论文检索

Yifeng Wang, Yi Zhao

Low-cost accelerometers play a crucial role in modern society due to their advantages of small size, ease of integration, wearability, and mass production, making them widely applicable in automotive systems, aerospace, and wearable technology. However, this widely used sensor suffers from severe accuracy and range limitations. To this end, we propose a honed-energy regularized and optimal supervised GAN (HEROS-GAN), which transforms low-cost sensor signals into high-cost equivalents, thereby overcoming the precision and range limitations of low-cost accelerometers. Due to the lack of frame-level paired low-cost and high-cost signals for training, we propose an Optimal Transport Supervision (OTS), which leverages optimal transport theory to explore potential consistency between unpaired data, thereby maximizing supervisory information. Moreover, we propose a Modulated Laplace Energy (MLE), which injects appropriate energy into the generator to encourage it to break range limitations, enhance local changes, and enrich signal details. Given the absence of a dedicated dataset, we specifically establish a Low-cost Accelerometer Signal Enhancement Dataset (LASED) containing tens of thousands of samples, which is the first dataset serving to improve the accuracy and range of accelerometers and is released in Github. Experimental results demonstrate that a GAN combined with either OTS or MLE alone can surpass the previous signal enhancement SOTA methods by an order of magnitude. Integrating both OTS and MLE, the HEROS-GAN achieves remarkable results, which doubles the accelerometer range while reducing signal noise by two orders of magnitude, establishing a benchmark in the accelerometer signal processing.

Shanfeng Wang, Jianzhao Li, Zaitian Liu, Yourun Zhang, Maoguo Gong

Federated few-shot learning (FedFSL) aims to enable the clients to obtain personalized generalization models for unseen categories with only a small number of referenceable samples in the distributed collaborative training paradigm. Most existing FedFSL-related algorithms suffer from domain bias and feature coupling in the presence of data heterogeneity and sample scarcity. In this work, we propose a collaborative feature representation disentanglement (CFRD) scheme for FedFSL to address these issues. After each client receives the global aggregation parameters, the original feature representation is decoupled into global communal features and local personality features with personalized bias representation, to maintain both global consistency and local relevance in the first feature representation disentanglement. On the few-shot metric space about the second feature representation disentanglement, category-independent information is encoded by class-specific and class-irrelevant reconstructions to separate the discriminative features. The proposed scheme collaboratively accomplishes global domain bias feature disentanglement and local category degradation feature disentanglement from client-wise and class-wise. Experiments on three few-shot benchmark datasets conforming to the FedFSL paradigm demonstrate that our proposed method outperforms state-of-the-art approaches in both global generality and local specificity.

Jiesheng Wang, Lin Li, Wei Wei, Yujia Zhang, Xin Yang

Offline reinforcement learning confronts the distributional shift challenge, a consequence of learning policy from static datasets. Current methods primarily handle this issue by aligning the learned policy with the behavior policy or conservatively estimating Q-values for out-of-distribution (OOD) actions. However, these approaches can lead to overly pessimistic estimation of Q-values of the OOD actions in unfamiliar situations, resulting in a suboptimal policy. To address this, we propose a new method, Dynamic Uncertainty estimation for Offline Reinforcement Learning. This method introduces a base density-truncated OOD data sampling approach to reduce the impact of extrapolation errors on uncertainty estimation. It enables conservative estimation of Q-values for OOD actions while avoiding negative impacts on in-distribution data. We also develop a dynamic uncertainty estimation mechanism to prevent excessive pessimism and enhance the generalization of the Q-function. This mechanism dynamically adjusts the degree of pessimism in the Q-function by minimizing the error between target and estimated values. Our method outperforms existing algorithms, as demonstrated by experimental results based on the D4RL benchmark, and proves its superiority in addressing the distributional shift challenge.

Bin Wang, Chunyu Xie, Dawei Leng, Yuhui Yin

In the field of multimodal large language models (MLLMs), common methods typically involve unfreezing the language model during training to foster profound visual understanding. However, the fine-tuning of such models with vision-language data often leads to a diminution of their natural language processing (NLP) capabilities. To avoid this performance degradation, a straightforward solution is to freeze the language model while developing multimodal competencies. Unfortunately, previous works have not attained satisfactory outcomes. Building on the strategy of freezing the language model, we conduct thorough structural exploration and introduce the Inner-Adaptor Architecture (IAA). Specifically, the architecture incorporates multiple multimodal adaptors at varying depths within the large language model to facilitate direct interaction with the inherently text-oriented transformer layers, thereby enabling the frozen language model to acquire multimodal capabilities. Unlike previous approaches of freezing language models that require large-scale aligned data, our proposed architecture is able to achieve superior performance on small-scale datasets. We conduct extensive experiments to improve the general multimodal capabilities and visual grounding abilities of the MLLM. Our approach remarkably outperforms previous state-of-the-art methods across various vision-language benchmarks without sacrificing performance on NLP tasks. Code and models will be released.

Songjun Tu, Jingbo Sun, Qichao Zhang, Yaocheng Zhang, Jia Liu, Ke Chen, Dongbin Zhao

Offline preference-based reinforcement learning (PbRL) typically operates in two phases: first, use human preferences to learn a reward model and annotate rewards for a reward-free offline dataset; second, learn a policy by optimizing the learned reward via offline RL. However, accurately modeling step-wise rewards from trajectory-level preference feedback presents inherent challenges. The reward bias introduced, particularly the overestimation of predicted rewards, leads to optimistic trajectory stitching, which undermines the pessimism mechanism critical to the offline RL phase. To address this challenge, we propose In-Dataset Trajectory Return Regularization (DTR) for offline PbRL, which leverages conditional sequence modeling to mitigate the risk of learning inaccurate trajectory stitching under reward bias. Specifically, DTR employs Decision Transformer and TD-Learning to strike a balance between maintaining fidelity to the behavior policy with high in-dataset trajectory returns and selecting optimal actions based on high reward labels. Additionally, we introduce an ensemble normalization technique that effectively integrates multiple reward models, balancing the trade-off between reward differentiation and accuracy. Empirical evaluations on various benchmarks demonstrate the superiority of DTR over other state-of-the-art baselines.

Changyuan Tian, Zhicong Lu, Zequn Zhang, Heming Yang, Wei Cao, Zhi Guo, Xian Sun, Li Jin

Long-term Multivariate Time Series (LMTS) forecasting aims to predict extended future trends based on channel-interrelated historical data. Considering the elusive channel correlations, most existing methods compromise by treating channels as independent or tentatively modeling pairwise channel interactions, making it challenging to handle the characteristics of both higher-order interactions and time variation in channel correlations. In this paper, we propose HyperMixer, a novel specializable hypergraph channel mixing plugin which introduces versatile hypergraph structures to capture group channel interactions and time-varying patterns for long-term multivariate time series forecasting. Specifically, to encode the higher-order channel interactions, we structure multiple channels into a hypergraph, achieving a two-phase message-passing mechanism: channel-to-group and group-to-channel. Moreover, the functionally specializable hypergraph structures are presented to boost the capability of hypergraph to capture the time-varying patterns across periods, further refining modeling of channel correlations. Extensive experimental results on seven available benchmark datasets demonstrate the effectiveness and generalization of our plugin in LMTS forecasting. The visual analysis further illustrates that HyperMixer with specializable hypergraphs tailors channel interactions specific to certain periods.

Zijian Tao, Shao-Yuan Li, Wenhai Wan, Jinpeng Zheng, Jia-Yao Chen, Yuchen Li, Sheng-Jun Huang, Songcan Chen

Long-tailed (LT) data distribution is common in multi-label image classification (MLC) and can significantly impact the performance of classification models. One reason is the challenge of learning unbiased instance representations (i.e. features) for imbalanced datasets. Additionally, the co-occurrence of head/tail classes within the same instance, along with complex label dependencies, introduces further challenges. In this work, we delve into this problem through the lens of neural collapse (NC). NC refers to a phenomenon where the last-layer features and classifier of a deep neural network model exhibit a simplex Equiangular Tight Frame (ETF) structure during its terminal training phase. This structure creates an optimal linearly separable state. However, this phenomenon typically occurs in balanced datasets but rarely applies to the typical imbalanced problem. To induce NC properties under Long-tailed multi-label classification (LT-MLC) conditions, we propose an approach named MLC-NC, which aims to learn high-quality data representations and improve the model’s generalization ability. Specifically, MLC-NC accounts for the fact that different labels correspond to different feature parts located in images. MLC-NC extracts class-wise features from each instance through a cross-attention mechanism. To guide the features toward the ETF structure, we introduce visual-semantic feature alignment with a fixed ETF structured label embedding, which helps to learn evenly distributed class centers. To reduce within-class feature variation, we introduce collapse calibration within a lower-dimensional feature space. To mitigate classification bias, we concatenate features and feed them into a binarized fixed ETF classifier. As an orthogonal approach to existing methods, MLC-NC can be seamlessly integrated into various frameworks. Extensive experiments on widely-used benchmarks demonstrate the effectiveness of our method.

Xiaoli Tang, Han Yu

Auction-based Federated Learning (AFL) has gained significant research interest due to its ability to incentivize data owners (DOs) to participate in FL model training tasks of data consumers (DCs) through economic mechanisms via the auctioneer. One of the critical research issues in AFL is decision support for the auctioneer. Existing approaches are based on the simplified assumption of a single, monopolistic AFL marketplace, which is unrealistic in real-world scenarios where multiple AFL marketplaces can co-exist and compete for the same pool of DOs. In this paper, we relax this assumption and frame the AFL auctioneer decision support problem from the perspective of helping them attract participants in a competitive AFL marketplace environment while safeguarding profit. To achieve this objective, we propose the Auctioneer Revenue Allocation Strategy for AFL (ARAS-AFL). We design the concepts of the attractiveness and competitiveness from the perspective of autioneer reputation. Based on the Lyapunov optimization, ARAS-AFL helps individual AFL auctioneer achieve the dual objective of balancing the reputation management costs and its own profit by designing a dynamic revenue allocation strategy. It takes into account both the auctioneer’s revenue and the changes in the number of participants on the AFL marketplace. Through extensive experiments on widely used benchmark datasets, ARAS-AFL demonstrates superior performance compared to state-of-the-art approaches. It outperforms the best baseline by 49.06%, 98.69%, 10.32%, and 4.77% in terms of total revenue, number of data owners, public reputation and accuracy of federated learning models, respectively.

Ege Onur Taga, Muhammed Emrullah Ildiz, Samet Oymak

The diversity of time series applications and scarcity of domain-specific data highlight the need for time-series models with strong few-shot learning capabilities. In this work, we propose a novel training scheme and a transformer-based architecture, collectively referred to as TimePFN, for multivariate time-series (MTS) forecasting. TimePFN is based on the concept of Prior-data Fitted Networks (PFN), which aims to approximate Bayesian inference. Our approach consists of (1) generating synthetic MTS data through diverse Gaussian process kernels and the linear coregionalization method, and (2) a novel MTS architecture capable of utilizing both temporal and cross-channel dependencies across all input patches. We evaluate TimePFN on several benchmark datasets and demonstrate that it outperforms the existing state-of-the-art models for MTS forecasting in both zero-shot and few-shot settings. Notably, fine-tuning TimePFN with as few as 500 data points nearly matches full dataset training error, and even 50 data points yield competitive results. We also find that TimePFN exhibits strong univariate forecasting performance, attesting to its generalization ability. Overall, this work unlocks the power of synthetic data priors for MTS forecasting and facilitates strong zero- and few-shot forecasting performance.

Hai-Long Sun, Da-Wei Zhou, Hanbin Zhao, Le Gan, De-Chuan Zhan, Han-Jia Ye

Class-Incremental Learning (CIL) requires models to continually acquire knowledge of new classes without forgetting old ones. Despite Pre-trained Models (PTMs) have shown excellent performance in CIL, catastrophic forgetting still occurs as the model learns new concepts. Existing work seeks to utilize lightweight components to adjust the PTM, while the forgetting phenomenon still comes from parameter and retrieval levels. Specifically, iterative updates of the model result in parameter drift, while mistakenly retrieving irrelevant modules leads to the mismatch during inference. To this end, we propose MOdel Surgery (MOS) to rescue the model from forgetting previous knowledge. By training task-specific adapters, we continually adjust the PTM to downstream tasks. To mitigate parameter-level forgetting, we present an adapter merging approach to learn task-specific adapters, which aims to bridge the gap between different components while reserve task-specific information. Besides, to address retrieval-level forgetting, we introduce a training-free self-refined adapter retrieval mechanism during inference, which leverages the model's inherent ability for better adapter retrieval. By jointly rectifying the model with those steps, MOS can robustly resist catastrophic forgetting in the learning process. Extensive experiments on seven benchmark datasets validate MOS's state-of-the-art performance.

Akshit Sinha, Sreeram Vennam, Charu Sharma, Ponnurangam Kumaraguru

Graph Neural Networks (GNNs) have emerged as powerful tools for learning representations of graph-structured data, demonstrating remarkable performance across various tasks. Recognizing their importance, there has been extensive research focused on explaining GNN predictions, aiming to enhance their interpretability and trustworthiness. However, GNNs and their explainers face a notable challenge: graphs are primarily designed to model pair-wise relationships between nodes, which can make it tough to capture higher-order, multi-node interactions. This characteristic can pose difficulties for existing explainers in fully representing multi-node relationships. To address this gap, we present Framework For Higher-Order Representations In Graph Explanations (FORGE), a framework that enables graph explainers to capture such interactions by incorporating higher-order structures, resulting in more accurate and faithful explanations. Extensive evaluation shows that on average real-world datasets from the GraphXAI benchmark and synthetic datasets across various graph explainers, FORGE improves average explanation accuracy by 1.9x and 2.25x, respectively. We perform ablation studies to confirm the importance of higher-order relations in improving explanations, while our scalability analysis demonstrates FORGE's efficacy on large graphs.

Yong-Min Shin, Siqing Li, Xin Cao, Won-Yong Shin

The self-attention mechanism has been adopted in various popular message passing neural networks (MPNNs), enabling the model to adaptively control the amount of information that flows along the edges of the underlying graph. Such attention-based MPNNs (Att-GNNs) have also been used as a baseline for multiple studies on explainable AI (XAI) since attention has steadily been seen as natural model interpretations, while being a viewpoint that has already been popularized in other domains (e.g., natural language processing and computer vision). However, existing studies often use naive calculations to derive attribution scores from attention, undermining the potential of attention as interpretations for Att-GNNs. In our study, we aim to fill the gap between the widespread usage of Att-GNNs and their potential explainability via attention. To this end, we propose GAtt, edge attribution calculation method for self-attention MPNNs based on the computation tree, a rooted tree that reflects the computation process of the underlying model. Despite its simplicity, we empirically demonstrate the effectiveness of GAtt in three aspects of model explanation: faithfulness, explanation accuracy, and case studies by using both synthetic and real-world benchmark datasets. In all cases, the results demonstrate that GAtt greatly improves edge attribution scores, especially compared to the previous naive approach.

Shuaijie Shen, Chao Wang, Renzhuo Huang, Yan Zhong, Qinghai Guo, Zhichao Lu, Jianguo Zhang, Luziwei Leng

Known as low energy consumption networks, spiking neural networks (SNNs) have gained a lot of attention within the past decades. While SNNs are increasing competitive with artificial neural networks (ANNs) for vision tasks, they are rarely used for long sequence tasks, despite their intrinsic temporal dynamics. In this work, we develop spiking state space models (SpikingSSMs) for long sequence learning by leveraging on the sequence learning abilities of state space models (SSMs). Inspired by dendritic neuron structure, we hierarchically integrate neuronal dynamics with the original SSM block, meanwhile realizing sparse synaptic computation. Furthermore, to solve the conflict of event-driven neuronal dynamics with parallel computing, we propose a light-weight surrogate dynamic network which accurately predicts the after-reset membrane potential and compatible to learnable thresholds, enabling orders of acceleration in training speed compared with conventional iterative methods. On the long range arena benchmark task, SpikingSSM achieves competitive performance to state-of-the-art SSMs meanwhile realizing on average 90% of network sparsity. On language modeling, our network significantly surpasses existing spiking large language models (spikingLLMs) on the WikiText-103 dataset with only a third of the model size, demonstrating its potential as backbone architecture for low computation cost LLMs.

Hongyu Shen, Zhizhen Zhao

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.

Kaan Sancak, Zhigang Hua, Jin Fang, Yan Xie, Andrey Malevich, Bo Long, Muhammed Fatih Balin, Ümit V. Çatalyürek

Graph Neural Networks (GNNs) have shown impressive performance in graph representation learning, but they face challenges in capturing long-range dependencies due to their limited expressive power. To address this, Graph Transformers (GTs) were introduced, utilizing self-attention mechanism to effectively model pairwise node relationships. Despite their advantages, GTs suffer from quadratic complexity w.r.t. the number of nodes in the graph, hindering their applicability to large graphs. In this work, we present Graph-Enhanced Contextual Operator (GECO), a scalable and effective alternative to GTs that leverages neighborhood propagation and global convolutions to effectively capture local and global dependencies in quasiliniear time. Our study on synthetic datasets reveals that GECO reaches 169x speedup on a graph with 2M nodes w.r.t. optimized attention. Further evaluations on diverse range of benchmarks showcase that it scales to large graphs where traditional GTs often face memory and time limitations. Notably, GECO consistently achieves comparable or superior quality compared to baselines, improving the SOTA up to 4.5%, and offering a scalable and effective solution for large-scale graph learning.

Luis Roque, Vítor Cerqueira, Carlos Soares, Luís Torgo

The importance of time series forecasting drives continuous research and the development of new approaches to tackle this problem. Typically, these methods are introduced through empirical studies that frequently claim superior accuracy for the proposed approaches. Nevertheless, concerns are rising about the reliability and generalizability of these results due to limitations in experimental setups. This paper addresses a critical limitation: the number and representativeness of the datasets used. We investigate the impact of dataset selection bias, particularly the practice of cherry-picking datasets, on the performance evaluation of forecasting methods. Through empirical analysis with a diverse set of benchmark datasets, our findings reveal that cherry-picking datasets can significantly distort the perceived performance of methods, often exaggerating their effectiveness. Furthermore, our results demonstrate that by selectively choosing just four datasets — what most studies report — 46% of methods could be deemed best in class, and 77% could rank within the top three. Additionally, recent deep learning-based approaches show high sensitivity to dataset selection, whereas classical methods exhibit greater robustness. Finally, our results indicate that, when empirically validating forecasting algorithms on a subset of the benchmarks, increasing the number of datasets tested from 3 to 6 reduces the risk of incorrectly identifying an algorithm as the best one by approximately 40%. Our study highlights the critical need for comprehensive evaluation frameworks that more accurately reflect real-world scenarios. Adopting such frameworks will ensure the development of robust and reliable forecasting methods.

Yiran Qiao, Yu Yin, Chen Chen, Jing Ma

While machine learning models have proven effective across various scenarios, it is widely acknowledged that many models are vulnerable to adversarial attacks. Recently, numerous efforts have emerged in adversarial defense. Among them, certified defense is well known for its theoretical guarantees against arbitrary adversarial perturbations on input within a certain range. However, most existing works in this line struggle to generalize their certified robustness in other data domains with distribution shifts. This issue is rooted in the difficulty of eliminating the negative impact of spurious correlations on robustness in different domains. To address this problem, in this work, we propose a novel certified defense framework GLEAN, which incorporates a causal perspective into the generalization problem in certified defense. More specifically, our framework integrates a certifiable causal factor learning component to disentangle the causal relations and spurious correlations between input and label, thereby excluding the negative effect of spurious correlations on defense. On top of that, we design a causally certified defense strategy to handle adversarial attacks on latent causal factors. In this way, our framework is not only robust against malicious noises on data in the training distribution but also can generalize its robustness across domains with distribution shifts. Extensive experiments on benchmark datasets validate the superiority of our framework in certified robustness generalization in different data domains.

Wasu Top Piriyakulkij, Yingheng Wang, Volodymyr Kuleshov

We propose denoising diffusion variational inference (DDVI), a black-box variational inference algorithm for latent variable models which relies on diffusion models as flexible approximate posteriors. Specifically, our method introduces an expressive class of diffusion-based variational posteriors that perform iterative refinement in latent space; we train these posteriors with a novel regularized evidence lower bound (ELBO) on the marginal likelihood inspired by the wake-sleep algorithm. Our method is easy to implement (it fits a regularized extension of the ELBO), is compatible with black-box variational inference, and outperforms alternative classes of approximate posteriors based on normalizing flows or adversarial networks. We find that DDVI improves inference and learning in deep latent variable models across common benchmarks as well as on a motivating task in biology---inferring latent ancestry from human genomes---where it outperforms strong baselines on the Thousand Genomes dataset.

Marcin Pietron, Kamil Faber, Dominik Żurek, Roberto Corizzo

Continual Learning (CL) is a highly relevant setting gaining traction in recent machine learning research. Among CL works, architectural and hybrid strategies are particularly effective due to their potential to adapt the model architecture as new tasks are presented. However, many existing solutions do not efficiently exploit model sparsity, and are prone to capacity saturation due to their inefficient use of available weights, which limits the number of learnable tasks. In this paper, we propose TinySubNets (TSN), a novel architectural CL strategy that addresses the issues through the unique combination of pruning with different sparsity levels, adaptive quantization, and weight sharing. Pruning identifies a subset of weights that preserve model performance, making less relevant weights available for future tasks. Adaptive quantization allows a single weight to be separated into multiple parts which can be assigned to different tasks. Weight sharing between tasks boosts the exploitation of capacity and task similarity, allowing for the identification of a better trade-off between model accuracy and capacity. These features allow TSN to efficiently leverage the available capacity, enhance knowledge transfer, and reduce computational resources consumption. Experimental results involving common benchmark CL datasets and scenarios show that our proposed strategy achieves better results in terms of accuracy than existing state-of-the-art CL strategies. Moreover, our strategy is shown to provide a significantly improved model capacity exploitation.

Haotian Peng, Jiawei Liu, Jinsong Du, Jie Gao, Wei Wang

We propose a bearing health management framework leveraging large language models (BearLLM), a novel multimodal model that unifies multiple bearing-related tasks by processing user prompts and vibration signals. Specifically, we introduce a prior knowledge-enhanced unified vibration signal representation to handle various working conditions across multiple datasets. This involves adaptively sampling the vibration signals based on the sampling rate of the sensor, incorporating the frequency domain to unify input dimensions, and using a fault-free reference signal as an auxiliary input. To extract features from vibration signals, we first train a fault classification network, then convert and align the extracted features into word embedding, and finally concatenate these with text embedding as input to an LLM. To evaluate the performance of the proposed method, we constructed the first large-scale multimodal bearing health management (MBHM) dataset, including paired vibration signals and textual descriptions. With our unified vibration signal representation, BearLLM using one set of pre-trained weights achieves state-of-the-art performance on nine publicly available fault diagnosis benchmarks, outperforming specific methods designed for individual datasets. We provide a dataset, our model, and code to inspire future research on building more capable industrial multimodal models.