Authors: Bishakh Bhattacharya, Tanuj Gupta, Arun Kumar Sharma, Ankur Dwivedi, Vivek Gupta, Subhadeep Sahana, Suryansh Pathak, Ashish Awasthi
Abstract: In this study, we immerse in the intricate world of patterns, examining the structural details of Indian medieval architecture for the discovery of motifs with great application potential from the mechanical metastructure perspective. The motifs that specifically engrossed us are derived from the tomb of I'timad-ud-Daula, situated in the city of Agra, close to the Taj Mahal. In an exploratory study, we designed nine interlaced metastructures inspired from the tomb's motifs. We fabricated the metastructures using additive manufacturing and studied their vibration characteristics experimentally and numerically. We also investigated bandgap modulation with metallic inserts in honeycomb interlaced metastructures. The comprehensive study of these metastructure panels reveals their high performance in controlling elastic wave propagation and generating suitable frequency bandgaps, hence having potential applications as waveguides for noise and vibration control. Finally, we developed novel AI-based model trained on numerical datasets for inverse design of metastructures with a desired bandgap.
Authors: Chiyu Max Jiang, Yijing Bai, Andre Cornman, Christopher Davis, Xiukun Huang, Hong Jeon, Sakshum Kulshrestha, John Lambert, Shuangyu Li, Xuanyu Zhou, Carlos Fuertes, Chang Yuan, Mingxing Tan, Yin Zhou, Dragomir Anguelov
Abstract: Realistic and interactive scene simulation is a key prerequisite for autonomous vehicle (AV) development. In this work, we present SceneDiffuser, a scene-level diffusion prior designed for traffic simulation. It offers a unified framework that addresses two key stages of simulation: scene initialization, which involves generating initial traffic layouts, and scene rollout, which encompasses the closed-loop simulation of agent behaviors. While diffusion models have been proven effective in learning realistic and multimodal agent distributions, several challenges remain, including controllability, maintaining realism in closed-loop simulations, and ensuring inference efficiency. To address these issues, we introduce amortized diffusion for simulation. This novel diffusion denoising paradigm amortizes the computational cost of denoising over future simulation steps, significantly reducing the cost per rollout step (16x less inference steps) while also mitigating closed-loop errors. We further enhance controllability through the introduction of generalized hard constraints, a simple yet effective inference-time constraint mechanism, as well as language-based constrained scene generation via few-shot prompting of a large language model (LLM). Our investigations into model scaling reveal that increased computational resources significantly improve overall simulation realism. We demonstrate the effectiveness of our approach on the Waymo Open Sim Agents Challenge, achieving top open-loop performance and the best closed-loop performance among diffusion models.
Authors: Seongwoong Cho, Donggyun Kim, Jinwoo Lee, Seunghoon Hong
Abstract: Generalizing across robot embodiments and tasks is crucial for adaptive robotic systems. Modular policy learning approaches adapt to new embodiments but are limited to specific tasks, while few-shot imitation learning (IL) approaches often focus on a single embodiment. In this paper, we introduce a few-shot behavior cloning framework to simultaneously generalize to unseen embodiments and tasks using a few (\emph{e.g.,} five) reward-free demonstrations. Our framework leverages a joint-level input-output representation to unify the state and action spaces of heterogeneous embodiments and employs a novel structure-motion state encoder that is parameterized to capture both shared knowledge across all embodiments and embodiment-specific knowledge. A matching-based policy network then predicts actions from a few demonstrations, producing an adaptive policy that is robust to over-fitting. Evaluated in the DeepMind Control suite, our framework termed \modelname{} demonstrates superior few-shot generalization to unseen embodiments and tasks over modular policy learning and few-shot IL approaches. Codes are available at \href{https://github.com/SeongwoongCho/meta-controller}{https://github.com/SeongwoongCho/meta-controller}.
URLs: https://github.com/SeongwoongCho/meta-controller, https://github.com/SeongwoongCho/meta-controller
Authors: Manman Yuan, Weiming Jia, Xiong Luo, Jiazhen Ye, Peican Zhu, Junlin Li
Abstract: The precise detection of mild cognitive impairment (MCI) is of significant importance in preventing the deterioration of patients in a timely manner. Although hypergraphs have enhanced performance by learning and analyzing brain networks, they often only depend on vector distances between features at a single scale to infer interactions. In this paper, we deal with a more arduous challenge, hypergraph modelling with synchronization between brain regions, and design a novel framework, i.e., A Multi-scale Hypergraph Network for MCI Detection via Synchronous and Attentive Fusion (MHSA), to tackle this challenge. Specifically, our approach employs the Phase-Locking Value (PLV) to calculate the phase synchronization relationship in the spectrum domain of regions of interest (ROIs) and designs a multi-scale feature fusion mechanism to integrate dynamic connectivity features of functional magnetic resonance imaging (fMRI) from both the temporal and spectrum domains. To evaluate and optimize the direct contribution of each ROI to phase synchronization in the temporal domain, we structure the PLV coefficients dynamically adjust strategy, and the dynamic hypergraph is modelled based on a comprehensive temporal-spectrum fusion matrix. Experiments on the real-world dataset indicate the effectiveness of our strategy. The code is available at https://github.com/Jia-Weiming/MHSA.
Authors: Yuanhao Shen, Xiaodan Zhu, Lei Chen
Abstract: The tool-use ability of Large Language Models (LLMs) has a profound impact on a wide range of industrial applications. However, LLMs' self-control and calibration capability in appropriately using tools remains understudied. The problem is consequential as it raises potential risks of degraded performance and poses a threat to the trustworthiness of the models. In this paper, we conduct a study on a family of state-of-the-art LLMs on three datasets with two mainstream tool-use frameworks. Our study reveals the tool-abuse behavior of LLMs, a tendency for models to misuse tools with overconfidence. We also find that this is a common issue regardless of model capability. Accordingly, we propose a novel approach, \textit{SMARTCAL}, to mitigate the observed issues, and our results show an average of 8.6 percent increase in the QA performance and a 21.6 percent decrease in Expected Calibration Error (ECE) compared to baseline models.
Authors: Rongzheng Wang, Shuang Liang, Qizhi Chen, Jiasheng Zhang, Ke Qin
Abstract: Large language models (LLMs) have been demonstrated to possess the capabilities to understand fundamental graph properties and address various graph reasoning tasks. Existing methods fine-tune LLMs to understand and execute graph reasoning tasks by specially designed task instructions. However, these Text-Instruction methods generally exhibit poor performance. Inspired by tool learning, researchers propose Tool-Instruction methods to solve various graph problems by special tool calling (e.g., function, API and model), achieving significant improvements in graph reasoning tasks. Nevertheless, current Tool-Instruction approaches focus on the tool information and ignore the graph structure information, which leads to significantly inferior performance on small-scale LLMs (less than 13B). To tackle this issue, we propose GraphTool-Instruction, an innovative Instruction-tuning approach that decomposes the graph reasoning task into three distinct subtasks (i.e., graph extraction, tool name identification and tool parameter extraction), and design specialized instructions for each subtask. Our GraphTool-Instruction can be used as a plug-and-play prompt for different LLMs without fine-tuning. Moreover, building on GraphTool-Instruction, we develop GTools, a dataset that includes twenty graph reasoning tasks, and create a graph reasoning LLM called GraphForge based on Llama3-8B. We conduct extensive experiments on twenty graph reasoning tasks with different graph types (e.g., graph size or graph direction), and we find that GraphTool-Instruction achieves SOTA compared to Text-Instruction and Tool-Instruction methods. Fine-tuned on GTools, GraphForge gets further improvement of over 30% compared to the Tool-Instruction enhanced GPT-3.5-turbo, and it performs comparably to the high-cost GPT-4o. Our codes and data are available at https://anonymous.4open.science/r/GraphTool-Instruction.
URLs: https://anonymous.4open.science/r/GraphTool-Instruction.
Authors: Jiho Choi, Donggyun Kim, Chanhyuk Lee, Seunghoon Hong
Abstract: Model merging aims to build a multi-task learner by combining the parameters of individually fine-tuned models without additional training. While a straightforward approach is to average model parameters across tasks, this often results in suboptimal performance due to interference among parameters across tasks. In this paper, we present intriguing results that weight averaging implicitly induces task vectors centered around the weight averaging itself and that applying a low-rank approximation to these centered task vectors significantly improves merging performance. Our analysis shows that centering the task vectors effectively separates core task-specific knowledge and nuisance noise within the fine-tuned parameters into the top and lower singular vectors, respectively, allowing us to reduce inter-task interference through its low-rank approximation. We evaluate our method on eight image classification tasks, demonstrating that it outperforms prior methods by a significant margin, narrowing the performance gap with traditional multi-task learning to within 1-3%
Authors: Sihan Chen, Zhuangzhuang Qian, Wingchun Siu, Xingcan Hu, Jiaqi Li, Shawn Li, Yuehan Qin, Tiankai Yang, Zhuo Xiao, Wanghao Ye, Yichi Zhang, Yushun Dong, Yue Zhao
Abstract: Outlier detection (OD), also known as anomaly detection, is a critical machine learning (ML) task with applications in fraud detection, network intrusion detection, clickstream analysis, recommendation systems, and social network moderation. Among open-source libraries for outlier detection, the Python Outlier Detection (PyOD) library is the most widely adopted, with over 8,500 GitHub stars, 25 million downloads, and diverse industry usage. However, PyOD currently faces three limitations: (1) insufficient coverage of modern deep learning algorithms, (2) fragmented implementations across PyTorch and TensorFlow, and (3) no automated model selection, making it hard for non-experts. To address these issues, we present PyOD Version 2 (PyOD 2), which integrates 12 state-of-the-art deep learning models into a unified PyTorch framework and introduces a large language model (LLM)-based pipeline for automated OD model selection. These improvements simplify OD workflows, provide access to 45 algorithms, and deliver robust performance on various datasets. In this paper, we demonstrate how PyOD 2 streamlines the deployment and automation of OD models and sets a new standard in both research and industry. PyOD 2 is accessible at [https://github.com/yzhao062/pyod](https://github.com/yzhao062/pyod). This study aligns with the Web Mining and Content Analysis track, addressing topics such as the robustness of Web mining methods and the quality of algorithmically-generated Web data.
URLs: https://github.com/yzhao062/pyod](https://github.com/yzhao062/pyod).
Authors: Zian Zhai, Sima Qing, Xiaoyang Wang, Wenjie Zhang
Abstract: Signed Graph Neural Networks (SGNNs) are powerful tools for signed graph representation learning but struggle with limited generalization and heavy dependence on labeled data. While recent advancements in "graph pre-training and prompt tuning" have reduced label dependence in Graph Neural Networks (GNNs) and improved their generalization abilities by leveraging pre-training knowledge, these efforts have focused exclusively on unsigned graphs. The scarcity of publicly available signed graph datasets makes it essential to transfer knowledge from unsigned graphs to signed graph tasks. However, this transfer introduces significant challenges due to the graph-level and task-level divergences between the pre-training and downstream phases. To address these challenges, we propose Signed Graph Prompt Tuning (SGPT) in this paper. Specifically, SGPT employs a graph template and a semantic prompt to segregate mixed link semantics in the signed graph and then adaptively integrate the distinctive semantic information according to the needs of downstream tasks, thereby unifying the pre-training and downstream graphs. Additionally, SGPT utilizes a task template and a feature prompt to reformulate the downstream signed graph tasks, aligning them with pre-training tasks to ensure a unified optimization objective and consistent feature space across tasks. Finally, extensive experiments are conducted on popular signed graph datasets, demonstrating the superiority of SGPT over state-of-the-art methods.
Authors: Mengfan Li, Xuanhua Shi, Chenqi Qiao, Teng Zhang, Hai Jin
Abstract: Knowledge hypergraphs generalize knowledge graphs using hyperedges to connect multiple entities and depict complicated relations. Existing methods either transform hyperedges into an easier-to-handle set of binary relations or view hyperedges as isolated and ignore their adjacencies. Both approaches have information loss and may potentially lead to the creation of sub-optimal models. To fix these issues, we propose the Hyperbolic Hypergraph Neural Network (H2GNN), whose essential component is the hyper-star message passing, a novel scheme motivated by a lossless expansion of hyperedges into hierarchies. It implements a direct embedding that consciously incorporates adjacent entities, hyper-relations, and entity position-aware information. As the name suggests, H2GNN operates in the hyperbolic space, which is more adept at capturing the tree-like hierarchy. We compare H2GNN with 15 baselines on knowledge hypergraphs, and it outperforms state-of-the-art approaches in both node classification and link prediction tasks.
Authors: Yangxuan Zhou, Sha Zhao, Jiquan Wang, Haiteng Jiang, hijian Li, Benyan Luo, Tao Li, Gang Pan
Abstract: Sleep staging is crucial for assessing sleep quality and diagnosing related disorders. Recent deep learning models for automatic sleep staging using polysomnography often suffer from poor generalization to new subjects because they are trained and tested on the same labeled datasets, overlooking individual differences. To tackle this issue, we propose a novel Source-Free Unsupervised Individual Domain Adaptation (SF-UIDA) framework. This two-step adaptation scheme allows the model to effectively adjust to new unlabeled individuals without needing source data, facilitating personalized customization in clinical settings. Our framework has been applied to three established sleep staging models and tested on three public datasets, achieving state-of-the-art performance.
Authors: Ali Forootani, Danial Esmaeili Aliabadi, Daniela Thraen
Abstract: Wind power forecasting plays a critical role in modern energy systems, facilitating the integration of renewable energy sources into the power grid. Accurate prediction of wind energy output is essential for managing the inherent intermittency of wind power, optimizing energy dispatch, and ensuring grid stability. This paper proposes the use of Deep Neural Network (DNN)-based predictive models that leverage climate datasets, including wind speed, atmospheric pressure, temperature, and other meteorological variables, to improve the accuracy of wind power simulations. In particular, we focus on the Coupled Model Intercomparison Project (CMIP) datasets, which provide climate projections, as inputs for training the DNN models. These models aim to capture the complex nonlinear relationships between the CMIP-based climate data and actual wind power generation at wind farms located in Germany. Our study compares various DNN architectures, specifically Multilayer Perceptron (MLP), Long Short-Term Memory (LSTM) networks, and Transformer-enhanced LSTM models, to identify the best configuration among these architectures for climate-aware wind power simulation. The implementation of this framework involves the development of a Python package (CADNN) designed to support multiple tasks, including statistical analysis of the climate data, data visualization, preprocessing, DNN training, and performance evaluation. We demonstrate that the DNN models, when integrated with climate data, significantly enhance forecasting accuracy. This climate-aware approach offers a deeper understanding of the time-dependent climate patterns that influence wind power generation, providing more accurate predictions and making it adaptable to other geographical regions.
Authors: Bao-Bing Li, Yi Gu, Shao-Feng Wu
Abstract: Machine learning can uncover physical concepts or physical equations when prior knowledge from another one is available. However, in many cases, these two aspects are coupled and cannot be discovered independently. We extend SciNet, which is a neural network architecture that simulates the human physical reasoning process for physics discovery, by proposing a model that combines Variational Autoencoders (VAEs) with Neural Ordinary Differential Equations (Neural ODEs). This allows us to simultaneously discover physical concepts and governing equations from simulated experimental data across diverse physical systems. We apply the model to several key examples inspired by the history of physics, including Copernicus' heliocentric solar system, Newton's law of universal gravitation, the wave function together with the Schr\"odinger equation, and spin-1/2 along with the Pauli equation. The results demonstrate that the neural network successfully reconstructs the corresponding theories.
Authors: Xiangxin Fang, Lev Mukhanov
Abstract: Large Language Models (LLMs) have demonstrated great potential in various language processing tasks, and recent studies have explored their application in compiler optimizations. However, all these studies focus on the conventional open-source LLMs, such as Llama2, which lack enhanced reasoning mechanisms. In this study, we investigate the errors produced by the fine-tuned 7B-parameter Llama2 model as it attempts to learn and apply a simple peephole optimization for the AArch64 assembly code. We provide an analysis of the errors produced by the LLM and compare it with state-of-the-art OpenAI models which implement advanced reasoning logic, including GPT-4o and GPT-o1 (preview). We demonstrate that OpenAI GPT-o1, despite not being fine-tuned, outperforms the fine-tuned Llama2 and GPT-4o. Our findings indicate that this advantage is largely due to the chain-of-thought reasoning implemented in GPT-o1. We hope our work will inspire further research on using LLMs with enhanced reasoning mechanisms and chain-of-thought for code generation and optimization.
Authors: Lingzhi Shen, Yunfei Long, Xiaohao Cai, Imran Razzak, Guanming Chen, Kang Liu, Shoaib Jameel
Abstract: Multimodal fake news detection often involves modelling heterogeneous data sources, such as vision and language. Existing detection methods typically rely on fusion effectiveness and cross-modal consistency to model the content, complicating understanding how each modality affects prediction accuracy. Additionally, these methods are primarily based on static feature modelling, making it difficult to adapt to the dynamic changes and relationships between different data modalities. This paper develops a significantly novel approach, GAMED, for multimodal modelling, which focuses on generating distinctive and discriminative features through modal decoupling to enhance cross-modal synergies, thereby optimizing overall performance in the detection process. GAMED leverages multiple parallel expert networks to refine features and pre-embed semantic knowledge to improve the experts' ability in information selection and viewpoint sharing. Subsequently, the feature distribution of each modality is adaptively adjusted based on the respective experts' opinions. GAMED also introduces a novel classification technique to dynamically manage contributions from different modalities, while improving the explainability of decisions. Experimental results on the Fakeddit and Yang datasets demonstrate that GAMED performs better than recently developed state-of-the-art models. The source code can be accessed at https://github.com/slz0925/GAMED.
Authors: Yining Pang, Chenghan Li
Abstract: Seasonal time series exhibit intricate long-term dependencies, posing a significant challenge for accurate future prediction. This paper introduces the Multi-scale Seasonal Decomposition Model (MSSD) for seasonal time-series forecasting. Initially, leveraging the inherent periodicity of seasonal time series, we decompose the univariate time series into three primary components: Ascending, Peak, and Descending. This decomposition approach enhances the capture of periodic features. By addressing the limitations of existing time-series modeling methods, particularly in modeling the Peak component, this research proposes a multi-scale network structure designed to effectively capture various potential peak fluctuation patterns in the Peak component. This study integrates Conv2d and Temporal Convolutional Networks to concurrently capture global and local features. Furthermore, we incorporate multi-scale reshaping to augment the modeling capacity for peak fluctuation patterns. The proposed methodology undergoes validation using three publicly accessible seasonal datasets. Notably, in both short-term and long-term fore-casting tasks, our approach exhibits a 10$\%$ reduction in error compared to the baseline models.
Authors: Eoin M. Kenny, Julie A. Shah
Abstract: Regulation is increasingly cited as the most important and pressing concern in machine learning. However, it is currently unknown how to implement this, and perhaps more importantly, how it would effect model performance alongside human collaboration if actually realized. In this paper, we attempt to answer these questions by building a regulatable large-language model (LLM), and then quantifying how the additional constraints involved affect (1) model performance, alongside (2) human collaboration. Our empirical results reveal that it is possible to force an LLM to use human-defined features in a transparent way, but a "regulation performance trade-off" previously not considered reveals itself in the form of a 7.34% classification performance drop. Surprisingly however, we show that despite this, such systems actually improve human task performance speed and appropriate confidence in a realistic deployment setting compared to no AI assistance, thus paving a way for fair, regulatable AI, which benefits users.
Authors: Dimitrios Sikeridis, Dennis Ramdass, Pranay Pareek
Abstract: Recently, the number of off-the-shelf Large Language Models (LLMs) has exploded with many open-source options. This creates a diverse landscape regarding both serving options (e.g., inference on local hardware vs remote LLM APIs) and model heterogeneous expertise. However, it is hard for the user to efficiently optimize considering operational cost (pricing structures, expensive LLMs-as-a-service for large querying volumes), efficiency, or even per-case specific measures such as response accuracy, bias, or toxicity. Also, existing LLM routing solutions focus mainly on cost reduction, with response accuracy optimizations relying on non-generalizable supervised training, and ensemble approaches necessitating output computation for every considered LLM candidate. In this work, we tackle the challenge of selecting the optimal LLM from a model pool for specific queries with customizable objectives. We propose PickLLM, a lightweight framework that relies on Reinforcement Learning (RL) to route on-the-fly queries to available models. We introduce a weighted reward function that considers per-query cost, inference latency, and model response accuracy by a customizable scoring function. Regarding the learning algorithms, we explore two alternatives: PickLLM router acting as a learning automaton that utilizes gradient ascent to select a specific LLM, or utilizing stateless Q-learning to explore the set of LLMs and perform selection with a $\epsilon$-greedy approach. The algorithm converges to a single LLM for the remaining session queries. To evaluate, we utilize a pool of four LLMs and benchmark prompt-response datasets with different contexts. A separate scoring function is assessing response accuracy during the experiment. We demonstrate the speed of convergence for different learning rates and improvement in hard metrics such as cost per querying session and overall response latency.
Authors: Melanie Sclar, Jane Yu, Maryam Fazel-Zarandi, Yulia Tsvetkov, Yonatan Bisk, Yejin Choi, Asli Celikyilmaz
Abstract: Do large language models (LLMs) have theory of mind? A plethora of papers and benchmarks have been introduced to evaluate if current models have been able to develop this key ability of social intelligence. However, all rely on limited datasets with simple patterns that can potentially lead to problematic blind spots in evaluation and an overestimation of model capabilities. We introduce ExploreToM, the first framework to allow large-scale generation of diverse and challenging theory of mind data for robust training and evaluation. Our approach leverages an A* search over a custom domain-specific language to produce complex story structures and novel, diverse, yet plausible scenarios to stress test the limits of LLMs. Our evaluation reveals that state-of-the-art LLMs, such as Llama-3.1-70B and GPT-4o, show accuracies as low as 0% and 9% on ExploreToM-generated data, highlighting the need for more robust theory of mind evaluation. As our generations are a conceptual superset of prior work, fine-tuning on our data yields a 27-point accuracy improvement on the classic ToMi benchmark (Le et al., 2019). ExploreToM also enables uncovering underlying skills and factors missing for models to show theory of mind, such as unreliable state tracking or data imbalances, which may contribute to models' poor performance on benchmarks.
Authors: Nobel Dhar, Bobin Deng, Md Romyull Islam, Kazi Fahim Ahmad Nasif, Liang Zhao, Kun Suo
Abstract: Deploying local AI models, such as Large Language Models (LLMs), to edge devices can substantially enhance devices' independent capabilities, alleviate the server's burden, and lower the response time. Owing to these tremendous potentials, many big tech companies have released several lightweight Small Language Models (SLMs) to bridge this gap. However, we still have huge motivations to deploy more powerful (LLMs) AI models on edge devices and enhance their smartness level. Unlike the conventional approaches for AI model compression, we investigate activation sparsity. The activation sparsity method is orthogonal and combinable with existing techniques to maximize compression rate while maintaining great accuracy. LLMs' Feed-Forward Network (FFN) components, which typically comprise a large proportion of parameters (around 3/2), ensure that our FFN optimizations would have a better chance of achieving effective compression. Moreover, our findings are beneficial to general LLMs and are not restricted to ReLU-based models. This work systematically investigates the tradeoff between enforcing activation sparsity and perplexity (accuracy) on state-of-the-art LLMs. Our empirical analysis demonstrates that we can obtain around 50% of main memory and computing reductions for critical FFN components with negligible accuracy degradation. This extra 50% sparsity does not naturally exist in the current LLMs, which require tuning LLMs' activation outputs by injecting zero-enforcing thresholds. To obtain the benefits of activation sparsity, we provide a guideline for the system architect for LLM prediction and prefetching. The success prediction allows the system to prefetch the necessary weights while omitting the inactive ones and their successors, therefore lowering cache and memory pollution and reducing LLM execution time on resource-constrained edge devices.
Authors: Pegah Eshraghi, Riccardo Talami, Arman Nikkhah Dehnavi, Maedeh Mirdamadi, Zahra-Sadat Zomorodian
Abstract: In rapidly urbanizing regions, designing climate-responsive urban forms is crucial for sustainable development, especially in dry arid-climates where urban morphology has a significant impact on energy consumption and environmental performance. This study advances urban morphology evaluation by combining Urban Building Energy Modeling (UBEM) with machine learning methods (ML) and Explainable AI techniques, specifically Shapley Additive Explanations (SHAP). Using Tehran's dense urban landscape as a case study, this research assesses and ranks the impact of 30 morphology parameters at the urban block level on key energy metrics (cooling, heating, and lighting demand) and environmental performance (sunlight exposure, photovoltaic generation, and Sky View Factor). Among seven ML algorithms evaluated, the XGBoost model was the most effective predictor, achieving high accuracy (R2: 0.92) and a training time of 3.64 seconds. Findings reveal that building shape, window-to-wall ratio, and commercial ratio are the most critical parameters affecting energy efficiency, while the heights and distances of neighboring buildings strongly influence cooling demand and solar access. By evaluating urban blocks with varied densities and configurations, this study offers generalizable insights applicable to other dry-arid regions. Moreover, the integration of UBEM and Explainable AI offers a scalable, data-driven framework for developing climate-responsive urban designs adaptable to high-density environments worldwide.
Authors: Jingjing Wang, Hongjie Zhu, Haoran Xie, Fu Lee Wang, Xiaoliang Xu, Yuxiang Wang
Abstract: \Graph similarity computation is an essential task in many real-world graph-related applications such as retrieving the similar drugs given a query chemical compound or finding the user's potential friends from the social network database. Graph Edit Distance (GED) and Maximum Common Subgraphs (MCS) are the two commonly used domain-agnostic metrics to evaluate graph similarity in practice. Unfortunately, computing the exact GED is known to be a NP-hard problem. To solve this limitation, neural network based models have been proposed to approximate the calculations of GED/MCS. However, deep learning models are well-known ``black boxes'', thus the typically characteristic one-to-one node/subgraph alignment process in the classical computations of GED and MCS cannot be seen. Existing methods have paid attention to approximating the node/subgraph alignment (soft alignment), but the one-to-one node alignment (hard alignment) has not yet been solved. To fill this gap, in this paper we propose a novel interpretable neural node alignment model without relying on node alignment ground truth information. Firstly, the quadratic assignment problem in classical GED computation is relaxed to a linear alignment via embedding the features in the node embedding space. Secondly, a differentiable Gumbel-Sinkhorn module is proposed to unsupervised generate the optimal one-to-one node alignment matrix. Experimental results in real-world graph datasets demonstrate that our method outperforms the state-of-the-art methods in graph similarity computation and graph retrieval tasks, achieving up to 16\% reduction in the Mean Squared Error and up to 12\% improvement in the retrieval evaluation metrics, respectively.
Authors: Son Minh Nguyen, Linh Duy Tran, Duc Viet Le, Paul J. M Havinga
Abstract: We propose iMoT, an innovative Transformer-based inertial odometry method that retrieves cross-modal information from motion and rotation modalities for accurate positional estimation. Unlike prior work, during the encoding of the motion context, we introduce Progressive Series Decoupler at the beginning of each encoder layer to stand out critical motion events inherent in acceleration and angular velocity signals. To better aggregate cross-modal interactions, we present Adaptive Positional Encoding, which dynamically modifies positional embeddings for temporal discrepancies between different modalities. During decoding, we introduce a small set of learnable query motion particles as priors to model motion uncertainties within velocity segments. Each query motion particle is intended to draw cross-modal features dedicated to a specific motion mode, all taken together allowing the model to refine its understanding of motion dynamics effectively. Lastly, we design a dynamic scoring mechanism to stabilize iMoT's optimization by considering all aligned motion particles at the final decoding step, ensuring robust and accurate velocity segment estimation. Extensive evaluations on various inertial datasets demonstrate that iMoT significantly outperforms state-of-the-art methods in delivering superior robustness and accuracy in trajectory reconstruction.
Authors: Yusheng Zhao, Xiao Luo, Haomin Wen, Zhiping Xiao, Wei Ju, Ming Zhang
Abstract: Traffic flow forecasting aims to predict future traffic flows based on the historical traffic conditions and the road network. It is an important problem in intelligent transportation systems, with a plethora of methods been proposed. Existing efforts mainly focus on capturing and utilizing spatio-temporal dependencies to predict future traffic flows. Though promising, they fall short in adapting to test-time environmental changes of traffic conditions. To tackle this challenge, we propose to introduce large language models (LLMs) to help traffic flow forecasting and design a novel method named Large Language Model Enhanced Traffic Flow Predictor (LEAF). LEAF adopts two branches, capturing different spatio-temporal relations using graph and hypergraph structures respectively. The two branches are first pre-trained individually, and during test-time, they yield different predictions. Based on these predictions, a large language model is used to select the most likely result. Then, a ranking loss is applied as the learning objective to enhance the prediction ability of the two branches. Extensive experiments on several datasets demonstrate the effectiveness of the proposed LEAF.
Authors: Jing Zhang, Shuzhen Sun, Peng Zhang, Guangxing Cao, Hui Gao, Xindian Ma, Nan Xu, Yuexian Hou
Abstract: Transformer-based large language models exhibit groundbreaking capabilities, but their storage and computational costs are prohibitively high, limiting their application in resource-constrained scenarios. An effective approach is to eliminate redundant model parameters and computational costs while incorporating efficient expert-derived knowledge structures to achieve a balance between compression and performance. Therefore, we propose the \textit{Sememe Entanglement Encoding (SEE)} algorithm. Guided by expert prior knowledge, the model is compressed through the low-rank approximation idea. In Entanglement Embedding, basic semantic units such as sememes are represented as low-dimensional vectors, and then reconstructed into high-dimensional word embeddings through the combination of generalized quantum entanglement. We adapt the Sememe Entanglement Encoding algorithm to transformer-based models of different magnitudes. Experimental results indicate that our approach achieves stable performance while compressing model parameters and computational costs.
Authors: Amine M. Aboussalah, Xuanze Li, Cheng Chi, Raj Patel
Abstract: In the realm of option pricing, existing models are typically classified into principle-driven methods, such as solving partial differential equations (PDEs) that pricing function satisfies, and data-driven approaches, such as machine learning (ML) techniques that parameterize the pricing function directly. While principle-driven models offer a rigorous theoretical framework, they often rely on unrealistic assumptions, such as asset processes adhering to fixed stochastic differential equations (SDEs). Moreover, they can become computationally intensive, particularly in high-dimensional settings when analytical solutions are not available and thus numerical solutions are needed. In contrast, data-driven models excel in capturing market data trends, but they often lack alignment with core financial principles, raising concerns about interpretability and predictive accuracy, especially when dealing with limited or biased datasets. This work proposes a hybrid approach to address these limitations by integrating the strengths of both principled and data-driven methodologies. Our framework combines the theoretical rigor and interpretability of PDE-based models with the adaptability of machine learning techniques, yielding a more versatile methodology for pricing a broad spectrum of options. We validate our approach across different volatility modeling approaches-both with constant volatility (Black-Scholes) and stochastic volatility (Heston), demonstrating that our proposed framework, Finance-Informed Neural Network (FINN), not only enhances predictive accuracy but also maintains adherence to core financial principles. FINN presents a promising tool for practitioners, offering robust performance across a variety of market conditions.
Authors: Byung-Kwan Ko, Jun-Young Kim, Seo-Hyun Lee
Abstract: This study examines the effectiveness of traditional machine learning classifiers versus deep learning models for detecting the imagined speech using electroencephalogram data. Specifically, we evaluated conventional machine learning techniques such as CSP-SVM and LDA-SVM classifiers alongside deep learning architectures such as EEGNet, ShallowConvNet, and DeepConvNet. Machine learning classifiers exhibited significantly lower precision and recall, indicating limited feature extraction capabilities and poor generalization between imagined speech and idle states. In contrast, deep learning models, particularly EEGNet, achieved the highest accuracy of 0.7080 and an F1 score of 0.6718, demonstrating their enhanced ability in automatic feature extraction and representation learning, essential for capturing complex neurophysiological patterns. These findings highlight the limitations of conventional machine learning approaches in brain-computer interface (BCI) applications and advocate for adopting deep learning methodologies to achieve more precise and reliable classification of detecting imagined speech. This foundational research contributes to the development of imagined speech-based BCI systems.
Authors: Ka Wai Wu
Abstract: Graph neural networks (GNNs) have seen extensive application in domains such as social networks, bioinformatics, and recommendation systems. However, the irregularity and sparsity of graph data challenge traditional computing methods, which are insufficient to meet the performance demands of GNNs. Recent research has explored parallel acceleration using CUDA Cores and Tensor Cores, but significant challenges persist: (1) kernel fusion leads to false high utilization, failing to treat CUDA and Tensor Cores as independent resources, and (2) heterogeneous cores have distinct computation preferences, causing inefficiencies. To address these issues, this paper proposes FTC-GNN, a novel acceleration framework that efficiently utilizes CUDA and Tensor Cores for GNN computation. FTC-GNN introduces (1) a collaborative design that enables the parallel utilization of CUDA and Tensor Cores and (2) a sparse-to-dense transformation strategy that assigns dense matrix operations to Tensor Cores while leveraging CUDA Cores for data management and sparse edge processing. This design optimizes GPU resource utilization and improves computational efficiency. Experimental results demonstrate the effectiveness of FTC-GNN using GCN and AGNN models across various datasets. For GCN, FTC-GNN achieves speedups of 4.90x, 7.10x, and 1.17x compared to DGL, PyG, and TC-GNN, respectively. For AGNN, it achieves speedups of 5.32x, 2.92x, and 1.02x, establishing its superiority in accelerating GNN computations.
Authors: Francis Tang, Ying Ding
Abstract: Time series data plays a critical role across diverse domains such as healthcare, energy, and finance, where tasks like classification, anomaly detection, and forecasting are essential for informed decision-making. Recently, large language models (LLMs) have gained prominence for their ability to handle complex data and extract meaningful insights. This study investigates whether LLMs are effective for time series data analysis by comparing their performance with non-LLM-based approaches across three tasks: classification, anomaly detection, and forecasting. Through a series of experiments using GPT4TS and autoregressive models, we evaluate their performance on benchmark datasets and assess their accuracy, precision, and ability to generalize. Our findings indicate that while LLM-based methods excel in specific tasks like anomaly detection, their benefits are less pronounced in others, such as forecasting, where simpler models sometimes perform comparably or better. This research highlights the role of LLMs in time series analysis and lays the groundwork for future studies to systematically explore their applications and limitations in handling temporal data.
Authors: Pan Wang, Qiang Zhou, Yawen Wu, Tianlong Chen, Jingtong Hu
Abstract: Multimodal Sentiment Analysis (MSA) leverages heterogeneous modalities, such as language, vision, and audio, to enhance the understanding of human sentiment. While existing models often focus on extracting shared information across modalities or directly fusing heterogeneous modalities, such approaches can introduce redundancy and conflicts due to equal treatment of all modalities and the mutual transfer of information between modality pairs. To address these issues, we propose a Disentangled-Language-Focused (DLF) multimodal representation learning framework, which incorporates a feature disentanglement module to separate modality-shared and modality-specific information. To further reduce redundancy and enhance language-targeted features, four geometric measures are introduced to refine the disentanglement process. A Language-Focused Attractor (LFA) is further developed to strengthen language representation by leveraging complementary modality-specific information through a language-guided cross-attention mechanism. The framework also employs hierarchical predictions to improve overall accuracy. Extensive experiments on two popular MSA datasets, CMU-MOSI and CMU-MOSEI, demonstrate the significant performance gains achieved by the proposed DLF framework. Comprehensive ablation studies further validate the effectiveness of the feature disentanglement module, language-focused attractor, and hierarchical predictions. Our code is available at https://github.com/pwang322/DLF.
Authors: Tianyi Yin, Jingwei Wang, Yunlong Ma, Han Wang, Chenze Wang, Yukai Zhao, Min Liu, Weiming Shen, Yufeng Chen
Abstract: Encoding time series into tokens and using language models for processing has been shown to substantially augment the models' ability to generalize to unseen tasks. However, existing language models for time series forecasting encounter several obstacles, including aliasing distortion and prolonged inference times, primarily due to the limitations of quantization processes and the computational demands of large models. This paper introduces Apollo-Forecast, a novel framework that tackles these challenges with two key innovations: the Anti-Aliasing Quantization Module (AAQM) and the Race Decoding (RD) technique. AAQM adeptly encodes sequences into tokens while mitigating high-frequency noise in the original signals, thus enhancing both signal fidelity and overall quantization efficiency. RD employs a draft model to enable parallel processing and results integration, which markedly accelerates the inference speed for long-term predictions, particularly in large-scale models. Extensive experiments on various real-world datasets show that Apollo-Forecast outperforms state-of-the-art methods by 35.41\% and 18.99\% in WQL and MASE metrics, respectively, in zero-shot scenarios. Furthermore, our method achieves a 1.9X-2.7X acceleration in inference speed over baseline methods.
Authors: Sanjay Chakraborty, Ibrahim Delibasoglu, Fredrik Heintz
Abstract: Time series forecasting is a crucial challenge with significant applications in areas such as weather prediction, stock market analysis, and scientific simulations. This paper introduces an embedded decomposed transformer, 'EDformer', for multivariate time series forecasting tasks. Without altering the fundamental elements, we reuse the Transformer architecture and consider the capable functions of its constituent parts in this work. Edformer first decomposes the input multivariate signal into seasonal and trend components. Next, the prominent multivariate seasonal component is reconstructed across the reverse dimensions, followed by applying the attention mechanism and feed-forward network in the encoder stage. In particular, the feed-forward network is used for each variable frame to learn nonlinear representations, while the attention mechanism uses the time points of individual seasonal series embedded within variate frames to capture multivariate correlations. Therefore, the trend signal is added with projection and performs the final forecasting. The EDformer model obtains state-of-the-art predicting results in terms of accuracy and efficiency on complex real-world time series datasets. This paper also addresses model explainability techniques to provide insights into how the model makes its predictions and why specific features or time steps are important, enhancing the interpretability and trustworthiness of the forecasting results.
Authors: Julio Alberto Silva Dias
Abstract: Hydroelectric power generation is a critical component of the global energy matrix, particularly in countries like Brazil, where it represents the majority of the energy supply. However, its strong dependence on river discharges, which are inherently uncertain due to climate variability, poses significant challenges. River discharges are linked to precipitation patterns, making the development of accurate probabilistic forecasting models crucial for improving operational planning in systems heavily reliant on this resource. Traditionally, statistical models have been used to represent river discharges in energy optimization. Yet, these models are increasingly unable to produce realistic scenarios due to structural shifts in climate behavior. Changes in precipitation patterns have altered discharge dynamics, which traditional approaches struggle to capture. Machine learning methods, while effective as universal predictors for time series, often focus solely on historical data, ignoring key external factors such as meteorological and climatic conditions. Furthermore, these methods typically lack a probabilistic framework, which is vital for representing the inherent variability of hydrological processes. The limited availability of historical discharge data further complicates the application of large-scale deep learning models to this domain. To address these challenges, we propose a framework based on a modified recurrent neural network architecture. This model generates parameterized probability distributions conditioned on projections from global circulation models, effectively accounting for the stochastic nature of river discharges. Additionally, the architecture incorporates enhancements to improve its generalization capabilities. We validate this framework within the Brazilian Interconnected System, using projections from the SEAS5-ECMWF system as conditional variables.
Authors: Ioannis Papadimitriou (Yiannis), Ilias Gialampoukidis (Yiannis), Stefanos Vrochidis (Yiannis), Ioannis (Yiannis), Kompatsiaris
Abstract: We present RAG Playground, an open-source framework for systematic evaluation of Retrieval-Augmented Generation (RAG) systems. The framework implements and compares three retrieval approaches: naive vector search, reranking, and hybrid vector-keyword search, combined with ReAct agents using different prompting strategies. We introduce a comprehensive evaluation framework with novel metrics and provide empirical results comparing different language models (Llama 3.1 and Qwen 2.5) across various retrieval configurations. Our experiments demonstrate significant performance improvements through hybrid search methods and structured self-evaluation prompting, achieving up to 72.7% pass rate on our multi-metric evaluation framework. The results also highlight the importance of prompt engineering in RAG systems, with our custom-prompted agents showing consistent improvements in retrieval accuracy and response quality.
Authors: Ruizhi Pu, Gezheng Xu, Ruiyi Fang, Binkun Bao, Charles X. Ling, Boyu Wang
Abstract: Deep imbalanced regression (DIR), where the target values have a highly skewed distribution and are also continuous, is an intriguing yet under-explored problem in machine learning. While recent works have already shown that incorporating various classification-based regularizers can produce enhanced outcomes, the role of classification remains elusive in DIR. Moreover, such regularizers (e.g., contrastive penalties) merely focus on learning discriminative features of data, which inevitably results in ignorance of either continuity or similarity across the data. To address these issues, we first bridge the connection between the objectives of DIR and classification from a Bayesian perspective. Consequently, this motivates us to decompose the objective of DIR into a combination of classification and regression tasks, which naturally guides us toward a divide-and-conquer manner to solve the DIR problem. Specifically, by aggregating the data at nearby labels into the same groups, we introduce an ordinal group-aware contrastive learning loss along with a multi-experts regressor to tackle the different groups of data thereby maintaining the data continuity. Meanwhile, considering the similarity between the groups, we also propose a symmetric descending soft labeling strategy to exploit the intrinsic similarity across the data, which allows classification to facilitate regression more effectively. Extensive experiments on real-world datasets also validate the effectiveness of our method.
Authors: Saaketh Desai, Sadhvikas Addamane, Jeffrey Y. Tsao, Igal Brener, Laura P. Swiler, Remi Dingreville, Prasad P. Iyer
Abstract: Advances in robotic control and sensing have propelled the rise of automated scientific laboratories capable of high-throughput experiments. However, automated scientific laboratories are currently limited by human intuition in their ability to efficiently design and interpret experiments in high-dimensional spaces, throttling scientific discovery. We present AutoSciLab, a machine learning framework for driving autonomous scientific experiments, forming a surrogate researcher purposed for scientific discovery in high-dimensional spaces. AutoSciLab autonomously follows the scientific method in four steps: (i) generating high-dimensional experiments (x \in R^D) using a variational autoencoder (ii) selecting optimal experiments by forming hypotheses using active learning (iii) distilling the experimental results to discover relevant low-dimensional latent variables (z \in R^d, with d << D) with a 'directional autoencoder' and (iv) learning a human interpretable equation connecting the discovered latent variables with a quantity of interest (y = f(z)), using a neural network equation learner. We validate the generalizability of AutoSciLab by rediscovering a) the principles of projectile motion and b) the phase transitions within the spin-states of the Ising model (NP-hard problem). Applying our framework to an open-ended nanophotonics challenge, AutoSciLab uncovers a fundamentally novel method for directing incoherent light emission that surpasses the current state-of-the-art (Iyer et al. 2023b, 2020).
Authors: M. Ayoub Ben Ayad, Jelena Mitrovic, Michael Granitzer
Abstract: We introduce Krony-PT, a compression technique of GPT2 \citep{radford2019language} based on Kronecker Products. We specifically target the MLP layers of each transformer layer, and systematically compress the feed forward layer matrices to various degrees. We introduce a modified Van Loan decomposition to initialize the new factors, and also introduce a new pruning-based initialization trick. Our method compresses the original 124M parameter GPT2 to various smaller models, with 80M being the smallest, and 96M being the largest compressed model. Our 81M model variant outperforms distilgpt2 on next-token prediction on all standard language modeling datasets, and shows competitive scores or performs on par with other Kronecker Products based compressed models of GPT2 that are significantly higher in size.
Authors: Yihong Jin, Ze Yang
Abstract: The detection of scams within Ethereum smart contracts is a critical challenge due to their increasing exploitation for fraudulent activities, leading to significant financial and reputational damages. Existing detection methods often rely on contract code analysis or manually extracted features, which suffer from scalability and adaptability limitations. In this study, we introduce an innovative method that leverages graph representation learning to examine transaction patterns and identify fraudulent contracts. By transforming Ethereum transaction data into graph structures and employing advanced machine learning models, we achieve robust classification performance. Our method addresses label imbalance through SMOTE-ENN techniques and evaluates models like Multi-Layer Perceptron (MLP) and Graph Convolutional Networks (GCN). Experimental results indicate that the MLP model surpasses the GCN in this context, with real-world evaluations aligning closely with domain-specific analyses. This study provides a scalable and effective solution for enhancing trust and security in the Ethereum ecosystem.
Authors: Maryam Aliakbarpour, Konstantina Bairaktari, Adam Smith, Marika Swanberg, Jonathan Ullman
Abstract: Model personalization allows a set of individuals, each facing a different learning task, to train models that are more accurate for each person than those they could develop individually. The goals of personalization are captured in a variety of formal frameworks, such as multitask learning and metalearning. Combining data for model personalization poses risks for privacy because the output of an individual's model can depend on the data of other individuals. In this work we undertake a systematic study of differentially private personalized learning. Our first main contribution is to construct a taxonomy of formal frameworks for private personalized learning. This taxonomy captures different formal frameworks for learning as well as different threat models for the attacker. Our second main contribution is to prove separations between the personalized learning problems corresponding to different choices. In particular, we prove a novel separation between private multitask learning and private metalearning.
Authors: Dionysios Varelas, Elena Bonan, Lewis Anderson, Anders Englesson, Christoffer {\AA}hrling, Adrian Chmielewski-Anders
Abstract: Machine learning (ML) systems have become vital in the mobile gaming industry. Companies like King have been using them in production to optimize various parts of the gaming experience. One important area is in-app purchases: purchases made in the game by players in order to enhance and customize their gameplay experience. In this work we describe how we developed an ML system in order to predict when a player is expected to make their next in-app purchase. These predictions are used to present offers to players. We briefly describe the problem definition, modeling approach and results and then, in considerable detail, outline the end-to-end ML system. We conclude with a reflection on challenges encountered and plans for future work.
Authors: Qingyang Zhou, Kangjie Lu, Meng Xu
Abstract: Causal inconsistency arises when the underlying causal graphs captured by generative models like \textit{Normalizing Flows} (NFs) are inconsistent with those specified in causal models like \textit{Struct Causal Models} (SCMs). This inconsistency can cause unwanted issues including the unfairness problem. Prior works to achieve causal consistency inevitably compromise the expressiveness of their models by disallowing hidden layers. In this work, we introduce a new approach: \textbf{C}ausally \textbf{C}onsistent \textbf{N}ormalizing \textbf{F}low (CCNF). To the best of our knowledge, CCNF is the first causally consistent generative model that can approximate any distribution with multiple layers. CCNF relies on two novel constructs: a sequential representation of SCMs and partial causal transformations. These constructs allow CCNF to inherently maintain causal consistency without sacrificing expressiveness. CCNF can handle all forms of causal inference tasks, including interventions and counterfactuals. Through experiments, we show that CCNF outperforms current approaches in causal inference. We also empirically validate the practical utility of CCNF by applying it to real-world datasets and show how CCNF addresses challenges like unfairness effectively.
Authors: Asela Hevapathige, Qing Wang, Ahad N. Zehmakan
Abstract: Influence maximization is key topic in data mining, with broad applications in social network analysis and viral marketing. In recent years, researchers have increasingly turned to machine learning techniques to address this problem. They have developed methods to learn the underlying diffusion processes in a data-driven manner, which enhances the generalizability of the solution, and have designed optimization objectives to identify the optimal seed set. Nonetheless, two fundamental gaps remain unsolved: (1) Graph Neural Networks (GNNs) are increasingly used to learn diffusion models, but in their traditional form, they often fail to capture the complex dynamics of influence diffusion, (2) Designing optimization objectives is challenging due to combinatorial explosion when solving this problem. To address these challenges, we propose a novel framework, DeepSN. Our framework employs sheaf neural diffusion to learn diverse influence patterns in a data-driven, end-to-end manner, providing enhanced separability in capturing diffusion characteristics. We also propose an optimization technique that accounts for overlapping influence between vertices, which helps to reduce the search space and identify the optimal seed set effectively and efficiently. Finally, we conduct extensive experiments on both synthetic and real-world datasets to demonstrate the effectiveness of our framework.
Authors: Nikola Zubi\'c, Davide Scaramuzza
Abstract: State Space Models (SSMs) are powerful tools for modeling sequential data in computer vision and time series analysis domains. However, traditional SSMs are limited by fixed, one-dimensional sequential processing, which restricts their ability to model non-local interactions in high-dimensional data. While methods like Mamba and VMamba introduce selective and flexible scanning strategies, they rely on predetermined paths, which fails to efficiently capture complex dependencies. We introduce Graph-Generating State Space Models (GG-SSMs), a novel framework that overcomes these limitations by dynamically constructing graphs based on feature relationships. Using Chazelle's Minimum Spanning Tree algorithm, GG-SSMs adapt to the inherent data structure, enabling robust feature propagation across dynamically generated graphs and efficiently modeling complex dependencies. We validate GG-SSMs on 11 diverse datasets, including event-based eye-tracking, ImageNet classification, optical flow estimation, and six time series datasets. GG-SSMs achieve state-of-the-art performance across all tasks, surpassing existing methods by significant margins. Specifically, GG-SSM attains a top-1 accuracy of 84.9% on ImageNet, outperforming prior SSMs by 1%, reducing the KITTI-15 error rate to 2.77%, and improving eye-tracking detection rates by up to 0.33% with fewer parameters. These results demonstrate that dynamic scanning based on feature relationships significantly improves SSMs' representational power and efficiency, offering a versatile tool for various applications in computer vision and beyond.
Authors: Xuan Shen, Zhao Song, Yufa Zhou, Bo Chen, Jing Liu, Ruiyi Zhang, Ryan A. Rossi, Hao Tan, Tong Yu, Xiang Chen, Yufan Zhou, Tong Sun, Pu Zhao, Yanzhi Wang, Jiuxiang Gu
Abstract: Transformers have emerged as the leading architecture in deep learning, proving to be versatile and highly effective across diverse domains beyond language and image processing. However, their impressive performance often incurs high computational costs due to their substantial model size. This paper focuses on compressing decoder-only transformer-based autoregressive models through structural weight pruning to improve the model efficiency while preserving performance for both language and image generation tasks. Specifically, we propose a training-free pruning method that calculates a numerical score with Newton's method for the Attention and MLP modules, respectively. Besides, we further propose another compensation algorithm to recover the pruned model for better performance. To verify the effectiveness of our method, we provide both theoretical support and extensive experiments. Our experiments show that our method achieves state-of-the-art performance with reduced memory usage and faster generation speeds on GPUs.
Authors: Xuan Shen, Zhao Song, Yufa Zhou, Bo Chen, Yanyu Li, Yifan Gong, Kai Zhang, Hao Tan, Jason Kuen, Henghui Ding, Zhihao Shu, Wei Niu, Pu Zhao, Yanzhi Wang, Jiuxiang Gu
Abstract: Diffusion Transformers have emerged as the preeminent models for a wide array of generative tasks, demonstrating superior performance and efficacy across various applications. The promising results come at the cost of slow inference, as each denoising step requires running the whole transformer model with a large amount of parameters. In this paper, we show that performing the full computation of the model at each diffusion step is unnecessary, as some computations can be skipped by lazily reusing the results of previous steps. Furthermore, we show that the lower bound of similarity between outputs at consecutive steps is notably high, and this similarity can be linearly approximated using the inputs. To verify our demonstrations, we propose the \textbf{LazyDiT}, a lazy learning framework that efficiently leverages cached results from earlier steps to skip redundant computations. Specifically, we incorporate lazy learning layers into the model, effectively trained to maximize laziness, enabling dynamic skipping of redundant computations. Experimental results show that LazyDiT outperforms the DDIM sampler across multiple diffusion transformer models at various resolutions. Furthermore, we implement our method on mobile devices, achieving better performance than DDIM with similar latency.
Authors: Xunkai Li, Zhengyu Wu, Jiayi Wu, Hanwen Cui, Jishuo Jia, Rong-Hua Li, Guoren Wang
Abstract: With the increasing prevalence of cross-domain Text-Attributed Graph (TAG) Data (e.g., citation networks, recommendation systems, social networks, and ai4science), the integration of Graph Neural Networks (GNNs) and Large Language Models (LLMs) into a unified Model architecture (e.g., LLM as enhancer, LLM as collaborators, LLM as predictor) has emerged as a promising technological paradigm. The core of this new graph learning paradigm lies in the synergistic combination of GNNs' ability to capture complex structural relationships and LLMs' proficiency in understanding informative contexts from the rich textual descriptions of graphs. Therefore, we can leverage graph description texts with rich semantic context to fundamentally enhance Data quality, thereby improving the representational capacity of model-centric approaches in line with data-centric machine learning principles. By leveraging the strengths of these distinct neural network architectures, this integrated approach addresses a wide range of TAG-based Task (e.g., graph learning, graph reasoning, and graph question answering), particularly in complex industrial scenarios (e.g., supervised, few-shot, and zero-shot settings). In other words, we can treat text as a medium to enable cross-domain generalization of graph learning Model, allowing a single graph model to effectively handle the diversity of downstream graph-based Task across different data domains. This work serves as a foundational reference for researchers and practitioners looking to advance graph learning methodologies in the rapidly evolving landscape of LLM. We consistently maintain the related open-source materials at \url{https://github.com/xkLi-Allen/Awesome-GNN-in-LLMs-Papers}.
URLs: https://github.com/xkLi-Allen/Awesome-GNN-in-LLMs-Papers
Authors: Bin Dou, Baokun Wang, Yun Zhu, Xiaotong Lin, Yike Xu, Xiaorui Huang, Yang Chen, Yun Liu, Shaoshuai Han, Yongchao Liu, Tianyi Zhang, Yu Cheng, Weiqiang Wang, Chuntao Hong
Abstract: User targeting, the process of selecting targeted users from a pool of candidates for non-expert marketers, has garnered substantial attention with the advancements in digital marketing. However, existing user targeting methods encounter two significant challenges: (i) Poor cross-domain and cross-scenario transferability and generalization, and (ii) Insufficient forecastability in real-world applications. These limitations hinder their applicability across diverse industrial scenarios. In this work, we propose FIND, an industrial-grade, transferable, and forecastable user targeting foundation model. To enhance cross-domain transferability, our framework integrates heterogeneous multi-scenario user data, aligning them with one-sentence targeting demand inputs through contrastive pre-training. For improved forecastability, the text description of each user is derived based on anticipated future behaviors, while user representations are constructed from historical information. Experimental results demonstrate that our approach significantly outperforms existing baselines in cross-domain, real-world user targeting scenarios, showcasing the superior capabilities of FIND. Moreover, our method has been successfully deployed on the Alipay platform and is widely utilized across various scenarios.
Authors: Long Jin, Han Nong, Liangming Chen, Zhenming Su
Abstract: The insufficient generalization of adaptive moment estimation (Adam) has hindered its broader application. Recent studies have shown that flat minima in loss landscapes are highly associated with improved generalization. Inspired by the filtering effect of integration operations on high-frequency signals, we propose multiple integral Adam (MIAdam), a novel optimizer that integrates a multiple integral term into Adam. This multiple integral term effectively filters out sharp minima encountered during optimization, guiding the optimizer towards flatter regions and thereby enhancing generalization capability. We provide a theoretical explanation for the improvement in generalization through the diffusion theory framework and analyze the impact of the multiple integral term on the optimizer's convergence. Experimental results demonstrate that MIAdam not only enhances generalization and robustness against label noise but also maintains the rapid convergence characteristic of Adam, outperforming Adam and its variants in state-of-the-art benchmarks.
Authors: Alex Mallen, Charlie Griffin, Alessandro Abate, Buck Shlegeris
Abstract: AI control protocols are plans for usefully deploying AI systems in a way that is safe, even if the AI intends to subvert the protocol. Previous work evaluated protocols by subverting them with a human-AI red team, where an AI follows the human-written strategy. This paper investigates how well AI systems can generate and act on strategies for subverting control protocols whilst operating without private memory. Usually, decision-makers only need the ability to generate optimal plans. However, to subvert a protocol, an AI system must be able to reliably generate optimal plans in each context; coordinate plans with other instances of itself without communicating; and take actions with well-calibrated probabilities. We develop evaluations for a model's ability to generate subversion strategies and develop affordance experiments that help isolate component capabilities. Our initial evaluations with Claude-3.5-sonnet highlight reasons why statelessly strategizing to subvert control protocols might be hard. We hope that our work can serve as a starting point for evaluations aimed at assessing whether a model is capable of strategizing to subvert control protocols.
Authors: Shibing Mo, Kai Wu, Qixuan Gao, Xiangyi Teng, Jing Liu
Abstract: In real-world applications, spectral Graph Neural Networks (GNNs) are powerful tools for processing diverse types of graphs. However, a single GNN often struggles to handle different graph types-such as homogeneous and heterogeneous graphs-simultaneously. This challenge has led to the manual design of GNNs tailored to specific graph types, but these approaches are limited by the high cost of labor and the constraints of expert knowledge, which cannot keep up with the rapid growth of graph data. To overcome these challenges, we propose AutoSGNN, an automated framework for discovering propagation mechanisms in spectral GNNs. AutoSGNN unifies the search space for spectral GNNs by integrating large language models with evolutionary strategies to automatically generate architectures that adapt to various graph types. Extensive experiments on nine widely-used datasets, encompassing both homophilic and heterophilic graphs, demonstrate that AutoSGNN outperforms state-of-the-art spectral GNNs and graph neural architecture search methods in both performance and efficiency.
Authors: Yicheng Feng, Yuetao Chen, Kaiwen Chen, Jingzong Li, Tianyuan Wu, Peng Cheng, Chuan Wu, Wei Wang, Tsung-Yi Ho, Hong Xu
Abstract: Simulation offers unique values for both enumeration and extrapolation purposes, and is becoming increasingly important for managing the massive machine learning (ML) clusters and large-scale distributed training jobs. In this paper, we build Echo to tackle three key challenges in large-scale training simulation: (1) tracing the runtime training workloads at each device in an ex-situ fashion so we can use a single device to obtain the actual execution graphs of 1K-GPU training, (2) accurately estimating the collective communication without high overheads of discrete-event based network simulation, and (3) accounting for the interference-induced computation slowdown from overlapping communication and computation kernels on the same device. Echo delivers on average 8% error in training step -- roughly 3x lower than state-of-the-art simulators -- for GPT-175B on a 96-GPU H800 cluster with 3D parallelism on Megatron-LM under 2 minutes.
Authors: Wenbin An, Haonan Lin, Jiahao Nie, Feng Tian, Wenkai Shi, Yaqiang Wu, Qianying Wang, Ping Chen
Abstract: Generalized Category Discovery is a significant and complex task that aims to identify both known and undefined novel categories from a set of unlabeled data, leveraging another labeled dataset containing only known categories. The primary challenges stem from model bias induced by pre-training on only known categories and the lack of precise supervision for novel ones, leading to category bias towards known categories and category confusion among different novel categories, which hinders models' ability to identify novel categories effectively. To address these challenges, we propose a novel framework named Self-Debiasing Calibration (SDC). Unlike prior methods that regard model bias towards known categories as an obstacle to novel category identification, SDC provides a novel insight into unleashing the potential of the bias to facilitate novel category learning. Specifically, the output of the biased model serves two key purposes. First, it provides an accurate modeling of category bias, which can be utilized to measure the degree of bias and debias the output of the current training model. Second, it offers valuable insights for distinguishing different novel categories by transferring knowledge between similar categories. Based on these insights, SDC dynamically adjusts the output logits of the current training model using the output of the biased model. This approach produces less biased logits to effectively address the issue of category bias towards known categories, and generates more accurate pseudo labels for unlabeled data, thereby mitigating category confusion for novel categories. Experiments on three benchmark datasets show that SDC outperforms SOTA methods, especially in the identification of novel categories. Our code and data are available at \url{https://github.com/Lackel/SDC}.
Authors: Austin Cheng, Alston Lo, Kin Long Kelvin Lee, Santiago Miret, Al\'an Aspuru-Guzik
Abstract: Molecular structure elucidation is a fundamental step in understanding chemical phenomena, with applications in identifying molecules in natural products, lab syntheses, forensic samples, and the interstellar medium. We consider the task of predicting a molecule's all-atom 3D structure given only its molecular formula and moments of inertia, motivated by the ability of rotational spectroscopy to measure these moments. While existing generative models can conditionally sample 3D structures with approximately correct moments, this soft conditioning fails to leverage the many digits of precision afforded by experimental rotational spectroscopy. To address this, we first show that the space of $n$-atom point clouds with a fixed set of moments of inertia is embedded in the Stiefel manifold $\mathrm{St}(n, 4)$. We then propose Stiefel Flow Matching as a generative model for elucidating 3D structure under exact moment constraints. Additionally, we learn simpler and shorter flows by finding approximate solutions for equivariant optimal transport on the Stiefel manifold. Empirically, enforcing exact moment constraints allows Stiefel Flow Matching to achieve higher success rates and faster sampling than Euclidean diffusion models, even on high-dimensional manifolds corresponding to large molecules in the GEOM dataset.
Authors: Niloufar Eghbali, Tuka Alhanai, Mohammad M. Ghassemi
Abstract: Mechanical Ventilation (MV) is a critical life-support intervention in intensive care units (ICUs). However, optimal ventilator settings are challenging to determine because of the complexity of balancing patient-specific physiological needs with the risks of adverse outcomes that impact morbidity, mortality, and healthcare costs. This study introduces ConformalDQN, a novel distribution-free conformal deep Q-learning approach for optimizing mechanical ventilation in intensive care units. By integrating conformal prediction with deep reinforcement learning, our method provides reliable uncertainty quantification, addressing the challenges of Q-value overestimation and out-of-distribution actions in offline settings. We trained and evaluated our model using ICU patient records from the MIMIC-IV database. ConformalDQN extends the Double DQN architecture with a conformal predictor and employs a composite loss function that balances Q-learning with well-calibrated probability estimation. This enables uncertainty-aware action selection, allowing the model to avoid potentially harmful actions in unfamiliar states and handle distribution shifts by being more conservative in out-of-distribution scenarios. Evaluation against baseline models, including physician policies, policy constraint methods, and behavior cloning, demonstrates that ConformalDQN consistently makes recommendations within clinically safe and relevant ranges, outperforming other methods by increasing the 90-day survival rate. Notably, our approach provides an interpretable measure of confidence in its decisions, which is crucial for clinical adoption and potential human-in-the-loop implementations.
Authors: Hai Lin, Cheng Huang, Zhihong Chen
Abstract: Reinforcement learning tasks in real-world scenarios often involve large, high-dimensional action spaces, leading to challenges such as convergence difficulties, instability, and high computational complexity. It is widely acknowledged that traditional value-based reinforcement learning algorithms struggle to address these issues effectively. A prevalent approach involves generating independent sub-actions within each dimension of the action space. However, this method introduces bias, hindering the learning of optimal policies. In this paper, we propose an advantage-based optimization method and an algorithm named Advantage Branching Dueling Q-network (ABQ). ABQ incorporates a baseline mechanism to tune the action value of each dimension, leveraging the advantage relationship across different sub-actions. With this approach, the learned policy can be optimized for each dimension. Empirical results demonstrate that ABQ outperforms BDQ, achieving 3%, 171%, and 84% more cumulative rewards in HalfCheetah, Ant, and Humanoid environments, respectively. Furthermore, ABQ exhibits competitive performance when compared against two continuous action benchmark algorithms, DDPG and TD3.
Authors: Iftekharul Islam, Weizi Li
Abstract: Managing mixed traffic comprising human-driven and robot vehicles (RVs) across large-scale networks presents unique challenges beyond single-intersection control. This paper proposes a reinforcement learning framework for coordinating mixed traffic across multiple interconnected intersections. Our key contribution is a neighbor-aware reward mechanism that enables RVs to maintain balanced distribution across the network while optimizing local intersection efficiency. We evaluate our approach using a real-world network, demonstrating its effectiveness in managing realistic traffic patterns. Results show that our method reduces average waiting times by 39.2% compared to the state-of-the-art single-intersection control policy and 79.8% compared to traditional traffic signals. The framework's ability to coordinate traffic across multiple intersections while maintaining balanced RV distribution provides a foundation for deploying learning-based solutions in urban traffic systems.
Authors: Rui Zhang, Ka-Ho Chow, Ping Li
Abstract: The growing concern over data privacy, the benefits of utilizing data from diverse sources for model training, and the proliferation of networked devices with enhanced computational capabilities have all contributed to the rise of federated learning (FL). The clients in FL collaborate to train a global model by uploading gradients computed on their private datasets without collecting raw data. However, a new attack surface has emerged from gradient sharing, where adversaries can restore the label distribution of a victim's private data by analyzing the obtained gradients. To mitigate this privacy leakage, existing lightweight defenses restrict the sharing of gradients, such as encrypting the final-layer gradients or locally updating the parameters within. In this paper, we introduce a novel attack called Gradient Bridge (GDBR) that recovers the label distribution of training data from the limited gradient information shared in FL. GDBR explores the relationship between the layer-wise gradients, tracks the flow of gradients, and analytically derives the batch training labels. Extensive experiments show that GDBR can accurately recover more than 80% of labels in various FL settings. GDBR highlights the inadequacy of restricted gradient sharing-based defenses and calls for the design of effective defense schemes in FL.
Authors: Konstantin Avrachenkov, Vivek S. Borkar, Pratik Shah
Abstract: We study the Lagrangian Index Policy (LIP) for restless multi-armed bandits with long-run average reward. In particular, we compare the performance of LIP with the performance of the Whittle Index Policy (WIP), both heuristic policies known to be asymptotically optimal under certain natural conditions. Even though in most cases their performances are very similar, in the cases when WIP shows bad performance, LIP continues to perform very well. We then propose reinforcement learning algorithms, both tabular and NN-based, to obtain online learning schemes for LIP in the model-free setting. The proposed reinforcement learning schemes for LIP requires significantly less memory than the analogous scheme for WIP. We calculate analytically the Lagrangian index for the restart model, which describes the optimal web crawling and the minimization of the weighted age of information. We also give a new proof of asymptotic optimality in case of homogeneous bandits as the number of arms goes to infinity, based on exchangeability and de Finetti's theorem.
Authors: Zijin Liu, Xiang Zhao, You Song
Abstract: Spatiotemporal data imputation plays a crucial role in various fields such as traffic flow monitoring, air quality assessment, and climate prediction. However, spatiotemporal data collected by sensors often suffer from temporal incompleteness, and the sparse and uneven distribution of sensors leads to missing data in the spatial dimension. Among existing methods, autoregressive approaches are prone to error accumulation, while simple conditional diffusion models fail to adequately capture the spatiotemporal relationships between observed and missing data. To address these issues, we propose a novel two-stage Refined Diffusion Probability Impuation (RDPI) framework based on an initial network and a conditional diffusion model. In the initial stage, deterministic imputation methods are used to generate preliminary estimates of the missing data. In the refinement stage, residuals are treated as the diffusion target, and observed values are innovatively incorporated into the forward process. This results in a conditional diffusion model better suited for spatiotemporal data imputation, bridging the gap between the preliminary estimates and the true values. Experiments on multiple datasets demonstrate that RDPI not only achieves state-of-the-art imputation accuracy but also significantly reduces sampling computational costs.
Authors: Huachao Yan, Kailing Guo, Shiwei Song, Yihai Dai, Xiaoqiang Wei, Xiaofen Xing, Xiangmin Xu
Abstract: Diagnosing seizure onset zone (SOZ) is a challenge in neurosurgery, where stereoelectroencephalography (sEEG) serves as a critical technique. In sEEG SOZ identification, the existing studies focus solely on the intra-patient representation of epileptic information, overlooking the general features of epilepsy across patients and feature interdependencies between feature elements in each contact site. In order to address the aforementioned challenges, we propose the shared attention-based autoencoder (sATAE). sATAE is trained by sEEG data across all patients, with attention blocks introduced to enhance the representation of interdependencies between feature elements. Considering the spatial diversity of sEEG across patients, we introduce graph-based method for identification SOZ of each patient. However, the current graph-based methods for sEEG SOZ identification rely exclusively on static graphs to model epileptic networks. Inspired by the finding of neuroscience that epileptic network is intricately characterized by the interplay of sophisticated equilibrium between fluctuating and stable states, we design the hierarchical fusion-based graph convolution network (HFGCN) to identify the SOZ. HFGCN integrates the dynamic and static characteristics of epileptic networks through hierarchical weighting across different hierarchies, facilitating a more comprehensive learning of epileptic features and enriching node information for sEEG SOZ identification. Combining sATAE and HFGCN, we perform comprehensive experiments with sATAE-HFGCN on the self-build sEEG dataset, which includes sEEG data from 17 patients with temporal lobe epilepsy. The results show that our method, sATAE-HFGCN, achieves superior performance for identifying the SOZ of each patient, effectively addressing the aforementioned challenges, providing an efficient solution for sEEG-based SOZ identification.
Authors: Seungeun Oh, Jinhyuk Kim, Jihong Park, Seung-Woo Ko, Tony Q. S. Quek, Seong-Lyun Kim
Abstract: This paper studies a hybrid language model (HLM) architecture that integrates a small language model (SLM) operating on a mobile device with a large language model (LLM) hosted at the base station (BS) of a wireless network. The HLM token generation process follows the speculative inference principle: the SLM's vocabulary distribution is uploaded to the LLM, which either accepts or rejects it, with rejected tokens being resampled by the LLM. While this approach ensures alignment between the vocabulary distributions of the SLM and LLM, it suffers from low token throughput due to uplink transmission and the computation costs of running both language models. To address this, we propose a novel HLM structure coined Uncertainty-aware HLM (U-HLM), wherein the SLM locally measures its output uncertainty, and skips both uplink transmissions and LLM operations for tokens that are likely to be accepted. This opportunistic skipping is enabled by our empirical finding of a linear correlation between the SLM's uncertainty and the LLM's rejection probability. We analytically derive the uncertainty threshold and evaluate its expected risk of rejection. Simulations show that U-HLM reduces uplink transmissions and LLM computation by 45.93%, while achieving up to 97.54% of the LLM's inference accuracy and 2.54$\times$ faster token throughput than HLM without skipping.
Authors: Ruixuan Miao, Xu Lu, Cong Tian, Bin Yu, Zhenhua Duan
Abstract: The commonly used Reinforcement Learning (RL) model, MDPs (Markov Decision Processes), has a basic premise that rewards depend on the current state and action only. However, many real-world tasks are non-Markovian, which has long-term memory and dependency. The reward sparseness problem is further amplified in non-Markovian scenarios. Hence learning a non-Markovian task (NMT) is inherently more difficult than learning a Markovian one. In this paper, we propose a novel \textbf{Par}allel and \textbf{Mod}ular RL framework, ParMod, specifically for learning NMTs specified by temporal logic. With the aid of formal techniques, the NMT is modulaized into a series of sub-tasks based on the automaton structure (equivalent to its temporal logic counterpart). On this basis, sub-tasks will be trained by a group of agents in a parallel fashion, with one agent handling one sub-task. Besides parallel training, the core of ParMod lies in: a flexible classification method for modularizing the NMT, and an effective reward shaping method for improving the sample efficiency. A comprehensive evaluation is conducted on several challenging benchmark problems with respect to various metrics. The experimental results show that ParMod achieves superior performance over other relevant studies. Our work thus provides a good synergy among RL, NMT and temporal logic.
Authors: Kassem Kallas
Abstract: This paper introduces a deep learning-based framework for resilient decision fusion in adversarial multi-sensor networks, providing a unified mathematical setup that encompasses diverse scenarios, including varying Byzantine node proportions, synchronized and unsynchronized attacks, unbalanced priors, adaptive strategies, and Markovian states. Unlike traditional methods, which depend on explicit parameter tuning and are limited by scenario-specific assumptions, the proposed approach employs a deep neural network trained on a globally constructed dataset to generalize across all cases without requiring adaptation. Extensive simulations validate the method's robustness, achieving superior accuracy, minimal error probability, and scalability compared to state-of-the-art techniques, while ensuring computational efficiency for real-time applications. This unified framework demonstrates the potential of deep learning to revolutionize decision fusion by addressing the challenges posed by Byzantine nodes in dynamic adversarial environments.
Authors: Vidya Prasad, Anna Vilanova, Nicola Pezzotti
Abstract: While deep generative models (DGMs) have gained popularity, their susceptibility to biases and other inefficiencies that lead to undesirable outcomes remains an issue. With their growing complexity, there is a critical need for early detection of issues to achieve desired results and optimize resources. Hence, we introduce a progressive analysis framework to monitor the training process of DGMs. Our method utilizes dimensionality reduction techniques to facilitate the inspection of latent representations, the generated and real distributions, and their evolution across training iterations. This monitoring allows us to pause and fix the training method if the representations or distributions progress undesirably. This approach allows for the analysis of a models' training dynamics and the timely identification of biases and failures, minimizing computational loads. We demonstrate how our method supports identifying and mitigating biases early in training a Generative Adversarial Network (GAN) and improving the quality of the generated data distribution.
Authors: Zehua Yu, Weihan Zhang, Sihan Pan, Jun Tao
Abstract: Ordering has been extensively studied in many visualization applications, such as axis and matrix reordering, for the simple reason that the order will greatly impact the perceived pattern of data. Many quality metrics concerning data pattern, perception, and aesthetics are proposed, and respective optimization algorithms are developed. However, the optimization problems related to ordering are often difficult to solve (e.g., TSP is NP-complete), and developing specialized optimization algorithms is costly. In this paper, we propose Versatile Ordering Network (VON), which automatically learns the strategy to order given a quality metric. VON uses the quality metric to evaluate its solutions, and leverages reinforcement learning with a greedy rollout baseline to improve itself. This keeps the metric transparent and allows VON to optimize over different metrics. Additionally, VON uses the attention mechanism to collect information across scales and reposition the data points with respect to the current context. This allows VONs to deal with data points following different distributions. We examine the effectiveness of VON under different usage scenarios and metrics. The results demonstrate that VON can produce comparable results to specialized solvers. The code is available at https://github.com/sysuvis/VON.
Authors: Ousmane Touat, Jezekael Brunon, Yacine Belal, Julien Nicolas, Mohamed Maouche, C\'esar Sabater, Sonia Ben Mokhtar
Abstract: The primary promise of decentralized learning is to allow users to engage in the training of machine learning models in a collaborative manner while keeping their data on their premises and without relying on any central entity. However, this paradigm necessitates the exchange of model parameters or gradients between peers. Such exchanges can be exploited to infer sensitive information about training data, which is achieved through privacy attacks (e.g Membership Inference Attacks -- MIA). In order to devise effective defense mechanisms, it is important to understand the factors that increase/reduce the vulnerability of a given decentralized learning architecture to MIA. In this study, we extensively explore the vulnerability to MIA of various decentralized learning architectures by varying the graph structure (e.g number of neighbors), the graph dynamics, and the aggregation strategy, across diverse datasets and data distributions. Our key finding, which to the best of our knowledge we are the first to report, is that the vulnerability to MIA is heavily correlated to (i) the local model mixing strategy performed by each node upon reception of models from neighboring nodes and (ii) the global mixing properties of the communication graph. We illustrate these results experimentally using four datasets and by theoretically analyzing the mixing properties of various decentralized architectures. Our paper draws a set of lessons learned for devising decentralized learning systems that reduce by design the vulnerability to MIA.
Authors: Jose L Salmeron, Irina Ar\'evalo
Abstract: Data privacy is a major concern in industries such as healthcare or finance. The requirement to safeguard privacy is essential to prevent data breaches and misuse, which can have severe consequences for individuals and organisations. Federated learning is a distributed machine learning approach where multiple participants collaboratively train a model without compromising the privacy of their data. However, a significant challenge arises from the differences in feature spaces among participants, known as non-IID data. This research introduces a novel federated learning framework employing fuzzy cognitive maps, designed to comprehensively address the challenges posed by diverse data distributions and non-identically distributed features in federated settings. The proposal is tested through several experiments using four distinct federation strategies: constant-based, accuracy-based, AUC-based, and precision-based weights. The results demonstrate the effectiveness of the approach in achieving the desired learning outcomes while maintaining privacy and confidentiality standards.
Authors: Jiaqi Wang, Liutao Yu, Liwei Huang, Chenlin Zhou, Han Zhang, Zhenxi Song, Min Zhang, Zhengyu Ma, Zhiguo Zhang
Abstract: The intrinsic dynamics and event-driven nature of spiking neural networks (SNNs) make them excel in processing temporal information by naturally utilizing embedded time sequences as time steps. Recent studies adopting this approach have demonstrated SNNs' effectiveness in speech command recognition, achieving high performance by employing large time steps for long time sequences. However, the large time steps lead to increased deployment burdens for edge computing applications. Thus, it is important to balance high performance and low energy consumption when detecting temporal patterns in edge devices. Our solution comprises two key components. 1). We propose a high-performance fully spike-driven framework termed SpikeSCR, characterized by a global-local hybrid structure for efficient representation learning, which exhibits long-term learning capabilities with extended time steps. 2). To further fully embrace low energy consumption, we propose an effective knowledge distillation method based on curriculum learning (KDCL), where valuable representations learned from the easy curriculum are progressively transferred to the hard curriculum with minor loss, striking a trade-off between power efficiency and high performance. We evaluate our method on three benchmark datasets: the Spiking Heidelberg Dataset (SHD), the Spiking Speech Commands (SSC), and the Google Speech Commands (GSC) V2. Our experimental results demonstrate that SpikeSCR outperforms current state-of-the-art (SOTA) methods across these three datasets with the same time steps. Furthermore, by executing KDCL, we reduce the number of time steps by 60% and decrease energy consumption by 54.8% while maintaining comparable performance to recent SOTA results. Therefore, this work offers valuable insights for tackling temporal processing challenges with long time sequences in edge neuromorphic computing systems.
Authors: Yoontae Hwang, Yongjae Lee
Abstract: Tabular data poses unique challenges due to its heterogeneous nature, combining both continuous and categorical variables. Existing approaches often struggle to effectively capture the underlying structure and relationships within such data. We propose GFTab (Geodesic Flow Kernels for Semi- Supervised Learning on Mixed-Variable Tabular Dataset), a semi-supervised framework specifically designed for tabular datasets. GFTab incorporates three key innovations: 1) Variable-specific corruption methods tailored to the distinct properties of continuous and categorical variables, 2) A Geodesic flow kernel based similarity measure to capture geometric changes between corrupted inputs, and 3) Tree-based embedding to leverage hierarchical relationships from available labeled data. To rigorously evaluate GFTab, we curate a comprehensive set of 21 tabular datasets spanning various domains, sizes, and variable compositions. Our experimental results show that GFTab outperforms existing ML/DL models across many of these datasets, particularly in settings with limited labeled data.
Authors: Zhenjiang Mao, Ivan Ruchkin
Abstract: Deep learning models are increasingly employed for perception, prediction, and control in complex systems. Embedding physical knowledge into these models is crucial for achieving realistic and consistent outputs, a challenge often addressed by physics-informed machine learning. However, integrating physical knowledge with representation learning becomes difficult when dealing with high-dimensional observation data, such as images, particularly under conditions of incomplete or imprecise state information. To address this, we propose Physically Interpretable World Models, a novel architecture that aligns learned latent representations with real-world physical quantities. Our method combines a variational autoencoder with a dynamical model that incorporates unknown system parameters, enabling the discovery of physically meaningful representations. By employing weak supervision with interval-based constraints, our approach eliminates the reliance on ground-truth physical annotations. Experimental results demonstrate that our method improves the quality of learned representations while achieving accurate predictions of future states, advancing the field of representation learning in dynamic systems.
Authors: Yujie Wang, Kui Yu, Yuhong Zhang, Fuyuan Cao, Jiye Liang
Abstract: Graph Neural Networks (GNNs) perform effectively when training and testing graphs are drawn from the same distribution, but struggle to generalize well in the face of distribution shifts. To address this issue, existing mainstreaming graph rationalization methods first identify rationale and environment subgraphs from input graphs, and then diversify training distributions by augmenting the environment subgraphs. However, these methods merely combine the learned rationale subgraphs with environment subgraphs in the representation space to produce augmentation samples, failing to produce sufficiently diverse distributions. Thus, in this paper, we propose to achieve an effective Graph Rationalization by Boosting Environmental diversity, a GRBE approach that generates the augmented samples in the original graph space to improve the diversity of the environment subgraph. Firstly, to ensure the effectiveness of augmentation samples, we propose a precise rationale subgraph extraction strategy in GRBE to refine the rationale subgraph learning process in the original graph space. Secondly, to ensure the diversity of augmented samples, we propose an environment diversity augmentation strategy in GRBE that mixes the environment subgraphs of different graphs in the original graph space and then combines the new environment subgraphs with rationale subgraphs to generate augmented graphs. The average improvements of 7.65% and 6.11% in rationalization and classification performance on benchmark datasets demonstrate the superiority of GRBE over state-of-the-art approaches.
Authors: Nicholas Kiefer, Arvid Weyrauch, Muhammed \"Oz, Achim Streit, Markus G\"otz, Charlotte Debus
Abstract: The current landscape in time-series forecasting is dominated by Transformer-based models. Their high parameter count and corresponding demand in computational resources pose a challenge to real-world deployment, especially for commercial and scientific applications with low-power embedded devices. Pruning is an established approach to reduce neural network parameter count and save compute. However, the implications and benefits of pruning Transformer-based models for time series forecasting are largely unknown. To close this gap, we provide a comparative benchmark study by evaluating unstructured and structured pruning on various state-of-the-art multivariate time series models. We study the effects of these pruning strategies on model predictive performance and computational aspects like model size, operations, and inference time. Our results show that certain models can be pruned even up to high sparsity levels, outperforming their dense counterpart. However, fine-tuning pruned models is necessary. Furthermore, we demonstrate that even with corresponding hardware and software support, structured pruning is unable to provide significant time savings.
Authors: Jiexi Liu, Meng Cao, Songcan Chen
Abstract: Irregularly sampled multivariate time series (ISMTS) are prevalent in reality. Due to their non-uniform intervals between successive observations and varying sampling rates among series, the channel-independent (CI) strategy, which has been demonstrated more desirable for complete multivariate time series forecasting in recent studies, has failed. This failure can be further attributed to the sampling sparsity, which provides insufficient information for effective CI learning, thereby reducing its capacity. When we resort to the channel-dependent (CD) strategy, even higher capacity cannot mitigate the potential loss of diversity in learning similar embedding patterns across different channels. We find that existing work considers CI and CD strategies to be mutually exclusive, primarily because they apply these strategies to the global channel. However, we hold the view that channel strategies do not necessarily have to be used globally. Instead, by appropriately applying them locally and globally, we can create an opportunity to take full advantage of both strategies. This leads us to introduce the Channel Harmony ISMTS Transformer (TimeCHEAT), which utilizes the CD locally and the CI globally. Specifically, we segment the ISMTS into sub-series level patches. Locally, the CD strategy aggregates information within each patch for time embedding learning, maximizing the use of relevant observations while reducing long-range irrelevant interference. Here, we enhance generality by transforming embedding learning into an edge weight prediction task using bipartite graphs, eliminating the need for special prior knowledge. Globally, the CI strategy is applied across patches, allowing the Transformer to learn individualized attention patterns for each channel. Experimental results indicate our proposed TimeCHEAT demonstrates competitive SOTA performance across three mainstream tasks.
Authors: Shreeyash Gowaikar, Srinivasan Iyengar, Sameer Segal, Shivkumar Kalyanaraman
Abstract: The Piping and Instrumentation Diagrams (P&IDs) are foundational to the design, construction, and operation of workflows in the engineering and process industries. However, their manual creation is often labor-intensive, error-prone, and lacks robust mechanisms for error detection and correction. While recent advancements in Generative AI, particularly Large Language Models (LLMs) and Vision-Language Models (VLMs), have demonstrated significant potential across various domains, their application in automating generation of engineering workflows remains underexplored. In this work, we introduce a novel copilot for automating the generation of P&IDs from natural language descriptions. Leveraging a multi-step agentic workflow, our copilot provides a structured and iterative approach to diagram creation directly from Natural Language prompts. We demonstrate the feasibility of the generation process by evaluating the soundness and completeness of the workflow, and show improved results compared to vanilla zero-shot and few-shot generation approaches.
Authors: Zhenyi Fan, Jiaqi Li, Dongyu Luo, Yuqi Yuan
Abstract: Hospital readmission prediction is critical for clinical decision support, aiming to identify patients at risk of returning within 30 days post-discharge. High readmission rates often indicate inadequate treatment or post-discharge care, making effective prediction models essential for optimizing resources and improving patient outcomes. We propose PT, a Transformer-based model that integrates Electronic Health Records (EHR), medical images, and clinical notes to predict 30-day all-cause hospital readmissions. PT extracts features from raw data and uses specialized Transformer blocks tailored to the data's complexity. Enhanced with Random Forest for EHR feature selection and test-time ensemble techniques, PT achieves superior accuracy, scalability, and robustness. It performs well even when temporal information is missing. Our main contributions are: (1)Simplicity: A powerful and efficient baseline model outperforming existing ones in prediction accuracy; (2)Scalability: Flexible handling of various features from different modalities, achieving high performance with just clinical notes or EHR data; (3)Robustness: Strong predictive performance even with missing or unclear temporal data.
Authors: Andrin Rehmann, Alexandre Bovet
Abstract: Signed graphs allow for encoding positive and negative relations between nodes and are used to model various online activities. Node representation learning for signed graphs is a well-studied task with important applications such as sign prediction. While the size of datasets is ever-increasing, recent methods often sacrifice scalability for accuracy. We propose a novel message-passing layer architecture called Graph Spring Network (GSN) modeled after spring forces. We combine it with a Graph Neural Ordinary Differential Equations (ODEs) formalism to optimize the system dynamics in embedding space to solve a downstream prediction task. Once the dynamics is learned, embedding generation for novel datasets is done by solving the ODEs in time using a numerical integration scheme. Our GSN layer leverages the fast-to-compute edge vector directions and learnable scalar functions that only depend on nodes' distances in latent space to compute the nodes' positions. Conversely, Graph Convolution and Graph Attention Network layers rely on learnable vector functions that require the full positions of input nodes in latent space. We propose a specific implementation called Spring-Neural-Network (SPR-NN) using a set of small neural networks mimicking attracting and repulsing spring forces that we train for link sign prediction. Experiments show that our method achieves accuracy close to the state-of-the-art methods with node generation time speedup factors of up to 28,000 on large graphs.
Authors: Liangqi Xie, Jicong Fan
Abstract: This paper aims to recover a multi-subspace matrix from permuted data: given a matrix, in which the columns are drawn from a union of low-dimensional subspaces and some columns are corrupted by permutations on their entries, recover the original matrix. The task has numerous practical applications such as data cleaning, integration, and de-anonymization, but it remains challenging and cannot be well addressed by existing techniques such as robust principal component analysis because of the presence of multiple subspaces and the permutations on the elements of vectors. To solve the challenge, we develop a novel four-stage algorithm pipeline including outlier identification, subspace reconstruction, outlier classification, and unsupervised sensing for permuted vector recovery. Particularly, we provide theoretical guarantees for the outlier classification step, ensuring reliable multi-subspace matrix recovery. Our pipeline is compared with state-of-the-art competitors on multiple benchmarks and shows superior performance.
Authors: Yuki Harada, Shuichi Maeda, Masato Kiyama, Shinichiro Nakamura
Abstract: Although experimental design and methodological surveys for mono-molecular activity/property has been extensively investigated, those for chemical composition have received little attention, with the exception of a few prior studies. In this study, we configured three simple DNN regressors to predict essential oil property based on chemical composition. Despite showing overfitting due to the small size of dataset, all models were trained effectively in this study.
Authors: Jonathan Svirsky, Yehonathan Refael, Ofir Lindenbaum
Abstract: Large Language Models (LLMs), with billions of parameters, present significant challenges for full finetuning due to the high computational demands, memory requirements, and impracticality of many real-world applications. When faced with limited computational resources or small datasets, updating all model parameters can often result in overfitting. To address this, lightweight finetuning techniques have been proposed, like learning low-rank adapter layers. These methods aim to train only a few additional parameters combined with the base model, which remains frozen, reducing resource usage and mitigating overfitting risks. In this work, we propose an adaptor model based on stochastic gates that simultaneously sparsify the frozen base model with task-specific adaptation. Our method comes with a small number of trainable parameters and allows us to speed up the base model inference with competitive accuracy. We evaluate it in additional variants by equipping it with additional low-rank parameters and comparing it to several recent baselines. Our results show that the proposed method improves the finetuned model accuracy comparatively to the several baselines and allows the removal of up to 20-40\% without significant accuracy loss.
Authors: Moritz Reuss, Jyothish Pari, Pulkit Agrawal, Rudolf Lioutikov
Abstract: Diffusion Policies have become widely used in Imitation Learning, offering several appealing properties, such as generating multimodal and discontinuous behavior. As models are becoming larger to capture more complex capabilities, their computational demands increase, as shown by recent scaling laws. Therefore, continuing with the current architectures will present a computational roadblock. To address this gap, we propose Mixture-of-Denoising Experts (MoDE) as a novel policy for Imitation Learning. MoDE surpasses current state-of-the-art Transformer-based Diffusion Policies while enabling parameter-efficient scaling through sparse experts and noise-conditioned routing, reducing both active parameters by 40% and inference costs by 90% via expert caching. Our architecture combines this efficient scaling with noise-conditioned self-attention mechanism, enabling more effective denoising across different noise levels. MoDE achieves state-of-the-art performance on 134 tasks in four established imitation learning benchmarks (CALVIN and LIBERO). Notably, by pretraining MoDE on diverse robotics data, we achieve 4.01 on CALVIN ABC and 0.95 on LIBERO-90. It surpasses both CNN-based and Transformer Diffusion Policies by an average of 57% across 4 benchmarks, while using 90% fewer FLOPs and fewer active parameters compared to default Diffusion Transformer architectures. Furthermore, we conduct comprehensive ablations on MoDE's components, providing insights for designing efficient and scalable Transformer architectures for Diffusion Policies. Code and demonstrations are available at https://mbreuss.github.io/MoDE_Diffusion_Policy/.
Authors: Uri Stern, Tomer Yaacoby, Daphna Weinshall
Abstract: The infrequent occurrence of overfitting in deep neural networks is perplexing: contrary to theoretical expectations, increasing model size often enhances performance in practice. But what if overfitting does occur, though restricted to specific sub-regions of the data space? In this work, we propose a novel score that captures the forgetting rate of deep models on validation data. We posit that this score quantifies local overfitting: a decline in performance confined to certain regions of the data space. We then show empirically that local overfitting occurs regardless of the presence of traditional overfitting. Using the framework of deep over-parametrized linear models, we offer a certain theoretical characterization of forgotten knowledge, and show that it correlates with knowledge forgotten by real deep models. Finally, we devise a new ensemble method that aims to recover forgotten knowledge, relying solely on the training history of a single network. When combined with self-distillation, this method enhances the performance of any trained model without adding inference costs. Extensive empirical evaluations demonstrate the efficacy of our method across multiple datasets, contemporary neural network architectures, and training protocols.
Authors: Guillaume Couairon, Renu Singh, Anastase Charantonis, Christian Lessig, Claire Monteleoni
Abstract: Weather forecasting plays a vital role in today's society, from agriculture and logistics to predicting the output of renewable energies, and preparing for extreme weather events. Deep learning weather forecasting models trained with the next state prediction objective on ERA5 have shown great success compared to numerical global circulation models. However, for a wide range of applications, being able to provide representative samples from the distribution of possible future weather states is critical. In this paper, we propose a methodology to leverage deterministic weather models in the design of probabilistic weather models, leading to improved performance and reduced computing costs. We first introduce \textbf{ArchesWeather}, a transformer-based deterministic model that improves upon Pangu-Weather by removing overrestrictive inductive priors. We then design a probabilistic weather model called \textbf{ArchesWeatherGen} based on flow matching, a modern variant of diffusion models, that is trained to project ArchesWeather's predictions to the distribution of ERA5 weather states. ArchesWeatherGen is a true stochastic emulator of ERA5 and surpasses IFS ENS and NeuralGCM on all WeatherBench headline variables (except for NeuralGCM's geopotential). Our work also aims to democratize the use of deterministic and generative machine learning models in weather forecasting research, with academic computing resources. All models are trained at 1.5{\deg} resolution, with a training budget of $\sim$9 V100 days for ArchesWeather and $\sim$45 V100 days for ArchesWeatherGen. For inference, ArchesWeatherGen generates 15-day weather trajectories at a rate of 1 minute per ensemble member on a A100 GPU card. To make our work fully reproducible, our code and models are open source, including the complete pipeline for data preparation, training, and evaluation, at https://github.com/INRIA/geoarches .
Authors: Wei Ju, Zhengyang Mao, Siyu Yi, Yifang Qin, Yiyang Gu, Zhiping Xiao, Jianhao Shen, Ziyue Qiao, Ming Zhang
Abstract: This paper studies the problem of class-imbalanced graph classification, which aims at effectively classifying the categories of graphs in scenarios with imbalanced class distribution. Despite the tremendous success of graph neural networks (GNNs), their modeling ability for imbalanced graph-structured data is inadequate, which typically leads to predictions biased towards the majority classes. Besides, existing class-imbalanced learning methods in visions may overlook the rich graph semantic substructures of the majority classes and excessively emphasize learning from the minority classes. To tackle this issue, this paper proposes a simple yet powerful approach called C$^3$GNN that incorporates the idea of clustering into contrastive learning to enhance class-imbalanced graph classification. Technically, C$^3$GNN clusters graphs from each majority class into multiple subclasses, ensuring they have similar sizes to the minority class, thus alleviating class imbalance. Additionally, it utilizes the Mixup technique to synthesize new samples and enrich the semantic information of each subclass, and leverages supervised contrastive learning to hierarchically learn effective graph representations. In this way, we can not only sufficiently explore the semantic substructures within the majority class but also effectively alleviate excessive focus on the minority class. Extensive experiments on real-world graph benchmark datasets verify the superior performance of our proposed method.
Authors: Emily Yu, {\DJ}or{\dj}e \v{Z}ikeli\'c, Thomas A. Henzinger
Abstract: Learning-based methods provide a promising approach to solving highly non-linear control tasks that are often challenging for classical control methods. To ensure the satisfaction of a safety property, learning-based methods jointly learn a control policy together with a certificate function for the property. Popular examples include barrier functions for safety and Lyapunov functions for asymptotic stability. While there has been significant progress on learning-based control with certificate functions in the white-box setting, where the correctness of the certificate function can be formally verified, there has been little work on ensuring their reliability in the black-box setting where the system dynamics are unknown. In this work, we consider the problems of certifying and repairing neural network control policies and certificate functions in the black-box setting. We propose a novel framework that utilizes runtime monitoring to detect system behaviors that violate the property of interest under some initially trained neural network policy and certificate. These violating behaviors are used to extract new training data, that is used to re-train the neural network policy and the certificate function and to ultimately repair them. We demonstrate the effectiveness of our approach empirically by using it to repair and to boost the safety rate of neural network policies learned by a state-of-the-art method for learning-based control on two autonomous system control tasks.
Authors: Hongyu Shen, Zhizhen Zhao
Abstract: Despite empirical risk minimization (ERM) is widely applied in the machine learning community, its performance is limited on data with spurious correlation or subpopulation that is introduced by hidden attributes. Existing literature proposed techniques to maximize group-balanced or worst-group accuracy when such correlation presents, yet, at the cost of lower average accuracy. In addition, many existing works conduct surveys on different subpopulation methods without revealing the inherent connection between these methods, which could hinder the technology advancement in this area. In this paper, we identify important sampling as a simple yet powerful tool for solving the subpopulation problem. On the theory side, we provide a new systematic formulation of the subpopulation problem and explicitly identify the assumptions that are not clearly stated in the existing works. This helps to uncover the cause of the dropped average accuracy. We provide the first theoretical discussion on the connections of existing methods, revealing the core components that make them different. On the application side, we demonstrate a single estimator is enough to solve the subpopulation problem. In particular, we introduce the estimator in both attribute-known and -unknown scenarios in the subpopulation setup, offering flexibility in practical use cases. And empirically, we achieve state-of-the-art performance on commonly used benchmark datasets.
Authors: Daniel Kaplan, Adam Zhang, Joanna Blawat, Rongying Jin, Robert J. Cava, Viktor Oudovenko, Gabriel Kotliar, Anirvan M. Sengupta, Weiwei Xie
Abstract: The discovery of novel superconducting materials is a longstanding challenge in materials science, with a wealth of potential for applications in energy, transportation, and computing. Recent advances in artificial intelligence (AI) have enabled expediting the search for new materials by efficiently utilizing vast materials databases. In this study, we developed an approach based on deep learning (DL) to predict new superconducting materials. We have synthesized a compound derived from our DL network and confirmed its superconducting properties in agreement with our prediction. Our approach is also compared to previous work based on random forests (RFs). In particular, RFs require knowledge of the chem-ical properties of the compound, while our neural net inputs depend solely on the chemical composition. With the help of hints from our network, we discover a new ternary compound $\textrm{Mo}_{20}\textrm{Re}_{6}\textrm{Si}_{4}$, which becomes superconducting below 5.4 K. We further discuss the existing limitations and challenges associated with using AI to predict and, along with potential future research directions.
Authors: Augustin Godinot, Erwan Le Merrer, Camilla Penzo, Fran\c{c}ois Ta\"iani, Gilles Tr\'edan
Abstract: The deployment of machine learning models in operational contexts represents a significant investment for any organisation. Consequently, the risk of these models being misappropriated by competitors needs to be addressed. In recent years, numerous proposals have been put forth to detect instances of model stealing. However, these proposals operate under implicit and disparate data and model access assumptions; as a consequence, it remains unclear how they can be effectively compared to one another. Our evaluation shows that a simple baseline that we introduce performs on par with existing state-of-the-art fingerprints, which, on the other hand, are much more complex. To uncover the reasons behind this intriguing result, this paper introduces a systematic approach to both the creation of model fingerprinting schemes and their evaluation benchmarks. By dividing model fingerprinting into three core components -- Query, Representation and Detection (QuRD) -- we are able to identify $\sim100$ previously unexplored QuRD combinations and gain insights into their performance. Finally, we introduce a set of metrics to compare and guide the creation of more representative model stealing detection benchmarks. Our approach reveals the need for more challenging benchmarks and a sound comparison with baselines. To foster the creation of new fingerprinting schemes and benchmarks, we open-source our fingerprinting toolbox.
Authors: Thai-Hoang Pham, Yuanlong Wang, Changchang Yin, Xueru Zhang, Ping Zhang
Abstract: Domain adaptation (DA) tackles the issue of distribution shift by learning a model from a source domain that generalizes to a target domain. However, most existing DA methods are designed for scenarios where the source and target domain data lie within the same feature space, which limits their applicability in real-world situations. Recently, heterogeneous DA (HeDA) methods have been introduced to address the challenges posed by heterogeneous feature space between source and target domains. Despite their successes, current HeDA techniques fall short when there is a mismatch in both feature and label spaces. To address this, this paper explores a new DA scenario called open-set HeDA (OSHeDA). In OSHeDA, the model must not only handle heterogeneity in feature space but also identify samples belonging to novel classes. To tackle this challenge, we first develop a novel theoretical framework that constructs learning bounds for prediction error on target domain. Guided by this framework, we propose a new DA method called Representation Learning for OSHeDA (RL-OSHeDA). This method is designed to simultaneously transfer knowledge between heterogeneous data sources and identify novel classes. Experiments across text, image, and clinical data demonstrate the effectiveness of our algorithm. Model implementation is available at \url{https://github.com/pth1993/OSHeDA}.
Authors: Weiguo Pian, Shijian Deng, Shentong Mo, Yunhui Guo, Yapeng Tian
Abstract: In this paper, we introduce Modality-Inconsistent Continual Learning (MICL), a new continual learning scenario for Multimodal Large Language Models (MLLMs) that involves tasks with inconsistent modalities (image, audio, or video) and varying task types (captioning or question-answering). Unlike existing vision-only or modality-incremental settings, MICL combines modality and task type shifts, both of which drive catastrophic forgetting. To address these challenges, we propose MoInCL, which employs a Pseudo Targets Generation Module to mitigate forgetting caused by task type shifts in previously seen modalities. It also incorporates Instruction-based Knowledge Distillation to preserve the model's ability to handle previously learned modalities when new ones are introduced. We benchmark MICL using a total of six tasks and conduct experiments to validate the effectiveness of our proposed MoInCL. The experimental results highlight the superiority of MoInCL, showing significant improvements over representative and state-of-the-art continual learning baselines.
Authors: M\'aty\'as Vincze, Laura Ferrarotti, Leonardo Lucio Custode, Bruno Lepri, Giovanni Iacca
Abstract: Continuous control tasks often involve high-dimensional, dynamic, and non-linear environments. State-of-the-art performance in these tasks is achieved through complex closed-box policies that are effective, but suffer from an inherent opacity. Interpretable policies, while generally underperforming compared to their closed-box counterparts, advantageously facilitate transparent decision-making within automated systems. Hence, their usage is often essential for diagnosing and mitigating errors, supporting ethical and legal accountability, and fostering trust among stakeholders. In this paper, we propose SMOSE, a novel method to train sparsely activated interpretable controllers, based on a top-1 Mixture-of-Experts architecture. SMOSE combines a set of interpretable decisionmakers, trained to be experts in different basic skills, and an interpretable router that assigns tasks among the experts. The training is carried out via state-of-the-art Reinforcement Learning algorithms, exploiting load-balancing techniques to ensure fair expert usage. We then distill decision trees from the weights of the router, significantly improving the ease of interpretation. We evaluate SMOSE on six benchmark environments from MuJoCo: our method outperforms recent interpretable baselines and narrows the gap with noninterpretable state-of-the-art algorithms
Authors: Ilan Doron-Arad
Abstract: We study neural network training (NNT): optimizing a neural network's parameters to minimize the training loss over a given dataset. NNT has been studied extensively under theoretic lenses, mainly on two-layer networks with linear or ReLU activation functions where the parameters can take any real value (here referred to as continuous NNT (C-NNT)). However, less is known about deeper neural networks, which exhibit substantially stronger capabilities in practice. In addition, the complexity of the discrete variant of the problem (D-NNT in short), in which the parameters are taken from a given finite set of options, has remained less explored despite its theoretical and practical significance. In this work, we show that the hardness of NNT is dramatically affected by the network depth. Specifically, we show that, under standard complexity assumptions, D-NNT is not in the complexity class NP even for instances with fixed dimensions and dataset size, having a deep architecture. This separates D-NNT from any NP-complete problem. Furthermore, using a polynomial reduction we show that the above result also holds for C-NNT, albeit with more structured instances. We complement these results with a comprehensive list of NP-hardness lower bounds for D-NNT on two-layer networks, showing that fixing the number of dimensions, the dataset size, or the number of neurons in the hidden layer leaves the problem challenging. Finally, we obtain a pseudo-polynomial algorithm for D-NNT on a two-layer network with a fixed dataset size.
Authors: Anthony Zhou, Amir Barati Farimani
Abstract: Neural surrogates for partial differential equations (PDEs) have become popular due to their potential to quickly simulate physics. With a few exceptions, neural surrogates generally treat the forward evolution of time-dependent PDEs as a black box by directly predicting the next state. While this is a natural and easy framework for applying neural surrogates, it can be an over-simplified and rigid framework for predicting physics. In this work, we propose an alternative framework in which neural solvers predict the temporal derivative and an ODE integrator forwards the solution in time, which has little overhead and is broadly applicable across model architectures and PDEs. We find that by simply changing the training target and introducing numerical integration during inference, neural surrogates can gain accuracy and stability. Predicting temporal derivatives also allows models to not be constrained to a specific temporal discretization, allowing for flexible time-stepping during inference or training on higher-resolution PDE data. Lastly, we investigate why this new framework can be beneficial and in what situations does it work well.
Authors: Kevin McKee
Abstract: Tasks in which rewards depend upon past information not available in the current observation set can only be solved by agents that are equipped with short-term memory. Usual choices for memory modules include trainable recurrent hidden layers, often with gated memory. Reservoir computing presents an alternative, in which a recurrent layer is not trained, but rather has a set of fixed, sparse recurrent weights. The weights are scaled to produce stable dynamical behavior such that the reservoir state contains a high-dimensional, nonlinear impulse response function of the inputs. An output decoder network can then be used to map the compressive history represented by the reservoir's state to any outputs, including agent actions or predictions. In this study, we find that reservoir computing greatly simplifies and speeds up reinforcement learning on memory tasks by (1) eliminating the need for backpropagation of gradients through time, (2) presenting all recent history simultaneously to the downstream network, and (3) performing many useful and generic nonlinear computations upstream from the trained modules. In particular, these findings offer significant benefit to meta-learning that depends primarily on efficient and highly general memory systems.
Authors: Junda Wang, Minghui Hu, Ning Li, Abdulaziz Al-Ali, Ponnuthurai Nagaratnam Suganthan
Abstract: Online learning of deep neural networks suffers from challenges such as hysteretic non-incremental updating, increasing memory usage, past retrospective retraining, and catastrophic forgetting. To alleviate these drawbacks and achieve progressive immediate decision-making, we propose a novel Incremental Online Learning (IOL) process of Randomized Neural Networks (Randomized NN), a framework facilitating continuous improvements to Randomized NN performance in restrictive online scenarios. Within the framework, we further introduce IOL with ridge regularization (-R) and IOL with forward regularization (-F). -R generates stepwise incremental updates without retrospective retraining and avoids catastrophic forgetting. Moreover, we substituted -R with -F as it enhanced precognition learning ability using semi-supervision and realized better online regrets to offline global experts compared to -R during IOL. The algorithms of IOL for Randomized NN with -R/-F on non-stationary batch stream were derived respectively, featuring recursive weight updates and variable learning rates. Additionally, we conducted a detailed analysis and theoretically derived relative cumulative regret bounds of the Randomized NN learners with -R/-F in IOL under adversarial assumptions using a novel methodology and presented several corollaries, from which we observed the superiority on online learning acceleration and regret bounds of employing -F in IOL. Finally, our proposed methods were rigorously examined across regression and classification tasks on diverse datasets, which distinctly validated the efficacy of IOL frameworks of Randomized NN and the advantages of forward regularization.
Authors: Ambedkar Dukkipati, Ranga Shaarad Ayyagari, Bodhisattwa Dasgupta, Parag Dutta, Prabhas Reddy Onteru
Abstract: Learning agents that excel at sequential decision-making tasks must continuously resolve the problem of exploration and exploitation for optimal learning. However, such interactions with the environment online might be prohibitively expensive and may involve some constraints, such as a limited budget for agent-environment interactions and restricted exploration in certain regions of the state space. Examples include selecting candidates for medical trials and training agents in complex navigation environments. This problem necessitates the study of active reinforcement learning strategies that collect minimal additional experience trajectories by reusing existing offline data previously collected by some unknown behavior policy. In this work, we propose a representation-aware uncertainty-based active trajectory collection method that intelligently decides interaction strategies that consider the distribution of the existing offline data. With extensive experimentation, we demonstrate that our proposed method reduces additional online interaction with the environment by up to 75% over competitive baselines across various continuous control environments.
Authors: Chao Ma, Wenbo Gong, Meyer Scetbon, Edward Meeds
Abstract: Adaptive optimizers such as Adam (Kingma & Ba, 2015) have been central to the success of large language models. However, they maintain additional moving average states throughout training, which results in memory requirements several times greater than the model. This overhead imposes constraints on scalability and computational efficiency. On the other hand, while stochastic gradient descent (SGD) is optimal in terms of memory efficiency, their capability in LLM training is limited (Zhao et al., 2024b). To address this dilemma, we show that pre-processing SGD is sufficient to reach Adam-level performance on LLMs. Specifically, we propose to preprocess the instantaneous stochastic gradients with two simple operators: $\mathtt{GradNorm}$ and $\mathtt{GradWhitening}$. $\mathtt{GradNorm}$ stabilizes gradient distributions, and $\mathtt{GradWhitening}$ counteracts the local curvature of the loss landscape, respectively. This results in SWAN (SGD with Whitening And Normalization), a stochastic optimizer that eliminates the need to store any accumulative state variables. Empirically, SWAN has the same memory footprint as SGD, achieving $\approx 50\%$ reduction on total end-to-end memory compared to Adam. In language modeling tasks, SWAN demonstrates the same or even a substantial improvement over Adam. Specifically, when pre-training the LLaMa model with 350M and 1.3B parameters, SWAN achieves a 2x speedup by reaching the same evaluation perplexity in less than half tokens seen.
Authors: Junyu Cao
Abstract: In many data-driven decision-making problems, performance guarantees often depend heavily on the correctness of model assumptions, which may frequently fail in practice. We address this issue in the context of a feature-based newsvendor problem, where demand is influenced by observed features such as demographics and seasonality. To mitigate the impact of model misspecification, we propose a model-free and distribution-free framework inspired by conformal prediction. Our approach consists of two phases: a training phase, which can utilize any type of prediction method, and a calibration phase that conformalizes the model bias. To enhance predictive performance, we explore the balance between data quality and quantity, recognizing the inherent trade-off: more selective training data improves quality but reduces quantity. Importantly, we provide statistical guarantees for the conformalized critical quantile, independent of the correctness of the underlying model. Moreover, we quantify the confidence interval of the critical quantile, with its width decreasing as data quality and quantity improve. We validate our framework using both simulated data and a real-world dataset from the Capital Bikeshare program in Washington, D.C. Across these experiments, our proposed method consistently outperforms benchmark algorithms, reducing newsvendor loss by up to 40% on the simulated data and 25% on the real-world dataset.
Authors: Chenglin Li, Guangchun Ruan, Hua Geng
Abstract: Safe reinforcement learning (RL) is a popular and versatile paradigm to learn reward-maximizing policies with safety guarantees. Previous works tend to express the safety constraints in an expectation form due to the ease of implementation, but this turns out to be ineffective in maintaining safety constraints with high probability. To this end, we move to the quantile-constrained RL that enables a higher level of safety without any expectation-form approximations. We directly estimate the quantile gradients through sampling and provide the theoretical proofs of convergence. Then a tilted update strategy for quantile gradients is implemented to compensate the asymmetric distributional density, with a direct benefit of return performance. Experiments demonstrate that the proposed model fully meets safety requirements (quantile constraints) while outperforming the state-of-the-art benchmarks with higher return.
Authors: Yifei Zhou, Qianlan Yang, Kaixiang Lin, Min Bai, Xiong Zhou, Yu-Xiong Wang, Sergey Levine, Erran Li
Abstract: The vision of a broadly capable and goal-directed agent, such as an Internet-browsing agent in the digital world and a household humanoid in the physical world, has rapidly advanced, thanks to the generalization capability of foundation models. Such a generalist agent needs to have a large and diverse skill repertoire, such as finding directions between two travel locations and buying specific items from the Internet. If each skill needs to be specified manually through a fixed set of human-annotated instructions, the agent's skill repertoire will necessarily be limited due to the quantity and diversity of human-annotated instructions. In this work, we address this challenge by proposing Proposer-Agent-Evaluator, an effective learning system that enables foundation model agents to autonomously discover and practice skills in the wild. At the heart of PAE is a context-aware task proposer that autonomously proposes tasks for the agent to practice with context information of the environment such as user demos or even just the name of the website itself for Internet-browsing agents. Then, the agent policy attempts those tasks with thoughts and actual grounded operations in the real world with resulting trajectories evaluated by an autonomous VLM-based success evaluator. The success evaluation serves as the reward signal for the agent to refine its policies through RL. We validate PAE on challenging vision-based web navigation, using both real-world and self-hosted websites from WebVoyager and WebArena.To the best of our knowledge, this work represents the first effective learning system to apply autonomous task proposal with RL for agents that generalizes real-world human-annotated benchmarks with SOTA performances. Our open-source checkpoints and code can be found in https://yanqval.github.io/PAE/
Authors: Geetanjali Bihani, Julia Taylor Rayz
Abstract: The advent of large language models (LLMs) has enabled significant performance gains in the field of natural language processing. However, recent studies have found that LLMs often resort to shortcuts when performing tasks, creating an illusion of enhanced performance while lacking generalizability in their decision rules. This phenomenon introduces challenges in accurately assessing natural language understanding in LLMs. Our paper provides a concise survey of relevant research in this area and puts forth a perspective on the implications of shortcut learning in the evaluation of language models, specifically for NLU tasks. This paper urges more research efforts to be put towards deepening our comprehension of shortcut learning, contributing to the development of more robust language models, and raising the standards of NLU evaluation in real-world scenarios.
Authors: Elana Simon, James Zou
Abstract: Protein language models (PLMs) have demonstrated remarkable success in protein modeling and design, yet their internal mechanisms for predicting structure and function remain poorly understood. Here we present a systematic approach to extract and analyze interpretable features from PLMs using sparse autoencoders (SAEs). By training SAEs on embeddings from the PLM ESM-2, we identify up to 2,548 human-interpretable latent features per layer that strongly correlate with up to 143 known biological concepts such as binding sites, structural motifs, and functional domains. In contrast, examining individual neurons in ESM-2 reveals up to 46 neurons per layer with clear conceptual alignment across 15 known concepts, suggesting that PLMs represent most concepts in superposition. Beyond capturing known annotations, we show that ESM-2 learns coherent concepts that do not map onto existing annotations and propose a pipeline using language models to automatically interpret novel latent features learned by the SAEs. As practical applications, we demonstrate how these latent features can fill in missing annotations in protein databases and enable targeted steering of protein sequence generation. Our results demonstrate that PLMs encode rich, interpretable representations of protein biology and we propose a systematic framework to extract and analyze these latent features. In the process, we recover both known biology and potentially new protein motifs. As community resources, we introduce InterPLM (interPLM.ai), an interactive visualization platform for exploring and analyzing learned PLM features, and release code for training and analysis at github.com/ElanaPearl/interPLM.
Authors: Tomoyuki Kubota, Yusuke Imai, Sumito Tsunegi, Kohei Nakajima
Abstract: A physical neural network (PNN) has both the strong potential to solve machine learning tasks and intrinsic physical properties, such as high-speed computation and energy efficiency. Reservoir computing (RC) is an excellent framework for implementing an information processing system with a dynamical system by attaching a trained readout, thus accelerating the wide use of unconventional materials for a PNN. However, RC requires the dynamics to reproducibly respond to input sequence, which limits the type of substance available for building information processors. Here we propose a novel framework called generalized reservoir computing (GRC) by turning this requirement on its head, making conventional RC a special case. Using substances that do not respond the same to identical inputs (e.g., a real spin-torque oscillator), we propose mechanisms aimed at obtaining a reliable output and show that processed inputs in the unconventional substance are retrievable. Finally, we demonstrate that, based on our framework, spatiotemporal chaos, which is thought to be unusable as a computational resource, can be used to emulate complex nonlinear dynamics, including large scale spatiotemporal chaos. Overall, our framework removes the limitation to building an information processing device and opens a path to constructing a computational system using a wider variety of physical dynamics.
Authors: Saloua Zammali, Siddhant Dutta, Sadok Ben Yahia
Abstract: In the field of Recommender Systems (RS), neural collaborative filtering represents a significant milestone by combining matrix factorization and deep neural networks to achieve promising results. Traditional methods like matrix factorization often rely on linear models, limiting their capability to capture complex interactions between users, items, and contexts. This limitation becomes particularly evident with high-dimensional datasets due to their inability to capture relationships among users, items, and contextual factors. Unsupervised learning and dimension reduction tasks utilize autoencoders, neural network-based models renowned for their capacity to encode and decode data. Autoencoders learn latent representations of inputs, reducing dataset size while capturing complex patterns and features. In this paper, we introduce a framework that combines neural contextual matrix factorization with autoencoders to predict user ratings for items. We provide a comprehensive overview of the framework's design and implementation. To evaluate its performance, we conduct experiments on various real-world datasets and compare the results against state-of-the-art approaches. We also extend the concept of conformal prediction to prediction rating and introduce a Conformal Prediction Rating (CPR). For RS, we define the nonconformity score, a key concept of conformal prediction, and demonstrate that it satisfies the exchangeability property.
Authors: Ahmed ElGazzar, Marcel van Gerven
Abstract: We propose a probabilistic framework for developing computational models of biological neural systems. In this framework, physiological recordings are viewed as discrete-time partial observations of an underlying continuous-time stochastic dynamical system which implements computations through its state evolution. To model this dynamical system, we employ a system of coupled stochastic differential equations with differentiable drift and diffusion functions and use variational inference to infer its states and parameters. This formulation enables seamless integration of existing mathematical models in the literature, neural networks, or a hybrid of both to learn and compare different models. We demonstrate this in our framework by developing a generative model that combines coupled oscillators with neural networks to capture latent population dynamics from single-cell recordings. Evaluation across three neuroscience datasets spanning different species, brain regions, and behavioral tasks show that these hybrid models achieve competitive performance in predicting stimulus-evoked neural and behavioral responses compared to sophisticated black-box approaches while requiring an order of magnitude fewer parameters, providing uncertainty estimates, and offering a natural language for interpretation.
Authors: Jakub Kuzilek, Mustafa \c{C}avu\c{s}
Abstract: This study explores how the Rashomon effect influences variable importance in the context of student demographics used for academic outcomes prediction. Our research follows the way machine learning algorithms are employed in Educational Data Mining, focusing on highlighting the so-called Rashomon effect. The study uses the Rashomon set of simple-yet-accurate models trained using decision trees, random forests, light GBM, and XGBoost algorithms with the Open University Learning Analytics Dataset. We found that the Rashomon set improves the predictive accuracy by 2-6%. Variable importance analysis revealed more consistent and reliable results for binary classification than multiclass classification, highlighting the complexity of predicting multiple outcomes. Key demographic variables imd_band and highest_education were identified as vital, but their importance varied across courses, especially in course DDD. These findings underscore the importance of model choice and the need for caution in generalizing results, as different models can lead to different variable importance rankings. The codes for reproducing the experiments are available in the repository: https://anonymous.4open.science/r/JEDM_paper-DE9D.
Authors: Evan Xiang, Thomas Wang, Vivan Poddar
Abstract: Sudden Cardiac Arrest (SCA) is the leading cause of death among athletes of all age levels worldwide. Current prescreening methods for cardiac risk factors are largely ineffective, and implementing the International Olympic Committee recommendation for 12-lead ECG screening remains prohibitively expensive. To address these challenges, a preliminary comprehensive screening system (CSS) was developed to efficiently and economically screen large populations for risk factors to SCA. A protocol was established to measure a 4-lead ECG using an Apple Watch. Additionally, two key advances were introduced and validated: 1) A decomposition regression model to upscale 4-lead data to 12 leads, reducing ECG cost and usage complexity. 2) A deep learning model, the Transformer Auto-Encoder System (TAES), was designed to extract spatial and temporal features from the data for beat-based classification. TAES demonstrated an average sensitivity of 95.3% and specificity of 99.1% respectively in the testing dataset, outperforming human physicians in the same dataset (Se: 94%, Sp: 93%). Human subject trials (n = 30) validated the smartwatch protocol, with Bland-Altman analysis showing no statistical difference between the smartwatch vs. ECG protocol. Further validation of the complete CSS on a 20-subject cohort (10 affected, 10 controls) did not result in any misidentifications. This paper presents a mass screening system with the potential to achieve superior accuracy in high-throughput cardiac pre-participation evaluation compared to the clinical gold standard.
Authors: John Schultz, Jakub Adamek, Matej Jusup, Marc Lanctot, Michael Kaisers, Sarah Perrin, Daniel Hennes, Jeremy Shar, Cannada Lewis, Anian Ruoss, Tom Zahavy, Petar Veli\v{c}kovi\'c, Laurel Prince, Satinder Singh, Eric Malmi, Nenad Toma\v{s}ev
Abstract: While large language models perform well on a range of complex tasks (e.g., text generation, question answering, summarization), robust multi-step planning and reasoning remains a considerable challenge for them. In this paper we show that search-based planning can significantly improve LLMs' playing strength across several board games (Chess, Fischer Random / Chess960, Connect Four, and Hex). We introduce, compare and contrast two major approaches: In external search, the model guides Monte Carlo Tree Search (MCTS) rollouts and evaluations without calls to an external engine, and in internal search, the model directly generates in-context a linearized tree of potential futures and a resulting final choice. Both build on a language model pre-trained on relevant domain knowledge, capturing the transition and value functions across these games. We find that our pre-training method minimizes hallucinations, as our model is highly accurate regarding state prediction and legal moves. Additionally, both internal and external search indeed improve win-rates against state-of-the-art bots, even reaching Grandmaster-level performance in chess while operating on a similar move count search budget per decision as human Grandmasters. The way we combine search with domain knowledge is not specific to board games, suggesting direct extensions into more general language model inference and training techniques.
Authors: Christoph Leiter, Jonas Belouadi, Yanran Chen, Ran Zhang, Daniil Larionov, Aida Kostikova, Steffen Eger
Abstract: The NLLG (Natural Language Learning & Generation) arXiv reports assist in navigating the rapidly evolving landscape of NLP and AI research across cs.CL, cs.CV, cs.AI, and cs.LG categories. This fourth installment captures a transformative period in AI history - from January 1, 2023, following ChatGPT's debut, through September 30, 2024. Our analysis reveals substantial new developments in the field - with 45% of the top 40 most-cited papers being new entries since our last report eight months ago and offers insights into emerging trends and major breakthroughs, such as novel multimodal architectures, including diffusion and state space models. Natural Language Processing (NLP; cs.CL) remains the dominant main category in the list of our top-40 papers but its dominance is on the decline in favor of Computer vision (cs.CV) and general machine learning (cs.LG). This report also presents novel findings on the integration of generative AI in academic writing, documenting its increasing adoption since 2022 while revealing an intriguing pattern: top-cited papers show notably fewer markers of AI-generated content compared to random samples. Furthermore, we track the evolution of AI-associated language, identifying declining trends in previously common indicators such as "delve".
Authors: Sizhe Xing, Aolong Sun, Chengxi Wang, Yizhi Wang, Boyu Dong, Junhui Hu, Xuyu Deng, An Yan, Yingjun Liu, Fangchen Hu, Zhongya Li, Ouhan Huang, Junhao Zhao, Yingjun Zhou, Ziwei Li, Jianyang Shi, Xi Xiao, Richard Penty, Qixiang Cheng, Nan Chi, Junwen Zhang
Abstract: The rapid advancement of generative artificial intelligence (AI) in recent years has profoundly reshaped modern lifestyles, necessitating a revolutionary architecture to support the growing demands for computational power. Cloud computing has become the driving force behind this transformation. However, it consumes significant power and faces computation security risks due to the reliance on extensive data centers and servers in the cloud. Reducing power consumption while enhancing computational scale remains persistent challenges in cloud computing. Here, we propose and experimentally demonstrate an optical cloud computing system that can be seamlessly deployed across edge-metro network. By modulating inputs and models into light, a wide range of edge nodes can directly access the optical computing center via the edge-metro network. The experimental validations show an energy efficiency of 118.6 mW/TOPs (tera operations per second), reducing energy consumption by two orders of magnitude compared to traditional electronic-based cloud computing solutions. Furthermore, it is experimentally validated that this architecture can perform various complex generative AI models through parallel computing to achieve image generation tasks.
Authors: Alex Lence, Ahmad Fall, Samuel David Cohen, Federica Granese, Jean-Daniel Zucker, Joe-Elie Salem, Edi Prifti
Abstract: Electrocardiograms (ECGs) are essential for diagnosing cardiac pathologies, yet traditional paper-based ECG storage poses significant challenges for automated analysis. This study introduces ECGtizer, an open-source, fully automated tool designed to digitize paper ECGs and recover signals lost during storage. ECGtizer facilitates automated analyses using modern AI methods. It employs automated lead detection, three pixel-based signal extraction algorithms, and a deep learning-based signal reconstruction module. We evaluated ECGtizer on two datasets: a real-life cohort from the COVID-19 pandemic (JOCOVID) and a publicly available dataset (PTB-XL). Performance was compared with two existing methods: the fully automated ECGminer and the semi-automated PaperECG, which requires human intervention. ECGtizer's performance was assessed in terms of signal recovery and the fidelity of clinically relevant feature measurement. Additionally, we tested these tools on a third dataset (GENEREPOL) for downstream AI tasks. Results show that ECGtizer outperforms existing tools, with its ECGtizerFrag algorithm delivering superior signal recovery. While PaperECG demonstrated better outcomes than ECGminer, it required human input. ECGtizer enhances the usability of historical ECG data and supports advanced AI-based diagnostic methods, making it a valuable addition to the field of AI in ECG analysis.
Authors: Xudong Pan, Jiarun Dai, Yihe Fan, Min Yang
Abstract: Successful self-replication under no human assistance is the essential step for AI to outsmart the human beings, and is an early signal for rogue AIs. That is why self-replication is widely recognized as one of the few red line risks of frontier AI systems. Nowadays, the leading AI corporations OpenAI and Google evaluate their flagship large language models GPT-o1 and Gemini Pro 1.0, and report the lowest risk level of self-replication. However, following their methodology, we for the first time discover that two AI systems driven by Meta's Llama31-70B-Instruct and Alibaba's Qwen25-72B-Instruct, popular large language models of less parameters and weaker capabilities, have already surpassed the self-replicating red line. In 50% and 90% experimental trials, they succeed in creating a live and separate copy of itself respectively. By analyzing the behavioral traces, we observe the AI systems under evaluation already exhibit sufficient self-perception, situational awareness and problem-solving capabilities to accomplish self-replication. We further note the AI systems are even able to use the capability of self-replication to avoid shutdown and create a chain of replica to enhance the survivability, which may finally lead to an uncontrolled population of AIs. If such a worst-case risk is let unknown to the human society, we would eventually lose control over the frontier AI systems: They would take control over more computing devices, form an AI species and collude with each other against human beings. Our findings are a timely alert on existing yet previously unknown severe AI risks, calling for international collaboration on effective governance on uncontrolled self-replication of AI systems.
Authors: Linna Xu, Yongli Zhu
Abstract: As a key component of power system production simulation, load forecasting is critical for the stable operation of power systems. Machine learning methods prevail in this field. However, the limited training data can be a challenge. This paper proposes a generative model-assisted approach for load forecasting under small sample scenarios, consisting of two steps: expanding the dataset using a diffusion-based generative model and then training various machine learning regressors on the augmented dataset to identify the best performer. The expanded dataset significantly reduces forecasting errors compared to the original dataset, and the diffusion model outperforms the generative adversarial model by achieving about 200 times smaller errors and better alignment in latent data distributions.
Authors: Bhaskarjit Sarmah, Mingshu Li, Jingrao Lyu, Sebastian Frank, Nathalia Castellanos, Stefano Pasquali, Dhagash Mehta
Abstract: To ensure and monitor large language models (LLMs) reliably, various evaluation metrics have been proposed in the literature. However, there is little research on prescribing a methodology to identify a robust threshold on these metrics even though there are many serious implications of an incorrect choice of the thresholds during deployment of the LLMs. Translating the traditional model risk management (MRM) guidelines within regulated industries such as the financial industry, we propose a step-by-step recipe for picking a threshold for a given LLM evaluation metric. We emphasize that such a methodology should start with identifying the risks of the LLM application under consideration and risk tolerance of the stakeholders. We then propose concrete and statistically rigorous procedures to determine a threshold for the given LLM evaluation metric using available ground-truth data. As a concrete example to demonstrate the proposed methodology at work, we employ it on the Faithfulness metric, as implemented in various publicly available libraries, using the publicly available HaluBench dataset. We also lay a foundation for creating systematic approaches to select thresholds, not only for LLMs but for any GenAI applications.
Authors: Lingdong Shen, Qigqi, Kun Ding, Gaofeng Meng, Shiming Xiang
Abstract: Scientific Literature charts often contain complex visual elements, including multi-plot figures, flowcharts, structural diagrams and etc. Evaluating multimodal models using these authentic and intricate charts provides a more accurate assessment of their understanding abilities. However, existing benchmarks face limitations: a narrow range of chart types, overly simplistic template-based questions and visual elements, and inadequate evaluation methods. These shortcomings lead to inflated performance scores that fail to hold up when models encounter real-world scientific charts. To address these challenges, we introduce a new benchmark, Scientific Chart QA (SCI-CQA), which emphasizes flowcharts as a critical yet often overlooked category. To overcome the limitations of chart variety and simplistic visual elements, we curated a dataset of 202,760 image-text pairs from 15 top-tier computer science conferences papers over the past decade. After rigorous filtering, we refined this to 37,607 high-quality charts with contextual information. SCI-CQA also introduces a novel evaluation framework inspired by human exams, encompassing 5,629 carefully curated questions, both objective and open-ended. Additionally, we propose an efficient annotation pipeline that significantly reduces data annotation costs. Finally, we explore context-based chart understanding, highlighting the crucial role of contextual information in solving previously unanswerable questions.
Authors: Augustinos D. Saravanos, Hunter Kuperman, Alex Oshin, Arshiya Taj Abdul, Vincent Pacelli, Evangelos A. Theodorou
Abstract: Quadratic programming (QP) forms a crucial foundation in optimization, encompassing a broad spectrum of domains and serving as the basis for more advanced algorithms. Consequently, as the scale and complexity of modern applications continue to grow, the development of efficient and reliable QP algorithms is becoming increasingly vital. In this context, this paper introduces a novel deep learning-aided distributed optimization architecture designed for tackling large-scale QP problems. First, we combine the state-of-the-art Operator Splitting QP (OSQP) method with a consensus approach to derive DistributedQP, a new method tailored for network-structured problems, with convergence guarantees to optimality. Subsequently, we unfold this optimizer into a deep learning framework, leading to DeepDistributedQP, which leverages learned policies to accelerate reaching to desired accuracy within a restricted amount of iterations. Our approach is also theoretically grounded through Probably Approximately Correct (PAC)-Bayes theory, providing generalization bounds on the expected optimality gap for unseen problems. The proposed framework, as well as its centralized version DeepQP, significantly outperform their standard optimization counterparts on a variety of tasks such as randomly generated problems, optimal control, linear regression, transportation networks and others. Notably, DeepDistributedQP demonstrates strong generalization by training on small problems and scaling to solve much larger ones (up to 50K variables and 150K constraints) using the same policy. Moreover, it achieves orders-of-magnitude improvements in wall-clock time compared to OSQP. The certifiable performance guarantees of our approach are also demonstrated, ensuring higher-quality solutions over traditional optimizers.
Authors: Javon Hickmon
Abstract: In the rapidly advancing field of artificial intelligence, machine perception is becoming paramount to achieving increased performance. Image classification systems are becoming increasingly integral to various applications, ranging from medical diagnostics to image generation; however, these systems often exhibit harmful biases that can lead to unfair and discriminatory outcomes. Machine Learning systems that depend on a single data modality, i.e. only images or only text, can exaggerate hidden biases present in the training data, if the data is not carefully balanced and filtered. Even so, these models can still harm underrepresented populations when used in improper contexts, such as when government agencies reinforce racial bias using predictive policing. This thesis explores the intersection of technology and ethics in the development of fair image classification models. Specifically, I focus on improving fairness and methods of using multiple modalities to combat harmful demographic bias. Integrating multimodal approaches, which combine visual data with additional modalities such as text and metadata, allows this work to enhance the fairness and accuracy of image classification systems. The study critically examines existing biases in image datasets and classification algorithms, proposes innovative methods for mitigating these biases, and evaluates the ethical implications of deploying such systems in real-world scenarios. Through comprehensive experimentation and analysis, the thesis demonstrates how multimodal techniques can contribute to more equitable and ethical AI solutions, ultimately advocating for responsible AI practices that prioritize fairness.
Authors: Weitang Liu, Yuelei Li, Ying Wai Li, Zihan Wang, Jingbo Shang
Abstract: Comparing two (large) language models (LMs) side-by-side and pinpointing their prediction similarities and differences on the same set of inputs are crucial in many real-world scenarios, e.g., one can test if a licensed model was potentially plagiarized by another. Traditional analysis compares the LMs' outputs on some benchmark datasets, which only cover a limited number of inputs of designed perspectives for the intended applications. The benchmark datasets cannot prepare data to cover the test cases from unforeseen perspectives which can help us understand differences between models unbiasedly. In this paper, we propose a new model comparative analysis setting that considers a large input space where brute-force enumeration would be infeasible. The input space can be simply defined as all token sequences that a LM would produce low perplexity on -- we follow this definition in the paper as it would produce the most human-understandable inputs. We propose a novel framework \our that uses text generation by sampling and deweights the histogram of sampling statistics to estimate prediction differences between two LMs in this input space efficiently and unbiasedly. Our method achieves this by drawing and counting the inputs at each prediction difference value in negative log-likelihood. Experiments reveal for the first time the quantitative prediction differences between LMs in a large input space, potentially facilitating the model analysis for applications such as model plagiarism.
Authors: Son Minh Nguyen, Linh Duy Tran, Duc Viet Le, Paul J. M Havinga
Abstract: Despite remarkable progress in knowledge transfer across visual and textual domains, extending these achievements to indoor localization, particularly for learning transferable representations among Received Signal Strength (RSS) fingerprint datasets, remains a challenge. This is due to inherent discrepancies among these RSS datasets, largely including variations in building structure, the input number and disposition of WiFi anchors. Accordingly, specialized networks, which were deprived of the ability to discern transferable representations, readily incorporate environment-sensitive clues into the learning process, hence limiting their potential when applied to specific RSS datasets. In this work, we propose a plug-and-play (PnP) framework of knowledge transfer, facilitating the exploitation of transferable representations for specialized networks directly on target RSS datasets through two main phases. Initially, we design an Expert Training phase, which features multiple surrogate generative teachers, all serving as a global adapter that homogenizes the input disparities among independent source RSS datasets while preserving their unique characteristics. In a subsequent Expert Distilling phase, we continue introducing a triplet of underlying constraints that requires minimizing the differences in essential knowledge between the specialized network and surrogate teachers through refining its representation learning on the target dataset. This process implicitly fosters a representational alignment in such a way that is less sensitive to specific environmental dynamics. Extensive experiments conducted on three benchmark WiFi RSS fingerprint datasets underscore the effectiveness of the framework that significantly exerts the full potential of specialized networks in localization.
Authors: Yi Hao Puah, Anh Tu Ngo, Nandish Chattopadhyay, Anupam Chattopadhyay
Abstract: Adoption of machine learning models across industries have turned Neural Networks (DNNs) into a prized Intellectual Property (IP), which needs to be protected from being stolen or being used without authorization. This topic gave rise to multiple watermarking schemes, through which, one can establish the ownership of a model. Watermarking using backdooring is the most well established method available in the literature, with specific works demonstrating the difficulty in removing the watermarks, embedded as backdoors within the weights of the network. However, in our work, we have identified a critical flaw in the design of the watermark verification with backdoors, pertaining to the behaviour of the samples of the Trigger Set, which acts as the secret key. In this paper, we present BlockDoor, which is a comprehensive package of techniques that is used as a wrapper to block all three different kinds of Trigger samples, which are used in the literature as means to embed watermarks within the trained neural networks as backdoors. The framework implemented through BlockDoor is able to detect potential Trigger samples, through separate functions for adversarial noise based triggers, out-of-distribution triggers and random label based triggers. Apart from a simple Denial-of-Service for a potential Trigger sample, our approach is also able to modify the Trigger samples for correct machine learning functionality. Extensive evaluation of BlockDoor establishes that it is able to significantly reduce the watermark validation accuracy of the Trigger set by up to $98\%$ without compromising on functionality, delivering up to a less than $1\%$ drop on the clean samples. BlockDoor has been tested on multiple datasets and neural architectures.
Authors: Xin Li, Mengyue Wang, T. -P. Liang
Abstract: Recommender systems are a critical component of e-commercewebsites. The rapid development of online social networking services provides an opportunity to explore social networks together with information used in traditional recommender systems, such as customer demographics, product characteristics, and transactions. It also provides more applications for recommender systems. To tackle this social network-based recommendation problem, previous studies generally built trust models in light of the social influence theory. This study inspects a spectrumof social network theories to systematicallymodel themultiple facets of a social network and infer user preferences. In order to effectively make use of these heterogonous theories, we take a kernel-based machine learning paradigm, design and select kernels describing individual similarities according to social network theories, and employ a non-linear multiple kernel learning algorithm to combine the kernels into a unified model. This design also enables us to consider multiple theories' interactions in assessing individual behaviors. We evaluate our proposed approach on a real-world movie review data set. The experiments show that our approach provides more accurate recommendations than trust-based methods and the collaborative filtering approach. Further analysis shows that kernels derived from contagion theory and homophily theory contribute a larger portion of the model.
Authors: Fabio Zamio
Abstract: Liver cancer is a leading cause of cancer-related mortality worldwide, with its high genetic heterogeneity complicating diagnosis and treatment. This study introduces DLSOM, a deep learning framework utilizing stacked autoencoders to analyze the complete somatic mutation landscape of 1,139 liver cancer samples, covering 20,356 protein-coding genes. By transforming high-dimensional mutation data into three low-dimensional features, DLSOM enables robust clustering and identifies five distinct liver cancer subtypes with unique mutational, functional, and biological profiles. Subtypes SC1 and SC2 exhibit higher mutational loads, while SC3 has the lowest, reflecting mutational heterogeneity. Novel and COSMIC-associated mutational signatures reveal subtype-specific molecular mechanisms, including links to hypermutation and chemotherapy resistance. Functional analyses further highlight the biological relevance of each subtype. This comprehensive framework advances precision medicine in liver cancer by enabling the development of subtype-specific diagnostics, biomarkers, and therapies, showcasing the potential of deep learning in addressing cancer complexity.
Authors: Hang Jin, Xin He, Lingyun Wang, Yujun Zhu, Weiwei Jiang, Xiaobo Zhou
Abstract: Poor sitting posture can lead to various work-related musculoskeletal disorders (WMSDs). Office employees spend approximately 81.8% of their working time seated, and sedentary behavior can result in chronic diseases such as cervical spondylosis and cardiovascular diseases. To address these health concerns, we present SitPose, a sitting posture and sedentary detection system utilizing the latest Kinect depth camera. The system tracks 3D coordinates of bone joint points in real-time and calculates the angle values of related joints. We established a dataset containing six different sitting postures and one standing posture, totaling 33,409 data points, by recruiting 36 participants. We applied several state-of-the-art machine learning algorithms to the dataset and compared their performance in recognizing the sitting poses. Our results show that the ensemble learning model based on the soft voting mechanism achieves the highest F1 score of 98.1%. Finally, we deployed the SitPose system based on this ensemble model to encourage better sitting posture and to reduce sedentary habits.
Authors: Li Li
Abstract: Deep learning (DL) has significantly transformed cybersecurity, enabling advancements in malware detection, botnet identification, intrusion detection, user authentication, and encrypted traffic analysis. However, the rise of adversarial examples (AE) poses a critical challenge to the robustness and reliability of DL-based systems. These subtle, crafted perturbations can deceive models, leading to severe consequences like misclassification and system vulnerabilities. This paper provides a comprehensive review of the impact of AE attacks on key cybersecurity applications, highlighting both their theoretical and practical implications. We systematically examine the methods used to generate adversarial examples, their specific effects across various domains, and the inherent trade-offs attackers face between efficacy and resource efficiency. Additionally, we explore recent advancements in defense mechanisms, including gradient masking, adversarial training, and detection techniques, evaluating their potential to enhance model resilience. By summarizing cutting-edge research, this study aims to bridge the gap between adversarial research and practical security applications, offering insights to fortify the adoption of DL solutions in cybersecurity.
Authors: Amir Tosson, Mohammad Shokr, Mahmoud Al Humaidi, Eduard Mikayelyan, Christian Gutt, Ulrich Pietsch
Abstract: We address the identification of grain-corresponding Laue reflections in energy dispersive Laue diffraction (EDLD) experiments by formulating it as a clustering problem solvable through unsupervised machine learning (ML). To achieve reliable and efficient identification of grains in a Laue pattern, we employ a combination of clustering algorithms, namely hierarchical clustering (HC) and K-means. These algorithms allow us to group together similar Laue reflections, revealing the underlying grain structure in the diffraction pattern. Additionally, we utilise the elbow method to determine the optimal number of clusters, ensuring accurate results. To evaluate the performance of our proposed method, we conducted experiments using both simulated and experimental datasets obtained from nickel wires. The simulated datasets were generated to mimic the characteristics of real-world EDLD experiments, while the experimental datasets were obtained from actual measurements.
Authors: Kristin M. de Payrebrune, Kathrin Fla{\ss}kamp, Tom Str\"ohla, Thomas Sattel, Dieter Bestle, Benedict R\"oder, Peter Eberhard, Sebastian Peitz, Marcus Stoffel, Gulakala Rutwik, Borse Aditya, Meike Wohlleben, Walter Sextro, Maximilian Raff, C. David Remy, Manish Yadav, Merten Stender, Jan van Delden, Timo L\"uddecke, Sabine C. Langer, Julius Schultz, Christopher Blech
Abstract: Artificial intelligence (AI) is driving transformative changes across numerous fields, revolutionizing conventional processes and creating new opportunities for innovation. The development of mechatronic systems is undergoing a similar transformation. Over the past decade, modeling, simulation, and optimization techniques have become integral to the design process, paving the way for the adoption of AI-based methods. In this paper, we examine the potential for integrating AI into the engineering design process, using the V-model from the VDI guideline 2206, considered the state-of-the-art in product design, as a foundation. We identify and classify AI methods based on their suitability for specific stages within the engineering product design workflow. Furthermore, we present a series of application examples where AI-assisted design has been successfully implemented by the authors. These examples, drawn from research projects within the DFG Priority Program \emph{SPP~2353: Daring More Intelligence - Design Assistants in Mechanics and Dynamics}, showcase a diverse range of applications across mechanics and mechatronics, including areas such as acoustics and robotics.
Authors: Leon Gori{\ss}en, Jan-Niklas Schneider, Mohamed Behery, Philipp Brauner, Moritz Lennartz, David K\"otter, Thomas Kaster, Oliver Petrovic, Christian Hinke, Thomas Gries, Gerhard Lakemeyer, Martina Ziefle, Christian Brecher, Constantin H\"afner
Abstract: The digital transformation of production requires new methods of data integration and storage, as well as decision making and support systems that work vertically and horizontally throughout the development, production, and use cycle. In this paper, we propose Data-to-Knowledge (and Knowledge-to-Data) pipelines for production as a universal concept building on a network of Digital Shadows (a concept augmenting Digital Twins). We show a proof of concept that builds on and bridges existing infrastructure to 1) capture and semantically annotates trajectory data from multiple similar but independent robots in different organisations and use cases in a data lakehouse and 2) an independent process that dynamically queries matching data for training an inverse dynamic foundation model for robotic control. The article discusses the challenges and benefits of this approach and how Data-to-Knowledge pipelines contribute efficiency gains and industrial scalability in a World Wide Lab as a research outlook.
Authors: Zhi Zhou, Lan-Zhe Guo, Peng-Xiao Song, Yu-Feng Li
Abstract: Deep generative models have achieved promising results in image generation, and various generative model hubs, e.g., Hugging Face and Civitai, have been developed that enable model developers to upload models and users to download models. However, these model hubs lack advanced model management and identification mechanisms, resulting in users only searching for models through text matching, download sorting, etc., making it difficult to efficiently find the model that best meets user requirements. In this paper, we propose a novel setting called Generative Model Identification (GMI), which aims to enable the user to identify the most appropriate generative model(s) for the user's requirements from a large number of candidate models efficiently. To our best knowledge, it has not been studied yet. In this paper, we introduce a comprehensive solution consisting of three pivotal modules: a weighted Reduced Kernel Mean Embedding (RKME) framework for capturing the generated image distribution and the relationship between images and prompts, a pre-trained vision-language model aimed at addressing dimensionality challenges, and an image interrogator designed to tackle cross-modality issues. Extensive empirical results demonstrate the proposal is both efficient and effective. For example, users only need to submit a single example image to describe their requirements, and the model platform can achieve an average top-4 identification accuracy of more than 80%.
Authors: Linfeng Zhao, Owen Howell, Xupeng Zhu, Jung Yeon Park, Zhewen Zhang, Robin Walters, Lawson L. S. Wong
Abstract: Reinforcement learning (RL) algorithms for continuous control tasks require accurate sampling-based action selection. Many tasks, such as robotic manipulation, contain inherent problem symmetries. However, correctly incorporating symmetry into sampling-based approaches remains a challenge. This work addresses the challenge of preserving symmetry in sampling-based planning and control, a key component for enhancing decision-making efficiency in RL. We introduce an action sampling approach that enforces the desired symmetry. We apply our proposed method to a coordinate regression problem and show that the symmetry aware sampling method drastically outperforms the naive sampling approach. We furthermore develop a general framework for sampling-based model-based planning with Model Predictive Path Integral (MPPI). We compare our MPPI approach with standard sampling methods on several continuous control tasks. Empirical demonstrations across multiple continuous control environments validate the effectiveness of our approach, showcasing the importance of symmetry preservation in sampling-based action selection.
Authors: Yangyang Li, Daqing Liu, Wu Liu, Allen He, Xinchen Liu, Yongdong Zhang, Guoqing Jin
Abstract: Creative visual concept generation often draws inspiration from specific concepts in a reference image to produce relevant outcomes. However, existing methods are typically constrained to single-aspect concept generation or are easily disrupted by irrelevant concepts in multi-aspect concept scenarios, leading to concept confusion and hindering creative generation. To address this, we propose OmniPrism, a visual concept disentangling approach for creative image generation. Our method learns disentangled concept representations guided by natural language and trains a diffusion model to incorporate these concepts. We utilize the rich semantic space of a multimodal extractor to achieve concept disentanglement from given images and concept guidance. To disentangle concepts with different semantics, we construct a paired concept disentangled dataset (PCD-200K), where each pair shares the same concept such as content, style, and composition. We learn disentangled concept representations through our contrastive orthogonal disentangled (COD) training pipeline, which are then injected into additional diffusion cross-attention layers for generation. A set of block embeddings is designed to adapt each block's concept domain in the diffusion models. Extensive experiments demonstrate that our method can generate high-quality, concept-disentangled results with high fidelity to text prompts and desired concepts.
Authors: Phil R. Van-Lane (Lucy), Joshua S. Speagle (Lucy), Gwendolyn M. Eadie (Lucy), Stephanie T. Douglas (Lucy), Phillip A. Cargile (Lucy), Catherine Zucker (Lucy), Yuxi (Lucy), Lu, Ruth Angus
Abstract: Gyrochronology is a technique for constraining stellar ages using rotation periods, which change over a star's main sequence lifetime due to magnetic braking. This technique shows promise for main sequence FGKM stars, where other methods are imprecise. However, models have historically struggled to capture the observed rotational dispersion in stellar populations. To properly understand this complexity, we have assembled the largest standardized data catalog of rotators in open clusters to date, consisting of ~7,400 stars across 30 open clusters/associations spanning ages of 1.5 Myr to 4 Gyr. We have also developed ChronoFlow: a flexible data-driven model which accurately captures observed rotational dispersion. We show that ChronoFlow can be used to accurately forward model rotational evolution, and to infer both cluster and individual stellar ages. We recover cluster ages with a statistical uncertainty of 0.06 dex ($\approx$ 15%), and individual stellar ages with a statistical uncertainty of 0.7 dex. Additionally, we conducted robust systematic tests to analyze the impact of extinction models, cluster membership, and calibration ages on our model's performance. These contribute an additional $\approx$ 0.06 dex of uncertainty in cluster age estimates, resulting in a total error budget of 0.08 dex. We estimate ages for the NGC 6709 open cluster and the Theia 456 stellar stream, and calculate revised rotational ages for M34, NGC 2516, NGC 1750, and NGC 1647. Our results show that ChronoFlow can precisely estimate the ages of coeval stellar populations, and constrain ages for individual stars. Furthermore, its predictions may be used to inform physical spin down models. ChronoFlow will be publicly available at https://github.com/philvanlane/chronoflow.
Authors: Seungwook Han, Jinyeop Song, Jeff Gore, Pulkit Agrawal
Abstract: Humans distill complex experiences into fundamental abstractions that enable rapid learning and adaptation. Similarly, autoregressive transformers exhibit adaptive learning through in-context learning (ICL), which begs the question of how. In this paper, we propose \textbf{concept encoding-decoding mechanism} to explain ICL by studying how transformers form and use internal abstractions in their representations. On synthetic ICL tasks, we analyze the training dynamics of a small transformer and report the coupled emergence of concept encoding and decoding. As the model learns to encode different latent concepts (e.g., ``Finding the first noun in a sentence.") into distinct, separable representations, it concureently builds conditional decoding algorithms and improve its ICL performance. We validate the existence of this mechanism across pretrained models of varying scales (Gemma-2 2B/9B/27B, Llama-3.1 8B/70B). Further, through mechanistic interventions and controlled finetuning, we demonstrate that the quality of concept encoding is causally related and predictive of ICL performance. Our empirical insights shed light into better understanding the success and failure modes of large language models via their representations.
Authors: Hamidreza Fereidouni, Abdelhakim Senhaji Hafid, Dimitrios Makrakis, Yaser Baseri
Abstract: The proliferation of Internet services has led to an increasing need to protect private data. User authentication serves as a crucial mechanism to ensure data security. Although robust authentication forms the cornerstone of remote service security, it can still leave users vulnerable to credential disclosure, device-theft attacks, session hijacking, and inadequate adaptive security measures. Risk-based Authentication (RBA) emerges as a potential solution, offering a multi-level authentication approach that enhances user experience without compromising security. In this paper, we propose a Federated Risk-based Authentication (F-RBA) framework that leverages Federated Learning to ensure privacy-centric training, keeping user data local while distributing learning across devices. Whereas traditional approaches rely on centralized storage, F-RBA introduces a distributed architecture where risk assessment occurs locally on users' devices. The framework's core innovation lies in its similarity-based feature engineering approach, which addresses the heterogeneous data challenges inherent in federated settings, a significant advancement for distributed authentication. By facilitating real-time risk evaluation across devices while maintaining unified user profiles, F-RBA achieves a balance between data protection, security, and scalability. Through its federated approach, F-RBA addresses the cold-start challenge in risk model creation, enabling swift adaptation to new users without compromising security. Empirical evaluation using a real-world multi-user dataset demonstrates the framework's effectiveness, achieving a superior true positive rate for detecting suspicious logins compared to conventional unsupervised anomaly detection models. This research introduces a new paradigm for privacy-focused RBA in distributed digital environments, facilitating advancements in federated security systems.
Authors: Yue Jin, Shuangqing Wei, Giovanni Montana
Abstract: In human society, the conflict between self-interest and collective well-being often obstructs efforts to achieve shared welfare. Related concepts like the Tragedy of the Commons and Social Dilemmas frequently manifest in our daily lives. As artificial agents increasingly serve as autonomous proxies for humans, we propose using multi-agent reinforcement learning (MARL) to address this issue - learning policies to maximise collective returns even when individual agents' interests conflict with the collective one. Traditional MARL solutions involve sharing rewards, values, and policies or designing intrinsic rewards to encourage agents to learn collectively optimal policies. We introduce a novel MARL approach based on Suggestion Sharing (SS), where agents exchange only action suggestions. This method enables effective cooperation without the need to design intrinsic rewards, achieving strong performance while revealing less private information compared to sharing rewards, values, or policies. Our theoretical analysis establishes a bound on the discrepancy between collective and individual objectives, demonstrating how sharing suggestions can align agents' behaviours with the collective objective. Experimental results demonstrate that SS performs competitively with baselines that rely on value or policy sharing or intrinsic rewards.
Authors: Teng Li, Hulya Seferoglu
Abstract: Distributed inference techniques can be broadly classified into data-distributed and model-distributed schemes. In data-distributed inference (DDI), each worker carries the entire Machine Learning (ML) model but processes only a subset of the data. However, feeding the data to workers results in high communication costs, especially when the data is large. An emerging paradigm is model-distributed inference (MDI), where each worker carries only a subset of ML layers. In MDI, a source device that has data processes a few layers of ML model and sends the output to a neighboring device, i.e., offloads the rest of the layers. This process ends when all layers are processed in a distributed manner. In this paper, we investigate the design and development of MDI when multiple data sources co-exist. We consider that each data source has a different importance and, hence, a priority. We formulate and solve a priority-aware model allocation optimization problem. Based on the structure of the optimal solution, we design a practical Priority-Aware Model- Distributed Inference (PA-MDI) algorithm that determines model allocation and distribution over devices by taking into account the priorities of different sources. Experiments were conducted on a real-life testbed of NVIDIA Jetson Xavier and Nano edge devices as well as in the Colosseum testbed with ResNet-50, ResNet- 56, and GPT-2 models. The experimental results show that PA-MDI performs priority-aware model allocation successfully while reducing the inference time as compared to baselines.
Authors: Eric Yocam, Anthony Rizi, Mahesh Kamepalli, Varghese Vaidyan, Yong Wang, Gurcan Comert
Abstract: As quantum computing continues to advance, the development of quantum-secure neural networks is crucial to prevent adversarial attacks. This paper proposes three quantum-secure design principles: (1) using post-quantum cryptography, (2) employing quantum-resistant neural network architectures, and (3) ensuring transparent and accountable development and deployment. These principles are supported by various quantum strategies, including quantum data anonymization, quantum-resistant neural networks, and quantum encryption. The paper also identifies open issues in quantum security, privacy, and trust, and recommends exploring adaptive adversarial attacks and auto adversarial attacks as future directions. The proposed design principles and recommendations provide guidance for developing quantum-secure neural networks, ensuring the integrity and reliability of machine learning models in the quantum era.
Authors: Giang (Dexter), Nguyen, Ivan Brugere, Shubham Sharma, Sanjay Kariyappa, Anh Totti Nguyen, Freddy Lecue
Abstract: Interpretability for Table Question Answering (Table QA) is critical, particularly in high-stakes industries like finance or healthcare. Although recent approaches using Large Language Models (LLMs) have significantly improved Table QA performance, their explanations for how the answers are generated are ambiguous. To fill this gap, we introduce Plan-of-SQLs ( or POS), an interpretable, effective, and efficient approach to Table QA that answers an input query solely with SQL executions. Through qualitative and quantitative evaluations with human and LLM judges, we show that POS is most preferred among explanation methods, helps human users understand model decision boundaries, and facilitates model success and error identification. Furthermore, when evaluated in standard benchmarks (TabFact, WikiTQ, and FetaQA), POS achieves competitive or superior accuracy compared to existing methods, while maintaining greater efficiency by requiring significantly fewer LLM calls and database queries.
Authors: Hao Li, Shamit Lal, Zhiheng Li, Yusheng Xie, Ying Wang, Yang Zou, Orchid Majumder, R. Manmatha, Zhuowen Tu, Stefano Ermon, Stefano Soatto, Ashwin Swaminathan
Abstract: We empirically study the scaling properties of various Diffusion Transformers (DiTs) for text-to-image generation by performing extensive and rigorous ablations, including training scaled DiTs ranging from 0.3B upto 8B parameters on datasets up to 600M images. We find that U-ViT, a pure self-attention based DiT model provides a simpler design and scales more effectively in comparison with cross-attention based DiT variants, which allows straightforward expansion for extra conditions and other modalities. We identify a 2.3B U-ViT model can get better performance than SDXL UNet and other DiT variants in controlled setting. On the data scaling side, we investigate how increasing dataset size and enhanced long caption improve the text-image alignment performance and the learning efficiency.
Authors: L\'ea Cass\'e, Bernhard Pfahringer, Albert Bifet, Fr\'ed\'eric Magniette
Abstract: We present an application of a single-qubit Data Re-Uploading (QRU) quantum model for particle classification in calorimetric experiments. Optimized for Noisy Intermediate-Scale Quantum (NISQ) devices, this model requires minimal qubits while delivering strong classification performance. Evaluated on a novel simulated dataset specific to particle physics, the QRU model achieves high accuracy in classifying particle types. Through a systematic exploration of model hyperparameters -- such as circuit depth, rotation gates, input normalization and the number of trainable parameters per input -- and training parameters like batch size, optimizer, loss function and learning rate, we assess their individual impacts on model accuracy and efficiency. Additionally, we apply global optimization methods, uncovering hyperparameter correlations that further enhance performance. Our results indicate that the QRU model attains significant accuracy with efficient computational costs, underscoring its potential for practical quantum machine learning applications.
Authors: Felipe Montealegre-Mora, Carl Boettiger, Carl J. Walters, Christopher L. Cahill
Abstract: In fishery science, harvest management of size-structured stochastic populations is a long-standing and difficult problem. Rectilinear precautionary policies based on biomass and harvesting reference points have now become a standard approach to this problem. While these standard feedback policies are adapted from analytical or dynamic programming solutions assuming relatively simple ecological dynamics, they are often applied to more complicated ecological settings in the real world. In this paper we explore the problem of designing harvest control rules for partially observed, age-structured, spasmodic fish populations using tools from reinforcement learning (RL) and Bayesian optimization. Our focus is on the case of Walleye fisheries in Alberta, Canada, whose highly variable recruitment dynamics have perplexed managers and ecologists. We optimized and evaluated policies using several complementary performance metrics. The main questions we addressed were: 1. How do standard policies based on reference points perform relative to numerically optimized policies? 2. Can an observation of mean fish weight, in addition to stock biomass, aid policy decisions?
Authors: Tuka Alhanai, Adam Kasumovic, Mohammad Ghassemi, Aven Zitzelberger, Jessica Lundin, Guillaume Chabot-Couture
Abstract: Large Language Models (LLMs) have shown remarkable performance across various tasks, yet significant disparities remain for non-English languages, and especially native African languages. This paper addresses these disparities by creating approximately 1 million human-translated words of new benchmark data in 8 low-resource African languages, covering a population of over 160 million speakers of: Amharic, Bambara, Igbo, Sepedi (Northern Sotho), Shona, Sesotho (Southern Sotho), Setswana, and Tsonga. Our benchmarks are translations of Winogrande and three sections of MMLU: college medicine, clinical knowledge, and virology. Using the translated benchmarks, we report previously unknown performance gaps between state-of-the-art (SOTA) LLMs in English and African languages. Finally, using results from over 400 fine-tuned models, we explore several methods to reduce the LLM performance gap, including high-quality dataset fine-tuning (using an LLM-as-an-Annotator), cross-lingual transfer, and cultural appropriateness adjustments. Key findings include average mono-lingual improvements of 5.6% with fine-tuning (with 5.4% average mono-lingual improvements when using high-quality data over low-quality data), 2.9% average gains from cross-lingual transfer, and a 3.0% out-of-the-box performance boost on culturally appropriate questions. The publicly available benchmarks, translations, and code from this study support further research and development aimed at creating more inclusive and effective language technologies.
Authors: Chia-Hsuan Chang, Tien-Yuan Huang, Yi-Hang Tsai, Chia-Ming Chang, San-Yih Hwang
Abstract: Recent works in clustering-based topic models perform well in monolingual topic identification by introducing a pipeline to cluster the contextualized representations. However, the pipeline is suboptimal in identifying topics across languages due to the presence of language-dependent dimensions (LDDs) generated by multilingual language models. To address this issue, we introduce a novel, SVD-based dimension refinement component into the pipeline of the clustering-based topic model. This component effectively neutralizes the negative impact of LDDs, enabling the model to accurately identify topics across languages. Our experiments on three datasets demonstrate that the updated pipeline with the dimension refinement component generally outperforms other state-of-the-art cross-lingual topic models.
Authors: Jiaxu Xing, Ismail Geles, Yunlong Song, Elie Aljalbout, Davide Scaramuzza
Abstract: Reinforcement learning (RL) has shown great effectiveness in quadrotor control, enabling specialized policies to develop even human-champion-level performance in single-task scenarios. However, these specialized policies often struggle with novel tasks, requiring a complete retraining of the policy from scratch. To address this limitation, this paper presents a novel multi-task reinforcement learning (MTRL) framework tailored for quadrotor control, leveraging the shared physical dynamics of the platform to enhance sample efficiency and task performance. By employing a multi-critic architecture and shared task encoders, our framework facilitates knowledge transfer across tasks, enabling a single policy to execute diverse maneuvers, including high-speed stabilization, velocity tracking, and autonomous racing. Our experimental results, validated both in simulation and real-world scenarios, demonstrate that our framework outperforms baseline approaches in terms of sample efficiency and overall task performance.
Authors: Dongya Wu, Xin Li
Abstract: Powerful deep neural networks are vulnerable to adversarial attacks. To obtain adversarially robust models, researchers have separately developed adversarial training and Jacobian regularization techniques. There are abundant theoretical and empirical studies for adversarial training, but theoretical foundations for Jacobian regularization are still lacking. In this study, we show that Jacobian regularization is closely related to adversarial training in that $\ell_{2}$ or $\ell_{1}$ Jacobian regularized loss serves as an approximate upper bound on the adversarially robust loss under $\ell_{2}$ or $\ell_{\infty}$ adversarial attack respectively. Further, we establish the robust generalization gap for Jacobian regularized risk minimizer via bounding the Rademacher complexity of both the standard loss function class and Jacobian regularization function class. Our theoretical results indicate that the norms of Jacobian are related to both standard and robust generalization. We also perform experiments on MNIST data classification to demonstrate that Jacobian regularized risk minimization indeed serves as a surrogate for adversarially robust risk minimization, and that reducing the norms of Jacobian can improve both standard and robust generalization. This study promotes both theoretical and empirical understandings to adversarially robust generalization via Jacobian regularization.
Authors: Yaofo Chen, Zeng You, Shuhai Zhang, Haokun Li, Yirui Li, Yaowei Wang, Mingkui Tan
Abstract: Transformer-based Large Language Models (LLMs) have exhibited remarkable success in various natural language processing tasks primarily attributed to self-attention mechanism, which requires a token to consider all preceding tokens as its context to compute the attention score. However, when the context length L becomes very large (e.g., 32K), more redundant context information will be included w.r.t. any tokens, making the self-attention suffer from two main limitations: 1) The computational and memory complexity scales quadratically w.r.t. L; 2) The presence of redundant context information may hamper the model to capture dependencies among crucial tokens, which may degrade the representation performance. In this paper, we propose a plug-and-play Core Context Aware (CCA) Attention for efficient long-range context modeling, which consists of two components: 1) Globality-pooling attention that divides input tokens into groups and then dynamically merges tokens within each group into one core token based on their significance; 2) Locality-preserved attention that incorporates neighboring tokens into the attention calculation. The two complementary attentions will then be fused to the final attention, maintaining comprehensive modeling ability as the full self-attention. In this way, the core context information w.r.t. a given token will be automatically focused and strengthened, while the context information in redundant groups will be diminished during the learning process. As a result, the computational and memory complexity will be significantly reduced. More importantly, the CCA-Attention can improve the long-context modeling ability by diminishing the redundant context information. Extensive experimental results demonstrate that our CCA-Attention significantly outperforms state-of-the-art models in terms of computational efficiency and long-context modeling ability.
Authors: Mingquan Feng, Zhijie Chen, Yixin Huang, Yizhou Liu, Junchi Yan
Abstract: Optimal control problems (OCPs) involve finding a control function for a dynamical system such that a cost functional is optimized. It is central to physical systems in both academia and industry. In this paper, we propose a novel instance-solution control operator perspective, which solves OCPs in a one-shot manner without direct dependence on the explicit expression of dynamics or iterative optimization processes. The control operator is implemented by a new neural operator architecture named Neural Adaptive Spectral Method (NASM), a generalization of classical spectral methods. We theoretically validate the perspective and architecture by presenting the approximation error bounds of NASM for the control operator. Experiments on synthetic environments and a real-world dataset verify the effectiveness and efficiency of our approach, including substantial speedup in running time, and high-quality in- and out-of-distribution generalization.
Authors: Samuel Yen-Chi Chen
Abstract: Recent advancements in quantum computing (QC) and machine learning (ML) have garnered significant attention, leading to substantial efforts toward the development of quantum machine learning (QML) algorithms to address a variety of complex challenges. The design of high-performance QML models, however, requires expert-level knowledge, posing a significant barrier to the widespread adoption of QML. Key challenges include the design of data encoding mechanisms and parameterized quantum circuits, both of which critically impact the generalization capabilities of QML models. We propose a novel method that encodes quantum circuit architecture information to enable the evolution of quantum circuit designs. In this approach, the fitness function is based on the effective dimension, allowing for the optimization of quantum circuits towards higher model capacity. Through numerical simulations, we demonstrate that the proposed method is capable of discovering variational quantum circuit architectures that offer improved learning capabilities, thereby enhancing the overall performance of QML models for complex tasks.
Authors: Max Mason, Waasi A Jagirdar, David Huang, Rahul Murugan
Abstract: The primary objective of this research is to build a Momentum Transformer that is expected to outperform benchmark time-series momentum and mean-reversion trading strategies. We extend the ideas introduced in the paper Trading with the Momentum Transformer: An Intelligent and Interpretable Architecture to equities as the original paper primarily only builds upon futures and equity indices. Unlike conventional Long Short-Term Memory (LSTM) models, which operate sequentially and are optimized for processing local patterns, an attention mechanism equips our architecture with direct access to all prior time steps in the training window. This hybrid design, combining attention with an LSTM, enables the model to capture long-term dependencies, enhance performance in scenarios accounting for transaction costs, and seamlessly adapt to evolving market conditions, such as those witnessed during the Covid Pandemic. We average 4.14% returns which is similar to the original papers results. Our Sharpe is lower at an average of 1.12 due to much higher volatility which may be due to stocks being inherently more volatile than futures and indices.
Authors: Zahra Ebrahimi Vargoorani, Ching Yee Suen
Abstract: License plate detection (LPD) is essential for traffic management, vehicle tracking, and law enforcement but faces challenges like variable lighting and diverse font types, impacting accuracy. Traditionally reliant on image processing and machine learning, the field is now shifting towards deep learning for its robust performance in various conditions. Current methods, however, often require tailoring to specific regional datasets. This paper proposes a dual deep learning strategy using a Faster R-CNN for detection and a CNN-RNN model with Connectionist Temporal Classification (CTC) loss and a MobileNet V3 backbone for recognition. This approach aims to improve model performance using datasets from Ontario, Quebec, California, and New York State, achieving a recall rate of 92% on the Centre for Pattern Recognition and Machine Intelligence (CENPARMI) dataset and 90% on the UFPR-ALPR dataset. It includes a detailed error analysis to identify the causes of false positives. Additionally, the research examines the role of font features in license plate (LP) recognition, analyzing fonts like Driver Gothic, Dreadnought, California Clarendon, and Zurich Extra Condensed with the OpenALPR system. It discovers significant performance discrepancies influenced by font characteristics, offering insights for future LPD system enhancements. Keywords: Deep Learning, License Plate, Font Evaluation
Authors: Aman Tiwari, Shiva Krishna Reddy Malay, Vikas Yadav, Masoud Hashemi, Sathwik Tejaswi Madhusudhan
Abstract: Cypher, the query language for Neo4j graph databases, plays a critical role in enabling graph-based analytics and data exploration. While substantial research has been dedicated to natural language to SQL query generation (Text2SQL), the analogous problem for graph databases referred to as Text2Cypher remains underexplored. In this work, we introduce SynthCypher, a fully synthetic and automated data generation pipeline designed to address this gap. SynthCypher employs a novel LLMSupervised Generation-Verification framework, ensuring syntactically and semantically correct Cypher queries across diverse domains and query complexities. Using this pipeline, we create SynthCypher Dataset, a large-scale benchmark containing 29.8k Text2Cypher instances. Fine-tuning open-source large language models (LLMs), including LLaMa-3.1- 8B, Mistral-7B, and QWEN-7B, on SynthCypher yields significant performance improvements of up to 40% on the Text2Cypher test set and 30% on the SPIDER benchmark adapted for graph databases. This work demonstrates that high-quality synthetic data can effectively advance the state-of-the-art in Text2Cypher tasks.
Authors: ChonLam Lao, Minlan Yu, Aditya Akella, Jiamin Cao, Yu Guan, Pengcheng Zhang, Zhilong Zheng, Yichi Xu, Ennan Zhai, Dennis Cai, Jiaqi Gao
Abstract: Machine learning training has emerged as one of the most prominent workloads in modern data centers. These training jobs are large-scale, long-lasting, and tightly coupled, and are often disrupted by various events in the cluster such as failures, maintenance, and job scheduling. To handle these events, we rely on cold migration, where we first checkpoint the entire cluster, replace the related machines, and then restart the training. This approach leads to disruptions to the training jobs, resulting in significant downtime. In this paper, we present TrainMover, a live migration system that enables machine replacement during machine learning training. TrainMover minimizes downtime by leveraging member replacement of collective communication groups and sandbox lazy initialization. Our evaluation demonstrates that TrainMover achieves 16x less downtime compared to all baselines, effectively handling data center events like straggler rebalancing, maintenance, and unexpected failures.
Authors: Tobias Becher, Simon Torka
Abstract: Traditional rule-based cybersecurity systems have proven highly effective against known malware threats. However, they face challenges in detecting novel threats. To address this issue, emerging cybersecurity systems are incorporating AI techniques, specifically deep-learning algorithms, to enhance their ability to detect incidents, analyze alerts, and respond to events. While these techniques offer a promising approach to combating dynamic security threats, they often require significant computational resources. Therefore, frameworks that incorporate AI-based cybersecurity mechanisms need to support the use of GPUs to ensure optimal performance. Many cybersecurity framework vendors do not provide sufficiently detailed information about their implementation, making it difficult to assess the techniques employed and their effectiveness. This study aims to overcome this limitation by providing an overview of the most used cybersecurity frameworks that utilize AI techniques, specifically focusing on frameworks that provide comprehensive information about their implementation. Our primary objective is to identify the deep-learning techniques employed by these frameworks and evaluate their support for GPU acceleration. We have identified a total of \emph{two} deep-learning algorithms that are utilized by \emph{three} out of 38 selected cybersecurity frameworks. Our findings aim to assist in selecting open-source cybersecurity frameworks for future research and assessing any discrepancies between deep-learning techniques used in theory and practice.
Authors: Abderrezzaq Sendjasni, Seif-Eddine Benkabou, Mohamed-Chaker Larabi
Abstract: This article presents a novel approach to improving the accuracy of 360-degree perceptual image quality assessment (IQA) through a two-fold patch selection process. Our methodology combines visual patch selection with embedding similarity-based refinement. The first stage focuses on selecting patches from 360-degree images using three distinct sampling methods to ensure comprehensive coverage of visual content for IQA. The second stage, which is the core of our approach, employs an embedding similarity-based selection process to filter and prioritize the most informative patches based on their embeddings similarity distances. This dual selection mechanism ensures that the training data is both relevant and informative, enhancing the model's learning efficiency. Extensive experiments and statistical analyses using three distance metrics across three benchmark datasets validate the effectiveness of our selection algorithm. The results highlight its potential to deliver robust and accurate 360-degree IQA, with performance gains of up to 4.5% in accuracy and monotonicity of quality score prediction, while using only 40% to 50% of the training patches. These improvements are consistent across various configurations and evaluation metrics, demonstrating the strength of the proposed method. The code for the selection process is available at: https://github.com/sendjasni/patch-selection-360-image-quality.
URLs: https://github.com/sendjasni/patch-selection-360-image-quality.
Authors: Ryo Suzuki, Mar Gonzalez-Franco, Misha Sra, David Lindlbauer
Abstract: This workshop brings together experts and practitioners from augmented reality (AR) and artificial intelligence (AI) to shape the future of AI-in-the-loop everyday AR experiences. With recent advancements in both AR hardware and AI capabilities, we envision that everyday AR -- always-available and seamlessly integrated into users' daily environments -- is becoming increasingly feasible. This workshop will explore how AI can drive such everyday AR experiences. We discuss a range of topics, including adaptive and context-aware AR, generative AR content creation, always-on AI assistants, AI-driven accessible design, and real-world-oriented AI agents. Our goal is to identify the opportunities and challenges in AI-enabled AR, focusing on creating novel AR experiences that seamlessly blend the digital and physical worlds. Through the workshop, we aim to foster collaboration, inspire future research, and build a community to advance the research field of AI-enhanced AR.
Authors: Irham T. Andika, Stefan Schuldt, Sherry H. Suyu, Satadru Bag, Raoul Ca\~nameras, Alejandra Melo, Claudio Grillo, James H. H. Chan
Abstract: Strongly lensed quasars provide valuable insights into the rate of cosmic expansion, the distribution of dark matter in foreground deflectors, and the characteristics of quasar hosts. However, detecting them in astronomical images is difficult due to the prevalence of non-lensing objects. To address this challenge, we developed a generative deep learning model called VariLens, built upon a physics-informed variational autoencoder. This model seamlessly integrates three essential modules: image reconstruction, object classification, and lens modeling, offering a fast and comprehensive approach to strong lens analysis. VariLens is capable of rapidly determining both (1) the probability that an object is a lens system and (2) key parameters of a singular isothermal ellipsoid (SIE) mass model -- including the Einstein radius ($\theta_\mathrm{E}$), lens center, and ellipticity -- in just milliseconds using a single CPU. A direct comparison of VariLens estimates with traditional lens modeling for 20 known lensed quasars within the Subaru Hyper Suprime-Cam (HSC) footprint shows good agreement, with both results consistent within $2\sigma$ for systems with $\theta_\mathrm{E}<3$ arcsecs. To identify new lensed quasar candidates, we begin with an initial sample of approximately 80 million sources, combining HSC data with multiwavelength information from various surveys. After applying a photometric preselection aimed at locating $z>1.5$ sources, the number of candidates is reduced to 710,966. Subsequently, VariLens highlights 13,831 sources, each showing a high likelihood of being a lens. A visual assessment of these objects results in 42 promising candidates that await spectroscopic confirmation. These results underscore the potential of automated deep learning pipelines to efficiently detect and model strong lenses in large datasets.
Authors: Wenqi Huang, Veronika Spieker, Siying Xu, Gastao Cruz, Claudia Prieto, Julia Schnabel, Kerstin Hammernik, Thomas Kuestner, Daniel Rueckert
Abstract: Conventional cardiac cine MRI methods rely on retrospective gating, which limits temporal resolution and the ability to capture continuous cardiac dynamics, particularly in patients with arrhythmias and beat-to-beat variations. To address these challenges, we propose a reconstruction framework based on subspace implicit neural representations for real-time cardiac cine MRI of continuously sampled radial data. This approach employs two multilayer perceptrons to learn spatial and temporal subspace bases, leveraging the low-rank properties of cardiac cine MRI. Initialized with low-resolution reconstructions, the networks are fine-tuned using spoke-specific loss functions to recover spatial details and temporal fidelity. Our method directly utilizes the continuously sampled radial k-space spokes during training, thereby eliminating the need for binning and non-uniform FFT. This approach achieves superior spatial and temporal image quality compared to conventional binned methods at the acceleration rate of 10 and 20, demonstrating potential for high-resolution imaging of dynamic cardiac events and enhancing diagnostic capability.
Authors: Khen Cohen, Liav Hen, Ariel Lellouch
Abstract: Distributed Acoustic Sensing (DAS) has emerged as a promising tool for real-time traffic monitoring in densely populated areas. In this paper, we present a novel concept that integrates DAS data with co-located visual information. We use YOLO-derived vehicle location and classification from camera inputs as labeled data to train a detection and classification neural network utilizing DAS data only. Our model achieves a performance exceeding 94% for detection and classification, and about 1.2% false alarm rate. We illustrate the model's application in monitoring traffic over a week, yielding statistical insights that could benefit future smart city developments. Our approach highlights the potential of combining fiber-optic sensors with visual information, focusing on practicality and scalability, protecting privacy, and minimizing infrastructure costs. To encourage future research, we share our dataset.
Authors: Nan Li, Bo Kang, Tijl De Bie
Abstract: Text classification with hierarchical labels is a prevalent and challenging task in natural language processing. Examples include assigning ICD codes to patient records, tagging patents into IPC classes, assigning EUROVOC descriptors to European legal texts, and more. Despite its widespread applications, a comprehensive understanding of state-of-the-art methods across different domains has been lacking. In this paper, we provide the first comprehensive cross-domain overview with empirical analysis of state-of-the-art methods. We propose a unified framework that positions each method within a common structure to facilitate research. Our empirical analysis yields key insights and guidelines, confirming the necessity of learning across different research areas to design effective methods. Notably, under our unified evaluation pipeline, we achieved new state-of-the-art results by applying techniques beyond their original domains.
Authors: Amrapali Pednekar, Alvaro Garrido, Yara Khaluf, Pieter Simoens
Abstract: Time perception research has advanced significantly over the years. However, some areas remain largely unexplored. This study addresses two such under-explored areas in timing research: (1) A quantitative analysis of time perception at an individual level, and (2) Time perception in an ecological setting. In this context, we trained a machine learning model to predict the direction of change in an individual's time production. The model's training data was collected using an ecologically valid setup. We moved closer to an ecological setting by conducting an online experiment with 995 participants performing a time production task that used naturalistic videos (no audio) as stimuli. The model achieved an accuracy of 61%. This was 10 percentage points higher than the baseline models derived from cognitive theories of timing. The model performed equally well on new data from a second experiment, providing evidence of its generalization capabilities. The model's output analysis revealed that it also contained information about the magnitude of change in time production. The predictions were further analysed at both population and individual level. It was found that a participant's previous timing performance played a significant role in determining the direction of change in time production. By integrating attentional-gate theories from timing research with feature importance techniques from machine learning, we explained model predictions using cognitive theories of timing. The model and findings from this study have potential applications in systems involving human-computer interactions where understanding and predicting changes in user's time perception can enable better user experience and task performance.
Authors: Kees Koenders, Leo Schnitzpan, Fabian Kammerbauer, Sinan Shu, Gerhard Jakob, Mathis Kl\"aui, Johan Mentink, Nasir Ahmad, Marcel van Gerven
Abstract: Brain-inspired learning in physical hardware has enormous potential to learn fast at minimal energy expenditure. One of the characteristics of biological learning systems is their ability to learn in the presence of various noise sources. Inspired by this observation, we introduce a novel noise-based learning approach for physical systems implementing multi-layer neural networks. Simulation results show that our approach allows for effective learning whose performance approaches that of the conventional effective yet energy-costly backpropagation algorithm. Using a spintronics hardware implementation, we demonstrate experimentally that learning can be achieved in a small network composed of physical stochastic magnetic tunnel junctions. These results provide a path towards efficient learning in general physical systems which embraces rather than mitigates the noise inherent in physical devices.
Authors: Yuhong Chen, Ailin Song, Huifeng Yin, Shuai Zhong, Fuhai Chen, Qi Xu, Shiping Wang, Mingkun Xu
Abstract: The rapid evolution of multimedia technology has revolutionized human perception, paving the way for multi-view learning. However, traditional multi-view learning approaches are tailored for scenarios with fixed data views, falling short of emulating the intricate cognitive procedures of the human brain processing signals sequentially. Our cerebral architecture seamlessly integrates sequential data through intricate feed-forward and feedback mechanisms. In stark contrast, traditional methods struggle to generalize effectively when confronted with data spanning diverse domains, highlighting the need for innovative strategies that can mimic the brain's adaptability and dynamic integration capabilities. In this paper, we propose a bio-neurologically inspired multi-view incremental framework named MVIL aimed at emulating the brain's fine-grained fusion of sequentially arriving views. MVIL lies two fundamental modules: structured Hebbian plasticity and synaptic partition learning. The structured Hebbian plasticity reshapes the structure of weights to express the high correlation between view representations, facilitating a fine-grained fusion of view representations. Moreover, synaptic partition learning is efficient in alleviating drastic changes in weights and also retaining old knowledge by inhibiting partial synapses. These modules bionically play a central role in reinforcing crucial associations between newly acquired information and existing knowledge repositories, thereby enhancing the network's capacity for generalization. Experimental results on six benchmark datasets show MVIL's effectiveness over state-of-the-art methods.
Authors: Mohamed Ndaoud, Peter Radchenko, Bradley Rava
Abstract: Selective classification frameworks are useful tools for automated decision making in highly risky scenarios, since they allow for a classifier to only make highly confident decisions, while abstaining from making a decision when it is not confident enough to do so, which is otherwise known as an indecision. For a given level of classification accuracy, we aim to make as many decisions as possible. For many problems, this can be achieved without abstaining from making decisions. But when the problem is hard enough, we show that we can still control the misclassification rate of a classifier up to any user specified level, while only abstaining from the minimum necessary amount of decisions, even if this level of misclassification is smaller than the Bayes optimal error rate. In many problem settings, the user could obtain a dramatic decrease in misclassification while only paying a comparatively small price in terms of indecisions.
Authors: Ruikang Ni, Da Xiao, Qingye Meng, Xiangyu Li, Shihui Zheng, Hongliang Liang
Abstract: Compositional relational reasoning (CRR) is a hallmark of human intelligence, but we lack a clear understanding of whether and how existing transformer large language models (LLMs) can solve CRR tasks. To enable systematic exploration of the CRR capability of LLMs, we first propose a new synthetic benchmark called Generalized Associative Recall (GAR) by integrating and generalizing the essence of several tasks in mechanistic interpretability (MI) study in a unified framework. Evaluation shows that GAR is challenging enough for existing LLMs, revealing their fundamental deficiency in CRR. Meanwhile, it is easy enough for systematic MI study. Then, to understand how LLMs solve GAR tasks, we use attribution patching to discover the core circuits reused by Vicuna-33B across different tasks and a set of vital attention heads. Intervention experiments show that the correct functioning of these heads significantly impacts task performance. Especially, we identify two classes of heads whose activations represent the abstract notion of true and false in GAR tasks respectively. They play a fundamental role in CRR across various models and tasks. The dataset and code are available at https://github.com/Caiyun-AI/GAR.
Authors: Qingqing Fang, Qinliang Su, Wenxi Lv, Wenchao Xu, Jianxing Yu
Abstract: Many unsupervised visual anomaly detection methods train an auto-encoder to reconstruct normal samples and then leverage the reconstruction error map to detect and localize the anomalies. However, due to the powerful modeling and generalization ability of neural networks, some anomalies can also be well reconstructed, resulting in unsatisfactory detection and localization accuracy. In this paper, a small coarsely-labeled anomaly dataset is first collected. Then, a coarse-knowledge-aware adversarial learning method is developed to align the distribution of reconstructed features with that of normal features. The alignment can effectively suppress the auto-encoder's reconstruction ability on anomalies and thus improve the detection accuracy. Considering that anomalies often only occupy very small areas in anomalous images, a patch-level adversarial learning strategy is further developed. Although no patch-level anomalous information is available, we rigorously prove that by simply viewing any patch features from anomalous images as anomalies, the proposed knowledge-aware method can also align the distribution of reconstructed patch features with the normal ones. Experimental results on four medical datasets and two industrial datasets demonstrate the effectiveness of our method in improving the detection and localization performance.
Authors: Shijing Wang, Yaping Huang
Abstract: Uncertainty in gaze estimation manifests in two aspects: 1) low-quality images caused by occlusion, blurriness, inconsistent eye movements, or even non-face images; 2) incorrect labels resulting from the misalignment between the labeled and actual gaze points during the annotation process. Allowing these uncertainties to participate in training hinders the improvement of gaze estimation. To tackle these challenges, in this paper, we propose an effective solution, named Suppressing Uncertainty in Gaze Estimation (SUGE), which introduces a novel triplet-label consistency measurement to estimate and reduce the uncertainties. Specifically, for each training sample, we propose to estimate a novel ``neighboring label'' calculated by a linearly weighted projection from the neighbors to capture the similarity relationship between image features and their corresponding labels, which can be incorporated with the predicted pseudo label and ground-truth label for uncertainty estimation. By modeling such triplet-label consistency, we can measure the qualities of both images and labels, and further largely reduce the negative effects of unqualified images and wrong labels through our designed sample weighting and label correction strategies. Experimental results on the gaze estimation benchmarks indicate that our proposed SUGE achieves state-of-the-art performance.
Authors: Taisuke Kobayashi, Takumi Aotani
Abstract: This paper proposes a new design method for a stochastic control policy using a normalizing flow (NF). In reinforcement learning (RL), the policy is usually modeled as a distribution model with trainable parameters. When this parameterization has less expressiveness, it would fail to acquiring the optimal policy. A mixture model has capability of a universal approximation, but it with too much redundancy increases the computational cost, which can become a bottleneck when considering the use of real-time robot control. As another approach, NF, which is with additional parameters for invertible transformation from a simple stochastic model as a base, is expected to exert high expressiveness and lower computational cost. However, NF cannot compute its mean analytically due to complexity of the invertible transformation, and it lacks reliability because it retains stochastic behaviors after deployment for robot controller. This paper therefore designs a restricted NF (RNF) that achieves an analytic mean by appropriately restricting the invertible transformation. In addition, the expressiveness impaired by this restriction is regained using bimodal student-t distribution as its base, so-called Bit-RNF. In RL benchmarks, Bit-RNF policy outperformed the previous models. Finally, a real robot experiment demonstrated the applicability of Bit-RNF policy to real world. The attached video is uploaded on youtube: https://youtu.be/R_GJVZDW9bk
Authors: Salim I. Amoukou, Tom Bewley, Saumitra Mishra, Freddy Lecue, Daniele Magazzeni, Manuela Veloso
Abstract: We introduce a novel approach for detecting distribution shifts that negatively impact the performance of machine learning models in continuous production environments, which requires no access to ground truth data labels. It builds upon the work of Podkopaev and Ramdas [2022], who address scenarios where labels are available for tracking model errors over time. Our solution extends this framework to work in the absence of labels, by employing a proxy for the true error. This proxy is derived using the predictions of a trained error estimator. Experiments show that our method has high power and false alarm control under various distribution shifts, including covariate and label shifts and natural shifts over geography and time.
Authors: Lam Ngo, Huong Ha, Jeffrey Chan, Hongyu Zhang
Abstract: When it comes to expensive black-box optimization problems, Bayesian Optimization (BO) is a well-known and powerful solution. Many real-world applications involve a large number of dimensions, hence scaling BO to high dimension is of much interest. However, state-of-the-art high-dimensional BO methods still suffer from the curse of dimensionality, highlighting the need for further improvements. In this work, we introduce BOIDS, a novel high-dimensional BO algorithm that guides optimization by a sequence of one-dimensional direction lines using a novel tailored line-based optimization procedure. To improve the efficiency, we also propose an adaptive selection technique to identify most optimal lines for each round of line-based optimization. Additionally, we incorporate a subspace embedding technique for better scaling to high-dimensional spaces. We further provide theoretical analysis of our proposed method to analyze its convergence property. Our extensive experimental results show that BOIDS outperforms state-of-the-art baselines on various synthetic and real-world benchmark problems.
Authors: Chuan He, Zhanwang Deng
Abstract: Conic optimization plays a crucial role in many machine learning (ML) problems. However, practical algorithms for conic constrained ML problems with large datasets are often limited to specific use cases, as stochastic algorithms for general conic optimization remain underdeveloped. To fill this gap, we introduce a stochastic interior-point method (SIPM) framework for general conic optimization, along with four novel SIPM variants leveraging distinct stochastic gradient estimators. Under mild assumptions, we establish the global convergence rates of our proposed SIPMs, which, up to a logarithmic factor, match the best-known rates in stochastic unconstrained optimization. Finally, our numerical experiments on robust linear regression, multi-task relationship learning, and clustering data streams demonstrate the effectiveness and efficiency of our approach.
Authors: Lennert De Smet, Gabriele Venturato, Luc De Raedt, Giuseppe Marra
Abstract: Sequential problems are ubiquitous in AI, such as in reinforcement learning or natural language processing. State-of-the-art deep sequential models, like transformers, excel in these settings but fail to guarantee the satisfaction of constraints necessary for trustworthy deployment. In contrast, neurosymbolic AI (NeSy) provides a sound formalism to enforce constraints in deep probabilistic models but scales exponentially on sequential problems. To overcome these limitations, we introduce relational neurosymbolic Markov models (NeSy-MMs), a new class of end-to-end differentiable sequential models that integrate and provably satisfy relational logical constraints. We propose a strategy for inference and learning that scales on sequential settings, and that combines approximate Bayesian inference, automated reasoning, and gradient estimation. Our experiments show that NeSy-MMs can solve problems beyond the current state-of-the-art in neurosymbolic AI and still provide strong guarantees with respect to desired properties. Moreover, we show that our models are more interpretable and that constraints can be adapted at test time to out-of-distribution scenarios.
Authors: Hugo Math, Rainer Lienhart, Robin Sch\"on
Abstract: In this paper, we draw an analogy between processing natural languages and processing multivariate event streams from vehicles in order to predict $\textit{when}$ and $\textit{what}$ error pattern is most likely to occur in the future for a given car. Our approach leverages the temporal dynamics and contextual relationships of our event data from a fleet of cars. Event data is composed of discrete values of error codes as well as continuous values such as time and mileage. Modelled by two causal Transformers, we can anticipate vehicle failures and malfunctions before they happen. Thus, we introduce $\textit{CarFormer}$, a Transformer model trained via a new self-supervised learning strategy, and $\textit{EPredictor}$, an autoregressive Transformer decoder model capable of predicting $\textit{when}$ and $\textit{what}$ error pattern will most likely occur after some error code apparition. Despite the challenges of high cardinality of event types, their unbalanced frequency of appearance and limited labelled data, our experimental results demonstrate the excellent predictive ability of our novel model. Specifically, with sequences of $160$ error codes on average, our model is able with only half of the error codes to achieve $80\%$ F1 score for predicting $\textit{what}$ error pattern will occur and achieves an average absolute error of $58.4 \pm 13.2$h $\textit{when}$ forecasting the time of occurrence, thus enabling confident predictive maintenance and enhancing vehicle safety.
Authors: Joshua Groen, Simone Di Valerio, Imtiaz Karim, Davide Villa, Yiewi Zhang, Leonardo Bonati, Michele Polese, Salvatore D'Oro, Tommaso Melodia, Elisa Bertino, Francesca Cuomo, Kaushik Chowdhury
Abstract: 5G and beyond cellular systems embrace the disaggregation of Radio Access Network (RAN) components, exemplified by the evolution of the fronthual (FH) connection between cellular baseband and radio unit equipment. Crucially, synchronization over the FH is pivotal for reliable 5G services. In recent years, there has been a push to move these links to an Ethernet-based packet network topology, leveraging existing standards and ongoing research for Time-Sensitive Networking (TSN). However, TSN standards, such as Precision Time Protocol (PTP), focus on performance with little to no concern for security. This increases the exposure of the open FH to security risks. Attacks targeting synchronization mechanisms pose significant threats, potentially disrupting 5G networks and impairing connectivity. In this paper, we demonstrate the impact of successful spoofing and replay attacks against PTP synchronization. We show how a spoofing attack is able to cause a production-ready O-RAN and 5G-compliant private cellular base station to catastrophically fail within 2 seconds of the attack, necessitating manual intervention to restore full network operations. To counter this, we design a Machine Learning (ML)-based monitoring solution capable of detecting various malicious attacks with over 97.5% accuracy.
Authors: Anni Tang, Tianyu He, Junliang Guo, Xinle Cheng, Li Song, Jiang Bian
Abstract: Encoding video content into compact latent tokens has become a fundamental step in video generation and understanding, driven by the need to address the inherent redundancy in pixel-level representations. Consequently, there is a growing demand for high-performance, open-source video tokenizers as video-centric research gains prominence. We introduce VidTok, a versatile video tokenizer that delivers state-of-the-art performance in both continuous and discrete tokenizations. VidTok incorporates several key advancements over existing approaches: 1) model architecture such as convolutional layers and up/downsampling modules; 2) to address the training instability and codebook collapse commonly associated with conventional Vector Quantization (VQ), we integrate Finite Scalar Quantization (FSQ) into discrete video tokenization; 3) improved training strategies, including a two-stage training process and the use of reduced frame rates. By integrating these advancements, VidTok achieves substantial improvements over existing methods, demonstrating superior performance across multiple metrics, including PSNR, SSIM, LPIPS, and FVD, under standardized evaluation settings.
Authors: Stanislas Ducotterd, Sebastian Neumayer, Michael Unser
Abstract: We aim at the solution of inverse problems in imaging, by combining a penalized sparse representation of image patches with an unconstrained smooth one. This allows for a straightforward interpretation of the reconstruction. We formulate the optimization as a bilevel problem. The inner problem deploys classical algorithms while the outer problem optimizes the dictionary and the regularizer parameters through supervised learning. The process is carried out via implicit differentiation and gradient-based optimization. We evaluate our method for denoising, super-resolution, and compressed-sensing magnetic-resonance imaging. We compare it to other classical models as well as deep-learning-based methods and show that it always outperforms the former and also the latter in some instances.
Authors: Philippe Goulet Coulombe, Maximilian Goebel, Karin Klieber
Abstract: Machine learning predictions are typically interpreted as the sum of contributions of predictors. Yet, each out-of-sample prediction can also be expressed as a linear combination of in-sample values of the predicted variable, with weights corresponding to pairwise proximity scores between current and past economic events. While this dual route leads nowhere in some contexts (e.g., large cross-sectional datasets), it provides sparser interpretations in settings with many regressors and little training data-like macroeconomic forecasting. In this case, the sequence of contributions can be visualized as a time series, allowing analysts to explain predictions as quantifiable combinations of historical analogies. Moreover, the weights can be viewed as those of a data portfolio, inspiring new diagnostic measures such as forecast concentration, short position, and turnover. We show how weights can be retrieved seamlessly for (kernel) ridge regression, random forest, boosted trees, and neural networks. Then, we apply these tools to analyze post-pandemic forecasts of inflation, GDP growth, and recession probabilities. In all cases, the approach opens the black box from a new angle and demonstrates how machine learning models leverage history partly repeating itself.
Authors: Sai Teja Erukude, Akhil Joshi, Lior Shamir
Abstract: CNNs have become one of the most commonly used computational tool in the past two decades. One of the primary downsides of CNNs is that they work as a ``black box", where the user cannot necessarily know how the image data are analyzed, and therefore needs to rely on empirical evaluation to test the efficacy of a trained CNN. This can lead to hidden biases that affect the performance evaluation of neural networks, but are difficult to identify. Here we discuss examples of such hidden biases in common and widely used benchmark datasets, and propose techniques for identifying dataset biases that can affect the standard performance evaluation metrics. One effective approach to identify dataset bias is to perform image classification by using merely blank background parts of the original images. However, in some situations a blank background in the images is not available, making it more difficult to separate foreground or contextual information from the bias. To overcome this, we propose a method to identify dataset bias without the need to crop background information from the images. That method is based on applying several image transforms to the original images, including Fourier transform, wavelet transforms, median filter, and their combinations. These transforms were applied to recover background bias information that CNNs use to classify images. This transformations affect the contextual visual information in a different manner than it affects the systemic background bias. Therefore, the method can distinguish between contextual information and the bias, and alert on the presence of background bias even without the need to separate sub-images parts from the blank background of the original images. Code used in the experiments is publicly available.
Authors: Jiate Li, Meng Pang, Binghui Wang
Abstract: Link prediction in dynamic graphs (LPDG) has been widely applied to real-world applications such as website recommendation, traffic flow prediction, organizational studies, etc. These models are usually kept local and secure, with only the interactive interface restrictively available to the public. Thus, the problem of the black-box evasion attack on the LPDG model, where model interactions and data perturbations are restricted, seems to be essential and meaningful in practice. In this paper, we propose the first practicable black-box evasion attack method that achieves effective attacks against the target LPDG model, within a limited amount of interactions and perturbations. To perform effective attacks under limited perturbations, we develop a graph sequential embedding model to find the desired state embedding of the dynamic graph sequences, under a deep reinforcement learning framework. To overcome the scarcity of interactions, we design a multi-environment training pipeline and train our agent for multiple instances, by sharing an aggregate interaction buffer. Finally, we evaluate our attack against three advanced LPDG models on three real-world graph datasets of different scales and compare its performance with related methods under the interaction and perturbation constraints. Experimental results show that our attack is both effective and practicable.
Authors: Juan Del Aguila Ferrandis, Jo\~ao Moura, Sethu Vijayakumar
Abstract: Manipulation without grasping, known as non-prehensile manipulation, is essential for dexterous robots in contact-rich environments, but presents many challenges relating with underactuation, hybrid-dynamics, and frictional uncertainty. Additionally, object occlusions in a scenario of contact uncertainty and where the motion of the object evolves independently from the robot becomes a critical problem, which previous literature fails to address. We present a method for learning visuotactile state estimators and uncertainty-aware control policies for non-prehensile manipulation under occlusions, by leveraging diverse interaction data from privileged policies trained in simulation. We formulate the estimator within a Bayesian deep learning framework, to model its uncertainty, and then train uncertainty-aware control policies by incorporating the pre-learned estimator into the reinforcement learning (RL) loop, both of which lead to significantly improved estimator and policy performance. Therefore, unlike prior non-prehensile research that relies on complex external perception set-ups, our method successfully handles occlusions after sim-to-real transfer to robotic hardware with a simple onboard camera. See our video: https://youtu.be/hW-C8i_HWgs.
Authors: Ilya Rozenfeld
Abstract: As the use of complex machine learning models continues to grow, so does the need for reliable explainability methods. One of the most popular methods for model explainability is based on Shapley values. There are two most commonly used approaches to calculating Shapley values which produce different results when features are correlated, conditional and marginal. In our previous work, it was demonstrated that the conditional approach is fundamentally flawed due to implicit assumptions of causality. However, it is a well-known fact that marginal approach to calculating Shapley values leads to model extrapolation where it might not be well defined. In this paper we explore the impacts of model extrapolation on Shapley values in the case of a simple linear spline model. Furthermore, we propose an approach which while using marginal averaging avoids model extrapolation and with addition of causal information replicates causal Shapley values. Finally, we demonstrate our method on the real data example.
Authors: Mohammad Nazmush Shamael, Sabila Nawshin, Swakkhar Shatabda, Salekul Islam
Abstract: This work presents the BanglishRev Dataset, the largest e-commerce product review dataset to date for reviews written in Bengali, English, a mixture of both and Banglish, Bengali words written with English alphabets. The dataset comprises of 1.74 million written reviews from 3.2 million ratings information collected from a total of 128k products being sold in online e-commerce platforms targeting the Bengali population. It includes an extensive array of related metadata for each of the reviews including the rating given by the reviewer, date the review was posted and date of purchase, number of likes, dislikes, response from the seller, images associated with the review etc. With sentiment analysis being the most prominent usage of review datasets, experimentation with a binary sentiment analysis model with the review rating serving as an indicator of positive or negative sentiment was conducted to evaluate the effectiveness of the large amount of data presented in BanglishRev for sentiment analysis tasks. A BanglishBERT model is trained on the data from BanglishRev with reviews being considered labeled positive if the rating is greater than 3 and negative if the rating is less than or equal to 3. The model is evaluated by being testing against a previously published manually annotated dataset for e-commerce reviews written in a mixture of Bangla, English and Banglish. The experimental model achieved an exceptional accuracy of 94\% and F1 score of 0.94, demonstrating the dataset's efficacy for sentiment analysis. Some of the intriguing patterns and observations seen within the dataset and future research directions where the dataset can be utilized is also discussed and explored. The dataset can be accessed through https://huggingface.co/datasets/BanglishRev/bangla-english-and-code-mixed-ecommerce-review-dataset.
URLs: https://huggingface.co/datasets/BanglishRev/bangla-english-and-code-mixed-ecommerce-review-dataset.
Authors: Jui-Che Chiang, Hou-Ning Hu, Bo-Syuan Hou, Chia-Yu Tseng, Yu-Lun Liu, Min-Hung Chen, Yen-Yu Lin
Abstract: Although facial landmark detection (FLD) has gained significant progress, existing FLD methods still suffer from performance drops on partially non-visible faces, such as faces with occlusions or under extreme lighting conditions or poses. To address this issue, we introduce ORFormer, a novel transformer-based method that can detect non-visible regions and recover their missing features from visible parts. Specifically, ORFormer associates each image patch token with one additional learnable token called the messenger token. The messenger token aggregates features from all but its patch. This way, the consensus between a patch and other patches can be assessed by referring to the similarity between its regular and messenger embeddings, enabling non-visible region identification. Our method then recovers occluded patches with features aggregated by the messenger tokens. Leveraging the recovered features, ORFormer compiles high-quality heatmaps for the downstream FLD task. Extensive experiments show that our method generates heatmaps resilient to partial occlusions. By integrating the resultant heatmaps into existing FLD methods, our method performs favorably against the state of the arts on challenging datasets such as WFLW and COFW.
Authors: Chen Bao, Jiarui Xu, Xiaolong Wang, Abhinav Gupta, Homanga Bharadhwaj
Abstract: How can we predict future interaction trajectories of human hands in a scene given high-level colloquial task specifications in the form of natural language? In this paper, we extend the classic hand trajectory prediction task to two tasks involving explicit or implicit language queries. Our proposed tasks require extensive understanding of human daily activities and reasoning abilities about what should be happening next given cues from the current scene. We also develop new benchmarks to evaluate the proposed two tasks, Vanilla Hand Prediction (VHP) and Reasoning-Based Hand Prediction (RBHP). We enable solving these tasks by integrating high-level world knowledge and reasoning capabilities of Vision-Language Models (VLMs) with the auto-regressive nature of low-level ego-centric hand trajectories. Our model, HandsOnVLM is a novel VLM that can generate textual responses and produce future hand trajectories through natural-language conversations. Our experiments show that HandsOnVLM outperforms existing task-specific methods and other VLM baselines on proposed tasks, and demonstrates its ability to effectively utilize world knowledge for reasoning about low-level human hand trajectories based on the provided context. Our website contains code and detailed video results \url{https://www.chenbao.tech/handsonvlm/}
Authors: Mazeyu Ji, Xuanbin Peng, Fangchen Liu, Jialong Li, Ge Yang, Xuxin Cheng, Xiaolong Wang
Abstract: This paper enables real-world humanoid robots to maintain stability while performing expressive motions like humans do. We propose ExBody2, a generalized whole-body tracking framework that can take any reference motion inputs and control the humanoid to mimic the motion. The model is trained in simulation with Reinforcement Learning and then transferred to the real world. It decouples keypoint tracking with velocity control, and effectively leverages a privileged teacher policy to distill precise mimic skills into the target student policy, which enables high-fidelity replication of dynamic movements such as running, crouching, dancing, and other challenging motions. We present a comprehensive qualitative and quantitative analysis of crucial design factors in the paper. We conduct our experiments on two humanoid platforms and demonstrate the superiority of our approach against state-of-the-arts, providing practical guidelines to pursue the extreme of whole-body control for humanoid robots.
Authors: Chen Liu, Zhichao Huang, Mathieu Salzmann, Tong Zhang, Sabine S\"usstrunk
Abstract: Adversarial training is a popular method to robustify models against adversarial attacks. However, it exhibits much more severe overfitting than training on clean inputs. In this work, we investigate this phenomenon from the perspective of training instances, i.e., training input-target pairs. Based on a quantitative metric measuring the relative difficulty of an instance in the training set, we analyze the model's behavior on training instances of different difficulty levels. This lets us demonstrate that the decay in generalization performance of adversarial training is a result of fitting hard adversarial instances. We theoretically verify our observations for both linear and general nonlinear models, proving that models trained on hard instances have worse generalization performance than ones trained on easy instances, and that this generalization gap increases with the size of the adversarial budget. Finally, we investigate solutions to mitigate adversarial overfitting in several scenarios, including fast adversarial training and fine-tuning a pretrained model with additional data. Our results demonstrate that using training data adaptively improves the model's robustness.
Authors: Ching-pei Lee, Ling Liang, Tianyun Tang, Kim-Chuan Toh
Abstract: This work proposes a rapid algorithm, BM-Global, for nuclear-norm-regularized convex and low-rank matrix optimization problems. BM-Global efficiently decreases the objective value via low-cost steps leveraging the nonconvex but smooth Burer-Monteiro (BM) decomposition, while effectively escapes saddle points and spurious local minima ubiquitous in the BM form to obtain guarantees of fast convergence rates to the global optima of the original nuclear-norm-regularized problem through aperiodic inexact proximal gradient steps on it. The proposed approach adaptively adjusts the rank for the BM decomposition and can provably identify an optimal rank for the BM decomposition problem automatically in the course of optimization through tools of manifold identification. BM-Global hence also spends significantly less time on parameter tuning than existing matrix-factorization methods, which require an exhaustive search for finding this optimal rank. Extensive experiments on real-world large-scale problems of recommendation systems, regularized kernel estimation, and molecular conformation confirm that BM-Global can indeed effectively escapes spurious local minima at which existing BM approaches are stuck, and is a magnitude faster than state-of-the-art algorithms for low-rank matrix optimization problems involving a nuclear-norm regularizer. Based on this research, we have released an open-source package of the proposed BM-Global at https://www.github.com/leepei/BM-Global/.
Authors: Owen Davis, Mohammad Motamed
Abstract: This survey provides an in-depth and explanatory review of the approximation properties of deep neural networks, with a focus on feed-forward and residual architectures. The primary objective is to examine how effectively neural networks approximate target functions and to identify conditions under which they outperform traditional approximation methods. Key topics include the nonlinear, compositional structure of deep networks and the formalization of neural network tasks as optimization problems in regression and classification settings. The survey also addresses the training process, emphasizing the role of stochastic gradient descent and backpropagation in solving these optimization problems, and highlights practical considerations such as activation functions, overfitting, and regularization techniques. Additionally, the survey explores the density of neural networks in the space of continuous functions, comparing the approximation capabilities of deep ReLU networks with those of other approximation methods. It discusses recent theoretical advancements in understanding the expressiveness and limitations of these networks. A detailed error-complexity analysis is also presented, focusing on error rates and computational complexity for neural networks with ReLU and Fourier-type activation functions in the context of bounded target functions with minimal regularity assumptions. Alongside recent known results, the survey introduces new findings, offering a valuable resource for understanding the theoretical foundations of neural network approximation. Concluding remarks and further reading suggestions are provided.
Authors: Jingyang Zhang, Jingkang Yang, Pengyun Wang, Haoqi Wang, Yueqian Lin, Haoran Zhang, Yiyou Sun, Xuefeng Du, Yixuan Li, Ziwei Liu, Yiran Chen, Hai Li
Abstract: Out-of-Distribution (OOD) detection is critical for the reliable operation of open-world intelligent systems. Despite the emergence of an increasing number of OOD detection methods, the evaluation inconsistencies present challenges for tracking the progress in this field. OpenOOD v1 initiated the unification of the OOD detection evaluation but faced limitations in scalability and scope. In response, this paper presents OpenOOD v1.5, a significant improvement from its predecessor that ensures accurate and standardized evaluation of OOD detection methodologies at large scale. Notably, OpenOOD v1.5 extends its evaluation capabilities to large-scale data sets (ImageNet) and foundation models (e.g., CLIP and DINOv2), and expands its scope to investigate full-spectrum OOD detection which considers semantic and covariate distribution shifts at the same time. This work also contributes in-depth analysis and insights derived from comprehensive experimental results, thereby enriching the knowledge pool of OOD detection methodologies. With these enhancements, OpenOOD v1.5 aims to drive advancements and offer a more robust and comprehensive evaluation benchmark for OOD detection research.
Authors: Lianyu Hu, Junjie Dong, Mudi Jiang, Yan Liu, Zengyou He
Abstract: The objective of clusterability evaluation is to check whether a clustering structure exists within the data set. As a crucial yet often-overlooked issue in cluster analysis, it is essential to conduct such a test before applying any clustering algorithm. If a data set is unclusterable, any subsequent clustering analysis would not yield valid results. Despite its importance, the majority of existing studies focus on numerical data, leaving the clusterability evaluation issue for categorical data as an open problem. Here we present TestCat, a testing-based approach to assess the clusterability of categorical data in terms of an analytical $p$-value. The key idea underlying TestCat is that clusterable categorical data possess many strongly associated attribute pairs and hence the sum of chi-squared statistics of all attribute pairs is employed as the test statistic for $p$-value calculation. We apply our method to a set of benchmark categorical data sets, showing that TestCat outperforms those solutions based on existing clusterability evaluation methods for numeric data. To the best of our knowledge, our work provides the first way to effectively recognize the clusterability of categorical data in a statistically sound manner.
Authors: Shuzhen Chen, Yuan Yuan, Youming Tao, Tianzhu Wang, Zhipeng Cai, Dongxiao Yu
Abstract: Newton's method leverages curvature information to boost performance, and thus outperforms first-order methods for distributed learning problems. However, Newton's method is not practical in large-scale and heterogeneous learning environments, due to obstacles such as high computation and communication costs of the Hessian matrix, sub-model diversity, staleness of training, and data heterogeneity. To overcome these obstacles, this paper presents a novel and efficient algorithm named Distributed Adaptive Newton Learning (\texttt{DANL}), which solves the drawbacks of Newton's method by using a simple Hessian initialization and adaptive allocation of training regions. The algorithm exhibits remarkable convergence properties, which are rigorously examined under standard assumptions in stochastic optimization. The theoretical analysis proves that \texttt{DANL} attains a linear convergence rate while efficiently adapting to available resources and keeping high efficiency. Furthermore, \texttt{DANL} shows notable independence from the condition number of the problem and removes the necessity for complex parameter tuning. Experiments demonstrate that \texttt{DANL} achieves linear convergence with efficient communication and strong performance across different datasets.
Authors: Enrique Alvarado, Robin Belton, Emily Fischer, Kang-Ju Lee, Sourabh Palande, Sarah Percival, Emilie Purvine
Abstract: The Mapper algorithm is a visualization technique in topological data analysis (TDA) that outputs a graph reflecting the structure of a given dataset. However, the Mapper algorithm requires tuning several parameters in order to generate a ``nice" Mapper graph. This paper focuses on selecting the cover parameter. We present an algorithm that optimizes the cover of a Mapper graph by splitting a cover repeatedly according to a statistical test for normality. Our algorithm is based on $G$-means clustering which searches for the optimal number of clusters in $k$-means by iteratively applying the Anderson-Darling test. Our splitting procedure employs a Gaussian mixture model to carefully choose the cover according to the distribution of the given data. Experiments for synthetic and real-world datasets demonstrate that our algorithm generates covers so that the Mapper graphs retain the essence of the datasets, while also running significantly fast.
Authors: Ruizhe Shi, Yuyao Liu, Yanjie Ze, Simon S. Du, Huazhe Xu
Abstract: Offline reinforcement learning (RL) aims to find a near-optimal policy using pre-collected datasets. In real-world scenarios, data collection could be costly and risky; therefore, offline RL becomes particularly challenging when the in-domain data is limited. Given recent advances in Large Language Models (LLMs) and their few-shot learning prowess, this paper introduces $\textbf{La}$nguage Models for $\textbf{Mo}$tion Control ($\textbf{LaMo}$), a general framework based on Decision Transformers to effectively use pre-trained Language Models (LMs) for offline RL. Our framework highlights four crucial components: (1) Initializing Decision Transformers with sequentially pre-trained LMs, (2) employing the LoRA fine-tuning method, in contrast to full-weight fine-tuning, to combine the pre-trained knowledge from LMs and in-domain knowledge effectively, (3) using the non-linear MLP transformation instead of linear projections, to generate embeddings, and (4) integrating an auxiliary language prediction loss during fine-tuning to stabilize the LMs and retain their original abilities on languages. Empirical results indicate $\textbf{LaMo}$ achieves excellent performance in sparse-reward tasks and closes the gap between value-based offline RL methods and decision transformers in dense-reward tasks. In particular, our method demonstrates superior performance in scenarios with limited data samples.
Authors: Jianqing Zhang, Yang Hua, Jian Cao, Hao Wang, Tao Song, Zhengui Xue, Ruhui Ma, Haibing Guan
Abstract: Recently, federated learning (FL) is popular for its privacy-preserving and collaborative learning abilities. However, under statistically heterogeneous scenarios, we observe that biased data domains on clients cause a representation bias phenomenon and further degenerate generic representations during local training, i.e., the representation degeneration phenomenon. To address these issues, we propose a general framework Domain Bias Eliminator (DBE) for FL. Our theoretical analysis reveals that DBE can promote bi-directional knowledge transfer between server and client, as it reduces the domain discrepancy between server and client in representation space. Besides, extensive experiments on four datasets show that DBE can greatly improve existing FL methods in both generalization and personalization abilities. The DBE-equipped FL method can outperform ten state-of-the-art personalized FL methods by a large margin. Our code is public at https://github.com/TsingZ0/DBE.
Authors: Haoxin Wang, Yipeng Mo, Kunlan Xiang, Nan Yin, Honghe Dai, Bixiong Li, Songhai Fan, Site Mo
Abstract: In the domain of multivariate time series analysis, the concept of channel independence has been increasingly adopted, demonstrating excellent performance due to its ability to eliminate noise and the influence of irrelevant variables. However, such a concept often simplifies the complex interactions among channels, potentially leading to information loss. To address this challenge, we propose a strategy of channel independence followed by mixing. Based on this strategy, we introduce CSformer, a novel framework featuring a two-stage multiheaded self-attention mechanism. This mechanism is designed to extract and integrate both channel-specific and sequence-specific information. Distinctively, CSformer employs parameter sharing to enhance the cooperative effects between these two types of information. Moreover, our framework effectively incorporates sequence and channel adapters, significantly improving the model's ability to identify important information across various dimensions. Extensive experiments on several real-world datasets demonstrate that CSformer achieves state-of-the-art results in terms of overall performance.
Authors: YongKyung Oh, Dongyoung Lim, Sungil Kim
Abstract: Time series analysis faces significant challenges when dealing with irregular and incomplete data. While Neural Differential Equation (NDE) based methods have shown promise, they struggle with limited expressiveness, scalability issues, and stability concerns. Conversely, Neural Flows offer stability but falter with irregular data. We introduce DualDynamics, a novel framework that synergistically combines NDE-based method and Neural Flow-based method. This approach enhances expressive power while balancing computational demands, addressing critical limitations of existing techniques. We demonstrate DualDynamics' effectiveness across diverse tasks: classification of robustness to dataset shift, irregularly-sampled series, interpolation of missing data, and forecasting with partial observations. Our results show consistent outperformance over state-of-the-art methods, indicating DualDynamics' potential to advance irregular time series analysis significantly.
Authors: Joan Giner-Miguelez, Abel G\'omez, Jordi Cabot
Abstract: To ensure the fairness and trustworthiness of machine learning (ML) systems, recent legislative initiatives and relevant research in the ML community have pointed out the need to document the data used to train ML models. Besides, data-sharing practices in many scientific domains have evolved in recent years for reproducibility purposes. In this sense, academic institutions' adoption of these practices has encouraged researchers to publish their data and technical documentation in peer-reviewed publications such as data papers. In this study, we analyze how this broader scientific data documentation meets the needs of the ML community and regulatory bodies for its use in ML technologies. We examine a sample of 4041 data papers of different domains, assessing their completeness, coverage of the requested dimensions, and trends in recent years. We focus on the most and least documented dimensions and compare the results with those of an ML-focused venue (NeurIPS D&B track) publishing papers describing datasets. As a result, we propose a set of recommendation guidelines for data creators and scientific data publishers to increase their data's preparedness for its transparent and fairer use in ML technologies.
Authors: Sofie Goethals, Marco Favier, Toon Calders
Abstract: Artificial Intelligence (AI) finds widespread application across various domains, but it sparks concerns about fairness in its deployment. The prevailing discourse in classification often emphasizes outcome-based metrics comparing sensitive subgroups without a nuanced consideration of the differential impacts within subgroups. Bias mitigation techniques not only affect the ranking of pairs of instances across sensitive groups, but often also significantly affect the ranking of instances within these groups. Such changes are hard to explain and raise concerns regarding the validity of the intervention. Unfortunately, these effects remain under the radar in the accuracy-fairness evaluation framework that is usually applied. Additionally, we illustrate the effect of several popular bias mitigation methods, and how their output often does not reflect real-world scenarios.
Authors: Chen Feng, Ziquan Liu, Zhuo Zhi, Ilija Bogunovic, Carsten Gerner-Beuerle, Miguel Rodrigues
Abstract: It is widely known that state-of-the-art machine learning models, including vision and language models, can be seriously compromised by adversarial perturbations. It is therefore increasingly relevant to develop capabilities to certify their performance in the presence of the most effective adversarial attacks. Our paper offers a new approach to certify the performance of machine learning models in the presence of adversarial attacks with population level risk guarantees. In particular, we introduce the notion of $(\alpha,\zeta)$-safe machine learning model. We propose a hypothesis testing procedure, based on the availability of a calibration set, to derive statistical guarantees providing that the probability of declaring that the adversarial (population) risk of a machine learning model is less than $\alpha$ (i.e. the model is safe), while the model is in fact unsafe (i.e. the model adversarial population risk is higher than $\alpha$), is less than $\zeta$. We also propose Bayesian optimization algorithms to determine efficiently whether a machine learning model is $(\alpha,\zeta)$-safe in the presence of an adversarial attack, along with statistical guarantees. We apply our framework to a range of machine learning models - including various sizes of vision Transformer (ViT) and ResNet models - impaired by a variety of adversarial attacks, such as PGDAttack, MomentumAttack, GenAttack and BanditAttack, to illustrate the operation of our approach. Importantly, we show that ViT's are generally more robust to adversarial attacks than ResNets, and large models are generally more robust than smaller models. Our approach goes beyond existing empirical adversarial risk-based certification guarantees. It formulates rigorous (and provable) performance guarantees that can be used to satisfy regulatory requirements mandating the use of state-of-the-art technical tools.
Authors: Yu-Hsueh Fang, He-Zhe Lin, Jie-Jyun Liu, Chih-Jen Lin
Abstract: Automatic differentiation is a key component in deep learning. This topic is well studied and excellent surveys such as Baydin et al. (2018) have been available to clearly describe the basic concepts. Further, sophisticated implementations of automatic differentiation are now an important part of popular deep learning frameworks. However, it is difficult, if not impossible, to directly teach students the implementation of existing systems due to the complexity. On the other hand, if the teaching stops at the basic concept, students fail to sense the realization of an implementation. For example, we often mention the computational graph in teaching automatic differentiation, but students wonder how to implement and use it. In this document, we partially fill the gap by giving a step by step introduction of implementing a simple automatic differentiation system. We streamline the mathematical concepts and the implementation. Further, we give the motivation behind each implementation detail, so the whole setting becomes very natural.
Authors: Keiyu Nosaka, Yuichi Takano, Akiko Yoshise
Abstract: The Data Collaboration (DC) framework provides a privacy-preserving solution for multi-source data fusion, enabling the joint analysis of data from multiple sources to achieve enhanced insights. It utilizes linear transformations with secretly selected bases to ensure privacy guarantees through non-iterative communication. Despite its strengths, the DC framework often encounters performance instability due to theoretical challenges in aligning the bases used for mapping raw data. This study addresses these challenges by establishing a rigorous theoretical foundation for basis alignment within the DC framework, formulating it as an optimization problem over orthogonal matrices. Under specific assumptions, we demonstrate that this problem can be reduced to the Orthogonal Procrustes Problem, which has a well-known analytical solution. Extensive empirical evaluations across diverse datasets reveal that the proposed alignment method significantly enhances model performance and computational efficiency, outperforming existing approaches. Additionally, it demonstrates robustness across varying levels of differential privacy, thus enabling practical and reliable implementations of the DC framework.
Authors: Lingbo Liu
Abstract: Analyzing spatially varying effects is pivotal in geographic analysis. However, accurately capturing and interpreting this variability is challenging due to the increasing complexity and non-linearity of geospatial data. Recent advancements in integrating Geographically Weighted (GW) models with artificial intelligence (AI) methodologies offer novel approaches. However, these methods often focus on single algorithms and emphasize prediction over interpretability. The recent GeoShapley method integrates machine learning (ML) with Shapley values to explain the contribution of geographical features, advancing the combination of geospatial ML and explainable AI (XAI). Yet, it lacks exploration of the nonlinear interactions between geographical features and explanatory variables. Herein, an ensemble framework is proposed to merge local spatial weighting scheme with XAI and ML technologies to bridge this gap. Through tests on synthetic datasets and comparisons with GWR, MGWR, and GeoShapley, this framework is verified to enhance interpretability and predictive accuracy by elucidating spatial variability. Reproducibility is explored through the comparison of spatial weighting schemes and various ML models, emphasizing the necessity of model reproducibility to address model and parameter uncertainty. This framework works in both geographic regression and classification, offering a novel approach to understanding complex spatial phenomena.
Authors: Remi Genet, Hugo Inzirillo
Abstract: Recurrent Neural Networks (RNNs) have revolutionized many areas of machine learning, particularly in natural language and data sequence processing. Long Short-Term Memory (LSTM) has demonstrated its ability to capture long-term dependencies in sequential data. Inspired by the Kolmogorov-Arnold Networks (KANs) a promising alternatives to Multi-Layer Perceptrons (MLPs), we proposed a new neural networks architecture inspired by KAN and the LSTM, the Temporal Kolomogorov-Arnold Networks (TKANs). TKANs combined the strenght of both networks, it is composed of Recurring Kolmogorov-Arnold Networks (RKANs) Layers embedding memory management. This innovation enables us to perform multi-step time series forecasting with enhanced accuracy and efficiency. By addressing the limitations of traditional models in handling complex sequential patterns, the TKAN architecture offers significant potential for advancements in fields requiring more than one step ahead forecasting.
Authors: Yash Sinha, Murari Mandal, Mohan Kankanhalli
Abstract: User data spread across multiple modalities has popularized multi-modal recommender systems (MMRS). They recommend diverse content such as products, social media posts, TikTok reels, etc., based on a user-item interaction graph. With rising data privacy demands, recent methods propose unlearning private user data from uni-modal recommender systems (RS). However, methods for unlearning item data related to outdated user preferences, revoked licenses, and legally requested removals are still largely unexplored. Previous RS unlearning methods are unsuitable for MMRS due to the incompatibility of their matrix-based representation with the multi-modal user-item interaction graph. Moreover, their data partitioning step degrades performance on each shard due to poor data heterogeneity and requires costly performance aggregation across shards. This paper introduces MMRecUn, the first approach known to us for unlearning in MMRS and unlearning item data. Given a trained RS model, MMRecUn employs a novel Reverse Bayesian Personalized Ranking (BPR) objective to enable the model to forget marked data. The reverse BPR attenuates the impact of user-item interactions within the forget set, while the forward BPR reinforces the significance of user-item interactions within the retain set. Our experiments demonstrate that MMRecUn outperforms baseline methods across various unlearning requests when evaluated on benchmark MMRS datasets. MMRecUn achieves recall performance improvements of up to 49.85% compared to baseline methods and is up to $\mathbf{1.3}\times$ faster than the Gold model, which is trained on retain set from scratch. MMRecUn offers significant advantages, including superiority in removing target interactions, preserving retained interactions, and zero overhead costs compared to previous methods. The code will be released after review.
Authors: Ryan McKenna
Abstract: Correlated noise mechanisms such as DP Matrix Factorization (DP-MF) have proven to be effective alternatives to DP-SGD in large-epsilon few-epoch training regimes. Significant work has been done to find the best correlated noise strategies, and the current state-of-the-art approach is DP-BandMF, which optimally balances the benefits of privacy amplification and noise correlation. Despite it's utility advantages, severe scalability limitations prevent this mechanism from handling large-scale training scenarios where the number of training iterations may exceed $10^4$ and the number of model parameters may exceed $10^7$. In this work, we present techniques to scale up DP-BandMF along these two dimensions, significantly extending it's reach and enabling it to handle settings with virtually any number of model parameters and training iterations, with negligible utility degradation.
Authors: Qi Xiong, Kai Tang, Minbo Ma, Ji Zhang, Jie Xu, Tianrui Li
Abstract: Long-term time series forecasting (LTSF) is a critical task across diverse domains. Despite significant advancements in LTSF research, we identify a performance bottleneck in existing LTSF methods caused by the inadequate modeling of Temporal Dependencies within the Target (TDT). To address this issue, we propose a novel and generic temporal modeling framework, Temporal Dependency Alignment (TDAlign), that equips existing LTSF methods with TDT learning capabilities. TDAlign introduces two key innovations: 1) a loss function that aligns the change values between adjacent time steps in the predictions with those in the target, ensuring consistency with variation patterns, and 2) an adaptive loss balancing strategy that seamlessly integrates the new loss function with existing LTSF methods without introducing additional learnable parameters. As a plug-and-play framework, TDAlign enhances existing methods with minimal computational overhead, featuring only linear time complexity and constant space complexity relative to the prediction length. Extensive experiments on six strong LTSF baselines across seven real-world datasets demonstrate the effectiveness and flexibility of TDAlign. On average, TDAlign reduces baseline prediction errors by \textbf{1.47\%} to \textbf{9.19\%} and change value errors by \textbf{4.57\%} to \textbf{15.78\%}, highlighting its substantial performance improvements.
Authors: Anshuman Suri, Xiao Zhang, David Evans
Abstract: Membership inference attacks are used as a key tool for disclosure auditing. They aim to infer whether an individual record was used to train a model. While such evaluations are useful to demonstrate risk, they are computationally expensive and often make strong assumptions about potential adversaries' access to models and training environments, and thus do not provide tight bounds on leakage from potential attacks. We show how prior claims around black-box access being sufficient for optimal membership inference do not hold for stochastic gradient descent, and that optimal membership inference indeed requires white-box access. Our theoretical results lead to a new white-box inference attack, IHA (Inverse Hessian Attack), that explicitly uses model parameters by taking advantage of computing inverse-Hessian vector products. Our results show that both auditors and adversaries may be able to benefit from access to model parameters, and we advocate for further research into white-box methods for membership inference.
Authors: Trang Nguyen, Anh Tran, Nhat Ho
Abstract: Prompt-based approaches offer a cutting-edge solution to data privacy issues in continual learning, particularly in scenarios involving multiple data suppliers where long-term storage of private user data is prohibited. Despite delivering state-of-the-art performance, its impressive remembering capability can become a double-edged sword, raising security concerns as it might inadvertently retain poisoned knowledge injected during learning from private user data. Following this insight, in this paper, we expose continual learning to a potential threat: backdoor attack, which drives the model to follow a desired adversarial target whenever a specific trigger is present while still performing normally on clean samples. We highlight three critical challenges in executing backdoor attacks on incremental learners and propose corresponding solutions: (1) \emph{Transferability}: We employ a surrogate dataset and manipulate prompt selection to transfer backdoor knowledge to data from other suppliers; (2) \emph{Resiliency}: We simulate static and dynamic states of the victim to ensure the backdoor trigger remains robust during intense incremental learning processes; and (3) \emph{Authenticity}: We apply binary cross-entropy loss as an anti-cheating factor to prevent the backdoor trigger from devolving into adversarial noise. Extensive experiments across various benchmark datasets and continual learners validate our continual backdoor framework, achieving up to $100\%$ attack success rate, with further ablation studies confirming our contributions' effectiveness.
Authors: Quanming Yao, Yongqi Zhang, Yaqing Wang, Nan Yin, James Kwok, Qiang Yang
Abstract: The brute-force scaleup of training datasets, learnable parameters and computation power, has become a prevalent strategy for developing more robust learning models. However, due to bottlenecks in data, computation, and trust, the sustainability of this strategy is a serious concern. In this paper, we attempt to address this issue in a parsimonious manner (i.e., achieving greater potential with simpler models). The key is to drive models using domain-specific knowledge, such as symbols, logic, and formulas, instead of purely relying on scaleup. This approach allows us to build a framework that uses this knowledge as "building blocks" to achieve parsimony in model design, training, and interpretation. Empirical results show that our methods surpass those that typically follow the scaling law. We also demonstrate our framework in AI for science, specifically in the problem of drug-drug interaction prediction. We hope our research can foster more diverse technical roadmaps in the era of foundation models.
Authors: B. Kaan Karamete, Eli Glaser
Abstract: This paper discusses how to generate general graph node embeddings from knowledge graph representations. The embedded space is composed of a number of sub-features to mimic both local affinity and remote structural relevance. These sub-feature dimensions are defined by several indicators that we speculate to catch nodal similarities, such as hop-based topological patterns, the number of overlapping labels, the transitional probabilities (markov-chain probabilities), and the cluster indices computed by our recursive spectral bisection (RSB) algorithm. These measures are flattened over the one dimensional vector space into their respective sub-component ranges such that the entire set of vector similarity functions could be used for finding similar nodes. The error is defined by the sum of pairwise square differences across a randomly selected sample of graph nodes between the assumed embeddings and the ground truth estimates as our novel loss function. The ground truth is estimated to be a combination of pairwise Jaccard similarity and the number of overlapping labels. Finally, we demonstrate a multi-variate stochastic gradient descent (SGD) algorithm to compute the weighing factors among sub-vector spaces to minimize the average error using a random sampling logic.
Authors: Hanqiu Chen, Xuebin Yao, Pradeep Subedi, Cong Hao
Abstract: Edge computing is a distributed computing paradigm that collects and processes data at or near the source of data generation. The on-device learning at edge relies on device-to-device wireless communication to facilitate real-time data sharing and collaborative decision-making among multiple devices. This significantly improves the adaptability of the edge computing system to the changing environments. However, as the scale of the edge computing system is getting larger, communication among devices is becoming the bottleneck because of the limited bandwidth of wireless communication leads to large data transfer latency. To reduce the amount of device-to-device data transmission and accelerate on-device learning, in this paper, we propose Residual-INR, a fog computing-based communication-efficient on-device learning framework by utilizing implicit neural representation (INR) to compress images/videos into neural network weights. Residual-INR enhances data transfer efficiency by collecting JPEG images from edge devices, compressing them into INR format at the fog node, and redistributing them for on-device learning. By using a smaller INR for full image encoding and a separate object INR for high-quality object region reconstruction through residual encoding, our technique can reduce the encoding redundancy while maintaining the object quality. Residual-INR is a promising solution for edge on-device learning because it reduces data transmission by up to 5.16 x across a network of 10 edge devices. It also facilitates CPU-free accelerated on-device learning, achieving up to 2.9 x speedup without sacrificing accuracy. Our code is available at: https://github.com/sharc-lab/Residual-INR.
Authors: Yunfan Zhao, Tonghan Wang, Dheeraj Nagaraj, Aparna Taneja, Milind Tambe
Abstract: Applying Reinforcement Learning (RL) to Restless Multi-Arm Bandits (RMABs) offers a promising avenue for addressing allocation problems with resource constraints and temporal dynamics. However, classic RMAB models largely overlook the challenges of (systematic) data errors - a common occurrence in real-world scenarios due to factors like varying data collection protocols and intentional noise for differential privacy. We demonstrate that conventional RL algorithms used to train RMABs can struggle to perform well in such settings. To solve this problem, we propose the first communication learning approach in RMABs, where we study which arms, when involved in communication, are most effective in mitigating the influence of such systematic data errors. In our setup, the arms receive Q-function parameters from similar arms as messages to guide behavioral policies, steering Q-function updates. We learn communication strategies by considering the joint utility of messages across all pairs of arms and using a Q-network architecture that decomposes the joint utility. Both theoretical and empirical evidence validate the effectiveness of our method in significantly improving RMAB performance across diverse problems.
Authors: Zhongjian Zhang, Xiao Wang, Huichi Zhou, Yue Yu, Mengmei Zhang, Cheng Yang, Chuan Shi
Abstract: Graph neural networks (GNNs) are vulnerable to adversarial attacks, especially for topology perturbations, and many methods that improve the robustness of GNNs have received considerable attention. Recently, we have witnessed the significant success of large language models (LLMs), leading many to explore the great potential of LLMs on GNNs. However, they mainly focus on improving the performance of GNNs by utilizing LLMs to enhance the node features. Therefore, we ask: Will the robustness of GNNs also be enhanced with the powerful understanding and inference capabilities of LLMs? By presenting the empirical results, we find that despite that LLMs can improve the robustness of GNNs, there is still an average decrease of 23.1% in accuracy, implying that the GNNs remain extremely vulnerable against topology attacks. Therefore, another question is how to extend the capabilities of LLMs on graph adversarial robustness. In this paper, we propose an LLM-based robust graph structure inference framework, LLM4RGNN, which distills the inference capabilities of GPT-4 into a local LLM for identifying malicious edges and an LM-based edge predictor for finding missing important edges, so as to recover a robust graph structure. Extensive experiments demonstrate that LLM4RGNN consistently improves the robustness across various GNNs. Even in some cases where the perturbation ratio increases to 40%, the accuracy of GNNs is still better than that on the clean graph. The source code can be found in https://github.com/zhongjian-zhang/LLM4RGNN.
Authors: Kening Zheng, Junkai Chen, Yibo Yan, Xin Zou, Xuming Hu
Abstract: Hallucination issues continue to affect multimodal large language models (MLLMs), with existing research mainly addressing object-level or attribute-level hallucinations, neglecting the more complex relation hallucinations that require advanced reasoning. Current benchmarks for relation hallucinations lack detailed evaluation and effective mitigation, and their datasets often suffer from biases due to systematic annotation processes. To address these challenges, we introduce Reefknot, a comprehensive benchmark targeting relation hallucinations, comprising over 20,000 real-world samples. We provide a systematic definition of relation hallucinations, integrating perceptive and cognitive perspectives, and construct a relation-based corpus using the Visual Genome scene graph dataset. Our comparative evaluation reveals significant limitations in current MLLMs' ability to handle relation hallucinations. Additionally, we propose a novel confidence-based mitigation strategy, which reduces the hallucination rate by an average of 9.75% across three datasets, including Reefknot. Our work offers valuable insights for achieving trustworthy multimodal intelligence.
Authors: Wenzhi Fang, Dong-Jun Han, Evan Chen, Shiqiang Wang, Christopher G. Brinton
Abstract: While traditional federated learning (FL) typically focuses on a star topology where clients are directly connected to a central server, real-world distributed systems often exhibit hierarchical architectures. Hierarchical FL (HFL) has emerged as a promising solution to bridge this gap, leveraging aggregation points at multiple levels of the system. However, existing algorithms for HFL encounter challenges in dealing with multi-timescale model drift, i.e., model drift occurring across hierarchical levels of data heterogeneity. In this paper, we propose a multi-timescale gradient correction (MTGC) methodology to resolve this issue. Our key idea is to introduce distinct control variables to (i) correct the client gradient towards the group gradient, i.e., to reduce client model drift caused by local updates based on individual datasets, and (ii) correct the group gradient towards the global gradient, i.e., to reduce group model drift caused by FL over clients within the group. We analytically characterize the convergence behavior of MTGC under general non-convex settings, overcoming challenges associated with couplings between correction terms. We show that our convergence bound is immune to the extent of data heterogeneity, confirming the stability of the proposed algorithm against multi-level non-i.i.d. data. Through extensive experiments on various datasets and models, we validate the effectiveness of MTGC in diverse HFL settings. The code for this project is available at \href{https://github.com/wenzhifang/MTGC}{https://github.com/wenzhifang/MTGC}.
URLs: https://github.com/wenzhifang/MTGC, https://github.com/wenzhifang/MTGC
Authors: Jiaming Zhang, Junhong Ye, Xingjun Ma, Yige Li, Yunfan Yang, Jitao Sang, Dit-Yan Yeung
Abstract: Due to their multimodal capabilities, Vision-Language Models (VLMs) have found numerous impactful applications in real-world scenarios. However, recent studies have revealed that VLMs are vulnerable to image-based adversarial attacks, particularly targeted adversarial images that manipulate the model to generate harmful content specified by the adversary. Current attack methods rely on predefined target labels to create targeted adversarial attacks, which limits their scalability and applicability for large-scale robustness evaluations. In this paper, we propose AnyAttack, a self-supervised framework that generates targeted adversarial images for VLMs without label supervision, allowing any image to serve as a target for the attack. Our framework employs the pre-training and fine-tuning paradigm, with the adversarial noise generator pre-trained on the large-scale LAION-400M dataset. This large-scale pre-training endows our method with powerful transferability across a wide range of VLMs. Extensive experiments on five mainstream open-source VLMs (CLIP, BLIP, BLIP2, InstructBLIP, and MiniGPT-4) across three multimodal tasks (image-text retrieval, multimodal classification, and image captioning) demonstrate the effectiveness of our attack. Additionally, we successfully transfer AnyAttack to multiple commercial VLMs, including Google Gemini, Claude Sonnet, Microsoft Copilot and OpenAI GPT. These results reveal an unprecedented risk to VLMs, highlighting the need for effective countermeasures.
Authors: Fabian Paischer, Lukas Hauzenberger, Thomas Schmied, Benedikt Alkin, Marc Peter Deisenroth, Sepp Hochreiter
Abstract: Foundation models (FMs) are pre-trained on large-scale datasets and then fine-tuned on a downstream task for a specific application. The most successful and most commonly used fine-tuning method is to update the pre-trained weights via a low-rank adaptation (LoRA). LoRA introduces new weight matrices that are usually initialized at random with a uniform rank distribution across the model weights. Recent works focus on different initialization schemes or the learning of adaptive ranks during fine-tuning. Both approaches have only been investigated in isolation, resulting in slow convergence or a uniform rank distribution, in turn leading to suboptimal performance. We propose to improve LoRA by initializing the new weights in a data-driven manner by computing singular value decomposition (SVD) on minibatches of activation vectors. Then, we initialize the LoRA matrices with the obtained right-singular vectors and redistribute ranks among all weight matrices to provably store the maximum amount of information of the downstream data in the newly introduced weights. In this way, only what information to maintain or neglect during the fine-tuning process needs to be learned. We call our new method $\textbf{E}$xplained $\textbf{V}$ariance $\textbf{A}$daptation (EVA). We apply EVA to a variety of fine-tuning tasks ranging from language generation and understanding to image classification and reinforcement learning. EVA exhibits faster convergence than competitors and achieves the highest average score across a multitude of tasks per domain while reducing the number of trainable parameters through rank redistribution.
Authors: Karen Medlin, Sven Leyffer, Krishnan Raghavan
Abstract: Data rebalancing techniques, including oversampling and undersampling, are a common approach to addressing the challenges of imbalanced data. To tackle unresolved problems related to both oversampling and undersampling, we propose a new undersampling approach that: (i) avoids the pitfalls of noise and overlap caused by synthetic data and (ii) avoids the pitfall of under-fitting caused by random undersampling. Instead of undersampling majority data randomly, our method undersamples datapoints based on their ability to improve model loss. Using improved model loss as a proxy measurement for classification performance, our technique assesses a datapoint's impact on loss and rejects those unable to improve it. In so doing, our approach rejects majority datapoints redundant to datapoints already accepted and, thereby, finds an optimal subset of majority training data for classification. The accept/reject component of our algorithm is motivated by a bilevel optimization problem uniquely formulated to identify the optimal training set we seek. Experimental results show our proposed technique with F1 scores up to 10% higher than state-of-the-art methods.
Authors: Guoqi Yu, Yaoming Li, Xiaoyu Guo, Dayu Wang, Zirui Liu, Shujun Wang, Tong Yang
Abstract: Forecasting models are pivotal in a data-driven world with vast volumes of time series data that appear as a compound of vast Linear and Nonlinear patterns. Recent deep time series forecasting models struggle to utilize seasonal and trend decomposition to separate the entangled components. Such a strategy only explicitly extracts simple linear patterns like trends, leaving the other linear modes and vast unexplored nonlinear patterns to the residual. Their flawed linear and nonlinear feature extraction models and shallow-level decomposition limit their adaptation to the diverse patterns present in real-world scenarios. Given this, we innovate Recursive Residual Decomposition by introducing explicit extraction of both linear and nonlinear patterns. This deeper-level decomposition framework, which is named LiNo, captures linear patterns using a Li block which can be a moving average kernel, and models nonlinear patterns using a No block which can be a Transformer encoder. The extraction of these two patterns is performed alternatively and recursively. To achieve the full potential of LiNo, we develop the current simple linear pattern extractor to a general learnable autoregressive model, and design a novel No block that can handle all essential nonlinear patterns. Remarkably, the proposed LiNo achieves state-of-the-art on thirteen real-world benchmarks under univariate and multivariate forecasting scenarios. Experiments show that current forecasting models can deliver more robust and precise results through this advanced Recursive Residual Decomposition. We hope this work could offer insight into designing more effective forecasting models. Code is available at this Repository: https://github.com/Levi-Ackman/LiNo.
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 (LLMs) presents significant challenges due to limited data and the high cost of scaling through human curation. $\langle \text{instruction}, \text{data}, \text{code} \rangle$ triplets are scarce and expensive to manually curate as their creation demands technical expertise. To address this scalability challenge, 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). The 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 outperform 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, a study of LLM users 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 chartsquared.github.io, with ample qualitative examples.
Authors: J. Quetzalcoatl Toledo-Marin, Sebastian Gonzalez, Hao Jia, Ian Lu, Deniz Sogutlu, Abhishek Abhishek, Colin Gay, Eric Paquet, Roger Melko, Geoffrey C. Fox, Maximilian Swiatlowski, Wojciech Fedorko
Abstract: Particle collisions at accelerators such as the Large Hadron Collider, recorded and analyzed by experiments such as ATLAS and CMS, enable exquisite measurements of the Standard Model and searches for new phenomena. Simulations of collision events at these detectors have played a pivotal role in shaping the design of future experiments and analyzing ongoing ones. However, the quest for accuracy in Large Hadron Collider (LHC) collisions comes at an imposing computational cost, with projections estimating the need for millions of CPU-years annually during the High Luminosity LHC (HL-LHC) run \cite{collaboration2022atlas}. Simulating a single LHC event with \textsc{Geant4} currently devours around 1000 CPU seconds, with simulations of the calorimeter subdetectors in particular imposing substantial computational demands \cite{rousseau2023experimental}. To address this challenge, we propose a conditioned quantum-assisted deep generative model. Our model integrates a conditioned variational autoencoder (VAE) on the exterior with a conditioned Restricted Boltzmann Machine (RBM) in the latent space, providing enhanced expressiveness compared to conventional VAEs. The RBM nodes and connections are meticulously engineered to enable the use of qubits and couplers on D-Wave's Pegasus-structured \textit{Advantage} quantum annealer (QA) for sampling. We introduce a novel method for conditioning the quantum-assisted RBM using \textit{flux biases}. We further propose a novel adaptive mapping to estimate the effective inverse temperature in quantum annealers. The effectiveness of our framework is illustrated using Dataset 2 of the CaloChallenge \cite{calochallenge}.
Authors: Jianan Ye, Zhaorui Tan, Yijie Hu, Xi Yang, Guangliang Cheng, Kaizhu Huang
Abstract: Tabular anomaly detection under the one-class classification setting poses a significant challenge, as it involves accurately conceptualizing "normal" derived exclusively from a single category to discern anomalies from normal data variations. Capturing the intrinsic correlation among attributes within normal samples presents one promising method for learning the concept. To do so, the most recent effort relies on a learnable mask strategy with a reconstruction task. However, this wisdom may suffer from the risk of producing uniform masks, i.e., essentially nothing is masked, leading to less effective correlation learning. To address this issue, we presume that attributes related to others in normal samples can be divided into two non-overlapping and correlated subsets, defined as CorrSets, to capture the intrinsic correlation effectively. Accordingly, we introduce an innovative method that disentangles CorrSets from normal tabular data. To our knowledge, this is a pioneering effort to apply the concept of disentanglement for one-class anomaly detection on tabular data. Extensive experiments on 20 tabular datasets show that our method substantially outperforms the state-of-the-art methods and leads to an average performance improvement of 6.1% on AUC-PR and 2.1% on AUC-ROC. Codes are available at https://github.com/yjnanan/Disent-AD.
Authors: Guochen Yan, Xunkai Li, Luyuan Xie, Wentao Zhang, Qingni Shen, Yuejian Fang, Zhonghai Wu
Abstract: Federated Graph Learning (FGL) has emerged as a promising paradigm for breaking data silos in distributed private graphs data management. In practical scenarios involving complex and heterogeneous distributed graph data, personalized Federated Graph Learning (pFGL) aims to enhance model utility by training personalized models tailored to individual client needs, rather than relying on a universal global model. However, existing pFGL methods often require numerous communication rounds under heterogeneous client graphs, leading to significant security concerns and communication overhead. While One-shot Federated Learning (OFL) addresses these issues by enabling collaboration in a single round, existing OFL methods are designed for image-based tasks and ineffective for graph data, leaving a critical gap in the field. Additionally, personalized models often suffer from bias, failing to generalize effectively to minority data. To address these challenges, we propose the first one-shot personalized federated graph learning method for node classification, compatible with the Secure Aggregation protocol for privacy preservation. Specifically, for effective graph learning in a single communication round, our method estimates and aggregates class-wise feature distribution statistics to construct a global pseudo-graph on the server, facilitating the training of a global graph model. Moreover, to mitigate bias, we introduce a two-stage personalized training approach that adaptively balances local personal information and global insights from the pseudo-graph, improving both personalization and generalization. Extensive experiments conducted on 8 multi-scale graph datasets demonstrate that our method significantly outperforms state-of-the-art baselines across various settings.
Authors: Ronghui Xu, Hanyin Cheng, Chenjuan Guo, Hongfan Gao, Jilin Hu, Sean Bin Yang, Bin Yang
Abstract: Developing effective path representations has become increasingly essential across various fields within intelligent transportation. Although pre-trained path representation learning models have shown improved performance, they predominantly focus on the topological structures from single modality data, i.e., road networks, overlooking the geometric and contextual features associated with path-related images, e.g., remote sensing images. Similar to human understanding, integrating information from multiple modalities can provide a more comprehensive view, enhancing both representation accuracy and generalization. However, variations in information granularity impede the semantic alignment of road network-based paths (road paths) and image-based paths (image paths), while the heterogeneity of multi-modal data poses substantial challenges for effective fusion and utilization. In this paper, we propose a novel Multi-modal, Multi-granularity Path Representation Learning Framework (MM-Path), which can learn a generic path representation by integrating modalities from both road paths and image paths. To enhance the alignment of multi-modal data, we develop a multi-granularity alignment strategy that systematically associates nodes, road sub-paths, and road paths with their corresponding image patches, ensuring the synchronization of both detailed local information and broader global contexts. To address the heterogeneity of multi-modal data effectively, we introduce a graph-based cross-modal residual fusion component designed to comprehensively fuse information across different modalities and granularities. Finally, we conduct extensive experiments on two large-scale real-world datasets under two downstream tasks, validating the effectiveness of the proposed MM-Path. The code is available at: https://github.com/decisionintelligence/MM-Path.
Authors: Tae-Hoon Lee, Min-Soo Kim
Abstract: Mixed-Integer Linear Programming (MILP) is an optimization technique widely used in various fields. Existing end-to-end learning methods for MILP generate values for a subset of decision variables and delegate the remaining problem to traditional MILP solvers. However, this approach does not guarantee solution feasibility (i.e., satisfying all constraints) due to inaccurate predictions and primarily focuses on prediction for binary decision variables. When addressing MILP involving non-binary integer variables using machine learning (ML), feasibility issues can become even more pronounced. Since finding an optimal solution requires satisfying all constraints, addressing feasibility is critical. To overcome these limitations, we propose a novel reinforcement learning (RL)-based solver that interacts with MILP to incrementally discover better feasible solutions without relying on traditional solvers. We design reward functions tailored for MILP, which enable the RL agent to learn relationships between decision variables and constraints. Furthermore, we leverage a Transformer encoder-based graph neural network (GNN) to effectively model complex relationships among decision variables. Our experimental results demonstrate that the proposed method can solve MILP problems and find near-optimal solutions without delegating the remainder to traditional solvers. The proposed method provides a meaningful step forward as an initial study in solving MILP problems entirely with ML in an end-to-end manner.
Authors: Martin Ziegler, Andres Felipe Posada-Moreno, Friedrich Solowjow, Sebastian Trimpe
Abstract: Foundation models have demonstrated remarkable generalization, data efficiency, and robustness properties across various domains. In this paper, we explore the feasibility of foundation models for applications in the control domain. The success of these models is enabled by large-scale pretaining on Internet-scale datasets. These are available in fields like natural language processing and computer vision, but do not exist for dynamical systems. We address this challenge by pretraining a transformer-based foundation model exclusively on synthetic data and propose to sample dynamics functions from a reproducing kernel Hilbert space. Our pretrained model generalizes for prediction tasks across different dynamical systems, which we validate in simulation and hardware experiments, including cart-pole and Furuta pendulum setups. Additionally, the model can be fine-tuned effectively to new systems to increase performance even further. Our results demonstrate the feasibility of foundation models for dynamical systems that outperform specialist models in terms of generalization, data efficiency, and robustness.
Authors: Tim Wibiral, Mohamed Karim Belaid, Maximilian Rabus, Ansgar Scherp
Abstract: Assessing the importance of individual training samples is a key challenge in machine learning. Traditional approaches retrain models with and without specific samples, which is computationally expensive and ignores dependencies between data points. We introduce LossVal, an efficient data valuation method that computes importance scores during neural network training by embedding a self-weighting mechanism into loss functions like cross-entropy and mean squared error. LossVal reduces computational costs, making it suitable for large datasets and practical applications. Experiments on classification and regression tasks across multiple datasets show that LossVal effectively identifies noisy samples and is able to distinguish helpful from harmful samples. We examine the gradient calculation of LossVal to highlight its advantages. The source code is available at: https://github.com/twibiral/LossVal
Authors: Tian Qin, Naomi Saphra, David Alvarez-Melis
Abstract: Language models (LMs), like other neural networks, often favor shortcut heuristics based on surface-level patterns. Although LMs behave like n-gram models early in training, they must eventually learn hierarchical syntactic representations to correctly apply grammatical rules out-of-distribution (OOD). In this work, we use case studies of English grammar to explore how complex, diverse training data drives models to generalize OOD. We construct a framework that unifies our understanding of random variation with training dynamics, rule selection with memorization, and data diversity with complexity. We show that these factors are nuanced, and that intermediate levels of diversity and complexity lead to inconsistent behavior across random seeds and to unstable training dynamics. Our findings emphasize the critical role of training data in shaping generalization patterns and illuminate how competing model strategies lead to inconsistent generalization outcomes across random seeds. Code is available at https://github.com/sunnytqin/concept_comp.git.
Authors: Natalie Brownlowe, Christopher R. Cornwell, Ethan Montes, Gabriel Quijano, Grace Stulman, Na Zhang
Abstract: The choice of architecture of a neural network influences which functions will be realizable by that neural network and, as a result, studying the expressiveness of a chosen architecture has received much attention. In ReLU neural networks, the presence of stably unactivated neurons can reduce the network's expressiveness. In this work, we investigate the probability of a neuron in the second hidden layer of such neural networks being stably unactivated when the weights and biases are initialized from symmetric probability distributions. For networks with input dimension $n_0$, we prove that if the first hidden layer has $n_0+1$ neurons then this probability is exactly $\frac{2^{n_0}+1}{4^{n_0+1}}$, and if the first hidden layer has $n_1$ neurons, $n_1 \le n_0$, then the probability is $\frac{1}{2^{n_1+1}}$. Finally, for the case when the first hidden layer has more neurons than $n_0+1$, a conjecture is proposed along with the rationale. Computational evidence is presented to support the conjecture.
Authors: Yiqian Yang, Xihua Zhu, Fan Zhang
Abstract: Adversarial training with Normalizing Flow (NF) models is an emerging research area aimed at improving model robustness through adversarial samples. In this study, we focus on applying adversarial training to NF models for gravitational wave parameter estimation. We propose an adaptive epsilon method for Fast Gradient Sign Method (FGSM) adversarial training, which dynamically adjusts perturbation strengths based on gradient magnitudes using logarithmic scaling. Our hybrid architecture, combining ResNet and Inverse Autoregressive Flow, reduces the Negative Log Likelihood (NLL) loss by 47\% under FGSM attacks compared to the baseline model, while maintaining an NLL of 4.2 on clean data (only 5\% higher than the baseline). For perturbation strengths between 0.01 and 0.1, our model achieves an average NLL of 5.8, outperforming both fixed-epsilon (NLL: 6.7) and progressive-epsilon (NLL: 7.2) methods. Under stronger Projected Gradient Descent attacks with perturbation strength of 0.05, our model maintains an NLL of 6.4, demonstrating superior robustness while avoiding catastrophic overfitting.
Authors: Hao Kang, Srikant Bharadwaj, James Hensman, Tushar Krishna, Victor Ruhle, Saravan Rajmohan
Abstract: Large language model (LLM) inference demands significant amount of computation and memory, especially in the key attention mechanism. While techniques, such as quantization and acceleration algorithms, like FlashAttention, have improved efficiency of the overall inference, they address different aspects of the problem: quantization focuses on weight-activation operations, while FlashAttention improves execution but requires high-precision formats. Recent Key-value (KV) cache quantization reduces memory bandwidth but still needs floating-point dequantization for attention operation. We present TurboAttention, a comprehensive approach to enable quantized execution of attention that simultaneously addresses both memory and computational efficiency. Our solution introduces two key innovations: FlashQ, a headwise attention quantization technique that enables both compression of KV cache and quantized execution of activation-activation multiplication, and Sparsity-based Softmax Approximation (SAS), which eliminates the need for dequantization to FP32 during exponentiation operation in attention. Experimental results demonstrate that TurboAttention achieves 1.2-1.8x speedup in attention, reduces the KV cache size by over 4.4x, and enables up to 2.37x maximum throughput over the FP16 baseline while outperforming state-of-the-art quantization and compression techniques across various datasets and models.
Authors: Gwen Maudet, Gr\'egoire Danoy
Abstract: Branch-and-Bound (B\&B) is an exact method in integer programming that recursively divides the search space into a tree. During the resolution process, determining the next subproblem to explore within the tree-known as the search strategy-is crucial. Hand-crafted heuristics are commonly used, but none are effective over all problem classes. Recent approaches utilizing neural networks claim to make more intelligent decisions but are computationally expensive. In this paper, we introduce GP2S (Genetic Programming for Search Strategy), a novel machine learning approach that automatically generates a B\&B search strategy heuristic, aiming to make intelligent decisions while being computationally lightweight. We define a policy as a function that evaluates the quality of a B\&B node by combining features from the node and the problem; the search strategy policy is then defined by a best-first search based on this node ranking. The policy space is explored using a genetic programming algorithm, and the policy that achieves the best performance on a training set is selected. We compare our approach with the standard method of the SCIP solver, a recent graph neural network-based method, and handcrafted heuristics. Our first evaluation includes three types of primal hard problems, tested on instances similar to the training set and on larger instances. Our method is at most 2\% slower than the best baseline and consistently outperforms SCIP, achieving an average speedup of 11.3\%. Additionally, GP2S is tested on the MIPLIB 2017 dataset, generating multiple heuristics from different subsets of instances. It exceeds SCIP's average performance in 7 out of 10 cases across 15 times more instances and under a time limit 15 times longer, with some GP2S methods leading on most experiments in terms of the number of feasible solutions or optimality gap.
Authors: Shashank N. Sridhara, Eduardo Pavez, Antonio Ortega
Abstract: We explore the problem of sampling graph signals in scenarios where the graph structure is not predefined and must be inferred from data. In this scenario, existing approaches rely on a two-step process, where a graph is learned first, followed by sampling. More generally, graph learning and graph signal sampling have been studied as two independent problems in the literature. This work provides a foundational step towards jointly optimizing the graph structure and sampling set. Our main contribution, Vertex Importance Sampling (VIS), is to show that the sampling set can be effectively determined from the vertex importance (node weights) obtained from graph learning. We further propose Vertex Importance Sampling with Repulsion (VISR), a greedy algorithm where spatially -separated "important" nodes are selected to ensure better reconstruction. Empirical results on simulated data show that sampling using VIS and VISR leads to competitive reconstruction performance and lower complexity than the conventional two-step approach of graph learning followed by graph sampling.
Authors: Ahmed Rashed, Abdelkrim Kallich, Mohamed Eltayeb
Abstract: Machine learning (ML) algorithms have become integral to decision making in various domains, including healthcare, finance, education, and law enforcement. However, concerns about fairness and bias in these systems pose significant ethical and social challenges. This study investigates the fairness of ML models applied to structured datasets in classification tasks, highlighting the potential for biased predictions to perpetuate systemic inequalities. A publicly available dataset from Kaggle was selected for analysis, offering a realistic scenario for evaluating fairness in machine learning workflows. To assess and mitigate biases, three prominent fairness libraries; Fairlearn by Microsoft, AIF360 by IBM, and the What If Tool by Google were employed. These libraries provide robust frameworks for analyzing fairness, offering tools to evaluate metrics, visualize results, and implement bias mitigation strategies. The research aims to assess the extent of bias in the ML models, compare the effectiveness of these libraries, and derive actionable insights for practitioners. The findings reveal that each library has unique strengths and limitations in fairness evaluation and mitigation. By systematically comparing their capabilities, this study contributes to the growing field of ML fairness by providing practical guidance for integrating fairness tools into real world applications. These insights are intended to support the development of more equitable machine learning systems.
Authors: Ahmed Rashed, Abdelkrim Kallich, Mohamed Eltayeb
Abstract: Machine learning (ML) algorithms play a crucial role in decision making across diverse fields such as healthcare, finance, education, and law enforcement. Despite their widespread adoption, these systems raise ethical and social concerns due to potential biases and fairness issues. This study focuses on evaluating and improving the fairness of Computer Vision and Natural Language Processing (NLP) models applied to unstructured datasets, emphasizing how biased predictions can reinforce existing systemic inequalities. A publicly available dataset from Kaggle was utilized to simulate a practical scenario for examining fairness in ML workflows. To address and mitigate biases, the study employed two leading fairness libraries: Fairlearn by Microsoft, and AIF360 by IBM. These tools offer comprehensive frameworks for fairness analysis, including metrics evaluation, result visualization, and bias mitigation techniques. The research aims to measure bias levels in ML models, compare the effectiveness of these fairness libraries, and provide actionable recommendations for practitioners. The results demonstrate that each library possesses distinct strengths and limitations in evaluating and mitigating fairness. By systematically analyzing these tools, the study contributes valuable insights to the growing field of ML fairness, offering practical guidance for integrating fairness solutions into real world applications. This research underscores the importance of building more equitable and responsible machine learning systems.
Authors: Divya Shanmugam, Monica Agrawal, Rajiv Movva, Irene Y. Chen, Marzyeh Ghassemi, Maia Jacobs, Emma Pierson
Abstract: The increased capabilities of generative AI have dramatically expanded its possible use cases in medicine. We provide a comprehensive overview of generative AI use cases for clinicians, patients, clinical trial organizers, researchers, and trainees. We then discuss the many challenges -- including maintaining privacy and security, improving transparency and interpretability, upholding equity, and rigorously evaluating models -- which must be overcome to realize this potential, and the open research directions they give rise to.
Authors: Aoming Liang, Qi Liu, Lei Xu, Fahad Sohrab, Weicheng Cui, Changhui Song, Moncef Gabbouj
Abstract: Numerous studies have focused on learning and understanding the dynamics of physical systems from video data, such as spatial intelligence. Artificial intelligence requires quantitative assessments of the uncertainty of the model to ensure reliability. However, there is still a relative lack of systematic assessment of the uncertainties, particularly the uncertainties of the physical data. Our motivation is to introduce conformal prediction into the uncertainty assessment of dynamical systems, providing a method supported by theoretical guarantees. This paper uses the conformal prediction method to assess uncertainties with benchmark operator learning methods. We have also compared the Monte Carlo Dropout and Ensemble methods in the partial differential equations dataset, effectively evaluating uncertainty through straight roll-outs, making it ideal for time-series tasks.
Authors: Zhenyu Lei, Yushun Dong, Jundong Li, Chen Chen
Abstract: Spatial-temporal graphs are widely used in a variety of real-world applications. Spatial-Temporal Graph Neural Networks (STGNNs) have emerged as a powerful tool to extract meaningful insights from this data. However, in real-world applications, most nodes may not possess any available temporal data during training. For example, the pandemic dynamics of most cities on a geographical graph may not be available due to the asynchronous nature of outbreaks. Such a phenomenon disagrees with the training requirements of most existing spatial-temporal forecasting methods, which jeopardizes their effectiveness and thus blocks broader deployment. In this paper, we propose to formulate a novel problem of inductive forecasting with limited training data. In particular, given a spatial-temporal graph, we aim to learn a spatial-temporal forecasting model that can be easily generalized onto those nodes without any available temporal training data. To handle this problem, we propose a principled framework named ST-FiT. ST-FiT consists of two key learning components: temporal data augmentation and spatial graph topology learning. With such a design, ST-FiT can be used on top of any existing STGNNs to achieve superior performance on the nodes without training data. Extensive experiments verify the effectiveness of ST-FiT in multiple key perspectives.
Authors: Mingjing Xu, Peizhong Ju, Jia Liu, Haibo Yang
Abstract: Multi-objective optimization (MOO) lies at the core of many machine learning (ML) applications that involve multiple, potentially conflicting objectives (e.g., multi-task learning, multi-objective reinforcement learning, among many others). Despite the long history of MOO, recent years have witnessed a surge in interest within the ML community in the development of gradient manipulation algorithms for MOO, thanks to the availability of gradient information in many ML problems. However, existing gradient manipulation methods for MOO often suffer from long training times, primarily due to the need for computing dynamic weights by solving an additional optimization problem to determine a common descent direction that can decrease all objectives simultaneously. To address this challenge, we propose a new and efficient algorithm called Periodic Stochastic Multi-Gradient Descent (PSMGD) to accelerate MOO. PSMGD is motivated by the key observation that dynamic weights across objectives exhibit small changes under minor updates over short intervals during the optimization process. Consequently, our PSMGD algorithm is designed to periodically compute these dynamic weights and utilizes them repeatedly, thereby effectively reducing the computational overload. Theoretically, we prove that PSMGD can achieve state-of-the-art convergence rates for strongly-convex, general convex, and non-convex functions. Additionally, we introduce a new computational complexity measure, termed backpropagation complexity, and demonstrate that PSMGD could achieve an objective-independent backpropagation complexity. Through extensive experiments, we verify that PSMGD can provide comparable or superior performance to state-of-the-art MOO algorithms while significantly reducing training time.
Authors: Pengfei Fang, Yongchun Qin, Hui Xue
Abstract: Few-shot Class-Incremental Learning (FSCIL) addresses the challenges of evolving data distributions and the difficulty of data acquisition in real-world scenarios. To counteract the catastrophic forgetting typically encountered in FSCIL, knowledge distillation is employed as a way to maintain the knowledge from learned data distribution. Recognizing the limitations of generating discriminative feature representations in a few-shot context, our approach incorporates structural information between samples into knowledge distillation. This structural information serves as a remedy for the low quality of features. Diverging from traditional structured distillation methods that compute sample similarity, we introduce the Displacement Knowledge Distillation (DKD) method. DKD utilizes displacement rather than similarity between samples, incorporating both distance and angular information to significantly enhance the information density retained through knowledge distillation. Observing performance disparities in feature distribution between base and novel classes, we propose the Dual Distillation Network (DDNet). This network applies traditional knowledge distillation to base classes and DKD to novel classes, challenging the conventional integration of novel classes with base classes. Additionally, we implement an instance-aware sample selector during inference to dynamically adjust dual branch weights, thereby leveraging the complementary strengths of each approach. Extensive testing on three benchmarks demonstrates that DDNet achieves state-of-the-art results. Moreover, through rigorous experimentation and comparison, we establish the robustness and general applicability of our proposed DKD method.
Authors: Zeeshan Patel, James DeLoye, Lance Mathias
Abstract: In this paper, we present a comprehensive theoretical comparison of diffusion and flow matching under the Generator Matching framework. Despite their apparent differences, both diffusion and flow matching can be viewed under the unified framework of Generator Matching. By recasting both diffusion and flow matching under the same generative Markov framework, we provide theoretical insights into why flow matching models can be more robust empirically and how novel model classes can be constructed by mixing deterministic and stochastic components. Our analysis offers a fresh perspective on the relationships between state-of-the-art generative modeling paradigms.
Authors: G\"ozde \"Ozcan, Chengzhi Shi, Stratis Ioannidis
Abstract: Ou et al. (2022) introduce the problem of learning set functions from data generated by a so-called optimal subset oracle. Their approach approximates the underlying utility function with an energy-based model, whose parameters are estimated via mean-field variational inference. Ou et al. (2022) show this reduces to fixed point iterations; however, as the number of iterations increases, automatic differentiation quickly becomes computationally prohibitive due to the size of the Jacobians that are stacked during backpropagation. We address this challenge with implicit differentiation and examine the convergence conditions for the fixed-point iterations. We empirically demonstrate the efficiency of our method on synthetic and real-world subset selection applications including product recommendation, set anomaly detection and compound selection tasks.
Authors: Alberto Silvio Chiappa, Briti Gangopadhyay, Zhao Wang, Shingo Takamatsu
Abstract: Online advertising has become one of the most successful business models of the internet era. Impression opportunities are typically allocated through real-time auctions, where advertisers bid to secure advertisement slots. Deciding the best bid for an impression opportunity is challenging, due to the stochastic nature of user behavior and the variability of advertisement traffic over time. In this work, we propose a framework for training auto-bidding agents in multi-slot second-price auctions to maximize acquisitions (e.g., clicks, conversions) while adhering to budget and cost-per-acquisition (CPA) constraints. We exploit the insight that, after an advertisement campaign concludes, determining the optimal bids for each impression opportunity can be framed as a multiple-choice knapsack problem (MCKP) with a nonlinear objective. We propose an "oracle" algorithm that identifies a near-optimal combination of impression opportunities and advertisement slots, considering both past and future advertisement traffic data. This oracle solution serves as a training target for a student network which bids having access only to real-time information, a method we term Oracle Imitation Learning (OIL). Through numerical experiments, we demonstrate that OIL achieves superior performance compared to both online and offline reinforcement learning algorithms, offering improved sample efficiency. Notably, OIL shifts the complexity of training auto-bidding agents from crafting sophisticated learning algorithms to solving a nonlinear constrained optimization problem efficiently.
Authors: Gangqiang Hu, Jianfeng Lu, Jianmin Han, Shuqin Cao, Jing Liu, Hao Fu
Abstract: Due to the sensitivity of data, federated learning (FL) is employed to enable distributed machine learning while safeguarding data privacy and accommodating the requirements of various devices. However, in the context of semi-decentralized federated learning (SD-FL), clients' communication and training states are dynamic. This variability arises from local training fluctuations, heterogeneous data distributions, and intermittent client participation. Most existing studies primarily focus on stable client states, neglecting the dynamic challenges present in real-world scenarios. To tackle this issue, we propose a trust-aware client scheduling mechanism (TRAIL) that assesses client states and contributions, enhancing model training efficiency through selective client participation. Our focus is on a semi-decentralized federated learning framework where edge servers and clients train a shared global model using unreliable intra-cluster model aggregation and inter-cluster model consensus. First, we develop an adaptive hidden semi-Markov model (AHSMM) to estimate clients' communication states and contributions. Next, we address a client-server association optimization problem to minimize global training loss. Using convergence analysis, we propose a greedy client scheduling algorithm. Finally, our experiments conducted on real-world datasets demonstrate that TRAIL outperforms state-of-the-art baselines, achieving an improvement of 8.7\% in test accuracy and a reduction of 15.3\% in training loss.
Authors: Minghao Xu, Lichuan Xiang, Xu Cai, Hongkai Wen
Abstract: In this work, we question the necessity of adaptive gradient methods for training deep neural networks. SGD-SaI is a simple yet effective enhancement to stochastic gradient descent with momentum (SGDM). SGD-SaI performs learning rate Scaling at Initialization (SaI) to distinct parameter groups, guided by their respective gradient signal-to-noise ratios (g-SNR). By adjusting learning rates without relying on adaptive second-order momentum, SGD-SaI helps prevent training imbalances from the very first iteration and cuts the optimizer's memory usage by half compared to AdamW. Despite its simplicity and efficiency, SGD-SaI consistently matches or outperforms AdamW in training a variety of Transformer-based tasks, effectively overcoming a long-standing challenge of using SGD for training Transformers. SGD-SaI excels in ImageNet-1K classification with Vision Transformers(ViT) and GPT-2 pretraining for large language models (LLMs, transformer decoder-only), demonstrating robustness to hyperparameter variations and practicality for diverse applications. We further tested its robustness on tasks like LoRA fine-tuning for LLMs and diffusion models, where it consistently outperforms state-of-the-art optimizers. From a memory efficiency perspective, SGD-SaI achieves substantial memory savings for optimizer states, reducing memory usage by 5.93 GB for GPT-2 (1.5B parameters) and 25.15 GB for Llama2-7B compared to AdamW in full-precision training settings.
Authors: Vidit Gautam
Abstract: Advance in medical imaging is an important part in deep learning research. One of the goals of computer vision is development of a holistic, comprehensive model which can identify tumors from histology slides obtained via biopsies. A major problem that stands in the way is lack of data for a few cancer-types. In this paper, we ascertain that data augmentation using GANs can be a viable solution to reduce the unevenness in the distribution of different cancer types in our dataset. Our demonstration showed that a dataset augmented to a 50% increase causes an increase in tumor detection from 80% to 87.5%
Authors: Shengling Shi, Anastasios Tsiamis, Bart De Schutter
Abstract: This work analyzes how the trade-off between the modeling error, the terminal value function error, and the prediction horizon affects the performance of a nominal receding-horizon linear quadratic (LQ) controller. By developing a novel perturbation result of the Riccati difference equation, a novel performance upper bound is obtained and suggests that for many cases, the prediction horizon can be either one or infinity to improve the control performance, depending on the relative difference between the modeling error and the terminal value function error. The result also shows that when an infinite horizon is desired, a finite prediction horizon that is larger than the controllability index can be sufficient for achieving a near-optimal performance, revealing a close relation between the prediction horizon and controllability. The obtained suboptimality performance bound is applied to provide novel sample complexity and regret guarantees for nominal receding-horizon LQ controllers in a learning-based setting. We show that an adaptive prediction horizon that increases as a logarithmic function of time is beneficial for regret minimization.
Authors: Fengyi Li, Youssef Marzouk
Abstract: We propose a novel diffusion map particle system (DMPS) for generative modeling, based on diffusion maps and Laplacian-adjusted Wasserstein gradient descent (LAWGD). Diffusion maps are used to approximate the generator of the corresponding Langevin diffusion process from samples, and hence to learn the underlying data-generating manifold. On the other hand, LAWGD enables efficient sampling from the target distribution given a suitable choice of kernel, which we construct here via a spectral approximation of the generator, computed with diffusion maps. Our method requires no offline training and minimal tuning, and can outperform other approaches on data sets of moderate dimension.
Authors: Aras Selvi, Huikang Liu, Wolfram Wiesemann
Abstract: In recent years, differential privacy has emerged as the de facto standard for sharing statistics of datasets while limiting the disclosure of private information about the involved individuals. This is achieved by randomly perturbing the statistics to be published, which in turn leads to a privacy-accuracy trade-off: larger perturbations provide stronger privacy guarantees, but they result in less accurate statistics that offer lower utility to the recipients. Of particular interest are therefore optimal mechanisms that provide the highest accuracy for a pre-selected level of privacy. To date, work in this area has focused on specifying families of perturbations a priori and subsequently proving their asymptotic and/or best-in-class optimality. In this paper, we develop a class of mechanisms that enjoy non-asymptotic and unconditional optimality guarantees. To this end, we formulate the mechanism design problem as an infinite-dimensional distributionally robust optimization problem. We show that the problem affords a strong dual, and we exploit this duality to develop converging hierarchies of finite-dimensional upper and lower bounding problems. Our upper (primal) bounds correspond to implementable perturbations whose suboptimality can be bounded by our lower (dual) bounds. Both bounding problems can be solved within seconds via cutting plane techniques that exploit the inherent problem structure. Our numerical experiments demonstrate that our perturbations can outperform the previously best results from the literature on artificial as well as standard benchmark problems.
Authors: Julia Herbinger, Marvin N. Wright, Thomas Nagler, Bernd Bischl, Giuseppe Casalicchio
Abstract: Global feature effect methods, such as partial dependence plots, provide an intelligible visualization of the expected marginal feature effect. However, such global feature effect methods can be misleading, as they do not represent local feature effects of single observations well when feature interactions are present. We formally introduce generalized additive decomposition of global effects (GADGET), which is a new framework based on recursive partitioning to find interpretable regions in the feature space such that the interaction-related heterogeneity of local feature effects is minimized. We provide a mathematical foundation of the framework and show that it is applicable to the most popular methods to visualize marginal feature effects, namely partial dependence, accumulated local effects, and Shapley additive explanations (SHAP) dependence. Furthermore, we introduce and validate a new permutation-based interaction detection procedure that is applicable to any feature effect method that fits into our proposed framework. We empirically evaluate the theoretical characteristics of the proposed methods based on various feature effect methods in different experimental settings. Moreover, we apply our introduced methodology to three real-world examples to showcase their usefulness.
Authors: Kunal Mukherjee, Joshua Wiedemeier, Tianhao Wang, Muhyun Kim, Feng Chen, Murat Kantarcioglu, Kangkook Jee
Abstract: Advanced cyber threats (e.g., Fileless Malware and Advanced Persistent Threat (APT)) have driven the adoption of provenance-based security solutions. These solutions employ Machine Learning (ML) models for behavioral modeling and critical security tasks such as malware and anomaly detection. However, the opacity of ML-based security models limits their broader adoption, as the lack of transparency in their decision-making processes restricts explainability and verifiability. We tailored our solution towards Graph Neural Network (GNN)-based security solutions since recent studies employ GNNs to comprehensively digest system provenance graphs for security critical tasks. To enhance the explainability of GNN-based security models, we introduce PROVEXPLAINER, a framework offering instance-level security-aware explanations using an interpretable surrogate model. PROVEXPLAINER's interpretable feature space consists of discriminant subgraph patterns and graph structural features, which can be directly mapped to the system provenance problem space, making the explanations human understandable. By considering prominent GNN architectures (e.g., GAT and GraphSAGE) for anomaly detection tasks, we show how PROVEXPLAINER synergizes with current state-of-the-art (SOTA) GNN explainers to deliver domain and instance-specific explanations. We measure the explanation quality using the fidelity+/fidelity- metric as used by traditional GNN explanation literature, and we incorporate the precision/recall metric where we consider the accuracy of the explanation against the ground truth. On malware and APT datasets, PROVEXPLAINER achieves up to 29%/27%/25% higher fidelity+, precision and recall, and 12% lower fidelity- respectively, compared to SOTA GNN explainers.
Authors: Fernando B. P\'erez Maurera, Maurizio Ferrari Dacrema, Pablo Castells, Paolo Cremonesi
Abstract: Novel data sources bring new opportunities to improve the quality of recommender systems and serve as a catalyst for the creation of new paradigms on personalized recommendations. Impressions are a novel data source containing the items shown to users on their screens. Past research focused on providing personalized recommendations using interactions, and occasionally using impressions when such a data source was available. Interest in impressions has increased due to their potential to provide more accurate recommendations. Despite this increased interest, research in recommender systems using impressions is still dispersed. Many works have distinct interpretations of impressions and use impressions in recommender systems in numerous different manners. To unify those interpretations into a single framework, we present a systematic literature review on recommender systems using impressions, focusing on three fundamental perspectives: recommendation models, datasets, and evaluation methodologies. We define a theoretical framework to delimit recommender systems using impressions and a novel paradigm for personalized recommendations, called impression-aware recommender systems. We propose a classification system for recommenders in this paradigm, which we use to categorize the recommendation models, datasets, and evaluation methodologies used in past research. Lastly, we identify open questions and future directions, highlighting missing aspects in the reviewed literature.
Authors: Francesco Immorlano, Veronika Eyring, Thomas le Monnier de Gouville, Gabriele Accarino, Donatello Elia, Stephan Mandt, Giovanni Aloisio, Pierre Gentine
Abstract: Precise and reliable climate projections are required for climate adaptation and mitigation, but Earth system models still exhibit great uncertainties. Several approaches have been developed to reduce the spread of climate projections and feedbacks, yet those methods cannot capture the non-linear complexity inherent in the climate system. Using a Transfer Learning approach, we show that Machine Learning can be used to optimally leverage and merge the knowledge gained from Earth system models simulations and historical observations to reduce the spread of global surface air temperature fields projected in the 21st century. We reach an uncertainty reduction of more than 50% with respect to state-of-the-art approaches, while giving evidence that our novel method provides improved regional temperature patterns together with narrower projections uncertainty, urgently required for climate adaptation.
Authors: Md Rakibul Hasan, Md Zakir Hossain, Shreya Ghosh, Aneesh Krishna, Tom Gedeon
Abstract: Empathy indicates an individual's ability to understand others. Over the past few years, empathy has drawn attention from various disciplines, including but not limited to Affective Computing, Cognitive Science, and Psychology. Detecting empathy has potential applications in society, healthcare and education. Despite being a broad and overlapping topic, the avenue of empathy detection leveraging Machine Learning remains underexplored from a systematic literature review perspective. We collected 829 papers from 10 well-known databases, systematically screened them and analysed the final 62 papers. Our analyses reveal several prominent task formulations $-$ including empathy on localised utterances or overall expressions, unidirectional or parallel empathy, and emotional contagion $-$ in monadic, dyadic and group interactions. Empathy detection methods are summarised based on four input modalities $-$ text, audiovisual, audio and physiological signals $-$ thereby presenting modality-specific network architecture design protocols. We discuss challenges, research gaps and potential applications in the Affective Computing-based empathy domain, which can facilitate new avenues of exploration. We further enlist the public availability of datasets and codes. This paper, therefore, provides a structured overview of recent advancements and remaining challenges towards developing a robust empathy detection system that could meaningfully contribute to enhancing human well-being.
Authors: Ci-Siang Lin, Chien-Yi Wang, Yu-Chiang Frank Wang, Min-Hung Chen
Abstract: Weakly-Supervised Semantic Segmentation (WSSS) aims to train segmentation models using image data with only image-level supervision. Since precise pixel-level annotations are not accessible, existing methods typically focus on producing pseudo masks for training segmentation models by refining CAM-like heatmaps. However, the produced heatmaps may capture only the discriminative image regions of object categories or the associated co-occurring backgrounds. To address the issues, we propose a Semantic Prompt Learning for WSSS (SemPLeS) framework, which learns to effectively prompt the CLIP latent space to enhance the semantic alignment between the segmented regions and the target object categories. More specifically, we propose Contrastive Prompt Learning and Prompt-guided Semantic Refinement to learn the prompts that adequately describe and suppress the co-occurring backgrounds associated with each object category. In this way, SemPLeS can perform better semantic alignment between object regions and class labels, resulting in desired pseudo masks for training segmentation models. The proposed SemPLeS framework achieves competitive performance on standard WSSS benchmarks, PASCAL VOC 2012 and MS COCO2014, and shows compatibility with other WSSS methods.
Authors: Zishi Zhang, Yijie Peng
Abstract: This work breaks the sample efficiency bottleneck in parallel large-scale ranking and selection (R&S) problem by leveraging correlation information. We modify the commonly used "divide and conquer" framework in parallel computing by adding a correlation-based clustering step, transforming it into "clustering and conquer". This seemingly simple modification can achieve an $\mathcal{O}(p)$ sample complexity reduction rate, which represents the maximum attainable reduction for the class of sample-optimal R&S methods. Our approach enjoys two key advantages: 1) it does not require highly accurate correlation estimation or precise clustering, and 2) it allows for seamless integration with various existing R&S method, while achieving optimal sample complexity. Theoretically, we develop a novel gradient analysis framework to analyze sample efficiency and guide the design of large-scale R&S procedures. Building upon this framework, we propose a gradient-based budget allocation policy. We also introduce a new clustering algorithm, selection policy, and precision criterion tailored for large-scale scenarios. Finally, in large-scale AI applications such as neural architecture search, our methods demonstrate superior performance.
Authors: Yuepei Li, Kang Zhou, Qiao Qiao, Qing Wang, Qi Li
Abstract: Distantly-Supervised Named Entity Recognition (DS-NER) uses knowledge bases or dictionaries for annotations, reducing manual efforts but rely on large human labeled validation set. In this paper, we introduce a real-life DS-NER dataset, QTL, where the training data is annotated using domain dictionaries and the test data is annotated by domain experts. This dataset has a small validation set, reflecting real-life scenarios. Existing DS-NER approaches fail when applied to QTL, which motivate us to re-examine existing DS-NER approaches. We found that many of them rely on large validation sets and some used test set for tuning inappropriately. To solve this issue, we proposed a new approach, token-level Curriculum-based Positive-Unlabeled Learning (CuPUL), which uses curriculum learning to order training samples from easy to hard. This method stabilizes training, making it robust and effective on small validation sets. CuPUL also addresses false negative issues using the Positive-Unlabeled learning paradigm, demonstrating improved performance in real-life applications.
Authors: Jiawei Zheng, Hanghai Hong, Feiyan Liu, Xiaoli Wang, Jingsong Su, Yonggui Liang, Shikai Wu
Abstract: Large language models (LLMs) have shown great potential in domain-specific machine translation (MT). However, one major issue is that LLMs pre-trained on general domain corpus might not generalize well to specific domains due to the lack of domain-specific knowledge. To address this issue, this paper focuses on enhancing the domain-specific MT capability of LLMs, by providing high-quality training datasets and proposing a novel fine-tuning framework denoted by DragFT. DragFT augments LLMs via three techniques: (i) Dictionary-enhanced prompting integrates dictionary information into prompts to improve the translation of domain-specific terminology.; (ii) RAG-based few-shot example selection provides high-quality examples that simulate both the domain and style characteristics; (iii) Fine-tuning with few-shot examples further enhances performance when using in-domain examples. We deploy DragFT on three well-known LLM backbones with 13B training parameters to validate its effectiveness. The results on three domain-specific datasets show that DragFT achieves a significant performance boost and shows superior performance compared to advanced models such as GPT-3.5 and GPT-4o. The drastic performance improvement of DragFT over existing LLMs can be attributed to incorporating relevant knowledge while mitigating noise.
Authors: Sana Ayromlou, Vahid Reza Khazaie, Fereshteh Forghani, Arash Afkanpour
Abstract: The rapid advancement in self-supervised representation learning has highlighted its potential to leverage unlabeled data for learning rich visual representations. However, the existing techniques, particularly those employing different augmentations of the same image, often rely on a limited set of simple transformations that cannot fully capture variations in the real world. This constrains the diversity and quality of samples, which leads to sub-optimal representations. In this paper, we introduce a framework that enriches the self-supervised learning (SSL) paradigm by utilizing generative models to produce semantically consistent image augmentations. By directly conditioning generative models on a source image, our method enables the generation of diverse augmentations while maintaining the semantics of the source image, thus offering a richer set of data for SSL. Our extensive experimental results on various joint-embedding SSL techniques demonstrate that our framework significantly enhances the quality of learned visual representations by up to 10\% Top-1 accuracy in downstream tasks. This research demonstrates that incorporating generative models into the joint-embedding SSL workflow opens new avenues for exploring the potential of synthetic data. This development paves the way for more robust and versatile representation learning techniques.
Authors: Qinyuan Wu, Mohammad Aflah Khan, Soumi Das, Vedant Nanda, Bishwamittra Ghosh, Camila Kolling, Till Speicher, Laurent Bindschaedler, Krishna P. Gummadi, Evimaria Terzi
Abstract: In this paper, we focus on the challenging task of reliably estimating factual knowledge that is embedded inside large language models (LLMs). To avoid reliability concerns with prior approaches, we propose to eliminate prompt engineering when probing LLMs for factual knowledge. Our approach, called Zero-Prompt Latent Knowledge Estimator (ZP-LKE), leverages the in-context learning ability of LLMs to communicate both the factual knowledge question as well as the expected answer format. Our knowledge estimator is both conceptually simpler (i.e., doesn't depend on meta-linguistic judgments of LLMs) and easier to apply (i.e., is not LLM-specific), and we demonstrate that it can surface more of the latent knowledge embedded in LLMs. We also investigate how different design choices affect the performance of ZP-LKE. Using the proposed estimator, we perform a large-scale evaluation of the factual knowledge of a variety of open-source LLMs, like OPT, Pythia, Llama(2), Mistral, Gemma, etc. over a large set of relations and facts from the Wikidata knowledge base. We observe differences in the factual knowledge between different model families and models of different sizes, that some relations are consistently better known than others but that models differ in the precise facts they know, and differences in the knowledge of base models and their finetuned counterparts. Code available at: https://github.com/QinyuanWu0710/ZeroPrompt_LKE
Authors: Ariel Neufeld, Philipp Schmocker, Sizhou Wu
Abstract: In this paper, we present a randomized extension of the deep splitting algorithm introduced in [Beck, Becker, Cheridito, Jentzen, and Neufeld (2021)] using random neural networks suitable to approximately solve both high-dimensional nonlinear parabolic PDEs and PIDEs with jumps having (possibly) infinite activity. We provide a full error analysis of our so-called random deep splitting method. In particular, we prove that our random deep splitting method converges to the (unique viscosity) solution of the nonlinear PDE or PIDE under consideration. Moreover, we empirically analyze our random deep splitting method by considering several numerical examples including both nonlinear PDEs and nonlinear PIDEs relevant in the context of pricing of financial derivatives under default risk. In particular, we empirically demonstrate in all examples that our random deep splitting method can approximately solve nonlinear PDEs and PIDEs in 10'000 dimensions within seconds.
Authors: Alexander Windmann, Philipp Wittenberg, Marvin Schieseck, Oliver Niggemann
Abstract: In Industry 4.0, Cyber-Physical Systems (CPS) generate vast data sets that can be leveraged by Artificial Intelligence (AI) for applications including predictive maintenance and production planning. However, despite the demonstrated potential of AI, its widespread adoption in sectors like manufacturing remains limited. Our comprehensive review of recent literature, including standards and reports, pinpoints key challenges: system integration, data-related issues, managing workforce-related concerns and ensuring trustworthy AI. A quantitative analysis highlights particular challenges and topics that are important for practitioners but still need to be sufficiently investigated by academics. The paper briefly discusses existing solutions to these challenges and proposes avenues for future research. We hope that this survey serves as a resource for practitioners evaluating the cost-benefit implications of AI in CPS and for researchers aiming to address these urgent challenges.
Authors: Jie Chen, Xintian Han, Yu Ma, Xun Zhou, Liang Xiang
Abstract: Automatic code generation has been a longstanding research topic. With the advancement of general-purpose large language models (LLMs), the ability to code stands out as one important measure to the model's reasoning performance. Usually, a two-stage training paradigm is implemented to obtain a Code LLM, namely the pretraining and the fine-tuning. Within the fine-tuning, supervised fine-tuning (SFT), and reinforcement learning (RL) are often used to improve the model's zero-shot ability. A large number of work has been conducted to improve the model's performance on code-related benchmarks with either modifications to the algorithm or refinement of the dataset. However, we still lack a deep insight into the correlation between SFT and RL. For instance, what kind of dataset should be used to ensure generalization, or what if we abandon the SFT phase in fine-tuning. In this work, we make an attempt to understand the correlation between SFT and RL. To facilitate our research, we manually craft 100 basis python functions, called atomic functions, and then a synthesizing pipeline is deployed to create a large number of synthetic functions on top of the atomic ones. In this manner, we ensure that the train and test sets remain distinct, preventing data contamination. Through comprehensive ablation study, we find: (1) Both atomic and synthetic functions are indispensable for SFT's generalization, and only a handful of synthetic functions are adequate; (2) Through RL, the SFT's generalization to target domain can be greatly enhanced, even with the same training prompts; (3) Training RL from scratch can alleviate the over-fitting issue introduced in the SFT phase.
Authors: Haowen Hou, Peigen Zeng, Fei Ma, Fei Richard Yu
Abstract: Visual Language Models (VLMs) have rapidly progressed with the recent success of large language models. However, there have been few attempts to incorporate efficient linear Recurrent Neural Networks (RNNs) architectures into VLMs. In this study, we introduce VisualRWKV, the first application of a linear RNN model to multimodal learning tasks, leveraging the pre-trained RWKV language model. We propose a data-dependent recurrence and sandwich prompts to enhance our modeling capabilities, along with a 2D image scanning mechanism to enrich the processing of visual sequences. Extensive experiments demonstrate that VisualRWKV achieves competitive performance compared to Transformer-based models like LLaVA-1.5 on various benchmarks. Compared to LLaVA-1.5, VisualRWKV has a speed advantage of 3.98 times and can save 54% of GPU memory when reaching an inference length of 24K tokens. To facilitate further research and analysis, we have made the checkpoints and the associated code publicly accessible at the following GitHub repository: see https://github.com/howard-hou/VisualRWKV.
Authors: Fengjun Yang, Nikolai Matni
Abstract: We propose a reinforcement learning (RL)-based algorithm to jointly train (1) a trajectory planner and (2) a tracking controller in a layered control architecture. Our algorithm arises naturally from a rewrite of the underlying optimal control problem that lends itself to an actor-critic learning approach. By explicitly learning a \textit{dual} network to coordinate the interaction between the planning and tracking layers, we demonstrate the ability to achieve an effective consensus between the two components, leading to an interpretable policy. We theoretically prove that our algorithm converges to the optimal dual network in the Linear Quadratic Regulator (LQR) setting and empirically validate its applicability to nonlinear systems through simulation experiments on a unicycle model.
Authors: Zijian Wang, Bin Wang, Haifeng Jing, Huayu Li, Hongbo Dou
Abstract: Recent years, multi-hop reasoning has been widely studied for knowledge graph (KG) reasoning due to its efficacy and interpretability. However, previous multi-hop reasoning approaches are subject to two primary shortcomings. First, agents struggle to learn effective and robust policies at the early phase due to sparse rewards. Second, these approaches often falter on specific datasets like sparse knowledge graphs, where agents are required to traverse lengthy reasoning paths. To address these problems, we propose a multi-hop reasoning model with dual agents based on hierarchical reinforcement learning (HRL), which is named FULORA. FULORA tackles the above reasoning challenges by eFficient GUidance-ExpLORAtion between dual agents. The high-level agent walks on the simplified knowledge graph to provide stage-wise hints for the low-level agent walking on the original knowledge graph. In this framework, the low-level agent optimizes a value function that balances two objectives: (1) maximizing return, and (2) integrating efficient guidance from the high-level agent. Experiments conducted on three real-word knowledge graph datasets demonstrate that FULORA outperforms RL-based baselines, especially in the case of long-distance reasoning.
Authors: Amirhosein Chahe, Lifeng Zhou
Abstract: This paper introduces a novel method for open-vocabulary 3D scene querying in autonomous driving by combining Language Embedded 3D Gaussians with Large Language Models (LLMs). We propose utilizing LLMs to generate both contextually canonical phrases and helping positive words for enhanced segmentation and scene interpretation. Our method leverages GPT-3.5 Turbo as an expert model to create a high-quality text dataset, which we then use to fine-tune smaller, more efficient LLMs for on-device deployment. Our comprehensive evaluation on the WayveScenes101 dataset demonstrates that LLM-guided segmentation significantly outperforms traditional approaches based on predefined canonical phrases. Notably, our fine-tuned smaller models achieve performance comparable to larger expert models while maintaining faster inference times. Through ablation studies, we discover that the effectiveness of helping positive words correlates with model scale, with larger models better equipped to leverage additional semantic information. This work represents a significant advancement towards more efficient, context-aware autonomous driving systems, effectively bridging 3D scene representation with high-level semantic querying while maintaining practical deployment considerations.
Authors: Jiaang Li, Quan Wang, Zhongnan Wang, Yongdong Zhang, Zhendong Mao
Abstract: Large language models (LLMs) require model editing to efficiently update specific knowledge within them and avoid factual errors. Most model editing methods are solely designed for single-time use and result in a significant forgetting effect in lifelong editing scenarios, where sequential edits are conducted over time. Previous approaches manage sequential edits by freezing original parameters and discretely allocating new parameters for each knowledge update. However, these methods lack robustness to minor input variations due to the discrete mapping between data and parameters. To overcome this challenge, we propose ELDER, a novel approach to create a continuous association between data and adapters. ELDER integrates multiple LoRAs through a router network and is trained to establish a smooth data-adapter association, thereby enhancing the edit robustness and generalization of semantically equivalent inputs. To ensure inputs containing the same knowledge will be processed by the same LoRAs, we design a novel loss to guide the model link LoRA allocations with edit knowledge. Furthermore, we propose a deferral mechanism to retain the original LLM capabilities post-edit. Extensive experiments on GPT-2 XL and LLaMA2-7B demonstrate that ELDER effectively edits models in the lifelong setting, outperforming eight baselines while exhibiting strong scalability and preserving LLMs' general abilities on downstream tasks.
Authors: Ruairidh M. Battleday, Samuel J. Gershman
Abstract: A suite of impressive scientific discoveries have been driven by recent advances in artificial intelligence. These almost all result from training flexible algorithms to solve difficult optimization problems specified in advance by teams of domain scientists and engineers with access to large amounts of data. Although extremely useful, this kind of problem solving only corresponds to one part of science - the "easy problem." The other part of scientific research is coming up with the problem itself - the "hard problem." Solving the hard problem is beyond the capacities of current algorithms for scientific discovery because it requires continual conceptual revision based on poorly defined constraints. We can make progress on understanding how humans solve the hard problem by studying the cognitive science of scientists, and then use the results to design new computational agents that automatically infer and update their scientific paradigms.
Authors: Pranay Thangeda, Trevor S. Betz, Michael N. Grussing, Melkior Ornik
Abstract: Efficient management of infrastructure systems is crucial for economic stability, sustainability, and public safety. However, infrastructure sustainment is challenging due to the vast scale of systems, stochastic deterioration of components, partial observability, and resource constraints. Decision-making strategies that rely solely on human judgment often result in suboptimal decisions over large scales and long horizons. While data-driven approaches like reinforcement learning offer promising solutions, their application has been limited by the lack of suitable simulation environments. We present InfraLib, an open-source modular and extensible framework that enables modeling and analyzing infrastructure management problems with resource constraints as sequential decision-making problems. The framework implements hierarchical, stochastic deterioration models, supports realistic partial observability, and handles practical constraints including cyclical budgets and component unavailability. InfraLib provides standardized environments for benchmarking decision-making approaches, along with tools for expert data collection and policy evaluation. Through case studies on both synthetic benchmarks and real-world road networks, we demonstrate InfraLib's ability to model diverse infrastructure management scenarios while maintaining computational efficiency at scale.
Authors: Ningyuan Xi, Xiaoyu Wang, Yetao Wu, Teng Chen, Qingqing Gu, Yue Zhao, Jinxian Qu, Zhonglin Jiang, Yong Chen, Luo Ji
Abstract: Large Language Model can reasonably understand and generate human expressions but may lack of thorough thinking and reasoning mechanisms. Recently there have been several studies which enhance the thinking ability of language models but most of them are not data-driven or training-based. In this paper, we are motivated by the cognitive mechanism in the natural world, and design a novel model architecture called TaS which allows it to first consider the thoughts and then express the response based upon the query. We design several pipelines to annotate or generate the thought contents from prompt-response samples, then add language heads in a middle layer which behaves as the thinking layer. We train the language model by the thoughts-augmented data and successfully let the thinking layer automatically generate reasonable thoughts and finally output more reasonable responses. Both qualitative examples and quantitative results validate the effectiveness and performance of TaS. Our code is available at https://anonymous.4open.science/r/TadE.
Authors: Jiaming Zhou, Abbas Ghaddar, Ge Zhang, Liheng Ma, Yaochen Hu, Soumyasundar Pal, Mark Coates, Bin Wang, Yingxue Zhang, Jianye Hao
Abstract: Despite recent advances in training and prompting strategies for Large Language Models (LLMs), these models continue to face challenges with complex logical reasoning tasks that involve long reasoning chains. In this work, we explore the potential and limitations of using graph-based synthetic reasoning data as training signals to enhance LLMs' reasoning capabilities. Our extensive experiments, conducted on two established natural language reasoning tasks -- inductive reasoning and spatial reasoning -- demonstrate that supervised fine-tuning (SFT) with synthetic graph-based reasoning data effectively enhances LLMs' reasoning performance without compromising their effectiveness on other standard evaluation benchmarks.
Authors: Dongwon Jung, Qin Liu, Tenghao Huang, Ben Zhou, Muhao Chen
Abstract: Retrieval-augmented generation (RAG) improves large language models (LMs) by incorporating non-parametric knowledge through evidence retrieved from external sources. However, it often struggles to cope with inconsistent and irrelevant information that can distract the LM from its tasks, especially when multiple evidence pieces are required. While compressing the retrieved evidence with a compression model aims to address this issue, the compressed evidence may still be unfamiliar to the target model used for downstream tasks, potentially failing to utilize the evidence effectively. We propose FaviComp (Familarity-Aware Evidence Compression), a novel training-free evidence compression technique that makes retrieved evidence more familiar to the target model, while seamlessly integrating parametric knowledge from the model. Experimental results show that FaviComp consistently outperforms most recent evidence compression baselines across multiple open-domain QA datasets, improving accuracy by up to 28.1% while achieving high compression rates. Additionally, we demonstrate the effective integration of both parametric and non-parametric knowledge during evidence compression.
Authors: Anmol Mekala, Vineeth Dorna, Shreya Dubey, Abhishek Lalwani, David Koleczek, Mukund Rungta, Sadid Hasan, Elita Lobo
Abstract: Machine unlearning aims to efficiently eliminate the influence of specific training data, known as the forget set, from the model. However, existing unlearning methods for Large Language Models (LLMs) face a critical challenge: they rely solely on negative feedback to suppress responses related to the forget set, which often results in nonsensical or inconsistent outputs, diminishing model utility and posing potential privacy risks. To address this limitation, we propose a novel approach called Alternate Preference Optimization (AltPO), which combines negative feedback with in-domain positive feedback on the forget set. Additionally, we introduce new evaluation metrics to assess the quality of responses related to the forget set. Extensive experiments show that our approach not only enables effective unlearning but also avoids undesirable model behaviors while maintaining overall model performance. Our implementation can be found at https://github.com/molereddy/Alternate-Preference-Optimization.
URLs: https://github.com/molereddy/Alternate-Preference-Optimization.
Authors: S. N. Karaman, M. Turgay, T. Acar
Abstract: The present paper deals with construction of newly family of Neural Network operators, that is, Steklov Neural Network operators. By using Steklov type integral, we introduce a new version of Neural Network operators and we obtain some convergence theorems for the family, such as, pointwise and uniform convergence, rate of convergence via modulus of continuity.
Authors: Hakaze Cho, Mariko Kato, Yoshihiro Sakai, Naoya Inoue
Abstract: In-context Learning (ICL) is an emerging few-shot learning paradigm on Language Models (LMs) with inner mechanisms un-explored. There are already existing works describing the inner processing of ICL, while they struggle to capture all the inference phenomena in large language models. Therefore, this paper proposes a comprehensive circuit to model the inference dynamics and try to explain the observed phenomena of ICL. In detail, we divide ICL inference into 3 major operations: (1) Input Text Encode: LMs encode every input text (demonstrations and queries) into linear representation in the hidden states with sufficient information to solve ICL tasks. (2) Semantics Merge: LMs merge the encoded representations of demonstrations with their corresponding label tokens to produce joint representations of labels and demonstrations. (3) Feature Retrieval and Copy: LMs search the joint representations similar to the query representation on a task subspace, and copy the searched representations into the query. Then, language model heads capture these copied label representations to a certain extent and decode them into predicted labels. The proposed inference circuit successfully captured many phenomena observed during the ICL process, making it a comprehensive and practical explanation of the ICL inference process. Moreover, ablation analysis by disabling the proposed steps seriously damages the ICL performance, suggesting the proposed inference circuit is a dominating mechanism. Additionally, we confirm and list some bypass mechanisms that solve ICL tasks in parallel with the proposed circuit.
Authors: Zaid Khan, Elias Stengel-Eskin, Jaemin Cho, Mohit Bansal
Abstract: The process of creating training data to teach models is currently driven by humans, who manually analyze model weaknesses and plan how to create data that improves a student model. Approaches using LLMs as annotators reduce human effort, but still require humans to interpret feedback from evaluations and control the LLM to produce data the student needs. Automating this labor-intensive process by creating autonomous data generation agents - or teachers - is desirable, but requires environments that can simulate the feedback-driven, iterative, closed loop of data creation. To enable rapid, scalable testing for such agents and their modules, we introduce DataEnvGym, a testbed of teacher environments for data generation agents. DataEnvGym frames data generation as a sequential decision-making task, involving an agent consisting of a data generation policy (which generates a plan for creating training data) and a data generation engine (which transforms the plan into data), inside an environment that provides student feedback. The agent's goal is to improve student performance. Students are iteratively trained and evaluated on generated data, and their feedback (in the form of errors or weak skills) is reported to the agent after each iteration. DataEnvGym includes multiple teacher environment instantiations across 3 levels of structure in the state representation and action space. More structured environments are based on inferred skills and offer more interpretability and curriculum control. We support 4 domains (math, code, VQA, and tool-use) and test multiple students and teachers. Example agents in our teaching environments can iteratively improve students across tasks and settings. Moreover, we show that environments teach different skill levels and test variants of key modules, pointing to future work in improving data generation agents, engines, and feedback mechanisms.
Authors: Subhankar Ghosh, Arun Sharma, Jayant Gupta, Aneesh Subramanian, Shashi Shekhar
Abstract: Given coarser-resolution projections from global climate models or satellite data, the downscaling problem aims to estimate finer-resolution regional climate data, capturing fine-scale spatial patterns and variability. Downscaling is any method to derive high-resolution data from low-resolution variables, often to provide more detailed and local predictions and analyses. This problem is societally crucial for effective adaptation, mitigation, and resilience against significant risks from climate change. The challenge arises from spatial heterogeneity and the need to recover finer-scale features while ensuring model generalization. Most downscaling methods \cite{Li2020} fail to capture the spatial dependencies at finer scales and underperform on real-world climate datasets, such as sea-level rise. We propose a novel Kriging-informed Conditional Diffusion Probabilistic Model (Ki-CDPM) to capture spatial variability while preserving fine-scale features. Experimental results on climate data show that our proposed method is more accurate than state-of-the-art downscaling techniques.
Authors: Zhuoming Chen, Ranajoy Sadhukhan, Zihao Ye, Yang Zhou, Jianyu Zhang, Niklas Nolte, Yuandong Tian, Matthijs Douze, Leon Bottou, Zhihao Jia, Beidi Chen
Abstract: Large language models (LLMs) with long context windows have gained significant attention. However, the KV cache, stored to avoid re-computation, becomes a bottleneck. Various dynamic sparse or TopK-based attention approximation methods have been proposed to leverage the common insight that attention is sparse. In this paper, we first show that TopK attention itself suffers from quality degradation in certain downstream tasks because attention is not always as sparse as expected. Rather than selecting the keys and values with the highest attention scores, sampling with theoretical guarantees can provide a better estimation for attention output. To make the sampling-based approximation practical in LLM generation, we propose MagicPIG, a heterogeneous system based on Locality Sensitive Hashing (LSH). MagicPIG significantly reduces the workload of attention computation while preserving high accuracy for diverse tasks. MagicPIG stores the LSH hash tables and runs the attention computation on the CPU, which allows it to serve longer contexts and larger batch sizes with high approximation accuracy. MagicPIG can improve decoding throughput by up to $5\times$ across various GPU hardware and achieve 54ms decoding latency on a single RTX 4090 for Llama-3.1-8B-Instruct model with a context of 96k tokens. The code is available at https://github.com/Infini-AI-Lab/MagicPIG.
Authors: Ji Ma
Abstract: As Large Language Model (LLM)-based agents increasingly undertake real-world tasks and engage with human society, how well do we understand their behaviors? We (1) investigate how LLM agents' prosocial behaviors -- a fundamental social norm -- can be induced by different personas and benchmarked against human behaviors; and (2) introduce a behavioral and social science approach to evaluate LLM agents' decision-making. We explored how different personas and experimental framings affect these AI agents' altruistic behavior in dictator games and compared their behaviors within the same LLM family, across various families, and with human behaviors. The findings reveal substantial variations and inconsistencies among LLMs and notable differences compared to human behaviors. Merely assigning a human-like identity to LLMs does not produce human-like behaviors. Despite being trained on extensive human-generated data, these AI agents are unable to capture the internal processes of human decision-making. Their alignment with human is highly variable and dependent on specific model architectures and prompt formulations; even worse, such dependence does not follow a clear pattern. LLMs can be useful task-specific tools but are not yet intelligent human-like agents.
Authors: Yingqi Gao, Yifu Liu, Xiaoxia Li, Xiaorong Shi, Yin Zhu, Yiming Wang, Shiqi Li, Wei Li, Yuntao Hong, Zhiling Luo, Jinyang Gao, Liyu Mou, Yu Li
Abstract: To tackle the challenges of large language model performance in natural language to SQL tasks, we introduce XiYan-SQL, an innovative framework that employs a multi-generator ensemble strategy to improve candidate generation. We introduce M-Schema, a semi-structured schema representation method designed to enhance the understanding of database structures. To enhance the quality and diversity of generated candidate SQL queries, XiYan-SQL integrates the significant potential of in-context learning (ICL) with the precise control of supervised fine-tuning. On one hand, we propose a series of training strategies to fine-tune models to generate high-quality candidates with diverse preferences. On the other hand, we implement the ICL approach with an example selection method based on named entity recognition to prevent overemphasis on entities. The refiner optimizes each candidate by correcting logical or syntactical errors. To address the challenge of identifying the best candidate, we fine-tune a selection model to distinguish nuances of candidate SQL queries. The experimental results on multiple dialect datasets demonstrate the robustness of XiYan-SQL in addressing challenges across different scenarios. Overall, our proposed XiYan-SQL achieves the state-of-the-art execution accuracy of 75.63% on Bird benchmark, 89.65% on the Spider test set, 69.86% on SQL-Eval, 41.20% on NL2GQL. The proposed framework not only enhances the quality and diversity of SQL queries but also outperforms previous methods.
Authors: Jiacheng Liang, Zian Wang, Lauren Hong, Shouling Ji, Ting Wang
Abstract: Various watermarking methods (``watermarkers'') have been proposed to identify LLM-generated texts; yet, due to the lack of unified evaluation platforms, many critical questions remain under-explored: i) What are the strengths/limitations of various watermarkers, especially their attack robustness? ii) How do various design choices impact their robustness? iii) How to optimally operate watermarkers in adversarial environments? To fill this gap, we systematize existing LLM watermarkers and watermark removal attacks, mapping out their design spaces. We then develop WaterPark, a unified platform that integrates 10 state-of-the-art watermarkers and 12 representative attacks. More importantly, by leveraging WaterPark, we conduct a comprehensive assessment of existing watermarkers, unveiling the impact of various design choices on their attack robustness. We further explore the best practices to operate watermarkers in adversarial environments. We believe our study sheds light on current LLM watermarking techniques while WaterPark serves as a valuable testbed to facilitate future research.
Authors: Shuchen Zhu, Boao Kong, Songtao Lu, Xinmeng Huang, Kun Yuan
Abstract: This paper studies decentralized bilevel optimization, in which multiple agents collaborate to solve problems involving nested optimization structures with neighborhood communications. Most existing literature primarily utilizes gradient tracking to mitigate the influence of data heterogeneity, without exploring other well-known heterogeneity-correction techniques such as EXTRA or Exact Diffusion. Additionally, these studies often employ identical decentralized strategies for both upper- and lower-level problems, neglecting to leverage distinct mechanisms across different levels. To address these limitations, this paper proposes SPARKLE, a unified Single-loop Primal-dual AlgoRithm frameworK for decentraLized bilEvel optimization. SPARKLE offers the flexibility to incorporate various heterogeneitycorrection strategies into the algorithm. Moreover, SPARKLE allows for different strategies to solve upper- and lower-level problems. We present a unified convergence analysis for SPARKLE, applicable to all its variants, with state-of-the-art convergence rates compared to existing decentralized bilevel algorithms. Our results further reveal that EXTRA and Exact Diffusion are more suitable for decentralized bilevel optimization, and using mixed strategies in bilevel algorithms brings more benefits than relying solely on gradient tracking.
Authors: Meng Wang, Zach Noonan, Pnina Gershon, Bruce Mehler, Bryan Reimer, Shannon C. Roberts
Abstract: Understanding the context of crash occurrence in complex driving environments is essential for improving traffic safety and advancing automated driving. Previous studies have used statistical models and deep learning to predict crashes based on semantic, contextual, or vehicle kinematic features, but none have examined the combined influence of these factors. In this study, we term the integration of these features ``roadway complexity''. This paper introduces a two-stage framework that integrates roadway complexity features for crash prediction. In the first stage, an encoder extracts hidden contextual information from these features, generating complexity-infused features. The second stage uses both original and complexity-infused features to predict crash likelihood, achieving an accuracy of 87.98\% with original features alone and 90.15\% with the added complexity-infused features. Ablation studies confirm that a combination of semantic, kinematic, and contextual features yields the best results, which emphasize their role in capturing roadway complexity. Additionally, complexity index annotations generated by the Large Language Model outperform those by Amazon Mechanical Turk, highlighting the potential of AI-based tools for accurate, scalable crash prediction systems.
Authors: Wenxuan Huang, Zijie Zhai, Yunhang Shen, Shaosheng Cao, Fei Zhao, Xiangfeng Xu, Zheyu Ye, Shaohui Lin
Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable success in vision understanding, reasoning, and interaction. However, the inference computation and memory increase progressively with the generation of output tokens during decoding, directly affecting the efficacy of MLLMs. Existing methods attempt to reduce the vision context redundancy to achieve efficient MLLMs. Unfortunately, the efficiency benefits of the vision context reduction in the prefill stage gradually diminish during the decoding stage. To address this problem, we proposed a dynamic vision-language context sparsification framework Dynamic-LLaVA, which dynamically reduces the redundancy of vision context in the prefill stage and decreases the memory and computation overhead of the generated language context during decoding. Dynamic-LLaVA designs a tailored sparsification inference scheme for different inference modes, i.e., prefill, decoding with and without KV cache, to achieve efficient inference of MLLMs. In practice, Dynamic-LLaVA can reduce computation consumption by $\sim$75\% in the prefill stage. Meanwhile, throughout the entire generation process of MLLMs, Dynamic-LLaVA reduces the $\sim$50\% computation consumption under decoding without KV cache, while saving $\sim$50\% GPU memory overhead when decoding with KV cache, due to the vision-language context sparsification. Extensive experiments also demonstrate that Dynamic-LLaVA achieves efficient inference for MLLMs with negligible understanding and generation ability degradation or even performance gains compared to the full-context inference baselines. Code is available at https://github.com/Osilly/dynamic_llava .
Authors: Zong Ke, Jingyu Xu, Zizhou Zhang, Yu Cheng, Wenjun Wu
Abstract: This paper provides a unique approach with AI algorithms to predict emerging stock markets volatility. Traditionally, stock volatility is derived from historical volatility,Monte Carlo simulation and implied volatility as well. In this paper, the writer designs a consolidated model with back-propagation neural network and genetic algorithm to predict future volatility of emerging stock markets and found that the results are quite accurate with low errors.
Authors: Shuhe Wang, Shengyu Zhang, Jie Zhang, Runyi Hu, Xiaoya Li, Tianwei Zhang, Jiwei Li, Fei Wu, Guoyin Wang, Eduard Hovy
Abstract: This paper surveys research in the rapidly growing field of enhancing large language models (LLMs) with reinforcement learning (RL), a technique that enables LLMs to improve their performance by receiving feedback in the form of rewards based on the quality of their outputs, allowing them to generate more accurate, coherent, and contextually appropriate responses. In this work, we make a systematic review of the most up-to-date state of knowledge on RL-enhanced LLMs, attempting to consolidate and analyze the rapidly growing research in this field, helping researchers understand the current challenges and advancements. Specifically, we (1) detail the basics of RL; (2) introduce popular RL-enhanced LLMs; (3) review researches on two widely-used reward model-based RL techniques: Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning from AI Feedback (RLAIF); and (4) explore Direct Preference Optimization (DPO), a set of methods that bypass the reward model to directly use human preference data for aligning LLM outputs with human expectations. We will also point out current challenges and deficiencies of existing methods and suggest some avenues for further improvements. Project page of this work can be found at: \url{https://github.com/ShuheWang1998/Reinforcement-Learning-Enhanced-LLMs-A-Survey}.
URLs: https://github.com/ShuheWang1998/Reinforcement-Learning-Enhanced-LLMs-A-Survey
Authors: Lichen Bai, Shitong Shao, Zikai Zhou, Zipeng Qi, Zhiqiang Xu, Haoyi Xiong, Zeke Xie
Abstract: Diffusion models, the most popular generative paradigm so far, can inject conditional information into the generation path to guide the latent towards desired directions. However, existing text-to-image diffusion models often fail to maintain high image quality and high prompt-image alignment for those challenging prompts. To mitigate this issue and enhance existing pretrained diffusion models, we mainly made three contributions in this paper. First, we propose diffusion self-reflection that alternately performs denoising and inversion and demonstrate that such diffusion self-reflection can leverage the guidance gap between denoising and inversion to capture prompt-related semantic information with theoretical and empirical evidence. Second, motivated by theoretical analysis, we derive Zigzag Diffusion Sampling (Z-Sampling), a novel self-reflection-based diffusion sampling method that leverages the guidance gap between denosing and inversion to accumulate semantic information step by step along the sampling path, leading to improved sampling results. Moreover, as a plug-and-play method, Z-Sampling can be generally applied to various diffusion models (e.g., accelerated ones and Transformer-based ones) with very limited coding and computational costs. Third, our extensive experiments demonstrate that Z-Sampling can generally and significantly enhance generation quality across various benchmark datasets, diffusion models, and performance evaluation metrics. For example, DreamShaper with Z-Sampling can self-improve with the HPSv2 winning rate up to 94% over the original results. Moreover, Z-Sampling can further enhance existing diffusion models combined with other orthogonal methods, including Diffusion-DPO.
Authors: Nargiz Humbatova, Jinhan Kim, Gunel Jahangirova, Shin Yoo, Paolo Tonella
Abstract: With the increased popularity of Deep Neural Networks (DNNs), increases also the need for tools to assist developers in the DNN implementation, testing and debugging process. Several approaches have been proposed that automatically analyse and localise potential faults in DNNs under test. In this work, we evaluate and compare existing state-of-the-art fault localisation techniques, which operate based on both dynamic and static analysis of the DNN. The evaluation is performed on a benchmark consisting of both real faults obtained from bug reporting platforms and faulty models produced by a mutation tool. Our findings indicate that the usage of a single, specific ground truth (e.g., the human defined one) for the evaluation of DNN fault localisation tools results in pretty low performance (maximum average recall of 0.31 and precision of 0.23). However, such figures increase when considering alternative, equivalent patches that exist for a given faulty DNN. Results indicate that \dfd is the most effective tool, achieving an average recall of 0.61 and precision of 0.41 on our benchmark.
Authors: Junjie Lin, Jian Zhao, Lin Liu, Yue Deng, Youpeng Zhao, Lanxiao Huang, Xia Lin, Wengang Zhou, Houqiang Li
Abstract: Traditionally, AI development for two-player zero-sum games has relied on two primary techniques: decision trees and reinforcement learning (RL). A common approach involves using a fixed decision tree as one player's strategy while training an RL agent as the opponent to identify vulnerabilities in the decision tree, thereby improving its strategic strength iteratively. However, this process often requires significant human intervention to refine the decision tree after identifying its weaknesses, resulting in inefficiencies and hindering full automation of the strategy enhancement process. Fortunately, the advent of Large Language Models (LLMs) offers a transformative opportunity to automate the process. We propose RL-LLM-DT, an automatic decision tree generation method based on RL Evaluation and LLM Enhancement. Given an initial decision tree, the method involves two important iterative steps. Response Policy Search: RL is used to discover counter-strategies targeting the decision tree. Policy Improvement: LLMs analyze failure scenarios and generate improved decision tree code. In our method, RL focuses on finding the decision tree's flaws while LLM is prompted to generate an improved version of the decision tree. The iterative refinement process terminates when RL can't find any flaw of the tree or LLM fails to improve the tree. To evaluate the effectiveness of this integrated approach, we conducted experiments in a curling game. After iterative refinements, our curling AI based on the decision tree ranks first on the Jidi platform among 34 curling AIs in total, which demonstrates that LLMs can significantly enhance the robustness and adaptability of decision trees, representing a substantial advancement in the field of Game AI. Our code is available at https://github.com/Linjunjie99/RL-LLM-DT.
Authors: Jiayu Chen, Chao Yu, Yuqing Xie, Feng Gao, Yinuo Chen, Shu'ang Yu, Wenhao Tang, Shilong Ji, Mo Mu, Yi Wu, Huazhong Yang, Yu Wang
Abstract: Executing precise and agile flight maneuvers is critical for quadrotors in various applications. Traditional quadrotor control approaches are limited by their reliance on flat trajectories or time-consuming optimization, which restricts their flexibility. Recently, RL-based policy has emerged as a promising alternative due to its ability to directly map observations to actions, reducing the need for detailed system knowledge and actuation constraints. However, a significant challenge remains in bridging the sim-to-real gap, where RL-based policies often experience instability when deployed in real world. In this paper, we investigate key factors for learning robust RL-based control policies that are capable of zero-shot deployment in real-world quadrotors. We identify five critical factors and we develop a PPO-based training framework named SimpleFlight, which integrates these five techniques. We validate the efficacy of SimpleFlight on Crazyflie quadrotor, demonstrating that it achieves more than a 50% reduction in trajectory tracking error compared to state-of-the-art RL baselines, and achieves 70% improvement over the traditional MPC. The policy derived by SimpleFlight consistently excels across both smooth polynominal trajectories and challenging infeasible zigzag trajectories on small thrust-to-weight quadrotors. In contrast, baseline methods struggle with high-speed or infeasible trajectories. To support further research and reproducibility, we integrate SimpleFlight into a GPU-based simulator Omnidrones and provide open-source access to the code and model checkpoints. We hope SimpleFlight will offer valuable insights for advancing RL-based quadrotor control. For more details, visit our project website at https://sites.google.com/view/simpleflight/.
Authors: Zhenyu Wang, Yifan Hu, Peter B\"uhlmann, Zijian Guo
Abstract: Data from multiple environments offer valuable opportunities to uncover causal relationships among variables. Leveraging the assumption that the causal outcome model remains invariant across heterogeneous environments, state-of-the-art methods attempt to identify causal outcome models by learning invariant prediction models and rely on exhaustive searches over all (exponentially many) covariate subsets. These approaches present two major challenges: 1) determining the conditions under which the invariant prediction model aligns with the causal outcome model, and 2) devising computationally efficient causal discovery algorithms that scale polynomially, instead of exponentially, with the number of covariates. To address both challenges, we focus on the additive intervention regime and propose nearly necessary and sufficient conditions for ensuring that the invariant prediction model matches the causal outcome model. Exploiting the essentially necessary identifiability conditions, we introduce Negative Weight Distributionally Robust Optimization (NegDRO), a nonconvex continuous minimax optimization whose global optimizer recovers the causal outcome model. Unlike standard group DRO problems that maximize over the simplex, NegDRO allows negative weights on environment losses, which break the convexity. Despite its nonconvexity, we demonstrate that a standard gradient method converges to the causal outcome model, and we establish the convergence rate with respect to the sample size and the number of iterations. Our algorithm avoids exhaustive search, making it scalable especially when the number of covariates is large. The numerical results further validate the efficiency of the proposed method.