\rm A}$lgorithm (FSPDA) that suggests an asynchronous decentralized procedure with (i) sparsified non-blocking communication on random undirected graphs and (ii) local stochastic gradient updates. FSPDA allows multiple local gradient steps to accelerate convergence to stationarity while finding a consensual solution with stochastic primal-dual updates. For problems with smooth (possibly non-convex) objective function, we show that FSPDA converges to an $\mathrm{\mathcal{O}( {\it \sigma /\sqrt{nT}} )}$-stationary solution after $\mathrm{\it T}$ iterations without assuming data heterogeneity. The performance of FSPDA is on par with state-of-the-art algorithms whose convergence depend on static graph and synchronous updates. To our best knowledge, FSPDA is the first asynchronous algorithm that converges exactly under the non-convex setting. Numerical experiments are presented to show the benefits of FSPDA.
Authors: Peizheng Li, Ioannis Mavromatis, Tim Farnham, Adnan Aijaz, Aftab Khan
Abstract: Seamless integration of artificial intelligence (AI) and machine learning (ML) techniques with wireless systems is a crucial step for 6G AInization. However, such integration faces challenges in terms of model functionality and lifecycle management. ML operations (MLOps) offer a systematic approach to tackle these challenges. Existing approaches toward implementing MLOps in a centralized platform often overlook the challenges posed by diverse learning paradigms and network heterogeneity. This article provides a new approach to MLOps targeting the intricacies of future wireless networks. Considering unique aspects of the future radio access network (RAN), we formulate three operational pipelines, namely reinforcement learning operations (RLOps), federated learning operations (FedOps), and generative AI operations (GenOps). These pipelines form the foundation for seamlessly integrating various learning/inference capabilities into networks. We outline the specific challenges and proposed solutions for each operation, facilitating large-scale deployment of AI-Native 6G networks.
Authors: Geoffrey Kasenbacher, Felix Ehret, Gerrit Ecke, Sebastian Otte
Abstract: The locally competitive algorithm (LCA) can solve sparse coding problems across a wide range of use cases. Recently, convolution-based LCA approaches have been shown to be highly effective for enhancing robustness for image recognition tasks in vision pipelines. To additionally maximize representational sparsity, LCA with hard-thresholding can be applied. While this combination often yields very good solutions satisfying an $\ell_0$ sparsity criterion, it comes with significant drawbacks for practical application: (i) LCA is very inefficient, typically requiring hundreds of optimization cycles for convergence; (ii) the use of hard-thresholding results in a non-convex loss function, which might lead to suboptimal minima. To address these issues, we propose the Locally Competitive Algorithm with State Warm-up via Predictive Priming (WARP-LCA), which leverages a predictor network to provide a suitable initial guess of the LCA state based on the current input. Our approach significantly improves both convergence speed and the quality of solutions, while maintaining and even enhancing the overall strengths of LCA. We demonstrate that WARP-LCA converges faster by orders of magnitude and reaches better minima compared to conventional LCA. Moreover, the learned representations are more sparse and exhibit superior properties in terms of reconstruction and denoising quality as well as robustness when applied in deep recognition pipelines. Furthermore, we apply WARP-LCA to image denoising tasks, showcasing its robustness and practical effectiveness. Our findings confirm that the naive use of LCA with hard-thresholding results in suboptimal minima, whereas initializing LCA with a predictive guess results in better outcomes. This research advances the field of biologically inspired deep learning by providing a novel approach to convolutional sparse coding.
Authors: Jacopo D'Ignazi, Andreas Kaltenbrunner, Yelena Mejova, Michele Tizzani, Kyriaki Kalimeri, Mariano Beir\'o, Pablo Arag\'on
Abstract: Over the last few years, content verification through reliable sources has become a fundamental need to combat disinformation. Here, we present a language-agnostic model designed to assess the reliability of sources across multiple language editions of Wikipedia. Utilizing editorial activity data, the model evaluates source reliability within different articles of varying controversiality such as Climate Change, COVID-19, History, Media, and Biology topics. Crafting features that express domain usage across articles, the model effectively predicts source reliability, achieving an F1 Macro score of approximately 0.80 for English and other high-resource languages. For mid-resource languages, we achieve 0.65 while the performance of low-resource languages varies; in all cases, the time the domain remains present in the articles (which we dub as permanence) is one of the most predictive features. We highlight the challenge of maintaining consistent model performance across languages of varying resource levels and demonstrate that adapting models from higher-resource languages can improve performance. This work contributes not only to Wikipedia's efforts in ensuring content verifiability but in ensuring reliability across diverse user-generated content in various language communities.
Authors: Alexandros Graikos, Nebojsa Jojic, Dimitris Samaras
Abstract: Diffusion models have dominated the field of large, generative image models, with the prime examples of Stable Diffusion and DALL-E 3 being widely adopted. These models have been trained to perform text-conditioned generation on vast numbers of image-caption pairs and as a byproduct, have acquired general knowledge about natural image statistics. However, when confronted with the task of constrained sampling, e.g. generating the right half of an image conditioned on the known left half, applying these models is a delicate and slow process, with previously proposed algorithms relying on expensive iterative operations that are usually orders of magnitude slower than text-based inference. This is counter-intuitive, as image-conditioned generation should rely less on the difficult-to-learn semantic knowledge that links captions and imagery, and should instead be achievable by lower-level correlations among image pixels. In practice, inverse models are trained or tuned separately for each inverse problem, e.g. by providing parts of images during training as an additional condition, to allow their application in realistic settings. However, we argue that this is not necessary and propose an algorithm for fast-constrained sampling in large pre-trained diffusion models (Stable Diffusion) that requires no expensive backpropagation operations through the model and produces results comparable even to the state-of-the-art \emph{tuned} models. Our method is based on a novel optimization perspective to sampling under constraints and employs a numerical approximation to the expensive gradients, previously computed using backpropagation, incurring significant speed-ups.
Authors: Sirui Chen, Shu Yu, Shengjie Zhao, Chaochao Lu
Abstract: Self-consciousness, the introspection of one's existence and thoughts, represents a high-level cognitive process. As language models advance at an unprecedented pace, a critical question arises: Are these models becoming self-conscious? Drawing upon insights from psychological and neural science, this work presents a practical definition of self-consciousness for language models and refines ten core concepts. Our work pioneers an investigation into self-consciousness in language models by, for the first time, leveraging causal structural games to establish the functional definitions of the ten core concepts. Based on our definitions, we conduct a comprehensive four-stage experiment: quantification (evaluation of ten leading models), representation (visualization of self-consciousness within the models), manipulation (modification of the models' representation), and acquisition (fine-tuning the models on core concepts). Our findings indicate that although models are in the early stages of developing self-consciousness, there is a discernible representation of certain concepts within their internal mechanisms. However, these representations of self-consciousness are hard to manipulate positively at the current stage, yet they can be acquired through targeted fine-tuning. Our datasets and code are at https://github.com/OpenCausaLab/SelfConsciousness.
Authors: Aya Ghoul, Kerstin Hammernik, Andreas Lingg, Patrick Krumm, Daniel Rueckert, Sergios Gatidis, Thomas K\"ustner
Abstract: In Magnetic Resonance Imaging (MRI), high temporal-resolved motion can be useful for image acquisition and reconstruction, MR-guided radiotherapy, dynamic contrast-enhancement, flow and perfusion imaging, and functional assessment of motion patterns in cardiovascular, abdominal, peristaltic, fetal, or musculoskeletal imaging. Conventionally, these motion estimates are derived through image-based registration, a particularly challenging task for complex motion patterns and high dynamic resolution. The accelerated scans in such applications result in imaging artifacts that compromise the motion estimation. In this work, we propose a novel self-supervised deep learning-based framework, dubbed the Local-All Pass Attention Network (LAPANet), for non-rigid motion estimation directly from the acquired accelerated Fourier space, i.e. k-space. The proposed approach models non-rigid motion as the cumulative sum of local translational displacements, following the Local All-Pass (LAP) registration technique. LAPANet was evaluated on cardiac motion estimation across various sampling trajectories and acceleration rates. Our results demonstrate superior accuracy compared to prior conventional and deep learning-based registration methods, accommodating as few as 2 lines/frame in a Cartesian trajectory and 3 spokes/frame in a non-Cartesian trajectory. The achieved high temporal resolution (less than 5 ms) for non-rigid motion opens new avenues for motion detection, tracking and correction in dynamic and real-time MRI applications.
Authors: M. Emrullah Ildiz, Halil Alperen Gozeten, Ege Onur Taga, Marco Mondelli, Samet Oymak
Abstract: A growing number of machine learning scenarios rely on knowledge distillation where one uses the output of a surrogate model as labels to supervise the training of a target model. In this work, we provide a sharp characterization of this process for ridgeless, high-dimensional regression, under two settings: (i) model shift, where the surrogate model is arbitrary, and (ii) distribution shift, where the surrogate model is the solution of empirical risk minimization with out-of-distribution data. In both cases, we characterize the precise risk of the target model through non-asymptotic bounds in terms of sample size and data distribution under mild conditions. As a consequence, we identify the form of the optimal surrogate model, which reveals the benefits and limitations of discarding weak features in a data-dependent fashion. In the context of weak-to-strong (W2S) generalization, this has the interpretation that (i) W2S training, with the surrogate as the weak model, can provably outperform training with strong labels under the same data budget, but (ii) it is unable to improve the data scaling law. We validate our results on numerical experiments both on ridgeless regression and on neural network architectures.
Authors: Sanghyuk Chun, Wonjae Kim, Song Park, Sangdoo Yun
Abstract: Vision-language models (VLMs) embed aligned image-text pairs into a joint space but often rely on deterministic embeddings, assuming a one-to-one correspondence between images and texts. This oversimplifies real-world relationships, which are inherently many-to-many, with multiple captions describing a single image and vice versa. We introduce Probabilistic Language-Image Pre-training (ProLIP), the first probabilistic VLM pre-trained on a billion-scale image-text dataset using only probabilistic objectives, achieving a strong zero-shot capability (e.g., 74.6% ImageNet zero-shot accuracy with ViT-B/16). ProLIP efficiently estimates uncertainty by an "uncertainty token" without extra parameters. We also introduce a novel inclusion loss that enforces distributional inclusion relationships between image-text pairs and between original and masked inputs. Experiments demonstrate that, by leveraging uncertainty estimates, ProLIP benefits downstream tasks and aligns with intuitive notions of uncertainty, e.g., shorter texts being more uncertain and more general inputs including specific ones. Utilizing text uncertainties, we further improve ImageNet accuracy from 74.6% to 75.8% (under a few-shot setting), supporting the practical advantages of our probabilistic approach. The code is available at https://github.com/naver-ai/prolip
Authors: Vittorio Erba, Emanuele Troiani, Luca Biggio, Antoine Maillard, Lenka Zdeborov\'a
Abstract: Current progress in artificial intelligence is centered around so-called large language models that consist of neural networks processing long sequences of high-dimensional vectors called tokens. Statistical physics provides powerful tools to study the functioning of learning with neural networks and has played a recognized role in the development of modern machine learning. The statistical physics approach relies on simplified and analytically tractable models of data. However, simple tractable models for long sequences of high-dimensional tokens are largely underexplored. Inspired by the crucial role models such as the single-layer teacher-student perceptron (aka generalized linear regression) played in the theory of fully connected neural networks, in this paper, we introduce and study the bilinear sequence regression (BSR) as one of the most basic models for sequences of tokens. We note that modern architectures naturally subsume the BSR model due to the skip connections. Building on recent methodological progress, we compute the Bayes-optimal generalization error for the model in the limit of long sequences of high-dimensional tokens, and provide a message-passing algorithm that matches this performance. We quantify the improvement that optimal learning brings with respect to vectorizing the sequence of tokens and learning via simple linear regression. We also unveil surprising properties of the gradient descent algorithms in the BSR model.
Authors: Sebasti\'an Espinel-R\'ios, Jos\'e Monta\~no L\'opez, Jos\'e L. Avalos
Abstract: This work presents an omics-driven modeling pipeline that integrates machine-learning tools to facilitate the dynamic modeling of multiscale biological systems. Random forests and permutation feature importance are proposed to mine omics datasets, guiding feature selection and dimensionality reduction for dynamic modeling. Continuous and differentiable machine-learning functions can be trained to link the reduced omics feature set to key components of the dynamic model, resulting in a hybrid model. As proof of concept, we apply this framework to a high-dimensional proteomics dataset of $\textit{Saccharomyces cerevisiae}$. After identifying key intracellular proteins that correlate with cell growth, targeted dynamic experiments are designed, and key model parameters are captured as functions of the selected proteins using Gaussian processes. This approach captures the dynamic behavior of yeast strains under varying proteome profiles while estimating the uncertainty in the hybrid model's predictions. The outlined modeling framework is adaptable to other scenarios, such as integrating additional layers of omics data for more advanced multiscale biological systems, or employing alternative machine-learning methods to handle larger datasets. Overall, this study outlines a strategy for leveraging omics data to inform multiscale dynamic modeling in systems biology and bioprocess engineering.
Authors: Zhaolin Gao, Joyce Zhou, Yijia Dai, Thorsten Joachims
Abstract: Many online platforms maintain user profiles for personalization. Unfortunately, these profiles are typically not interpretable or easily modifiable by the user. To remedy this shortcoming, we explore natural language-based user profiles, as they promise enhanced transparency and scrutability of recommender systems. While existing work has shown that language-based profiles from standard LLMs can be effective, such generalist LLMs are unlikely to be optimal for this task. In this paper, we introduce LangPTune, the first end-to-end learning method for training LLMs to produce language-based user profiles that optimize recommendation effectiveness. Through comprehensive evaluations of LangPTune across various training configurations and benchmarks, we demonstrate that our approach significantly outperforms existing profile-based methods. In addition, it approaches performance levels comparable to state-of-the-art, less transparent recommender systems, providing a robust and interpretable alternative to conventional systems. Finally, we validate the relative interpretability of these language-based user profiles through user studies involving crowdworkers and GPT-4-based evaluations. Implementation of LangPTune can be found at https://github.com/ZhaolinGao/LangPTune.
Authors: Alina A. Volnova, Patrick D. Aleo, Anastasia Lavrukhina, Etienne Russeil, Timofey Semenikhin, Emmanuel Gangler, Emille E. O. Ishida, Matwey V. Kornilov, Vladimir Korolev, Konstantin Malanchev, Maria V. Pruzhinskaya, Sreevarsha Sreejith
Abstract: SNAD is an international project with a primary focus on detecting astronomical anomalies within large-scale surveys, using active learning and other machine learning algorithms. The work carried out by SNAD not only contributes to the discovery and classification of various astronomical phenomena but also enhances our understanding and implementation of machine learning techniques within the field of astrophysics. This paper provides a review of the SNAD project and summarizes the advancements and achievements made by the team over several years.
Authors: Weijian Luo
Abstract: One-step text-to-image generator models offer advantages such as swift inference efficiency, flexible architectures, and state-of-the-art generation performance. In this paper, we study the problem of aligning one-step generator models with human preferences for the first time. Inspired by the success of reinforcement learning using human feedback (RLHF), we formulate the alignment problem as maximizing expected human reward functions while adding an Integral Kullback-Leibler divergence term to prevent the generator from diverging. By overcoming technical challenges, we introduce Diff-Instruct++ (DI++), the first, fast-converging and image data-free human preference alignment method for one-step text-to-image generators. We also introduce novel theoretical insights, showing that using CFG for diffusion distillation is secretly doing RLHF with DI++. Such an interesting finding brings understanding and potential contributions to future research involving CFG. In the experiment sections, we align both UNet-based and DiT-based one-step generators using DI++, which use the Stable Diffusion 1.5 and the PixelArt-$\alpha$ as the reference diffusion processes. The resulting DiT-based one-step text-to-image model achieves a strong Aesthetic Score of 6.19 and an Image Reward of 1.24 on the COCO validation prompt dataset. It also achieves a leading Human preference Score (HPSv2.0) of 28.48, outperforming other open-sourced models such as Stable Diffusion XL, DMD2, SD-Turbo, as well as PixelArt-$\alpha$. Both theoretical contributions and empirical evidence indicate that DI++ is a strong human-preference alignment approach for one-step text-to-image models.
Authors: Jussi Leinonen, Boris Bonev, Thorsten Kurth, Yair Cohen
Abstract: Weather and climate data are often available at limited temporal resolution, either due to storage limitations, or in the case of weather forecast models based on deep learning, their inherently long time steps. The coarse temporal resolution makes it difficult to capture rapidly evolving weather events. To address this limitation, we introduce an interpolation model that reconstructs the atmospheric state between two points in time for which the state is known. The model makes use of a novel network layer that modifies the adaptive Fourier neural operator (AFNO), which has been previously used in weather prediction and other applications of machine learning to physics problems. The modulated AFNO (ModAFNO) layer takes an embedding, here computed from the interpolation target time, as an additional input and applies a learned shift-scale operation inside the AFNO layers to adapt them to the target time. Thus, one model can be used to produce all intermediate time steps. Trained to interpolate between two time steps 6 h apart, the ModAFNO-based interpolation model produces 1 h resolution intermediate time steps that are visually nearly indistinguishable from the actual corresponding 1 h resolution data. The model reduces the RMSE loss of reconstructing the intermediate steps by approximately 50% compared to linear interpolation. We also demonstrate its ability to reproduce the statistics of extreme weather events such as hurricanes and heat waves better than 6 h resolution data. The ModAFNO layer is generic and is expected to be applicable to other problems, including weather forecasting with tunable lead time.
Authors: Caelan Garrett, Ajay Mandlekar, Bowen Wen, Dieter Fox
Abstract: Imitation learning from human demonstrations is an effective paradigm for robot manipulation, but acquiring large datasets is costly and resource-intensive, especially for long-horizon tasks. To address this issue, we propose SkillMimicGen (SkillGen), an automated system for generating demonstration datasets from a few human demos. SkillGen segments human demos into manipulation skills, adapts these skills to new contexts, and stitches them together through free-space transit and transfer motion. We also propose a Hybrid Skill Policy (HSP) framework for learning skill initiation, control, and termination components from SkillGen datasets, enabling skills to be sequenced using motion planning at test-time. We demonstrate that SkillGen greatly improves data generation and policy learning performance over a state-of-the-art data generation framework, resulting in the capability to produce data for large scene variations, including clutter, and agents that are on average 24% more successful. We demonstrate the efficacy of SkillGen by generating over 24K demonstrations across 18 task variants in simulation from just 60 human demonstrations, and training proficient, often near-perfect, HSP agents. Finally, we apply SkillGen to 3 real-world manipulation tasks and also demonstrate zero-shot sim-to-real transfer on a long-horizon assembly task. Videos, and more at https://skillgen.github.io.
Authors: Mingtong Zhang, Kaifeng Zhang, Yunzhu Li
Abstract: Videos of robots interacting with objects encode rich information about the objects' dynamics. However, existing video prediction approaches typically do not explicitly account for the 3D information from videos, such as robot actions and objects' 3D states, limiting their use in real-world robotic applications. In this work, we introduce a framework to learn object dynamics directly from multi-view RGB videos by explicitly considering the robot's action trajectories and their effects on scene dynamics. We utilize the 3D Gaussian representation of 3D Gaussian Splatting (3DGS) to train a particle-based dynamics model using Graph Neural Networks. This model operates on sparse control particles downsampled from the densely tracked 3D Gaussian reconstructions. By learning the neural dynamics model on offline robot interaction data, our method can predict object motions under varying initial configurations and unseen robot actions. The 3D transformations of Gaussians can be interpolated from the motions of control particles, enabling the rendering of predicted future object states and achieving action-conditioned video prediction. The dynamics model can also be applied to model-based planning frameworks for object manipulation tasks. We conduct experiments on various kinds of deformable materials, including ropes, clothes, and stuffed animals, demonstrating our framework's ability to model complex shapes and dynamics. Our project page is available at https://gs-dynamics.github.io.
Authors: Renato Ferreira Pinto Jr., Nathaniel Harms
Abstract: Consider two problems about an unknown probability distribution $p$: 1. How many samples from $p$ are required to test if $p$ is supported on $n$ elements or not? Specifically, given samples from $p$, determine whether it is supported on at most $n$ elements, or it is "$\epsilon$-far" (in total variation distance) from being supported on $n$ elements. 2. Given $m$ samples from $p$, what is the largest lower bound on its support size that we can produce? The best known upper bound for problem (1) uses a general algorithm for learning the histogram of the distribution $p$, which requires $\Theta(\tfrac{n}{\epsilon^2 \log n})$ samples. We show that testing can be done more efficiently than learning the histogram, using only $O(\tfrac{n}{\epsilon \log n} \log(1/\epsilon))$ samples, nearly matching the best known lower bound of $\Omega(\tfrac{n}{\epsilon \log n})$. This algorithm also provides a better solution to problem (2), producing larger lower bounds on support size than what follows from previous work. The proof relies on an analysis of Chebyshev polynomial approximations outside the range where they are designed to be good approximations, and the paper is intended as an accessible self-contained exposition of the Chebyshev polynomial method.
Authors: Muralikrishnna G. Sethuraman, Razieh Nabi, Faramarz Fekri
Abstract: Causal discovery in real-world systems, such as biological networks, is often complicated by feedback loops and incomplete data. Standard algorithms, which assume acyclic structures or fully observed data, struggle with these challenges. To address this gap, we propose MissNODAG, a differentiable framework for learning both the underlying cyclic causal graph and the missingness mechanism from partially observed data, including data missing not at random. Our framework integrates an additive noise model with an expectation-maximization procedure, alternating between imputing missing values and optimizing the observed data likelihood, to uncover both the cyclic structures and the missingness mechanism. We demonstrate the effectiveness of MissNODAG through synthetic experiments and an application to real-world gene perturbation data.
Authors: Jiaming Qiu, Ruiqi Wang, Brooks Hu, Roch Guerin, Chenyang Lu
Abstract: Recent advances in machine learning and hardware have produced embedded devices capable of performing real-time object detection with commendable accuracy. We consider a scenario in which embedded devices rely on an onboard object detector, but have the option to offload detection to a more powerful edge server when local accuracy is deemed too low. Resource constraints, however, limit the number of images that can be offloaded to the edge. Our goal is to identify which images to offload to maximize overall detection accuracy under those constraints. To that end, the paper introduces a reward metric designed to quantify potential accuracy improvements from offloading individual images, and proposes an efficient approach to make offloading decisions by estimating this reward based only on local detection results. The approach is computationally frugal enough to run on embedded devices, and empirical findings indicate that it outperforms existing alternatives in improving detection accuracy even when the fraction of offloaded images is small.
Authors: Muzhou Ma, Steven T. Flammia, John Preskill, Yu Tong
Abstract: We study the problem of learning a $k$-body Hamiltonian with $M$ unknown Pauli terms that are not necessarily geometrically local. We propose a protocol that learns the Hamiltonian to precision $\epsilon$ with total evolution time ${\mathcal{O}}(M^{1/2+1/p}/\epsilon)$ up to logarithmic factors, where the error is quantified by the $\ell^p$-distance between Pauli coefficients. Our learning protocol uses only single-qubit control operations and a GHZ state initial state, is non-adaptive, is robust against SPAM errors, and performs well even if $M$ and $k$ are not precisely known in advance or if the Hamiltonian is not exactly $M$-sparse. Methods from the classical theory of compressed sensing are used for efficiently identifying the $M$ terms in the Hamiltonian from among all possible $k$-body Pauli operators. We also provide a lower bound on the total evolution time needed in this learning task, and we discuss the operational interpretations of the $\ell^1$ and $\ell^2$ error metrics. In contrast to previous works, our learning protocol requires neither geometric locality nor any other relaxed locality conditions.
Authors: Tiange Liu, Nikola Surjanovic, Miguel Biron-Lattes, Alexandre Bouchard-C\^ot\'e, Trevor Campbell
Abstract: Many common Markov chain Monte Carlo (MCMC) kernels can be formulated using a deterministic involutive proposal with a step size parameter. Selecting an appropriate step size is often a challenging task in practice; and for complex multiscale targets, there may not be one choice of step size that works well globally. In this work, we address this problem with a novel class of involutive MCMC methods -- AutoStep MCMC -- that selects an appropriate step size at each iteration adapted to the local geometry of the target distribution. We prove that AutoStep MCMC is $\pi$-invariant and has other desirable properties under mild assumptions on the target distribution $\pi$ and involutive proposal. Empirical results examine the effect of various step size selection design choices, and show that AutoStep MCMC is competitive with state-of-the-art methods in terms of effective sample size per unit cost on a range of challenging target distributions.
Authors: Yatin Dandi, Luca Pesce, Hugo Cui, Florent Krzakala, Yue M. Lu, Bruno Loureiro
Abstract: A key property of neural networks is their capacity of adapting to data during training. Yet, our current mathematical understanding of feature learning and its relationship to generalization remain limited. In this work, we provide a random matrix analysis of how fully-connected two-layer neural networks adapt to the target function after a single, but aggressive, gradient descent step. We rigorously establish the equivalence between the updated features and an isotropic spiked random feature model, in the limit of large batch size. For the latter model, we derive a deterministic equivalent description of the feature empirical covariance matrix in terms of certain low-dimensional operators. This allows us to sharply characterize the impact of training in the asymptotic feature spectrum, and in particular, provides a theoretical grounding for how the tails of the feature spectrum modify with training. The deterministic equivalent further yields the exact asymptotic generalization error, shedding light on the mechanisms behind its improvement in the presence of feature learning. Our result goes beyond standard random matrix ensembles, and therefore we believe it is of independent technical interest. Different from previous work, our result holds in the challenging maximal learning rate regime, is fully rigorous and allows for finitely supported second layer initialization, which turns out to be crucial for studying the functional expressivity of the learned features. This provides a sharp description of the impact of feature learning in the generalization of two-layer neural networks, beyond the random features and lazy training regimes.
Authors: Jort Vincenti, Karim Abdel Sadek, Joan Velja, Matteo Nulli, Metod Jazbec
Abstract: Increasing the size of large language models (LLMs) has been shown to lead to better performance. However, this comes at the cost of slower and more expensive inference. Early-exiting is a promising approach for improving the efficiency of LLM inference by enabling next token prediction at intermediate layers. Yet, the large vocabulary size in modern LLMs makes the confidence estimation required for exit decisions computationally expensive, diminishing the efficiency gains. To address this, we propose dynamically pruning the vocabulary at test time for each token. Specifically, the vocabulary is pruned at one of the initial layers, and the smaller vocabulary is then used throughout the rest of the forward pass. Our experiments demonstrate that such post-hoc dynamic vocabulary pruning improves the efficiency of confidence estimation in early-exit LLMs while maintaining competitive performance.
Authors: Shivin Dass, Jiaheng Hu, Ben Abbatematteo, Peter Stone, Roberto Mart\'in-Mart\'in
Abstract: Many robot manipulation tasks require active or interactive exploration behavior in order to be performed successfully. Such tasks are ubiquitous in embodied domains, where agents must actively search for the information necessary for each stage of a task, e.g., moving the head of the robot to find information relevant to manipulation, or in multi-robot domains, where one scout robot may search for the information that another robot needs to make informed decisions. We identify these tasks with a new type of problem, factorized Contextual Markov Decision Processes, and propose DISaM, a dual-policy solution composed of an information-seeking policy that explores the environment to find the relevant contextual information and an information-receiving policy that exploits the context to achieve the manipulation goal. This factorization allows us to train both policies separately, using the information-receiving one to provide reward to train the information-seeking policy. At test time, the dual agent balances exploration and exploitation based on the uncertainty the manipulation policy has on what the next best action is. We demonstrate the capabilities of our dual policy solution in five manipulation tasks that require information-seeking behaviors, both in simulation and in the real-world, where DISaM significantly outperforms existing methods. More information at https://robin-lab.cs.utexas.edu/learning2look/.
Authors: Zhangheng Li, Keen You, Haotian Zhang, Di Feng, Harsh Agrawal, Xiujun Li, Mohana Prasad Sathya Moorthy, Jeff Nichols, Yinfei Yang, Zhe Gan
Abstract: Building a generalist model for user interface (UI) understanding is challenging due to various foundational issues, such as platform diversity, resolution variation, and data limitation. In this paper, we introduce Ferret-UI 2, a multimodal large language model (MLLM) designed for universal UI understanding across a wide range of platforms, including iPhone, Android, iPad, Webpage, and AppleTV. Building on the foundation of Ferret-UI, Ferret-UI 2 introduces three key innovations: support for multiple platform types, high-resolution perception through adaptive scaling, and advanced task training data generation powered by GPT-4o with set-of-mark visual prompting. These advancements enable Ferret-UI 2 to perform complex, user-centered interactions, making it highly versatile and adaptable for the expanding diversity of platform ecosystems. Extensive empirical experiments on referring, grounding, user-centric advanced tasks (comprising 9 subtasks $\times$ 5 platforms), GUIDE next-action prediction dataset, and GUI-World multi-platform benchmark demonstrate that Ferret-UI 2 significantly outperforms Ferret-UI, and also shows strong cross-platform transfer capabilities.
Authors: Cristian Daniel P\u{a}duraru, Antonio B\u{a}rb\u{a}lau, Radu Filipescu, Andrei Liviu Nicolicioiu, Elena Burceanu
Abstract: Datasets and pre-trained models come with intrinsic biases. Most methods rely on spotting them by analysing misclassified samples, in a semi-automated human-computer validation. In contrast, we propose ConceptDrift, a method which analyzes the weights of a linear probe, learned on top a foundational model. We capitalize on the weight update trajectory, which starts from the embedding of the textual representation of the class, and proceeds to drift towards embeddings that disclose hidden biases. Different from prior work, with this approach we can pin-point unwanted correlations from a dataset, providing more than just possible explanations for the wrong predictions. We empirically prove the efficacy of our method, by significantly improving zero-shot performance with biased-augmented prompting. Our method is not bounded to a single modality, and we experiment in this work with both image (Waterbirds, CelebA, Nico++) and text datasets (CivilComments).
Authors: Naitong Chen, Jonathan H. Huggins, Trevor Campbell
Abstract: A Bayesian coreset is a small, weighted subset of a data set that replaces the full data during inference to reduce computational cost. The state-of-the-art coreset construction algorithm, Coreset Markov chain Monte Carlo (Coreset MCMC), uses draws from an adaptive Markov chain targeting the coreset posterior to train the coreset weights via stochastic gradient optimization. However, the quality of the constructed coreset, and thus the quality of its posterior approximation, is sensitive to the stochastic optimization learning rate. In this work, we propose a learning-rate-free stochastic gradient optimization procedure, Hot-start Distance over Gradient (Hot DoG), for training coreset weights in Coreset MCMC without user tuning effort. Empirical results demonstrate that Hot DoG provides higher quality posterior approximations than other learning-rate-free stochastic gradient methods, and performs competitively to optimally-tuned ADAM.
Authors: Jialu Li, Yuanzhen Li, Neal Wadhwa, Yael Pritch, David E. Jacobs, Michael Rubinstein, Mohit Bansal, Nataniel Ruiz
Abstract: We introduce the concept of a generative infinite game, a video game that transcends the traditional boundaries of finite, hard-coded systems by using generative models. Inspired by James P. Carse's distinction between finite and infinite games, we leverage recent advances in generative AI to create Unbounded: a game of character life simulation that is fully encapsulated in generative models. Specifically, Unbounded draws inspiration from sandbox life simulations and allows you to interact with your autonomous virtual character in a virtual world by feeding, playing with and guiding it - with open-ended mechanics generated by an LLM, some of which can be emergent. In order to develop Unbounded, we propose technical innovations in both the LLM and visual generation domains. Specifically, we present: (1) a specialized, distilled large language model (LLM) that dynamically generates game mechanics, narratives, and character interactions in real-time, and (2) a new dynamic regional image prompt Adapter (IP-Adapter) for vision models that ensures consistent yet flexible visual generation of a character across multiple environments. We evaluate our system through both qualitative and quantitative analysis, showing significant improvements in character life simulation, user instruction following, narrative coherence, and visual consistency for both characters and the environments compared to traditional related approaches.
Authors: Sara Ghaboura, Ahmed Heakl, Omkar Thawakar, Ali Alharthi, Ines Riahi, Abduljalil Saif, Jorma Laaksonen, Fahad S. Khan, Salman Khan, Rao M. Anwer
Abstract: Recent years have witnessed a significant interest in developing large multimodal models (LMMs) capable of performing various visual reasoning and understanding tasks. This has led to the introduction of multiple LMM benchmarks to evaluate LMMs on different tasks. However, most existing LMM evaluation benchmarks are predominantly English-centric. In this work, we develop a comprehensive LMM evaluation benchmark for the Arabic language to represent a large population of over 400 million speakers. The proposed benchmark, named CAMEL-Bench, comprises eight diverse domains and 38 sub-domains including, multi-image understanding, complex visual perception, handwritten document understanding, video understanding, medical imaging, plant diseases, and remote sensing-based land use understanding to evaluate broad scenario generalizability. Our CAMEL-Bench comprises around 29,036 questions that are filtered from a larger pool of samples, where the quality is manually verified by native speakers to ensure reliable model assessment. We conduct evaluations of both closed-source, including GPT-4 series, and open-source LMMs. Our analysis reveals the need for substantial improvement, especially among the best open-source models, with even the closed-source GPT-4o achieving an overall score of 62%. Our benchmark and evaluation scripts are open-sourced.
Authors: Xin Fei, Wenzhao Zheng, Yueqi Duan, Wei Zhan, Masayoshi Tomizuka, Kurt Keutzer, Jiwen Lu
Abstract: We propose PixelGaussian, an efficient feed-forward framework for learning generalizable 3D Gaussian reconstruction from arbitrary views. Most existing methods rely on uniform pixel-wise Gaussian representations, which learn a fixed number of 3D Gaussians for each view and cannot generalize well to more input views. Differently, our PixelGaussian dynamically adapts both the Gaussian distribution and quantity based on geometric complexity, leading to more efficient representations and significant improvements in reconstruction quality. Specifically, we introduce a Cascade Gaussian Adapter to adjust Gaussian distribution according to local geometry complexity identified by a keypoint scorer. CGA leverages deformable attention in context-aware hypernetworks to guide Gaussian pruning and splitting, ensuring accurate representation in complex regions while reducing redundancy. Furthermore, we design a transformer-based Iterative Gaussian Refiner module that refines Gaussian representations through direct image-Gaussian interactions. Our PixelGaussian can effectively reduce Gaussian redundancy as input views increase. We conduct extensive experiments on the large-scale ACID and RealEstate10K datasets, where our method achieves state-of-the-art performance with good generalization to various numbers of views. Code: https://github.com/Barrybarry-Smith/PixelGaussian.
Authors: Hui-Po Wang, Sebastian U. Stich, Yang He, Mario Fritz
Abstract: Federated learning is a powerful distributed learning scheme that allows numerous edge devices to collaboratively train a model without sharing their data. However, training is resource-intensive for edge devices, and limited network bandwidth is often the main bottleneck. Prior work often overcomes the constraints by condensing the models or messages into compact formats, e.g., by gradient compression or distillation. In contrast, we propose ProgFed, the first progressive training framework for efficient and effective federated learning. It inherently reduces computation and two-way communication costs while maintaining the strong performance of the final models. We theoretically prove that ProgFed converges at the same asymptotic rate as standard training on full models. Extensive results on a broad range of architectures, including CNNs (VGG, ResNet, ConvNets) and U-nets, and diverse tasks from simple classification to medical image segmentation show that our highly effective training approach saves up to $20\%$ computation and up to $63\%$ communication costs for converged models. As our approach is also complimentary to prior work on compression, we can achieve a wide range of trade-offs by combining these techniques, showing reduced communication of up to $50\times$ at only $0.1\%$ loss in utility. Code is available at https://github.com/hui-po-wang/ProgFed.
Authors: Jim Smith, Richard J. Preen, Andrew McCarthy, Maha Albashir, Alba Crespi-Boixader, Shahzad Mumtaz, James Liley, Simon Rogers, Yola Jones
Abstract: We present SACRO-ML, an integrated suite of open source Python tools to facilitate the statistical disclosure control (SDC) of machine learning (ML) models trained on confidential data prior to public release. SACRO-ML combines (i) a SafeModel package that extends commonly used ML models to provide ante-hoc SDC by assessing the vulnerability of disclosure posed by the training regime; and (ii) an Attacks package that provides post-hoc SDC by rigorously assessing the empirical disclosure risk of a model through a variety of simulated attacks after training. The SACRO-ML code and documentation are available under an MIT license at https://github.com/AI-SDC/SACRO-ML
Authors: Luke Haliburton, Sinksar Ghebremedhin, Robin Welsch, Albrecht Schmidt, Sven Mayer
Abstract: In a world increasingly reliant on artificial intelligence, it is more important than ever to consider the ethical implications of artificial intelligence on humanity. One key under-explored challenge is labeler bias, which can create inherently biased datasets for training and subsequently lead to inaccurate or unfair decisions in healthcare, employment, education, and law enforcement. Hence, we conducted a study to investigate and measure the existence of labeler bias using images of people from different ethnicities and sexes in a labeling task. Our results show that participants possess stereotypes that influence their decision-making process and that labeler demographics impact assigned labels. We also discuss how labeler bias influences datasets and, subsequently, the models trained on them. Overall, a high degree of transparency must be maintained throughout the entire artificial intelligence training process to identify and correct biases in the data as early as possible.
Authors: Hui-Po Wang, Dingfan Chen, Raouf Kerkouche, Mario Fritz
Abstract: Conventional gradient-sharing approaches for federated learning (FL), such as FedAvg, rely on aggregation of local models and often face performance degradation under differential privacy (DP) mechanisms or data heterogeneity, which can be attributed to the inconsistency between the local and global objectives. To address this issue, we propose FedLAP-DP, a novel privacy-preserving approach for FL. Our formulation involves clients synthesizing a small set of samples that approximate local loss landscapes by simulating the gradients of real images within a local region. Acting as loss surrogates, these synthetic samples are aggregated on the server side to uncover the global loss landscape and enable global optimization. Building upon these insights, we offer a new perspective to enforce record-level differential privacy in FL. A formal privacy analysis demonstrates that FedLAP-DP incurs the same privacy costs as typical gradient-sharing schemes while achieving an improved trade-off between privacy and utility. Extensive experiments validate the superiority of our approach across various datasets with highly skewed distributions in both DP and non-DP settings. Beyond the promising performance, our approach presents a faster convergence speed compared to typical gradient-sharing methods and opens up the possibility of trading communication costs for better performance by sending a larger set of synthetic images. The source is available at \url{https://github.com/hui-po-wang/FedLAP-DP}.
Authors: Jhoan K. Hoyos-Osorio, Luis G. Sanchez-Giraldo
Abstract: Quantifying the difference between probability distributions is crucial in machine learning. However, estimating statistical divergences from empirical samples is challenging due to unknown underlying distributions. This work proposes the representation Jensen-Shannon divergence (RJSD), a novel measure inspired by the traditional Jensen-Shannon divergence. Our approach embeds data into a reproducing kernel Hilbert space (RKHS), representing distributions through uncentered covariance operators. We then compute the Jensen-Shannon divergence between these operators, thereby establishing a proper divergence measure between probability distributions in the input space. We provide estimators based on kernel matrices and empirical covariance matrices using Fourier features. Theoretical analysis reveals that RJSD is a lower bound on the Jensen-Shannon divergence, enabling variational estimation. Additionally, we show that RJSD is a higher-order extension of the maximum mean discrepancy (MMD), providing a more sensitive measure of distributional differences. Our experimental results demonstrate RJSD's superiority in two-sample testing, distribution shift detection, and unsupervised domain adaptation, outperforming state-of-the-art techniques. RJSD's versatility and effectiveness make it a promising tool for machine learning research and applications.
Authors: Farhad Mortezapour Shiri, Thinagaran Perumal, Norwati Mustapha, Raihani Mohamed
Abstract: Deep learning (DL) has emerged as a powerful subset of machine learning (ML) and artificial intelligence (AI), outperforming traditional ML methods, especially in handling unstructured and large datasets. Its impact spans across various domains, including speech recognition, healthcare, autonomous vehicles, cybersecurity, predictive analytics, and more. However, the complexity and dynamic nature of real-world problems present challenges in designing effective deep learning models. Consequently, several deep learning models have been developed to address different problems and applications. In this article, we conduct a comprehensive survey of various deep learning models, including Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Generative Models, Deep Reinforcement Learning (DRL), and Deep Transfer Learning. We examine the structure, applications, benefits, and limitations of each model. Furthermore, we perform an analysis using three publicly available datasets: IMDB, ARAS, and Fruit-360. We compare the performance of six renowned deep learning models: CNN, Simple RNN, Long Short-Term Memory (LSTM), Bidirectional LSTM, Gated Recurrent Unit (GRU), and Bidirectional GRU.
Authors: Haotian Jiang, Qianxiao Li
Abstract: The Transformer architecture is widely applied in sequence modeling applications, yet the theoretical understanding of its working principles remains limited. In this work, we investigate the approximation rate for single-layer Transformers with one head. We consider a class of non-linear relationships and identify a novel notion of complexity measures to establish an explicit Jackson-type approximation rate estimate for the Transformer. This rate reveals the structural properties of the Transformer and suggests the types of sequential relationships it is best suited for approximating. In particular, the results on approximation rates enable us to concretely analyze the differences between the Transformer and classical sequence modeling methods, such as recurrent neural networks.
Authors: Felix Dangel
Abstract: Despite their simple intuition, convolutions are more tedious to analyze than dense layers, which complicates the transfer of theoretical and algorithmic ideas to convolutions. We simplify convolutions by viewing them as tensor networks (TNs) that allow reasoning about the underlying tensor multiplications by drawing diagrams, manipulating them to perform function transformations like differentiation, and efficiently evaluating them with einsum. To demonstrate their simplicity and expressiveness, we derive diagrams of various autodiff operations and popular curvature approximations with full hyper-parameter support, batching, channel groups, and generalization to any convolution dimension. Further, we provide convolution-specific transformations based on the connectivity pattern which allow to simplify diagrams before evaluation. Finally, we probe performance. Our TN implementation accelerates a recently-proposed KFAC variant up to 4.5x while removing the standard implementation's memory overhead, and enables new hardware-efficient tensor dropout for approximate backpropagation.
Authors: Jiaxing Zhang, Zhuomin Chen, Hao Mei, Longchao Da, Dongsheng Luo, Hua Wei
Abstract: Graph regression is a fundamental task that has gained significant attention in various graph learning tasks. However, the inference process is often not easily interpretable. Current explanation techniques are limited to understanding Graph Neural Network (GNN) behaviors in classification tasks, leaving an explanation gap for graph regression models. In this work, we propose a novel explanation method to interpret the graph regression models (XAIG-R). Our method addresses the distribution shifting problem and continuously ordered decision boundary issues that hinder existing methods away from being applied in regression tasks. We introduce a novel objective based on the graph information bottleneck theory (GIB) and a new mix-up framework, which can support various GNNs and explainers in a model-agnostic manner. Additionally, we present a self-supervised learning strategy to tackle the continuously ordered labels in regression tasks. We evaluate our proposed method on three benchmark datasets and a real-life dataset introduced by us, and extensive experiments demonstrate its effectiveness in interpreting GNN models in regression tasks.
Authors: Feng Zhou, Antonio Cicone, Haomin Zhou
Abstract: Time-frequency analysis is an important and challenging task in many applications. Fourier and wavelet analysis are two classic methods that have achieved remarkable success in many fields. However, they also exhibit limitations when applied to nonlinear and non-stationary signals. To address this challenge, a series of nonlinear and adaptive methods, pioneered by the empirical mode decomposition method, have been proposed. The goal of these methods is to decompose a non-stationary signal into quasi-stationary components that enhance the clarity of features during time-frequency analysis. Recently, inspired by deep learning, we proposed a novel method called iterative residual convolutional neural network (IRCNN). IRCNN not only achieves more stable decomposition than existing methods but also handles batch processing of large-scale signals with low computational cost. Moreover, deep learning provides a unique perspective for non-stationary signal decomposition. In this study, we aim to further improve IRCNN with the help of several nimble techniques from deep learning and optimization to ameliorate the method and overcome some of the limitations of this technique.
Authors: Zikai Xiong, Niccol\`o Dalmasso, Alan Mishler, Vamsi K. Potluru, Tucker Balch, Manuela Veloso
Abstract: Recent years have seen a surge of machine learning approaches aimed at reducing disparities in model outputs across different subgroups. In many settings, training data may be used in multiple downstream applications by different users, which means it may be most effective to intervene on the training data itself. In this work, we present FairWASP, a novel pre-processing approach designed to reduce disparities in classification datasets without modifying the original data. FairWASP returns sample-level weights such that the reweighted dataset minimizes the Wasserstein distance to the original dataset while satisfying (an empirical version of) demographic parity, a popular fairness criterion. We show theoretically that integer weights are optimal, which means our method can be equivalently understood as duplicating or eliminating samples. FairWASP can therefore be used to construct datasets which can be fed into any classification method, not just methods which accept sample weights. Our work is based on reformulating the pre-processing task as a large-scale mixed-integer program (MIP), for which we propose a highly efficient algorithm based on the cutting plane method. Experiments demonstrate that our proposed optimization algorithm significantly outperforms state-of-the-art commercial solvers in solving both the MIP and its linear program relaxation. Further experiments highlight the competitive performance of FairWASP in reducing disparities while preserving accuracy in downstream classification settings.
Authors: Alessandro Barro
Abstract: We introduce the Pointer Q-Network (PQN), a hybrid neural architecture that integrates model-free Q-value policy approximation with Pointer Networks (Ptr-Nets) to enhance the optimality of attention-based sequence generation, focusing on long-term outcomes. This integration proves particularly effective in solving combinatorial optimization (CO) tasks, especially the Travelling Salesman Problem (TSP), which is the focus of our study. We address this challenge by defining a Markov Decision Process (MDP) compatible with PQN, which involves iterative graph embedding, encoding and decoding by an LSTM-based recurrent neural network. This process generates a context vector and computes raw attention scores, which are dynamically adjusted by Q-values calculated for all available state-action pairs before applying softmax. The resulting attention vector is utilized as an action distribution, with actions selected hinged to exploration-exploitation dynamic adaptibility of PQN. Our empirical results demonstrate the efficacy of this approach, also testing the model in unstable environments.
Authors: Shivam Barwey, Hojin Kim, Romit Maulik
Abstract: Data-driven surrogate modeling has surged in capability in recent years with the emergence of graph neural networks (GNNs), which can operate directly on mesh-based representations of data. The goal of this work is to introduce an interpretability enhancement procedure for GNNs, with application to unstructured mesh-based fluid dynamics modeling. Given a black-box baseline GNN model, the end result is an interpretable GNN model that isolates regions in physical space, corresponding to sub-graphs, that are intrinsically linked to the forecasting task while retaining the predictive capability of the baseline. These structures identified by the interpretable GNNs are adaptively produced in the forward pass and serve as explainable links between the baseline model architecture, the optimization goal, and known problem-specific physics. Additionally, through a regularization procedure, the interpretable GNNs can also be used to identify, during inference, graph nodes that correspond to a majority of the anticipated forecasting error, adding a novel interpretable error-tagging capability to baseline models. Demonstrations are performed using unstructured flow field data sourced from flow over a backward-facing step at high Reynolds numbers, with geometry extrapolations demonstrated for ramp and wall-mounted cube configurations.
Authors: Joschka Herteux, Christoph R\"ath, Giulia Martini, Amine Baha, Kyriacos Koupparis, Ilaria Lauzana, Duccio Piovani
Abstract: Early warning systems are an essential tool for effective humanitarian action. Advance warnings on impending disasters facilitate timely and targeted response which help save lives and livelihoods. In this work we present a quantitative methodology to forecast levels of food consumption for 60 consecutive days, at the sub-national level, in four countries: Mali, Nigeria, Syria, and Yemen. The methodology is built on publicly available data from the World Food Programme's global hunger monitoring system which collects, processes, and displays daily updates on key food security metrics, conflict, weather events, and other drivers of food insecurity. In this study we assessed the performance of various models including Autoregressive Integrated Moving Average (ARIMA), Extreme Gradient Boosting (XGBoost), Long Short Term Memory (LSTM) Network, Convolutional Neural Network (CNN), and Reservoir Computing (RC), by comparing their Root Mean Squared Error (RMSE) metrics. Our findings highlight Reservoir Computing as a particularly well-suited model in the field of food security given both its notable resistance to over-fitting on limited data samples and its efficient training capabilities. The methodology we introduce establishes the groundwork for a global, data-driven early warning system designed to anticipate and detect food insecurity.
Authors: Rui Xue, Xipeng Shen, Ruozhou Yu, Xiaorui Liu
Abstract: Learning from Text-Attributed Graphs (TAGs) has attracted significant attention due to its wide range of real-world applications. The rapid evolution of language models (LMs) has revolutionized the way we process textual data, which indicates a strong potential to replace shallow text embedding generally used in Graph Neural Networks (GNNs). However, we find that existing LM approaches that exploit text information in graphs suffer from inferior computation and data efficiency. In this study, we introduce LEADING, a novel and efficient approach for end-to-end fine-tuning of language models on TAGs. To enhance data efficiency, LEADING efficiently transfers rich knowledge from LMs to downstream graph learning tasks with limited labeled data by employing end-to-end training of LMs and GNNs in a semi-supervised learning setting. To address associated computation efficiency issues, it introduces two techniques: neighbor decoupling targeting LMs and implicit graph modeling targeting GNNs, respectively. Our proposed approach demonstrates superior performance, achieving state-of-the-art (SOTA) results on the ogbn-arxiv leaderboard, while maintaining computation cost and memory overhead comparable to graph-less fine-tuning of LMs. Through comprehensive experiments, we showcase its superior computation and data efficiency, presenting a promising solution for various LMs and graph learning tasks on TAGs.
Authors: Shiji Zhao, Xizhe Wang, Ranjie Duan, Xingxing Wei
Abstract: Adversarial Training (AT) has been widely proved to be an effective method to improve the adversarial robustness against adversarial examples for Deep Neural Networks (DNNs). As a variant of AT, Adversarial Robustness Distillation (ARD) has demonstrated its superior performance in improving the robustness of small student models with the guidance of large teacher models. However, both AT and ARD encounter the robust fairness problem: these models exhibit strong robustness when facing part of classes (easy class), but weak robustness when facing others (hard class). In this paper, we give an in-depth analysis of the potential factors and argue that the smoothness degree of samples' soft labels for different classes (i.e., hard class or easy class) will affect the robust fairness of DNNs from both empirical observation and theoretical analysis. Based on the above finding, we propose an Anti-Bias Soft Label Distillation (ABSLD) method to mitigate the adversarial robust fairness problem within the framework of Knowledge Distillation (KD). Specifically, ABSLD adaptively reduces the student's error risk gap between different classes to achieve fairness by adjusting the class-wise smoothness degree of samples' soft labels during the training process, and the smoothness degree of soft labels is controlled by assigning different temperatures in KD to different classes. Extensive experiments demonstrate that ABSLD outperforms state-of-the-art AT, ARD, and robust fairness methods in the comprehensive metric (Normalized Standard Deviation) of robustness and fairness.
Authors: Anupriya Kumari, Devansh Bhardwaj, Sukrit Jindal
Abstract: Machine learning models have demonstrated remarkable success across diverse domains but remain vulnerable to adversarial attacks. Empirical defense mechanisms often fail, as new attacks constantly emerge, rendering existing defenses obsolete, shifting the focus to certification-based defenses. Randomized smoothing has emerged as a promising technique among notable advancements. This study reviews the theoretical foundations and empirical effectiveness of randomized smoothing and its derivatives in verifying machine learning classifiers from a perspective of scalability. We provide an in-depth exploration of the fundamental concepts underlying randomized smoothing, highlighting its theoretical guarantees in certifying robustness against adversarial perturbations and discuss the challenges of existing methodologies.
Authors: Yinglun Xu, Gagandeep Singh
Abstract: Preference-based reinforcement learning (PBRL) in the offline setting has succeeded greatly in industrial applications such as chatbots. A two-step learning framework where one applies a reinforcement learning step after a reward modeling step has been widely adopted for the problem. However, such a method faces challenges from the risk of reward hacking and the complexity of reinforcement learning. To overcome the challenge, our insight is that both challenges come from the state-actions not supported in the dataset. Such state-actions are unreliable and increase the complexity of the reinforcement learning problem at the second step. Based on the insight, we develop a novel two-step learning method called PRC: preference-based reinforcement learning with constrained actions. The high-level idea is to limit the reinforcement learning agent to optimize over a constrained action space that excludes the out-of-distribution state-actions. We empirically verify that our method has high learning efficiency on various datasets in robotic control environments.
Authors: Michele Caprio, Maryam Sultana, Eleni Elia, Fabio Cuzzolin
Abstract: Statistical learning theory is the foundation of machine learning, providing theoretical bounds for the risk of models learned from a (single) training set, assumed to issue from an unknown probability distribution. In actual deployment, however, the data distribution may (and often does) vary, causing domain adaptation/generalization issues. In this paper we lay the foundations for a `credal' theory of learning, using convex sets of probabilities (credal sets) to model the variability in the data-generating distribution. Such credal sets, we argue, may be inferred from a finite sample of training sets. Bounds are derived for the case of finite hypotheses spaces (both assuming realizability or not), as well as infinite model spaces, which directly generalize classical results.
Authors: Andrea Schioppa
Abstract: The study of modern machine learning models often necessitates storing vast quantities of gradients or Hessian vector products (HVPs). Traditional sketching methods struggle to scale under these memory constraints. We present a novel framework for scalable gradient and HVP sketching, tailored for modern hardware. We provide theoretical guarantees and demonstrate the power of our methods in applications like training data attribution, Hessian spectrum analysis, and intrinsic dimension computation for pre-trained language models. Our work sheds new light on the behavior of pre-trained language models, challenging assumptions about their intrinsic dimensionality and Hessian properties.
Authors: Yinglun Xu, Rohan Gumaste, Gagandeep Singh
Abstract: We study the problem of universal black-boxed reward poisoning attacks against general offline reinforcement learning with deep neural networks. We consider a black-box threat model where the attacker is entirely oblivious to the learning algorithm, and its budget is limited by constraining the amount of corruption at each data point and the total perturbation. We require the attack to be universally efficient against any efficient algorithms that might be used by the agent. We propose an attack strategy called the `policy contrast attack.' The idea is to find low- and high-performing policies covered by the dataset and make them appear to be high- and low-performing to the agent, respectively. To the best of our knowledge, we propose the first universal black-box reward poisoning attack in the general offline RL setting. We provide theoretical insights on the attack design and empirically show that our attack is efficient against current state-of-the-art offline RL algorithms in different learning datasets.
Authors: Yuxuan Wang, Haixu Wu, Jiaxiang Dong, Guo Qin, Haoran Zhang, Yong Liu, Yunzhong Qiu, Jianmin Wang, Mingsheng Long
Abstract: Deep models have demonstrated remarkable performance in time series forecasting. However, due to the partially-observed nature of real-world applications, solely focusing on the target of interest, so-called endogenous variables, is usually insufficient to guarantee accurate forecasting. Notably, a system is often recorded into multiple variables, where the exogenous variables can provide valuable external information for endogenous variables. Thus, unlike well-established multivariate or univariate forecasting paradigms that either treat all the variables equally or ignore exogenous information, this paper focuses on a more practical setting: time series forecasting with exogenous variables. We propose a novel approach, TimeXer, to ingest external information to enhance the forecasting of endogenous variables. With deftly designed embedding layers, TimeXer empowers the canonical Transformer with the ability to reconcile endogenous and exogenous information, where patch-wise self-attention and variate-wise cross-attention are used simultaneously. Moreover, global endogenous tokens are learned to effectively bridge the causal information underlying exogenous series into endogenous temporal patches. Experimentally, TimeXer achieves consistent state-of-the-art performance on twelve real-world forecasting benchmarks and exhibits notable generality and scalability. Code is available at this repository: https://github.com/thuml/TimeXer.
Authors: Th\'eo Vincent, Daniel Palenicek, Boris Belousov, Jan Peters, Carlo D'Eramo
Abstract: The vast majority of Reinforcement Learning methods is largely impacted by the computation effort and data requirements needed to obtain effective estimates of action-value functions, which in turn determine the quality of the overall performance and the sample-efficiency of the learning procedure. Typically, action-value functions are estimated through an iterative scheme that alternates the application of an empirical approximation of the Bellman operator and a subsequent projection step onto a considered function space. It has been observed that this scheme can be potentially generalized to carry out multiple iterations of the Bellman operator at once, benefiting the underlying learning algorithm. However, till now, it has been challenging to effectively implement this idea, especially in high-dimensional problems. In this paper, we introduce iterated $Q$-Network (i-QN), a novel principled approach that enables multiple consecutive Bellman updates by learning a tailored sequence of action-value functions where each serves as the target for the next. We show that i-QN is theoretically grounded and that it can be seamlessly used in value-based and actor-critic methods. We empirically demonstrate the advantages of i-QN in Atari $2600$ games and MuJoCo continuous control problems.
Authors: Rahul Saxena, Taeyoun Kim, Aman Mehra, Christina Baek, Zico Kolter, Aditi Raghunathan
Abstract: Estimating the out-of-distribution performance in regimes where labels are scarce is critical to safely deploy foundation models. Recently, it was shown that ensembles of neural networks observe the phenomena "agreement-on-the-line", which can be leveraged to reliably predict OOD performance without labels. However, in contrast to classical neural networks that are trained on in-distribution data from scratch for numerous epochs, foundation models undergo minimal finetuning from heavily pretrained weights, which may reduce the ensemble diversity needed to observe agreement-on-the-line. In our work, we demonstrate that when lightly finetuning multiple runs from a single foundation model, the choice of randomness during training (linear head initialization, data ordering, and data subsetting) can lead to drastically different levels of agreement-on-the-line in the resulting ensemble. Surprisingly, only random head initialization is able to reliably induce agreement-on-the-line in finetuned foundation models across vision and language benchmarks. Second, we demonstrate that ensembles of multiple foundation models pretrained on different datasets but finetuned on the same task can also show agreement-on-the-line. In total, by careful construction of a diverse ensemble, we can utilize agreement-on-the-line-based methods to predict the OOD performance of foundation models with high precision.
Authors: Jackson Burns, William Green
Abstract: Quantitative Structure Property Relationship studies aim to define a mapping between molecular structure and arbitrary quantities of interest. This was historically accomplished via the development of descriptors which requires significant domain expertise and struggles to generalize. Thus the field has morphed into Molecular Property Prediction and been given over to learned representations which are highly generalizable. The paper introduces fastprop, a DeepQSPR framework which uses a cogent set of molecular level descriptors to meet and exceed the performance of learned representations on diverse datasets in dramatically less time. fastprop is freely available on github at github.com/JacksonBurns/fastprop.
Authors: Torbj{\o}rn Smith, Olav Egeland
Abstract: A method for learning Hamiltonian dynamics from a limited and noisy dataset is proposed. The method learns a Hamiltonian vector field on a reproducing kernel Hilbert space (RKHS) of inherently Hamiltonian vector fields, and in particular, odd Hamiltonian vector fields. This is done with a symplectic kernel, and it is shown how the kernel can be modified to an odd symplectic kernel to impose the odd symmetry. A random feature approximation is developed for the proposed odd kernel to reduce the problem size. The performance of the method is validated in simulations for three Hamiltonian systems. It is demonstrated that the use of an odd symplectic kernel improves prediction accuracy and data efficiency, and that the learned vector fields are Hamiltonian and exhibit the imposed odd symmetry characteristics.
Authors: Yuchen Zhu, Yufeng Zhang, Zhaoran Wang, Zhuoran Yang, Xiaohong Chen
Abstract: This paper studies minimax optimization problems defined over infinite-dimensional function classes of overparameterized two-layer neural networks. In particular, we consider the minimax optimization problem stemming from estimating linear functional equations defined by conditional expectations, where the objective functions are quadratic in the functional spaces. We address (i) the convergence of the stochastic gradient descent-ascent algorithm and (ii) the representation learning of the neural networks. We establish convergence under the mean-field regime by considering the continuous-time and infinite-width limit of the optimization dynamics. Under this regime, the stochastic gradient descent-ascent corresponds to a Wasserstein gradient flow over the space of probability measures defined over the space of neural network parameters. We prove that the Wasserstein gradient flow converges globally to a stationary point of the minimax objective at a $O(T^{-1} + \alpha^{-1})$ sublinear rate, and additionally finds the solution to the functional equation when the regularizer of the minimax objective is strongly convex. Here $T$ denotes the time and $\alpha$ is a scaling parameter of the neural networks. In terms of representation learning, our results show that the feature representation induced by the neural networks is allowed to deviate from the initial one by the magnitude of $O(\alpha^{-1})$, measured in terms of the Wasserstein distance. Finally, we apply our general results to concrete examples including policy evaluation, nonparametric instrumental variable regression, asset pricing, and adversarial Riesz representer estimation.
Authors: Tong Nie, Guoyang Qin, Wei Ma, Jian Sun
Abstract: Spatiotemporal Traffic Data (STTD) measures the complex dynamical behaviors of the multiscale transportation system. Existing methods aim to reconstruct STTD using low-dimensional models. However, they are limited to data-specific dimensions or source-dependent patterns, restricting them from unifying representations. Here, we present a novel paradigm to address the STTD learning problem by parameterizing STTD as an implicit neural representation. To discern the underlying dynamics in low-dimensional regimes, coordinate-based neural networks that can encode high-frequency structures are employed to directly map coordinates to traffic variables. To unravel the entangled spatial-temporal interactions, the variability is decomposed into separate processes. We further enable modeling in irregular spaces such as sensor graphs using spectral embedding. Through continuous representations, our approach enables the modeling of a variety of STTD with a unified input, thereby serving as a generalized learner of the underlying traffic dynamics. It is also shown that it can learn implicit low-rank priors and smoothness regularization from the data, making it versatile for learning different dominating data patterns. We validate its effectiveness through extensive experiments in real-world scenarios, showcasing applications from corridor to network scales. Empirical results not only indicate that our model has significant superiority over conventional low-rank models, but also highlight that the versatility of the approach extends to different data domains, output resolutions, and network topologies. Comprehensive model analyses provide further insight into the inductive bias of STTD. We anticipate that this pioneering modeling perspective could lay the foundation for universal representation of STTD in various real-world tasks. Code is available at https://github.com/tongnie/traffic_dynamics.
Authors: Rishabh Goel, YiZi Xiao, Ramin Ramezani
Abstract: Random numbers are incredibly important in a variety of fields, and the need for their validation remains important for safety. A Quantum Random Number Generator (QRNG) can theoretically generate truly random numbers, however their quality still needs to be thoroughly validated. Generally, the task of validating random numbers has been delegated to different statistical tests such as the tests from the NIST Statistical Test Suite (STS), which are often slow and only perform one test at a time. Our work presents a deep learning model utilizing the Transformer architecture that 1) performs multiple NIST STS tests at once, and 2) runs much faster. This model outputs multi-label classification results on passing these statistical tests. We performed a thorough hyper-parameter optimization to converge on the best possible model and as a result, achieved a high degree of accuracy with a Macro F1-score of above 0.96. We also compared this model to a conventional deep learning method (Long Short Term Memory Recurrent Neural Networks) to quantify randomness and showed our model achieved similar performances while being much more efficient and scalable. The high performance and efficiency of this Transformer-based deep learning model showed that it can be a viable replacement for the NIST STS for validating random numbers.
Authors: Alvin Heng, Alexandre H. Thiery, Harold Soh
Abstract: Out-of-distribution (OOD) detection is a critical task in machine learning that seeks to identify abnormal samples. Traditionally, unsupervised methods utilize a deep generative model for OOD detection. However, such approaches require a new model to be trained for each inlier dataset. This paper explores whether a single model can perform OOD detection across diverse tasks. To that end, we introduce Diffusion Paths (DiffPath), which uses a single diffusion model originally trained to perform unconditional generation for OOD detection. We introduce a novel technique of measuring the rate-of-change and curvature of the diffusion paths connecting samples to the standard normal. Extensive experiments show that with a single model, DiffPath is competitive with prior work using individual models on a variety of OOD tasks involving different distributions. Our code is publicly available at https://github.com/clear-nus/diffpath.
Authors: Zhicheng Zhang, Yong Wang, Shaoqi Tan, Bowei Xia, Yujie Luo
Abstract: Transformer-based models for long sequence time series forecasting problems have gained significant attention due to their exceptional forecasting precision. However, the self-attention mechanism introduces challenges in terms of computational efficiency due to its quadratic time complexity. To address these issues, we propose a novel architectural framework that enhances Transformer models through the integration of Surrogate Attention Blocks (SAB) and Surrogate Feed-Forward Neural Network Blocks (SFB). They replace the self-attention and feed-forward layer by leveraging structured matrices that reduce both time and space complexity while maintaining the expressive power of the original self-attention mechanism and feed-forward network. The equivalence of this substitution is fully demonstrated. Extensive experiments on nine Transformer variants across five distinct time series tasks demonstrate an average performance improvement of 9.45%, alongside a 46% reduction in model size. These results confirm the efficacy of our surrogate-based approach in maintaining prediction accuracy while significantly boosting computational efficiency.
Authors: Sepehr Sharifi, Andrea Stocco, Lionel C. Briand
Abstract: In learning-enabled autonomous systems, safety monitoring of learned components is crucial to ensure their outputs do not lead to system safety violations, given the operational context of the system. However, developing a safety monitor for practical deployment in real-world applications is challenging. This is due to limited access to internal workings and training data of the learned component. Furthermore, safety monitors should predict safety violations with low latency, while consuming a reasonable amount of computation. To address the challenges, we propose a safety monitoring method based on probabilistic time series forecasting. Given the learned component outputs and an operational context, we empirically investigate different Deep Learning (DL)-based probabilistic forecasting to predict the objective measure capturing the satisfaction or violation of a safety requirement (safety metric). We empirically evaluate safety metric and violation prediction accuracy, and inference latency and resource usage of four state-of-the-art models, with varying horizons, using autonomous aviation and autonomous driving case studies. Our results suggest that probabilistic forecasting of safety metrics, given learned component outputs and scenarios, is effective for safety monitoring. Furthermore, for both case studies, Temporal Fusion Transformer (TFT) was the most accurate model for predicting imminent safety violations, with acceptable latency and resource consumption.
Authors: Puning Zhao, Lifeng Lai, Li Shen, Qingming Li, Jiafei Wu, Zhe Liu
Abstract: Privacy protection of users' entire contribution of samples is important in distributed systems. The most effective approach is the two-stage scheme, which finds a small interval first and then gets a refined estimate by clipping samples into the interval. However, the clipping operation induces bias, which is serious if the sample distribution is heavy-tailed. Besides, users with large local sample sizes can make the sensitivity much larger, thus the method is not suitable for imbalanced users. Motivated by these challenges, we propose a Huber loss minimization approach to mean estimation under user-level differential privacy. The connecting points of Huber loss can be adaptively adjusted to deal with imbalanced users. Moreover, it avoids the clipping operation, thus significantly reducing the bias compared with the two-stage approach. We provide a theoretical analysis of our approach, which gives the noise strength needed for privacy protection, as well as the bound of mean squared error. The result shows that the new method is much less sensitive to the imbalance of user-wise sample sizes and the tail of sample distributions. Finally, we perform numerical experiments to validate our theoretical analysis.
Authors: Junghyuk Yeom, Yonghyeon Jo, Jungmo Kim, Sanghyeon Lee, Seungyul Han
Abstract: Constraint-based offline reinforcement learning (RL) involves policy constraints or imposing penalties on the value function to mitigate overestimation errors caused by distributional shift. This paper focuses on a limitation in existing offline RL methods with penalized value function, indicating the potential for underestimation bias due to unnecessary bias introduced in the value function. To address this concern, we propose Exclusively Penalized Q-learning (EPQ), which reduces estimation bias in the value function by selectively penalizing states that are prone to inducing estimation errors. Numerical results show that our method significantly reduces underestimation bias and improves performance in various offline control tasks compared to other offline RL methods
Authors: Emanuele Troiani, Yatin Dandi, Leonardo Defilippis, Lenka Zdeborov\'a, Bruno Loureiro, Florent Krzakala
Abstract: Multi-index models - functions which only depend on the covariates through a non-linear transformation of their projection on a subspace - are a useful benchmark for investigating feature learning with neural nets. This paper examines the theoretical boundaries of efficient learnability in this hypothesis class, focusing on the minimum sample complexity required for weakly recovering their low-dimensional structure with first-order iterative algorithms, in the high-dimensional regime where the number of samples $n\!=\!\alpha d$ is proportional to the covariate dimension $d$. Our findings unfold in three parts: (i) we identify under which conditions a trivial subspace can be learned with a single step of a first-order algorithm for any $\alpha\!>\!0$; (ii) if the trivial subspace is empty, we provide necessary and sufficient conditions for the existence of an easy subspace where directions that can be learned only above a certain sample complexity $\alpha\!>\!\alpha_c$, where $\alpha_{c}$ marks a computational phase transition. In a limited but interesting set of really hard directions -- akin to the parity problem -- $\alpha_c$ is found to diverge. Finally, (iii) we show that interactions between different directions can result in an intricate hierarchical learning phenomenon, where directions can be learned sequentially when coupled to easier ones. We discuss in detail the grand staircase picture associated to these functions (and contrast it with the original staircase one). Our theory builds on the optimality of approximate message-passing among first-order iterative methods, delineating the fundamental learnability limit across a broad spectrum of algorithms, including neural networks trained with gradient descent, which we discuss in this context.
Authors: Kaiwen Zheng, Guande He, Jianfei Chen, Fan Bao, Jun Zhu
Abstract: Denoising diffusion bridge models (DDBMs) are a powerful variant of diffusion models for interpolating between two arbitrary paired distributions given as endpoints. Despite their promising performance in tasks like image translation, DDBMs require a computationally intensive sampling process that involves the simulation of a (stochastic) differential equation through hundreds of network evaluations. In this work, we take the first step in fast sampling of DDBMs without extra training, motivated by the well-established recipes in diffusion models. We generalize DDBMs via a class of non-Markovian diffusion bridges defined on the discretized timesteps concerning sampling, which share the same marginal distributions and training objectives, and give rise to generative processes ranging from stochastic to deterministic, resulting in diffusion bridge implicit models (DBIMs). DBIMs are not only up to 25$\times$ faster than the vanilla sampler of DDBMs but also induce a novel, simple, and insightful form of ordinary differential equation (ODE) which inspires high-order numerical solvers. Moreover, DBIMs maintain the generation diversity in a distinguished way, by using a booting noise in the initial sampling step, which enables faithful encoding, reconstruction, and semantic interpolation in image translation tasks. Code is available at \url{https://github.com/thu-ml/DBIM}.
Authors: Li-Wen Chang, Wenlei Bao, Qi Hou, Chengquan Jiang, Ningxin Zheng, Yinmin Zhong, Xuanrun Zhang, Zuquan Song, Chengji Yao, Ziheng Jiang, Haibin Lin, Xin Jin, Xin Liu
Abstract: Large deep learning models have demonstrated strong ability to solve many tasks across a wide range of applications. Those large models typically require training and inference to be distributed. Tensor parallelism is a common technique partitioning computation of an operation or layer across devices to overcome the memory capacity limitation of a single processor, and/or to accelerate computation to meet a certain latency requirement. However, this kind of parallelism introduces additional communication that might contribute a significant portion of overall runtime. Thus limits scalability of this technique within a group of devices with high speed interconnects, such as GPUs with NVLinks in a node. This paper proposes a novel method, Flux, to significantly hide communication latencies with dependent computations for GPUs. Flux over-decomposes communication and computation operations into much finer-grained operations and further fuses them into a larger kernel to effectively hide communication without compromising kernel efficiency. Flux can potentially overlap up to 96% of communication given a fused kernel. Overall, it can achieve up to 1.24x speedups for training over Megatron-LM on a cluster of 128 GPUs with various GPU generations and interconnects, and up to 1.66x and 1.30x speedups for prefill and decoding inference over vLLM on a cluster with 8 GPUs with various GPU generations and interconnects.
Authors: Claude Formanek, Callum Rhys Tilbury, Louise Beyers, Jonathan Shock, Arnu Pretorius
Abstract: Offline multi-agent reinforcement learning (MARL) is an emerging field with great promise for real-world applications. Unfortunately, the current state of research in offline MARL is plagued by inconsistencies in baselines and evaluation protocols, which ultimately makes it difficult to accurately assess progress, trust newly proposed innovations, and allow researchers to easily build upon prior work. In this paper, we firstly identify significant shortcomings in existing methodologies for measuring the performance of novel algorithms through a representative study of published offline MARL work. Secondly, by directly comparing to this prior work, we demonstrate that simple, well-implemented baselines can achieve state-of-the-art (SOTA) results across a wide range of tasks. Specifically, we show that on 35 out of 47 datasets used in prior work (almost 75% of cases), we match or surpass the performance of the current purported SOTA. Strikingly, our baselines often substantially outperform these more sophisticated algorithms. Finally, we correct for the shortcomings highlighted from this prior work by introducing a straightforward standardised methodology for evaluation and by providing our baseline implementations with statistically robust results across several scenarios, useful for comparisons in future work. Our proposal includes simple and sensible steps that are easy to adopt, which in combination with solid baselines and comparative results, could substantially improve the overall rigour of empirical science in offline MARL moving forward.
Authors: Yinglun Xu, David Zhu, Rohan Gumaste, Gagandeep Singh
Abstract: Offline reinforcement learning has become one of the most practical RL settings. However, most existing works on offline RL focus on the standard setting with scalar reward feedback. It remains unknown how to universally transfer the existing rich understanding of offline RL from the reward-based to the preference-based setting. In this work, we propose a general framework to bridge this gap. Our key insight is transforming preference feedback to scalar rewards via binary reward labeling (BRL), and then any reward-based offline RL algorithms can be applied to the dataset with the reward labels. The information loss during the feedback signal transition is minimized with binary reward labeling in the practical learning scenarios. We theoretically show the connection between several recent PBRL techniques and our framework combined with specific offline RL algorithms. By combining reward labeling with different algorithms, our framework can lead to new and potentially more efficient offline PBRL algorithms. We empirically test our framework on preference datasets based on the standard D4RL benchmark. When combined with a variety of efficient reward-based offline RL algorithms, the learning result achieved under our framework is comparable to training the same algorithm on the dataset with actual rewards in many cases and better than the recent PBRL baselines in most cases.
Authors: Darko Drakulic, Sofia Michel, Jean-Marc Andreoli
Abstract: Machine Learning-based heuristics have recently shown impressive performance in solving a variety of hard combinatorial optimization problems (COPs). However they generally rely on a separate neural model, specialized and trained for each single problem. Any variation of a problem requires adjustment of its model and re-training from scratch. In this paper, we propose GOAL (for Generalist combinatorial Optimization Agent Learning), a generalist model capable of efficiently solving multiple COPs and which can be fine-tuned to solve new COPs. GOAL consists of a single backbone plus light-weight problem-specific adapters for input and output processing. The backbone is based on a new form of mixed-attention blocks which allows to handle problems defined on graphs with arbitrary combinations of node, edge and instance-level features. Additionally, problems which involve heterogeneous types of nodes or edges are handled through a novel multi-type transformer architecture, where the attention blocks are duplicated to attend the meaningful combinations of types while relying on the same shared parameters. We train GOAL on a set of routing, scheduling and classic graph problems and show that it is only slightly inferior to the specialized baselines while being the first multi-task model that solves a wide range of COPs. Finally we showcase the strong transfer learning capacity of GOAL by fine-tuning it on several new problems. Our code is available at https://github.com/naver/goal-co/.
Authors: Luke Sernau
Abstract: Common infinite-width architectures such as Neural Tangent Kernels (NTKs) have historically shown weak performance compared to finite models. This is usually attributed to the absence of feature learning. We show that this explanation is insufficient. Specifically, we show that infinite width NTKs obviate the need for feature learning. They can learn identical behavior by selecting relevant subfeatures from their (infinite) frozen feature vector. Furthermore, we show experimentally that NTKs under-perform traditional finite models even when feature learning is artificially disabled. Instead, we show that weak performance is at least partly due to the fact that existing constructions depend on weak optimizers like SGD. We provide a new infinite width limit based on ADAM-like learning dynamics and demonstrate empirically that the resulting models erase this performance gap.
Authors: Luke Sernau, Silvano Bonacina, Rif A. Saurous
Abstract: Random features are a powerful technique for rewriting positive-definite kernels as linear products. They bring linear tools to bear in important nonlinear domains like KNNs and attention. Unfortunately, practical implementations require approximating an expectation, usually via sampling. This has led to the development of increasingly elaborate representations with ever lower sample error. We resolve this arms race by deriving an optimal sampling policy. Under this policy all random features representations have the same approximation error, which we show is the lowest possible. This means that we are free to choose whatever representation we please, provided we sample optimally.
Authors: Itay Inbar, Luke Sernau
Abstract: A primary cost driver for training large models is wall-clock training time. We show that popular time estimates based on FLOPs are poor estimates, and construct a more accurate proxy based on memory copies. This allows us to accurately estimate the training speed of a transformer model from its hyperparameters. Combined with a scaling law curve like Chinchilla, this allows us to accurately predict the final loss of a model from a simple equation. We show that this expression is accurate across a wide range of model hyperparameter values, enabling us to analytically make architectural decisions and train models more efficiently. Crucially, this analysis predicts that in contrast to existing literature, models should be wider rather than deeper, as the benefits of speed outweigh the benefits of depth.
Authors: Ivan Rubachev, Nikolay Kartashev, Yury Gorishniy, Artem Babenko
Abstract: Advances in machine learning research drive progress in real-world applications. To ensure this progress, it is important to understand the potential pitfalls on the way from a novel method's success on academic benchmarks to its practical deployment. In this work, we analyze existing tabular benchmarks and find two common characteristics of tabular data in typical industrial applications that are underrepresented in the datasets usually used for evaluation in the literature. First, in real-world deployment scenarios, distribution of data often changes over time. To account for this distribution drift, time-based train/test splits should be used in evaluation. However, popular tabular datasets often lack timestamp metadata to enable such evaluation. Second, a considerable portion of datasets in production settings stem from extensive data acquisition and feature engineering pipelines. This can have an impact on the absolute and relative number of predictive, uninformative, and correlated features compared to academic datasets. In this work, we aim to understand how recent research advances in tabular deep learning transfer to these underrepresented conditions. To this end, we introduce TabReD -- a collection of eight industry-grade tabular datasets. We reassess a large number of tabular ML models and techniques on TabReD. We demonstrate that evaluation on time-based data splits leads to different methods ranking, compared to evaluation on random splits, which are common in current benchmarks. Furthermore, simple MLP-like architectures and GBDT show the best results on the TabReD datasets, while other methods are less effective in the new setting.
Authors: Th\'eo Uscidda, Luca Eyring, Karsten Roth, Fabian Theis, Zeynep Akata, Marco Cuturi
Abstract: Learning disentangled representations from unlabelled data is a fundamental challenge in machine learning. Solving it may unlock other problems, such as generalization, interpretability, or fairness. Although remarkably challenging to solve in theory, disentanglement is often achieved in practice through prior matching. Furthermore, recent works have shown that prior matching approaches can be enhanced by leveraging geometrical considerations, e.g., by learning representations that preserve geometric features of the data, such as distances or angles between points. However, matching the prior while preserving geometric features is challenging, as a mapping that fully preserves these features while aligning the data distribution with the prior does not exist in general. To address these challenges, we introduce a novel approach to disentangled representation learning based on quadratic optimal transport. We formulate the problem using Gromov-Monge maps that transport one distribution onto another with minimal distortion of predefined geometric features, preserving them as much as can be achieved. To compute such maps, we propose the Gromov-Monge-Gap (GMG), a regularizer quantifying whether a map moves a reference distribution with minimal geometry distortion. We demonstrate the effectiveness of our approach for disentanglement across four standard benchmarks, outperforming other methods leveraging geometric considerations.
Authors: Yixin Jin, Meiqi Wang, Meng Li, Wenjing Zhou, Yi Shen, Hao Liu
Abstract: In this paper, we describe our approaches to TREC Real-Time Summarization of Twitter. We focus on real time push notification scenario, which requires a system monitors the stream of sampled tweets and returns the tweets relevant and novel to given interest profiles. Dirichlet score with and with very little smoothing (baseline) are employed to classify whether a tweet is relevant to a given interest profile. Using metrics including Mean Average Precision (MAP, cumulative gain (CG) and discount cumulative gain (DCG), the experiment indicates that our approach has a good performance. It is also desired to remove the redundant tweets from the pushing queue. Due to the precision limit, we only describe the algorithm in this paper.
Authors: Yuren Mao, Yuhang Ge, Yijiang Fan, Wenyi Xu, Yu Mi, Zhonghao Hu, Yunjun Gao
Abstract: Low-Rank Adaptation~(LoRA), which updates the dense neural network layers with pluggable low-rank matrices, is one of the best performed parameter efficient fine-tuning paradigms. Furthermore, it has significant advantages in cross-task generalization and privacy-preserving. Hence, LoRA has gained much attention recently, and the number of related literature demonstrates exponential growth. It is necessary to conduct a comprehensive overview of the current progress on LoRA. This survey categorizes and reviews the progress from the perspectives of (1) downstream adaptation improving variants that improve LoRA's performance on downstream tasks; (2) cross-task generalization methods that mix multiple LoRA plugins to achieve cross-task generalization; (3) efficiency-improving methods that boost the computation-efficiency of LoRA; (4) data privacy-preserving methods that use LoRA in federated learning; (5) application. Besides, this survey also discusses the future directions in this field. At last, we provide a Github page~\footnote{\href{https://github.com/ZJU-LLMs/Awesome-LoRAs.git}{https://github.com/ZJU-LLMs/Awesome-LoRAs.git}} for readers to check the updates and initiate discussions on this survey paper.
URLs: https://github.com/ZJU-LLMs/Awesome-LoRAs.git, https://github.com/ZJU-LLMs/Awesome-LoRAs.git
Authors: Adittya Pal
Abstract: Stable states in complex systems correspond to local minima on the associated potential energy surface. Transitions between these local minima govern the dynamics of such systems. Precisely determining the transition pathways in complex and high-dimensional systems is challenging because these transitions are rare events, and isolating the relevant species in experiments is difficult. Most of the time, the system remains near a local minimum, with rare, large fluctuations leading to transitions between minima. The probability of such transitions decreases exponentially with the height of the energy barrier, making the system's dynamics highly sensitive to the calculated energy barriers. This work aims to formulate the problem of finding the minimum energy barrier between two stable states in the system's state space as a cost-minimization problem. We propose solving this problem using reinforcement learning algorithms. The exploratory nature of reinforcement learning agents enables efficient sampling and determination of the minimum energy barrier for transitions.
Authors: Nikolaus Howe, Ian McKenzie, Oskar Hollinsworth, Micha{\l} Zajac, Tom Tseng, Aaron Tucker, Pierre-Luc Bacon, Adam Gleave
Abstract: Language models exhibit scaling laws, whereby increasing model and dataset size yields predictable decreases in negative log likelihood, unlocking a dazzling array of capabilities. This phenomenon spurs many companies to train ever larger models in pursuit of ever improved performance. Yet, these models are vulnerable to adversarial inputs such as ``jailbreaks'' and prompt injections that induce models to perform undesired behaviors, posing a growing risk as models become more capable. Prior work indicates that computer vision models become more robust with model and data scaling, raising the question: does language model robustness also improve with scale? We study this question empirically in the classification setting, finding that without explicit defense training, larger models tend to be modestly more robust on most tasks, though the effect is not reliable. Even with the advantage conferred by scale, undefended models remain easy to attack in absolute terms, and we thus turn our attention to explicitly training models for adversarial robustness, which we show to be a much more compute-efficient defense than scaling model size alone. In this setting, we also observe that adversarially trained larger models generalize faster and better to modified attacks not seen during training when compared with smaller models. Finally, we analyze the offense/defense balance of increasing compute, finding parity in some settings and an advantage for offense in others, suggesting that adversarial training alone is not sufficient to solve robustness, even at greater model scales.
Authors: Shuowei Jin, Francis Y. Yan, Cheng Tan, Anuj Kalia, Xenofon Foukas, Z. Morley Mao
Abstract: The increasing adoption of neural networks in learning-augmented systems highlights the importance of model safety and robustness, particularly in safety-critical domains. Despite progress in the formal verification of neural networks, current practices require users to manually define model specifications -- properties that dictate expected model behavior in various scenarios. This manual process, however, is prone to human error, limited in scope, and time-consuming. In this paper, we introduce AutoSpec, the first framework to automatically generate comprehensive and accurate specifications for neural networks in learning-augmented systems. We also propose the first set of metrics for assessing the accuracy and coverage of model specifications, establishing a benchmark for future comparisons. Our evaluation across four distinct applications shows that AutoSpec outperforms human-defined specifications as well as two baseline approaches introduced in this study.
Authors: Chenlin Wu, Xiaoyu He, Zike Li, Jing Gong, Zibin Zheng
Abstract: Federated learning heavily relies on distributed gradient descent techniques. In the situation where gradient information is not available, the gradients need to be estimated from zeroth-order information, which typically involves computing finite-differences along isotropic random directions. This method suffers from high estimation errors, as the geometric features of the objective landscape may be overlooked during the isotropic sampling. In this work, we propose a non-isotropic sampling method to improve the gradient estimation procedure. Gradients in our method are estimated in a subspace spanned by historical trajectories of solutions, aiming to encourage the exploration of promising regions and hence improve the convergence. The proposed method uses a covariance matrix for sampling which is a convex combination of two parts. The first part is a thin projection matrix containing the basis of the subspace which is designed to improve the exploitation ability. The second part is the historical trajectories. We implement this method in zeroth-order federated settings, and show that the convergence rate aligns with existing ones while introducing no significant overheads in communication or local computation. The effectiveness of our proposal is verified on several numerical experiments in comparison to several commonly-used zeroth-order federated optimization algorithms.
Authors: Caleb Ju, Guanghui Lan
Abstract: This paper proposes a novel termination criterion, termed the advantage gap function, for finite state and action Markov decision processes (MDP) and reinforcement learning (RL). By incorporating this advantage gap function into the design of step size rules and deriving a new linear rate of convergence that is independent of the stationary state distribution of the optimal policy, we demonstrate that policy gradient methods can solve MDPs in strongly-polynomial time. To the best of our knowledge, this is the first time that such strong convergence properties have been established for policy gradient methods. Moreover, in the stochastic setting, where only stochastic estimates of policy gradients are available, we show that the advantage gap function provides close approximations of the optimality gap for each individual state and exhibits a sublinear rate of convergence at every state. The advantage gap function can be easily estimated in the stochastic case, and when coupled with easily computable upper bounds on policy values, they provide a convenient way to validate the solutions generated by policy gradient methods. Therefore, our developments offer a principled and computable measure of optimality for RL, whereas current practice tends to rely on algorithm-to-algorithm or baselines comparisons with no certificate of optimality.
Authors: Yuandong Tian
Abstract: We prove rich algebraic structures of the solution space for 2-layer neural networks with quadratic activation and $L_2$ loss, trained on reasoning tasks in Abelian group (e.g., modular addition). Such a rich structure enables analytical construction of global optimal solutions from partial solutions that only satisfy part of the loss, despite its high nonlinearity. We coin the framework as CoGO (Composing Global Optimizers). Specifically, we show that the weight space over different numbers of hidden nodes of the 2-layer network is equipped with a semi-ring algebraic structure, and the loss function to be optimized consists of monomial potentials, which are ring homomorphism, allowing partial solutions to be composed into global ones by ring addition and multiplication. Our experiments show that around $95\%$ of the solutions obtained by gradient descent match exactly our theoretical constructions. Although the global optimizers constructed only required a small number of hidden nodes, our analysis on gradient dynamics shows that over-parameterization asymptotically decouples training dynamics and is beneficial. We further show that training dynamics favors simpler solutions under weight decay, and thus high-order global optimizers such as perfect memorization are unfavorable.
Authors: Jiawei Liu, Thanh Nguyen, Mingyue Shang, Hantian Ding, Xiaopeng Li, Yu Yu, Varun Kumar, Zijian Wang
Abstract: Large Language Models (LLMs) have recently demonstrated remarkable coding capabilities. However, assessing code generation based on well-formed properties and aligning it with developer preferences remains challenging. In this paper, we explore two key questions under the new challenge of code preference learning: (i) How do we train models to predict meaningful preferences for code? and (ii) How do human and LLM preferences align with verifiable code properties and developer code tastes? To this end, we propose CodeFavor, a framework for training pairwise code preference models from synthetic evolution data, including code commits and code critiques. To evaluate code preferences, we introduce CodePrefBench, a benchmark comprising 1364 rigorously curated code preference tasks to cover three verifiable properties-correctness, efficiency, and security-along with human preference. Our evaluation shows that CodeFavor holistically improves the accuracy of model-based code preferences by up to 28.8%. Meanwhile, CodeFavor models can match the performance of models with 6-9x more parameters while being 34x more cost-effective. We also rigorously validate the design choices in CodeFavor via a comprehensive set of controlled experiments. Furthermore, we discover the prohibitive costs and limitations of human-based code preference: despite spending 23.4 person-minutes on each task, 15.1-40.3% of tasks remain unsolved. Compared to model-based preference, human preference tends to be more accurate under the objective of code correctness, while being sub-optimal for non-functional objectives.
Authors: Andrei Manolache, Dragos Tantaru, Mathias Niepert
Abstract: In this work, we propose a simple transformer-based baseline for multimodal molecular representation learning, integrating three distinct modalities: SMILES strings, 2D graph representations, and 3D conformers of molecules. A key aspect of our approach is the aggregation of 3D conformers, allowing the model to account for the fact that molecules can adopt multiple conformations-an important factor for accurate molecular representation. The tokens for each modality are extracted using modality-specific encoders: a transformer for SMILES strings, a message-passing neural network for 2D graphs, and an equivariant neural network for 3D conformers. The flexibility and modularity of this framework enable easy adaptation and replacement of these encoders, making the model highly versatile for different molecular tasks. The extracted tokens are then combined into a unified multimodal sequence, which is processed by a downstream transformer for prediction tasks. To efficiently scale our model for large multimodal datasets, we utilize Flash Attention 2 and bfloat16 precision. Despite its simplicity, our approach achieves state-of-the-art results across multiple datasets, demonstrating its effectiveness as a strong baseline for multimodal molecular representation learning.
Authors: Jialian Li, Yipin Zhang, Wei Shen, Yuzi Yan, Jian Xie, Dong Yan
Abstract: Logical reasoning is a crucial task for Large Language Models (LLMs), enabling them to tackle complex problems. Among reasoning tasks, multi-step reasoning poses a particular challenge. Grounded in the theory of formal logic, we have developed an automated method, Multi-step Deduction (MuseD), for deductive reasoning data. MuseD has allowed us to create training and testing datasets for multi-step reasoning. Our generation method enables control over the complexity of the generated instructions, facilitating training and evaluation of models across different difficulty levels. Through RLHF training, our training data has demonstrated significant improvements in logical capabilities for both in-domain of out-of-domain reasoning tasks. Additionally, we have conducted tests to assess the multi-step reasoning abilities of various models.
Authors: Yonatan Slutzky, Yotam Alexander, Noam Razin, Nadav Cohen
Abstract: Neural networks are powered by an implicit bias: a tendency of gradient descent to fit training data in a way that generalizes to unseen data. A recent class of neural network models gaining increasing popularity is structured state space models (SSMs), regarded as an efficient alternative to transformers. Prior work argued that the implicit bias of SSMs leads to generalization in a setting where data is generated by a low dimensional teacher. In this paper, we revisit the latter setting, and formally establish a phenomenon entirely undetected by prior work on the implicit bias of SSMs. Namely, we prove that while implicit bias leads to generalization under many choices of training data, there exist special examples whose inclusion in training completely distorts the implicit bias, to a point where generalization fails. This failure occurs despite the special training examples being labeled by the teacher, i.e. having clean labels! We empirically demonstrate the phenomenon, with SSMs trained independently and as part of non-linear neural networks. In the area of adversarial machine learning, disrupting generalization with cleanly labeled training examples is known as clean-label poisoning. Given the proliferation of SSMs, particularly in large language models, we believe significant efforts should be invested in further delineating their susceptibility to clean-label poisoning, and in developing methods for overcoming this susceptibility.
Authors: Zhi Wang, Li Zhang, Wenhao Wu, Yuanheng Zhu, Dongbin Zhao, Chunlin Chen
Abstract: A longstanding goal of artificial general intelligence is highly capable generalists that can learn from diverse experiences and generalize to unseen tasks. The language and vision communities have seen remarkable progress toward this trend by scaling up transformer-based models trained on massive datasets, while reinforcement learning (RL) agents still suffer from poor generalization capacity under such paradigms. To tackle this challenge, we propose Meta Decision Transformer (Meta-DT), which leverages the sequential modeling ability of the transformer architecture and robust task representation learning via world model disentanglement to achieve efficient generalization in offline meta-RL. We pretrain a context-aware world model to learn a compact task representation, and inject it as a contextual condition to the causal transformer to guide task-oriented sequence generation. Then, we subtly utilize history trajectories generated by the meta-policy as a self-guided prompt to exploit the architectural inductive bias. We select the trajectory segment that yields the largest prediction error on the pretrained world model to construct the prompt, aiming to encode task-specific information complementary to the world model maximally. Notably, the proposed framework eliminates the requirement of any expert demonstration or domain knowledge at test time. Experimental results on MuJoCo and Meta-World benchmarks across various dataset types show that Meta-DT exhibits superior few and zero-shot generalization capacity compared to strong baselines while being more practical with fewer prerequisites. Our code is available at https://github.com/NJU-RL/Meta-DT.
Authors: Jintao Zhang, Mingyue Cheng, Xiaoyu Tao, Zhiding Liu, Daoyu Wang
Abstract: Time series forecasting is vital in numerous web applications, influencing critical decision-making across industries. While diffusion models have recently gained increasing popularity for this task, we argue they suffer from a significant drawback: indiscriminate noise addition to the original time series followed by denoising, which can obscure underlying dynamic evolving trend and complicate forecasting. To address this limitation, we propose a novel flexible decoupled framework (FDF) that learns high-quality time series representations for enhanced forecasting performance. A key characteristic of our approach leverages the inherent inductive bias of time series data of its decomposed trend and seasonal components, each modeled separately to enable decoupled analysis and modeling. Specifically, we propose an innovative Conditional Denoising Seasonal Module (CDSM) within the diffusion model, which leverages statistical information from the historical window to conditionally model the complex seasonal component. Notably, we incorporate a Polynomial Trend Module (PTM) to effectively capture the smooth trend component, thereby enhancing the model's ability to represent temporal dependencies. Extensive experiments validate the effectiveness of our framework, demonstrating superior performance over existing methods and highlighting its flexibility in time series forecasting. The source code is available at https://github.com/zjt-gpu/FDF.
Authors: Vinod Raman, Ambuj Tewari
Abstract: We study generation through the lens of statistical learning theory. First, we abstract and formalize the results of Gold [1967], Angluin [1979, 1980], and Kleinberg and Mullainathan [2024] for language identification/generation in the limit in terms of a binary hypothesis class defined over an abstract instance space. Then, we formalize a different paradigm of generation studied by Kleinberg and Mullainathan [2024], which we call "uniform generation," and provide a characterization of which hypothesis classes are uniformly generatable. As is standard in statistical learning theory, our characterization is in terms of the finiteness of a new combinatorial dimension we call the Closure dimension. By doing so, we are able to compare generatability with predictability (captured via PAC and online learnability) and show that these two properties of hypothesis classes are \emph{incompatible} - there are classes that are generatable but not predictable and vice versa.
Authors: Mazda Moayeri, Vidhisha Balachandran, Varun Chandrasekaran, Safoora Yousefi, Thomas Fel, Soheil Feizi, Besmira Nushi, Neel Joshi, Vibhav Vineet
Abstract: With models getting stronger, evaluations have grown more complex, testing multiple skills in one benchmark and even in the same instance at once. However, skill-wise performance is obscured when inspecting aggregate accuracy, under-utilizing the rich signal modern benchmarks contain. We propose an automatic approach to recover the underlying skills relevant for any evaluation instance, by way of inspecting model-generated rationales. After validating the relevance of rationale-parsed skills and inferring skills for $46$k instances over $12$ benchmarks, we observe many skills to be common across benchmarks, resulting in the curation of hundreds of skill-slices (i.e. sets of instances testing a common skill). Inspecting accuracy over these slices yields novel insights on model trade-offs: e.g., compared to GPT-4o and Claude 3.5 Sonnet, on average, Gemini 1.5 Pro is $18\%$ more accurate in "computing molar mass", but $19\%$ less accurate in "applying constitutional law", despite the overall accuracies of the three models differing by a mere $0.4\%$. Furthermore, we demonstrate the practical utility of our approach by showing that insights derived from skill slice analysis can generalize to held-out instances: when routing each instance to the model strongest on the relevant skills, we see a $3\%$ accuracy improvement over our $12$ dataset corpus. Our skill-slices and framework open a new avenue in model evaluation, leveraging skill-specific analyses to unlock a more granular and actionable understanding of model capabilities.
Authors: Bruno Mlodozeniec, Runa Eschenhagen, Juhan Bae, Alexander Immer, David Krueger, Richard Turner
Abstract: Diffusion models have led to significant advancements in generative modelling. Yet their widespread adoption poses challenges regarding data attribution and interpretability. In this paper, we aim to help address such challenges in diffusion models by developing an \textit{influence functions} framework. Influence function-based data attribution methods approximate how a model's output would have changed if some training data were removed. In supervised learning, this is usually used for predicting how the loss on a particular example would change. For diffusion models, we focus on predicting the change in the probability of generating a particular example via several proxy measurements. We show how to formulate influence functions for such quantities and how previously proposed methods can be interpreted as particular design choices in our framework. To ensure scalability of the Hessian computations in influence functions, we systematically develop K-FAC approximations based on generalised Gauss-Newton matrices specifically tailored to diffusion models. We recast previously proposed methods as specific design choices in our framework and show that our recommended method outperforms previous data attribution approaches on common evaluations, such as the Linear Data-modelling Score (LDS) or retraining without top influences, without the need for method-specific hyperparameter tuning.
Authors: Yikang Chen, Dehui Du, Lili Tian
Abstract: We propose an importance sampling method for tractable and efficient estimation of counterfactual expressions in general settings, named Exogenous Matching. By minimizing a common upper bound of counterfactual estimators, we transform the variance minimization problem into a conditional distribution learning problem, enabling its integration with existing conditional distribution modeling approaches. We validate the theoretical results through experiments under various types and settings of Structural Causal Models (SCMs) and demonstrate the outperformance on counterfactual estimation tasks compared to other existing importance sampling methods. We also explore the impact of injecting structural prior knowledge (counterfactual Markov boundaries) on the results. Finally, we apply this method to identifiable proxy SCMs and demonstrate the unbiasedness of the estimates, empirically illustrating the applicability of the method to practical scenarios.
Authors: Xin Ma, Yang Liu, Jingjing Liu, Xiaoxu Ma
Abstract: Large language models (LLMs), although having revolutionized many fields, still suffer from the challenging extrapolation problem, where the inference ability of LLMs sharply declines beyond their max training lengths. In this work, we conduct a theoretical analysis to better understand why No Position Encoding (NoPE) fails outside its effective range, as well as examining the power of Position Encoding (PE) in this context. Our findings reveal that with meticulous weave position, PE can indeed be extended beyond effective range. Our theorems establish that LLMs equipped with weave PE can achieve improved extrapolation performance without additional cost. Furthermore, we introduce a novel weave PE method, Mesa-Extrapolation, which utilizes a chunk-based triangular attention matrix and applies Stair PE to manage the final chunk. This method not only retains competitive performance but also offers substantial benefits such as significantly reduced memory demand and faster inference speed. Extensive experiments validate the effectiveness of Mesa-Extrapolation, demonstrating its potential as a scalable solution to enhancing LLMs applicative reach. Our code is available at \url{https://github.com/soacker/Mesa-Extrapolation}.
Authors: Md Asifuzzaman Jishan, Vikas Singh, Ayan Kumar Ghosh, Md Shahabub Alam, Khan Raqib Mahmud, Bijan Paul
Abstract: This study applies Bayesian models to predict hotel booking cancellations, a key challenge affecting resource allocation, revenue, and customer satisfaction in the hospitality industry. Using a Kaggle dataset with 36,285 observations and 17 features, Bayesian Logistic Regression and Beta-Binomial models were implemented. The logistic model, applied to 12 features and 5,000 randomly selected observations, outperformed the Beta-Binomial model in predictive accuracy. Key predictors included the number of adults, children, stay duration, lead time, car parking space, room type, and special requests. Model evaluation using Leave-One-Out Cross-Validation (LOO-CV) confirmed strong alignment between observed and predicted outcomes, demonstrating the model's robustness. Special requests and parking availability were found to be the strongest predictors of cancellation. This Bayesian approach provides a valuable tool for improving booking management and operational efficiency in the hotel industry.
Authors: Gathika Ratnayaka, James Nichols, Qing Wang
Abstract: Partial graph matching addresses the limitations of traditional graph matching by allowing some nodes to remain unmatched, making it applicable to more complex scenarios. However, this flexibility introduces additional complexity, as both the subset of nodes to match and the optimal mapping must be determined. While recent studies have explored deep learning techniques for partial graph matching, a significant limitation remains: the absence of an optimization objective that fully captures the problem's intrinsic nature while enabling efficient solutions. In this paper, we propose a novel optimization framework for partial graph matching, inspired by optimal partial transport. Our approach formulates an objective that enables partial assignments while incorporating matching biases, using weighted total variation as the divergence function to guarantee optimal partial assignments. We employ the Hungarian algorithm to achieve efficient, exact solutions with cubic time complexity. Our contributions are threefold: (i) we introduce a robust optimization objective that balances matched and unmatched nodes; (ii) we establish a connection between partial graph matching and the linear sum assignment problem, enabling efficient solutions; (iii) we propose a deep graph matching architecture with a novel partial matching loss, providing an end-to-end solution. The empirical evaluations on standard graph matching benchmarks demonstrate the efficacy of the proposed approach.
Authors: Aditya Vikram Singh, Ethan Rathbun, Emma Graham, Lisa Oakley, Simona Boboila, Alina Oprea, Peter Chin
Abstract: Recent advances in multi-agent reinforcement learning (MARL) have created opportunities to solve complex real-world tasks. Cybersecurity is a notable application area, where defending networks against sophisticated adversaries remains a challenging task typically performed by teams of security operators. In this work, we explore novel MARL strategies for building autonomous cyber network defenses that address challenges such as large policy spaces, partial observability, and stealthy, deceptive adversarial strategies. To facilitate efficient and generalized learning, we propose a hierarchical Proximal Policy Optimization (PPO) architecture that decomposes the cyber defense task into specific sub-tasks like network investigation and host recovery. Our approach involves training sub-policies for each sub-task using PPO enhanced with domain expertise. These sub-policies are then leveraged by a master defense policy that coordinates their selection to solve complex network defense tasks. Furthermore, the sub-policies can be fine-tuned and transferred with minimal cost to defend against shifts in adversarial behavior or changes in network settings. We conduct extensive experiments using CybORG Cage 4, the state-of-the-art MARL environment for cyber defense. Comparisons with multiple baselines across different adversaries show that our hierarchical learning approach achieves top performance in terms of convergence speed, episodic return, and several interpretable metrics relevant to cybersecurity, including the fraction of clean machines on the network, precision, and false positives on recoveries.
Authors: Mridul Gupta, Samyak Jain, Vansh Ramani, Hariprasad Kodamana, Sayan Ranu
Abstract: Graph distillation has emerged as a promising avenue to enable scalable training of GNNs by compressing the training dataset while preserving essential graph characteristics. Our study uncovers significant shortcomings in current graph distillation techniques. First, the majority of the algorithms paradoxically require training on the full dataset to perform distillation. Second, due to their gradient-emulating approach, these methods require fresh distillation for any change in hyperparameters or GNN architecture, limiting their flexibility and reusability. Finally, they fail to achieve substantial size reduction due to synthesizing fully-connected, edge-weighted graphs. To address these challenges, we present Bonsai, a novel graph distillation method empowered by the observation that \textit{computation trees} form the fundamental processing units of message-passing GNNs. Bonsai distills datasets by encoding a careful selection of \textit{exemplar} trees that maximize the representation of all computation trees in the training set. This unique approach imparts Bonsai as the first linear-time, model-agnostic graph distillation algorithm for node classification that outperforms existing baselines across $6$ real-world datasets on accuracy, while being $22$ times faster on average. Bonsai is grounded in rigorous mathematical guarantees on the adopted approximation strategies making it robust to GNN architectures, datasets, and parameters.
Authors: Chanwoo Chun, SueYeon Chung, Daniel D. Lee
Abstract: Analyzing the structure of sampled features from an input data distribution is challenging when constrained by limited measurements in both the number of inputs and features. Traditional approaches often rely on the eigenvalue spectrum of the sample covariance matrix derived from finite measurement matrices; however, these spectra are sensitive to the size of the measurement matrix, leading to biased insights. In this paper, we introduce a novel algorithm that provides unbiased estimates of the spectral moments of the kernel integral operator in the limit of infinite inputs and features from finitely sampled measurement matrices. Our method, based on dynamic programming, is efficient and capable of estimating the moments of the operator spectrum. We demonstrate the accuracy of our estimator on radial basis function (RBF) kernels, highlighting its consistency with the theoretical spectra. Furthermore, we showcase the practical utility and robustness of our method in understanding the geometry of learned representations in neural networks.
Authors: Maria-Florina Balcan, Christopher Seiler, Dravyansh Sharma
Abstract: Data-driven algorithm design is a promising, learning-based approach for beyond worst-case analysis of algorithms with tunable parameters. An important open problem is the design of computationally efficient data-driven algorithms for combinatorial algorithm families with multiple parameters. As one fixes the problem instance and varies the parameters, the "dual" loss function typically has a piecewise-decomposable structure, i.e. is well-behaved except at certain sharp transition boundaries. In this work we initiate the study of techniques to develop efficient ERM learning algorithms for data-driven algorithm design by enumerating the pieces of the sum dual loss functions for a collection of problem instances. The running time of our approach scales with the actual number of pieces that appear as opposed to worst case upper bounds on the number of pieces. Our approach involves two novel ingredients -- an output-sensitive algorithm for enumerating polytopes induced by a set of hyperplanes using tools from computational geometry, and an execution graph which compactly represents all the states the algorithm could attain for all possible parameter values. We illustrate our techniques by giving algorithms for pricing problems, linkage-based clustering and dynamic-programming based sequence alignment.
Authors: Hiroyasu Tsukamoto, Soon-Jo Chung, Yashwanth Kumar Nakka, Benjamin Donitz, Declan Mages, Michel Ingham
Abstract: Interstellar objects (ISOs) are likely representatives of primitive materials invaluable in understanding exoplanetary star systems. Due to their poorly constrained orbits with generally high inclinations and relative velocities, however, exploring ISOs with conventional human-in-the-loop approaches is significantly challenging. This paper presents Neural-Rendezvous -- a deep learning-based guidance and control framework for encountering fast-moving objects, including ISOs, robustly, accurately, and autonomously in real time. It uses pointwise minimum norm tracking control on top of a guidance policy modeled by a spectrally-normalized deep neural network, where its hyperparameters are tuned with a loss function directly penalizing the MPC state trajectory tracking error. We show that Neural-Rendezvous provides a high probability exponential bound on the expected spacecraft delivery error, the proof of which leverages stochastic incremental stability analysis. In particular, it is used to construct a non-negative function with a supermartingale property, explicitly accounting for the ISO state uncertainty and the local nature of nonlinear state estimation guarantees. In numerical simulations, Neural-Rendezvous is demonstrated to satisfy the expected error bound for 100 ISO candidates. This performance is also empirically validated using our spacecraft simulator and in high-conflict and distributed UAV swarm reconfiguration with up to 20 UAVs.
Authors: Paul H\"ausner, Ozan \"Oktem, Jens Sj\"olund
Abstract: The convergence of the conjugate gradient method for solving large-scale and sparse linear equation systems depends on the spectral properties of the system matrix, which can be improved by preconditioning. In this paper, we develop a computationally efficient data-driven approach to accelerate the generation of effective preconditioners. We, therefore, replace the typically hand-engineered preconditioners by the output of graph neural networks. Our method generates an incomplete factorization of the matrix and is, therefore, referred to as neural incomplete factorization (NeuralIF). Optimizing the condition number of the linear system directly is computationally infeasible. Instead, we utilize a stochastic approximation of the Frobenius loss which only requires matrix-vector multiplications for efficient training. At the core of our method is a novel message-passing block, inspired by sparse matrix theory, that aligns with the objective of finding a sparse factorization of the matrix. We evaluate our proposed method on both synthetic problem instances and on problems arising from the discretization of the Poisson equation on varying domains. Our experiments show that by using data-driven preconditioners within the conjugate gradient method we are able to speed up the convergence of the iterative procedure. The code is available at https://github.com/paulhausner/neural-incomplete-factorization.
URLs: https://github.com/paulhausner/neural-incomplete-factorization.
Authors: Rohit Gandikota, Hadas Orgad, Yonatan Belinkov, Joanna Materzy\'nska, David Bau
Abstract: Text-to-image models suffer from various safety issues that may limit their suitability for deployment. Previous methods have separately addressed individual issues of bias, copyright, and offensive content in text-to-image models. However, in the real world, all of these issues appear simultaneously in the same model. We present a method that tackles all issues with a single approach. Our method, Unified Concept Editing (UCE), edits the model without training using a closed-form solution, and scales seamlessly to concurrent edits on text-conditional diffusion models. We demonstrate scalable simultaneous debiasing, style erasure, and content moderation by editing text-to-image projections, and we present extensive experiments demonstrating improved efficacy and scalability over prior work. Our code is available at https://unified.baulab.info
Authors: Abhishek Setty, Rasul Abdusalamov, Felix Motzoi
Abstract: Chebyshev polynomials have shown significant promise as an efficient tool for both classical and quantum neural networks to solve linear and nonlinear differential equations. In this work, we adapt and generalize this framework in a quantum machine learning setting for a variety of problems, including the 2D Poisson's equation, second-order differential equation, system of differential equations, and nonlinear Riccati equation. In particular, we propose in the quantum setting a modified Self-Adaptive Physics-Informed Neural Network (SAPINN) approach, where self-adaptive weights are applied to problems with multi-objective loss functions. We further explore capturing correlations in our loss function using a quantum-correlated measurement, resulting in improved accuracy for initial value problems. We analyse also the use of entangling layers and their impact on the solution accuracy for second-order differential equations. The results indicate a promising approach to the near-term evaluation of differential equations on quantum devices.
Authors: Torbj{\o}rn Smith, Olav Egeland
Abstract: This paper presents a method for learning Hamiltonian dynamics from a limited set of data points. The Hamiltonian vector field is found by regularized optimization over a reproducing kernel Hilbert space of vector fields that are inherently Hamiltonian, and where the vector field is required to be odd or even. This is done with a symplectic kernel, and it is shown how this symplectic kernel can be modified to be odd or even. The performance of the method is validated in simulations for two Hamiltonian systems. The simulations show that the learned dynamics reflect the energy-preservation of the Hamiltonian dynamics, and that the restriction to symplectic and odd dynamics gives improved accuracy over a large domain of the phase space.
Authors: Abdul Aziz, Nhat Pham, Neel Vora, Cody Reynolds, Jaime Lehnen, Pooja Venkatesh, Zhuoran Yao, Jay Harvey, Tam Vu, Kan Ding, Phuc Nguyen
Abstract: Epilepsy is one of the most common neurological diseases globally (around 50 million people worldwide). Fortunately, up to 70% of people with epilepsy could live seizure-free if properly diagnosed and treated, and a reliable technique to monitor the onset of seizures could improve the quality of life of patients who are constantly facing the fear of random seizure attacks. The scalp-based EEG test, despite being the gold standard for diagnosing epilepsy, is costly, necessitates hospitalization, demands skilled professionals for operation, and is discomforting for users. In this paper, we propose EarSD, a novel lightweight, unobtrusive, and socially acceptable ear-worn system to detect epileptic seizure onsets by measuring the physiological signals from behind the user's ears. EarSD includes an integrated custom-built sensing-computing-communication PCB to collect and amplify the signals of interest, remove the noises caused by motion artifacts and environmental impacts, and stream the data wirelessly to the computer/mobile phone nearby, where data are uploaded to the host computer for further processing. We conducted both in-lab and in-hospital experiments with epileptic seizure patients who were hospitalized for seizure studies.
Authors: Francisco Daunas, I\~naki Esnaola, Samir M. Perlaza, H. Vincent Poor
Abstract: The solution to empirical risk minimization with $f$-divergence regularization (ERM-$f$DR) is presented under mild conditions on $f$. Under such conditions, the optimal measure is shown to be unique. Examples of the solution for particular choices of the function $f$ are presented. Previously known solutions to common regularization choices are obtained by leveraging the flexibility of the family of $f$-divergences. These include the unique solutions to empirical risk minimization with relative entropy regularization (Type-I and Type-II). The analysis of the solution unveils the following properties of $f$-divergences when used in the ERM-$f$DR problem: $i\bigl)$ $f$-divergence regularization forces the support of the solution to coincide with the support of the reference measure, which introduces a strong inductive bias that dominates the evidence provided by the training data; and $ii\bigl)$ any $f$-divergence regularization is equivalent to a different $f$-divergence regularization with an appropriate transformation of the empirical risk function.
Authors: Samuel Teuber, Stefan Mitsch, Andr\'e Platzer
Abstract: While neural networks (NNs) have potential as autonomous controllers for Cyber-Physical Systems, verifying the safety of NN based control systems (NNCSs) poses significant challenges for the practical use of NNs, especially when safety is needed for unbounded time horizons. One reason is the intractability of analyzing NNs, ODEs and hybrid systems. To this end, we introduce VerSAILLE (Verifiably Safe AI via Logically Linked Envelopes): The first general approach that allows reusing control theory results for NNCS verification. By joining forces, we exploit the efficiency of NN verification tools while retaining the rigor of differential dynamic logic (dL). Based on provably safe control envelopes in dL, we derive specifications for the NN which is proven via NN verification. We show that a proof of the NN adhering to the specification is mirrored by a dL proof on the infinite-time safety of the NNCS. The NN verification properties resulting from hybrid systems typically contain nonlinear arithmetic and arbitrary logical structures while efficient NN verification merely supports linear constraints. To overcome this divide, we present Mosaic: An efficient, sound and complete verification approach for polynomial real arithmetic properties on piece-wise linear NNs. Mosaic partitions complex verification queries into simple queries and lifts off-the-shelf linear constraint tools to the nonlinear setting in a completeness-preserving manner by combining approximation with exact reasoning for counterexample regions. Our evaluation demonstrates the versatility of VerSAILLE and Mosaic: We prove infinite-time safety on the classical Vertical Airborne Collision Avoidance NNCS verification benchmark for two scenarios while (exhaustively) enumerating counterexample regions in unsafe scenarios. We also show that our approach significantly outperforms State-of-the-Art tools in closed-loop NNV.
Authors: Christina Giannoula, Peiming Yang, Ivan Fernandez Vega, Jiacheng Yang, Sankeerth Durvasula, Yu Xin Li, Mohammad Sadrosadati, Juan Gomez Luna, Onur Mutlu, Gennady Pekhimenko
Abstract: Graph Neural Networks (GNNs) are emerging ML models to analyze graph-structure data. Graph Neural Network (GNN) execution involves both compute-intensive and memory-intensive kernels, the latter dominates the total time, being significantly bottlenecked by data movement between memory and processors. Processing-In-Memory (PIM) systems can alleviate this data movement bottleneck by placing simple processors near or inside to memory arrays. In this work, we introduce PyGim, an efficient ML library that accelerates GNNs on real PIM systems. We propose intelligent parallelization techniques for memory-intensive kernels of GNNs tailored for real PIM systems, and develop handy Python API for them. We provide hybrid GNN execution, in which the compute-intensive and memory-intensive kernels are executed in processor-centric and memory-centric computing systems, respectively. We extensively evaluate PyGim on a real-world PIM system with 1992 PIM cores using emerging GNN models, and demonstrate that it outperforms its state-of-the-art CPU counterpart on Intel Xeon by on average 3.04x, and achieves higher resource utilization than CPU and GPU systems. Our work provides useful recommendations for software, system and hardware designers. PyGim is publicly available at https://github.com/CMU-SAFARI/PyGim.
Authors: Zhen Ye, Zeqian Ju, Haohe Liu, Xu Tan, Jianyi Chen, Yiwen Lu, Peiwen Sun, Jiahao Pan, Weizhen Bian, Shulin He, Wei Xue, Qifeng Liu, Yike Guo
Abstract: Recent progress in large-scale zero-shot speech synthesis has been significantly advanced by language models and diffusion models. However, the generation process of both methods is slow and computationally intensive. Efficient speech synthesis using a lower computing budget to achieve quality on par with previous work remains a significant challenge. In this paper, we present FlashSpeech, a large-scale zero-shot speech synthesis system with approximately 5\% of the inference time compared with previous work. FlashSpeech is built on the latent consistency model and applies a novel adversarial consistency training approach that can train from scratch without the need for a pre-trained diffusion model as the teacher. Furthermore, a new prosody generator module enhances the diversity of prosody, making the rhythm of the speech sound more natural. The generation processes of FlashSpeech can be achieved efficiently with one or two sampling steps while maintaining high audio quality and high similarity to the audio prompt for zero-shot speech generation. Our experimental results demonstrate the superior performance of FlashSpeech. Notably, FlashSpeech can be about 20 times faster than other zero-shot speech synthesis systems while maintaining comparable performance in terms of voice quality and similarity. Furthermore, FlashSpeech demonstrates its versatility by efficiently performing tasks like voice conversion, speech editing, and diverse speech sampling. Audio samples can be found in https://flashspeech.github.io/.
Authors: Jiang Zhang, Konstantinos Psounis, Salman Avestimehr
Abstract: Federated Learning (FL) with Secure Aggregation (SA) has gained significant attention as a privacy preserving framework for training machine learning models while preventing the server from learning information about users' data from their individual encrypted model updates. Recent research has extended privacy guarantees of FL with SA by bounding the information leakage through the aggregate model over multiple training rounds thanks to leveraging the "noise" from other users' updates. However, the privacy metric used in that work (mutual information) measures the on-average privacy leakage, without providing any privacy guarantees for worse-case scenarios. To address this, in this work we study the conditions under which FL with SA can provide worst-case differential privacy guarantees. Specifically, we formally identify the necessary condition that SA can provide DP without addition noise. We then prove that when the randomness inside the aggregated model update is Gaussian with non-singular covariance matrix, SA can provide differential privacy guarantees with the level of privacy $\epsilon$ bounded by the reciprocal of the minimum eigenvalue of the covariance matrix. However, we further demonstrate that in practice, these conditions are almost unlikely to hold and hence additional noise added in model updates is still required in order for SA in FL to achieve DP. Lastly, we discuss the potential solution of leveraging inherent randomness inside aggregated model update to reduce the amount of addition noise required for DP guarantee.
Authors: Jianqiao Lu, Zhiyang Dou, Hongru Wang, Zeyu Cao, Jianbo Dai, Yingjia Wan, Zhijiang Guo
Abstract: In this work, we propose a novel method named \textbf{Auto}mated \textbf{P}rocess-\textbf{S}upervised \textbf{V}erifier (\textbf{\textsc{AutoPSV}}) to enhance the reasoning capabilities of large language models (LLMs) by automatically annotating the reasoning steps. \textsc{AutoPSV} begins by training a verification model on the correctness of final answers, enabling it to generate automatic process annotations. This verification model assigns a confidence score to each reasoning step, indicating the probability of arriving at the correct final answer from that point onward. We detect relative changes in the verification's confidence scores across reasoning steps to automatically annotate the reasoning process, enabling error detection even in scenarios where ground truth answers are unavailable. This alleviates the need for numerous manual annotations or the high computational costs associated with model-induced annotation approaches. We experimentally validate that the step-level confidence changes learned by the verification model trained on the final answer correctness can effectively identify errors in the reasoning steps. We demonstrate that the verification model, when trained on process annotations generated by \textsc{AutoPSV}, exhibits improved performance in selecting correct answers from multiple LLM-generated outputs. Notably, we achieve substantial improvements across five datasets in mathematics and commonsense reasoning. The source code of \textsc{AutoPSV} is available at \url{https://github.com/rookie-joe/AutoPSV}.
Authors: Hongfu Gao, Feipeng Zhang, Wenyu Jiang, Jun Shu, Feng Zheng, Hongxin Wei
Abstract: Large language models (LLMs) have shown impressive performance on downstream tasks by in-context learning (ICL), which heavily relies on the quality of demonstrations selected from a large set of annotated examples. Recent works claim that in-context learning is robust to noisy demonstrations in text classification. In this work, we show that, on text generation tasks, noisy annotations significantly hurt the performance of in-context learning. To circumvent the issue, we propose a simple and effective approach called Local Perplexity Ranking (LPR), which replaces the "noisy" candidates with their nearest neighbors that are more likely to be clean. Our method is motivated by analyzing the perplexity deviation caused by noisy labels and decomposing perplexity into inherent perplexity and matching perplexity. Our key idea behind LPR is thus to decouple the matching perplexity by performing the ranking among the neighbors in semantic space. Our approach can prevent the selected demonstrations from including mismatched input-label pairs while preserving the effectiveness of the original selection methods. Extensive experiments demonstrate the effectiveness of LPR, improving the EM score by up to 18.75 on common benchmarks with noisy annotations. Our code is available at https://github.com/ml-stat-Sustech/Local-Perplexity-Ranking.
URLs: https://github.com/ml-stat-Sustech/Local-Perplexity-Ranking.
Authors: Roberto Ceraolo, Dmitrii Kharlapenko, Ahmad Khan, Am\'elie Reymond, Rada Mihalcea, Bernhard Sch\"olkopf, Mrinmaya Sachan, Zhijing Jin
Abstract: The recent development of Large Language Models (LLMs) has changed our role in interacting with them. Instead of primarily testing these models with questions we already know the answers to, we now use them to explore questions where the answers are unknown to us. This shift, which hasn't been fully addressed in existing datasets, highlights the growing need to understand naturally occurring human questions - that are more complex, open-ended, and reflective of real-world needs. To this end, we present NatQuest, a collection of 13,500 naturally occurring questions from three diverse sources: human-to-search-engine queries, human-to-human interactions, and human-to-LLM conversations. Our comprehensive collection enables a rich understanding of human curiosity across various domains and contexts. Our analysis reveals a significant presence of causal questions (up to 42%) within the dataset, for which we develop an iterative prompt improvement framework to identify all causal queries, and examine their unique linguistic properties, cognitive complexity, and source distribution. We also lay the groundwork to explore LLM performance on these questions and provide six efficient classification models to identify causal questions at scale for future work.
Authors: Faisal Hamman, Sanghamitra Dutta
Abstract: This paper introduces a novel information-theoretic perspective on the relationship between prominent group fairness notions in machine learning, namely statistical parity, equalized odds, and predictive parity. It is well known that simultaneous satisfiability of these three fairness notions is usually impossible, motivating practitioners to resort to approximate fairness solutions rather than stringent satisfiability of these definitions. However, a comprehensive analysis of their interrelations, particularly when they are not exactly satisfied, remains largely unexplored. Our main contribution lies in elucidating an exact relationship between these three measures of (un)fairness by leveraging a body of work in information theory called partial information decomposition (PID). In this work, we leverage PID to identify the granular regions where these three measures of (un)fairness overlap and where they disagree with each other leading to potential tradeoffs. We also include numerical simulations to complement our results.
Authors: Wolfgang Stammer, Antonia W\"ust, David Steinmann, Kristian Kersting
Abstract: The challenge in object-based visual reasoning lies in generating concept representations that are both descriptive and distinct. Achieving this in an unsupervised manner requires human users to understand the model's learned concepts and, if necessary, revise incorrect ones. To address this challenge, we introduce the Neural Concept Binder (NCB), a novel framework for deriving both discrete and continuous concept representations, which we refer to as "concept-slot encodings". NCB employs two types of binding: "soft binding", which leverages the recent SysBinder mechanism to obtain object-factor encodings, and subsequent "hard binding", achieved through hierarchical clustering and retrieval-based inference. This enables obtaining expressive, discrete representations from unlabeled images. Moreover, the structured nature of NCB's concept representations allows for intuitive inspection and the straightforward integration of external knowledge, such as human input or insights from other AI models like GPT-4. Additionally, we demonstrate that incorporating the hard binding mechanism preserves model performance while enabling seamless integration into both neural and symbolic modules for complex reasoning tasks. We validate the effectiveness of NCB through evaluations on our newly introduced CLEVR-Sudoku dataset.
Authors: Aleksander Ficek, Jiaqi Zeng, Oleksii Kuchaiev
Abstract: Parameter-Efficient Fine-Tuning (PEFT) and Retrieval-Augmented Generation (RAG) have become popular methods for adapting large language models while minimizing compute requirements. In this paper, we apply PEFT methods (P-tuning, Adapters, and LoRA) to a modified Retrieval-Enhanced Transformer (RETRO) and a baseline GPT model across several sizes, ranging from 823 million to 48 billion parameters. We show that RETRO models outperform GPT models in zero-shot settings due to their unique pre-training process but GPT models have higher performance potential with PEFT. Additionally, our study indicates that 8B parameter models strike an optimal balance between cost and performance and P-tuning lags behind other PEFT techniques. We further provide a comparative analysis between applying PEFT to an Instruction-tuned RETRO model and base RETRO model. This work presents the first comprehensive comparison of various PEFT methods integrated with RAG, applied to both GPT and RETRO models, highlighting their relative performance.
Authors: Annesha Ghosh, Deep Ghoshal, Bilol Banerjee, Anil K. Ghosh
Abstract: Nearest neighbor classifier is arguably the most simple and popular nonparametric classifier available in the literature. However, due to the concentration of pairwise distances and the violation of the neighborhood structure, this classifier often suffers in high-dimension, low-sample size (HDLSS) situations, especially when the scale difference between the competing classes dominates their location difference. Several attempts have been made in the literature to take care of this problem. In this article, we discuss some of these existing methods and propose some new ones. We carry out some theoretical investigations in this regard and analyze several simulated and benchmark datasets to compare the empirical performances of proposed methods with some of the existing ones.
Authors: Julien Quarez, Marc Modat, Sebastien Ourselin, Jonathan Shapey, Alejandro Granados
Abstract: In surgical skill assessment, the Objective Structured Assessments of Technical Skills (OSATS) and Global Rating Scale (GRS) are well-established tools for evaluating surgeons during training. These metrics, along with performance feedback, help surgeons improve and reach practice standards. Recent research on the open-source JIGSAWS dataset, which includes both GRS and OSATS labels, has focused on regressing GRS scores from kinematic data, video, or their combination. However, we argue that regressing GRS alone is limiting, as it aggregates OSATS scores and overlooks clinically meaningful variations during a surgical trial. To address this, we developed a recurrent transformer model that tracks a surgeon's performance throughout a session by mapping hidden states to six OSATS, derived from kinematic data, using a clinically motivated objective function. These OSATS scores are averaged to predict GRS, allowing us to compare our model's performance against state-of-the-art (SOTA) methods. We report Spearman's Correlation Coefficients (SCC) demonstrating that our model outperforms SOTA using kinematic data (SCC 0.83-0.88), and matches performance with video-based models. Our model also surpasses SOTA in most tasks for average OSATS predictions (SCC 0.46-0.70) and specific OSATS (SCC 0.56-0.95). The generation of pseudo-labels at the segment level translates quantitative predictions into qualitative feedback, vital for automated surgical skill assessment pipelines. A senior surgeon validated our model's outputs, agreeing with 77% of the weakly-supervised predictions (p=0.006).
Authors: Devaansh Gupta, Boyang Li
Abstract: Combining Large Language Models (LLMs) with heuristic search algorithms like A* holds the promise of enhanced LLM reasoning and scalable inference. To accelerate training and reduce computational demands, we investigate the coreset selection problem for the training data of LLM heuristic learning. Few methods to learn the heuristic functions consider the interaction between the search algorithm and the machine learning model. In this work, we empirically disentangle the requirements of A* search algorithm from the requirements of the LLM to generalise on this task. Surprisingly, we find an overlap between their requirements; A* requires more accurate predictions on search nodes near the goal, and LLMs need the same set of nodes for effective generalisation. With these insights, we derive a data-selection distribution for learning LLM-based heuristics. On three classical planning domains, maze navigation, Sokoban and sliding tile puzzles, our technique reduces the number of iterations required to find the solutions by up to 15x, with a wall-clock speed-up of search up to 5x. The codebase is at https://github.com/devaansh100/a_star.
Authors: Guorun Wang, Lucia Specia
Abstract: Text-to-image models are known to propagate social biases. For example, when prompted to generate images of people in certain professions, these models tend to systematically generate specific genders or ethnicities. In this paper, we show that this bias is already present in the text encoder of the model and introduce a Mixture-of-Experts approach by identifying text-encoded bias in the latent space and then creating a Bias-Identification Gate mechanism. More specifically, we propose MoESD (Mixture of Experts Stable Diffusion) with BiAs (Bias Adapters) to mitigate gender bias in text-to-image models. We also demonstrate that introducing an arbitrary special token to the prompt is essential during the mitigation process. With experiments focusing on gender bias, we show that our approach successfully mitigates gender bias while maintaining image quality.
Authors: Jakub Adamczyk, Piotr Ludynia
Abstract: In this work, we present \skfp, a Python package for computation of molecular fingerprints for applications in chemoinformatics. Our library offers an industry-standard scikit-learn interface, allowing intuitive usage and easy integration with machine learning pipelines. It is also highly optimized, featuring parallel computation that enables efficient processing of large molecular datasets. Currently, \skfp~stands as the most feature-rich library in the open source Python ecosystem, offering over 30 molecular fingerprints. Our library simplifies chemoinformatics tasks based on molecular fingerprints, including molecular property prediction and virtual screening. It is also flexible, highly efficient, and fully open source.
Authors: Sa\"uc Abadal Lloret, Shehzaad Dhuliawala, Keerthiram Murugesan, Mrinmaya Sachan
Abstract: We present ALT (ALignment with Textual feedback), an approach that aligns language models with user preferences expressed in text. We argue that text offers greater expressiveness, enabling users to provide richer feedback than simple comparative preferences and this richer feedback can lead to more efficient and effective alignment. ALT aligns the model by conditioning its generation on the textual feedback. Our method relies solely on language modeling techniques and requires minimal hyper-parameter tuning, though it still presents the main benefits of RL-based alignment algorithms and can effectively learn from textual feedback. We explore the efficacy and efficiency of textual feedback across different tasks such as toxicity reduction, summarization, and dialog response generation. We find that ALT outperforms PPO for the task of toxicity reduction while being able to match its performance on summarization with only 20% of the samples. We also explore how ALT can be used with feedback provided by an existing LLM where we explore an LLM providing constrained and unconstrained textual feedback. We also outline future directions to align models with natural language feedback.
Authors: Jun Wang, Ying Yuan, Haichuan Che, Haozhi Qi, Yi Ma, Jitendra Malik, Xiaolong Wang
Abstract: In-hand manipulation of pen-like objects is an important skill in our daily lives, as many tools such as hammers and screwdrivers are similarly shaped. However, current learning-based methods struggle with this task due to a lack of high-quality demonstrations and the significant gap between simulation and the real world. In this work, we push the boundaries of learning-based in-hand manipulation systems by demonstrating the capability to spin pen-like objects. We first use reinforcement learning to train an oracle policy with privileged information and generate a high-fidelity trajectory dataset in simulation. This serves two purposes: 1) pre-training a sensorimotor policy in simulation; 2) conducting open-loop trajectory replay in the real world. We then fine-tune the sensorimotor policy using these real-world trajectories to adapt it to the real world dynamics. With less than 50 trajectories, our policy learns to rotate more than ten pen-like objects with different physical properties for multiple revolutions. We present a comprehensive analysis of our design choices and share the lessons learned during development.
Authors: Hao-Yun Hsu, Yi-Ching Cheng, Guan-Hua Huang
Abstract: In this research, we revisit the architecture of semantic segmentation and evaluate the models excelling in polyp segmentation. We introduce an integrated framework that harnesses the advantages of different models to attain an optimal outcome. More specifically, we fuse the learned features from convolutional and transformer models for prediction, and we view this approach as an ensemble technique to enhance model performance. Our experiments on polyp segmentation reveal that the proposed architecture surpasses other top models, exhibiting improved learning capacity and resilience. The code is available at https://github.com/HuangDLab/EnFormer.
Authors: Arjhun Swaminathan, Mete Akg\"un
Abstract: Quantum computing promises to revolutionize machine learning, offering significant efficiency gains in tasks such as clustering and distance estimation. Additionally, it provides enhanced security through fundamental principles like the measurement postulate and the no-cloning theorem, enabling secure protocols such as quantum teleportation and quantum key distribution. While advancements in secure quantum machine learning are notable, the development of secure and distributed quantum analogues of kernel-based machine learning techniques remains underexplored. In this work, we present a novel approach for securely computing common kernels, including polynomial, radial basis function (RBF), and Laplacian kernels, when data is distributed, using quantum feature maps. Our methodology introduces a robust framework that leverages quantum teleportation to ensure secure and distributed kernel learning. The proposed architecture is validated using IBM's Qiskit Aer Simulator on various public datasets.
Authors: Dimitris Stripelis, Zijian Hu, Jipeng Zhang, Zhaozhuo Xu, Alay Dilipbhai Shah, Han Jin, Yuhang Yao, Salman Avestimehr, Chaoyang He
Abstract: With the rapid growth of Large Language Models (LLMs) across various domains, numerous new LLMs have emerged, each possessing domain-specific expertise. This proliferation has highlighted the need for quick, high-quality, and cost-effective LLM query response methods. Yet, no single LLM exists to efficiently balance this trilemma. Some models are powerful but extremely costly, while others are fast and inexpensive but qualitatively inferior. To address this challenge, we present TO-Router, a non-monolithic LLM querying system that seamlessly integrates various LLM experts into a single query interface and dynamically routes incoming queries to the most high-performant expert based on query's requirements. Through extensive experiments, we demonstrate that when compared to standalone expert models, TO-Router improves query efficiency by up to 40\%, and leads to significant cost reductions of up to 30%, while maintaining or enhancing model performance by up to 10%.
Authors: Edward Y. Chang
Abstract: Biases and errors in human-labeled data present significant challenges for machine learning, especially in supervised learning reliant on potentially flawed ground truth data. These flaws, including diagnostic errors and societal biases, risk being propagated and amplified through models trained using maximum likelihood estimation. We present the Reflective LLM Dialogue Framework RLDF, which leverages structured adversarial dialogues between multiple instances of a single LLM or different LLMs to uncover diverse perspectives and correct inconsistencies. By conditioning LLMs to adopt opposing stances, RLDF enables systematic bias detection through conditional statistics, information theory, and divergence metrics. Experiments show RLDF successfully identifies potential biases in public content while exposing limitations in human-labeled data. Our framework supports measurable progress tracking and explainable remediation actions, offering a scalable approach for improving content neutrality through transparent, multi-perspective analysis.
Authors: Jeremy Wayland, Russel J. Funk, Bastian Rieck
Abstract: Identifying (a) systemic barriers to quality healthcare access and (b) key indicators of care efficacy in the United States remains a significant challenge. To improve our understanding of regional disparities in care delivery, we introduce a novel application of curvature, a geometrical-topological property of networks, to Physician Referral Networks. Our initial findings reveal that Forman-Ricci and Ollivier-Ricci curvature measures, which are known for their expressive power in characterizing network structure, offer promising indicators for detecting variations in healthcare efficacy while capturing a range of significant regional demographic features. We also present APPARENT, an open-source tool that leverages Ricci curvature and other network features to examine correlations between regional Physician Referral Networks structure, local census data, healthcare effectiveness, and patient outcomes.
Authors: Anna M\'esz\'aros, Szilvia Ujv\'ary, Wieland Brendel, Patrik Reizinger, Ferenc Husz\'ar
Abstract: LLMs show remarkable emergent abilities, such as inferring concepts from presumably out-of-distribution prompts, known as in-context learning. Though this success is often attributed to the Transformer architecture, our systematic understanding is limited. In complex real-world data sets, even defining what is out-of-distribution is not obvious. To better understand the OOD behaviour of autoregressive LLMs, we focus on formal languages, which are defined by the intersection of rules. We define a new scenario of OOD compositional generalization, termed rule extrapolation. Rule extrapolation describes OOD scenarios, where the prompt violates at least one rule. We evaluate rule extrapolation in formal languages with varying complexity in linear and recurrent architectures, the Transformer, and state space models to understand the architectures' influence on rule extrapolation. We also lay the first stones of a normative theory of rule extrapolation, inspired by the Solomonoff prior in algorithmic information theory.
Authors: Ziru Chen, Shijie Chen, Yuting Ning, Qianheng Zhang, Boshi Wang, Botao Yu, Yifei Li, Zeyi Liao, Chen Wei, Zitong Lu, Vishal Dey, Mingyi Xue, Frazier N. Baker, Benjamin Burns, Daniel Adu-Ampratwum, Xuhui Huang, Xia Ning, Song Gao, Yu Su, Huan Sun
Abstract: The advancements of language language models (LLMs) have piqued growing interest in developing LLM-based language agents to automate scientific discovery end-to-end, which has sparked both excitement and skepticism about their true capabilities. In this work, we call for rigorous assessment of agents on individual tasks in a scientific workflow before making bold claims on end-to-end automation. To ensure the scientific authenticity and real-world relevance of our benchmark, we extract 102 tasks from 44 peer-reviewed publications in four disciplines and engage nine subject matter experts to validate them. We unify the target output for every task to a self-contained Python program file and employ an array of evaluation metrics to examine the generated programs, execution results, and costs. Each task goes through multiple rounds of manual validation by annotators and subject matter experts to ensure its annotation quality and scientific plausibility. We also propose two effective strategies to mitigate data contamination concerns. Using our benchmark, we evaluate five open-weight and proprietary LLMs, each with three frameworks: direct prompting, OpenHands CodeAct, and self-debug. Given three attempts for each task, the best-performing agent can only solve 32.4% of the tasks independently and 34.3% with expert-provided knowledge. In addition, we evaluate OpenAI o1 with direct prompting and self-debug, which demonstrates the effectiveness of increasing inference-time compute. Still, our results underscore the limitations of current language agents in generating code for data-driven discovery, let alone end-to-end automation for scientific research.
Authors: Rana Muhammad Shahroz Khan, Pingzhi Li, Sukwon Yun, Zhenyu Wang, Shahriar Nirjon, Chau-Wai Wong, Tianlong Chen
Abstract: As large language models (LLMs) increasingly shape the AI landscape, fine-tuning pretrained models has become more popular than in the pre-LLM era for achieving optimal performance in domain-specific tasks. However, pretrained LLMs such as ChatGPT are periodically evolved, i.e., model parameters are frequently updated), making it challenging for downstream users with limited resources to keep up with fine-tuning the newest LLMs for their domain application. Even though fine-tuning costs have nowadays been reduced thanks to the innovations of parameter-efficient fine-tuning such as LoRA, not all downstream users have adequate computing for frequent personalization. Moreover, access to fine-tuning datasets, particularly in sensitive domains such as healthcare, could be time-restrictive, making it crucial to retain the knowledge encoded in earlier fine-tuned rounds for future adaptation. In this paper, we present PortLLM, a training-free framework that (i) creates an initial lightweight model update patch to capture domain-specific knowledge, and (ii) allows a subsequent seamless plugging for the continual personalization of evolved LLM at minimal cost. Our extensive experiments cover seven representative datasets, from easier question-answering tasks {BoolQ, SST2} to harder reasoning tasks {WinoGrande, GSM8K}, and models including {Mistral-7B, Llama2, Llama3.1, and Gemma2}, validating the portability of our designed model patches and showcasing the effectiveness of our proposed framework. For instance, PortLLM achieves comparable performance to LoRA fine-tuning with reductions of up to 12.2x in GPU memory usage. Finally, we provide theoretical justifications to understand the portability of our model update patches, which offers new insights into the theoretical dimension of LLMs' personalization.
Authors: Jipeng Han
Abstract: Program synthesis methods, whether formal or neural-based, lack fine-grained control and flexible modularity, which limits their adaptation to complex software development. These limitations stem from rigid Domain-Specific Language (DSL) frameworks and neural network incorrect predictions. To this end, we propose the Chain of Logic (CoL), which organizes synthesis stages into a chain and provides precise heuristic control to guide the synthesis process. Furthermore, by integrating neural networks with libraries and introducing a Neural Network Feedback Control (NNFC) mechanism, our approach modularizes synthesis and mitigates the impact of neural network mispredictions. Experiments on relational and symbolic synthesis tasks show that CoL significantly enhances the efficiency and reliability of DSL program synthesis across multiple metrics. Specifically, CoL improves accuracy by 70% while reducing tree operations by 91% and time by 95%. Additionally, NNFC further boosts accuracy by 6%, with a 64% reduction in tree operations under challenging conditions such as insufficient training data, increased difficulty, and multidomain synthesis. These improvements confirm COOL as a highly efficient and reliable program synthesis framework.
Authors: Panagiotis Theodoropoulos, Nikolaos Komianos, Vincent Pacelli, Guan-Horng Liu, Evangelos A. Theodorou
Abstract: Recent advancements in diffusion bridges for distribution transport problems have heavily relied on matching frameworks, yet existing methods often face a trade-off between scalability and access to optimal pairings during training. Fully unsupervised methods make minimal assumptions but incur high computational costs, limiting their practicality. On the other hand, imposing full supervision of the matching process with optimal pairings improves scalability, however, it can be infeasible in many applications. To strike a balance between scalability and minimal supervision, we introduce Feedback Schr\"odinger Bridge Matching (FSBM), a novel semi-supervised matching framework that incorporates a small portion (less than 8% of the entire dataset) of pre-aligned pairs as state feedback to guide the transport map of non coupled samples, thereby significantly improving efficiency. This is achieved by formulating a static Entropic Optimal Transport (EOT) problem with an additional term capturing the semi-supervised guidance. The generalized EOT objective is then recast into a dynamic formulation to leverage the scalability of matching frameworks. Extensive experiments demonstrate that FSBM accelerates training and enhances generalization by leveraging coupled pairs guidance, opening new avenues for training matching frameworks with partially aligned datasets.
Authors: Mihail Stoian, Alexander van Renen, Jan Kobiolka, Ping-Lin Kuo, Josif Grabocka, Andreas Kipf
Abstract: The growing adoption of data lakes for managing relational data necessitates efficient, open storage formats that provide high scan performance and competitive compression ratios. While existing formats achieve fast scans through lightweight encoding techniques, they have reached a plateau in terms of minimizing storage footprint. Recently, correlation-aware compression schemes have been shown to reduce file sizes further. Yet, current approaches either incur significant scan overheads or require manual specification of correlations, limiting their practicability. We present $\texttt{Virtual}$, a framework that integrates seamlessly with existing open formats to automatically leverage data correlations, achieving substantial compression gains while having minimal scan performance overhead. Experiments on data-gov datasets show that $\texttt{Virtual}$ reduces file sizes by up to 40% compared to Apache Parquet.
Authors: Douglas Baptista de Souza, Bruno Paes Leao
Abstract: This work presents a novel data augmentation solution for non-stationary multivariate time series and its application to failure prognostics. The method extends previous work from the authors which is based on time-varying autoregressive processes. It can be employed to extract key information from a limited number of samples and generate new synthetic samples in a way that potentially improves the performance of PHM solutions. This is especially valuable in situations of data scarcity which are very usual in PHM, especially for failure prognostics. The proposed approach is tested based on the CMAPSS dataset, commonly employed for prognostics experiments and benchmarks. An AutoML approach from PHM literature is employed for automating the design of the prognostics solution. The empirical evaluation provides evidence that the proposed method can substantially improve the performance of PHM solutions.
Authors: Nelson Vadori, Antoine Gorceix, Bastien Le Chenadec, Ahmad Rammal, Manuela Veloso
Abstract: In this paper, we study the ability of large language models to learn specific mathematical rules such as distributivity or simplifying equations. We present an empirical analysis of their ability to generalize these rules, as well as to reuse them in the context of word problems. For this purpose, we provide a rigorous methodology to build synthetic data incorporating such rules, and perform fine-tuning of large language models on such data. Our experiments show that our model can learn and generalize these rules to some extent, as well as suitably reuse them in the context of word problems.