IEEE Transactions on Big Data最新文献

{"title":"Correlation Matters in Deep Clustering: Transforming Clustering Into Self-Supervised Multi-Label Learning","authors":"Jihong Ouyang;Qingyi Meng;Ximing Li;Zhengjie Zhang;Bo Fu;Wenting Wang","doi":"10.1109/TBDATA.2025.3627494","DOIUrl":"https://doi.org/10.1109/TBDATA.2025.3627494","url":null,"abstract":"Deep clustering nowadays has proven to significantly surpass the classical clustering method, so it has been widely used in diverse applications. One current branch of deep clustering methods enhances the primary task through auxiliary tasks, among which the most prevalent is over-clustering, i.e., jointly training clustering with different numbers of clusters in a multi-task manner. However, existing approaches typically treat these auxiliary tasks in isolation and neglect the inherent correlations among their cluster assignments. In this paper, we interpret the cluster assignment memberships of samples generated by all clustering tasks as correlated pseudo-labels. Motivated by this observation, we propose to explicitly exploit such correlation knowledge to improve clustering performance. To achieve this, we can formulate the collection of samples with pseudo-labels as a pseudo-multi-label learning problem, and solve it by employing any off-the-shelf multi-label learning methods which enable to capture correlations between pseudo-labels. Based on this idea, beyond the clustering tasks, we propose a correlation learning auxiliary task, namely Self-supervised Multi-Label Learning (SMLL); and we then specify a novel deep clustering method with SMLL, namely D<sc>csl<inline-formula><tex-math>$^{3}$</tex-math><alternatives><mml:math><mml:msup><mml:mrow/><mml:mn>3</mml:mn></mml:msup></mml:math><inline-graphic></alternatives></inline-formula></small>. We conduct several experiments to examine the performance of D<sc>csl<inline-formula><tex-math>$^{3}$</tex-math><alternatives><mml:math><mml:msup><mml:mrow/><mml:mn>3</mml:mn></mml:msup></mml:math><inline-graphic></alternatives></inline-formula></small> on benchmark datasets. Empirical results demonstrate the superiority of D<sc>csl<inline-formula><tex-math>$^{3}$</tex-math><alternatives><mml:math><mml:msup><mml:mrow/><mml:mn>3</mml:mn></mml:msup></mml:math><inline-graphic></alternatives></inline-formula></small> over the existing deep clustering baseline methods.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"12 2","pages":"496-508"},"PeriodicalIF":8.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148505554","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"GraphLLM: Boosting Graph Reasoning Ability of Large Language Model","authors":"Ziwei Chai;Tianjie Zhang;Liang Wu;Kaiqiao Han;Xiaohai Hu;Xuanwen Huang;Yang Yang","doi":"10.1109/TBDATA.2025.3627488","DOIUrl":"https://doi.org/10.1109/TBDATA.2025.3627488","url":null,"abstract":"The advancement of Large Language Models (LLMs) has remarkably pushed the boundaries towards artificial general intelligence (AGI), with their exceptional ability on understanding diverse types of information, including but not limited to images and audio. Despite this progress, a critical gap remains in empowering LLMs to proficiently understand and reason on graph data, which is ubiquitous in Big Data applications such as social networks, knowledge graphs, and molecular databases. Recent studies underscore LLMs’ underwhelming performance on fundamental graph reasoning tasks. In this paper, we endeavor to unearth the obstacles that impede LLMs in graph reasoning, pinpointing the common practice of converting graphs into natural language descriptions (<italic>Graph2Text</i>) as a fundamental bottleneck. To overcome this impediment, we introduce GraphLLM, a pioneering end-to-end approach that synergistically integrates graph learning models with LLMs through a novel Dynamic Task Configuration System. This system employs a Hierarchical Graph Processing Pipeline that combines Local Structure Analyzers for node-level features with Global Pattern Synthesizers for graph-level understanding, enabling scalable processing of large-scale graph data. Our empirical evaluations across four fundamental graph reasoning tasks validate the effectiveness of GraphLLM. The results exhibit a substantial average accuracy enhancement of 54.44%, alongside a noteworthy context reduction of 96.45% across various graph reasoning tasks, demonstrating significant potential for Big Data graph analytics.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"12 2","pages":"475-483"},"PeriodicalIF":8.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148505822","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"NTFormer: A Composite Node Tokenized Graph Transformer for Node Classification","authors":"Jinsong Chen;Siyu Jiang;Kun He","doi":"10.1109/TBDATA.2025.3624955","DOIUrl":"https://doi.org/10.1109/TBDATA.2025.3624955","url":null,"abstract":"Tokenized graph Transformers have advanced node classification by transforming graphs into token sequences, but existing methods suffer from limited flexibility due to single-type token generation, which captures partial graph information and requires tailored modifications. To address this, we propose NTFormer, a novel graph Transformer with a dedicated token generator called Node2Par. Node2Par constructs diverse token sequences for each node using multiple token elements (i.e., neighborhood tokens and node tokens) from both topology view and attribute view, enabling comprehensive expression of graph features from multi-perspectives. Leveraging the outputs of Node2Pars, NTFormer adopts a standard Transformer backbone without additional graph-aware modules and a learnable information fusion strategy to adaptively learn expressive node representations from generated different token sequences, eliminating the need for tailored encoding strategies. Extensive experiments on benchmark datasets including homophily and heterophily graphs showcase that NTFormer outperforms representative graph Transformers and GNNs in node classification.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"12 2","pages":"447-459"},"PeriodicalIF":8.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148504405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Structure-Aware Attack on Graph Neural Networks via Imperceptible Node Injection","authors":"Fei Yan;Yanlong Tang;Witold Pedrycz;Kaoru Hirota","doi":"10.1109/TBDATA.2025.3630819","DOIUrl":"https://doi.org/10.1109/TBDATA.2025.3630819","url":null,"abstract":"Graph neural networks (GNNs) excel in various graph-based tasks due to their exceptional ability to process non-Euclidean data. However, recent research indicates that their predictive performance is highly vulnerable to perturbations from intentionally manipulated data. Current node injection attack methods disrupt GNN training by injecting numerous nodes, often in excessive amounts, making them easily detectable. To address this issue, this study introduces a structure-aware node injection attack (SNIA), which enables effective and subtle attacks under extreme budget constraints. The scheme leverages the network topology to construct an attack candidate set and applies homogeneity constraints to regulate the generation of perturbed features. By eliminating the dependency on surrogate models for generating perturbed data, SNIA effectively diminishes the global classification performance of GNNs based on the network’s inherent structure. We conducted attack experiments with the SNIA scheme on real-world network datasets against both general and defensive GNNs. The experimental findings reveal that it significantly surpasses the existing state-of-the-art methods in attack efficiency, while also showcasing outstanding generalization and resilience.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"12 2","pages":"525-535"},"PeriodicalIF":8.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148505143","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Versatile and Risk-Sensitive Cardiac Diagnosis via Graph-Based ECG Signal Representation","authors":"Yue Wang;Yuyang Xu;Renjun Hu;Fanqi Shen;Hanyun Jiang;Jun Wang;Jintai Chen;Danny Z. Chen;Jian Wu;Haochao Ying","doi":"10.1109/TBDATA.2025.3639986","DOIUrl":"https://doi.org/10.1109/TBDATA.2025.3639986","url":null,"abstract":"Despite the rapid advancements of electrocardiogram (ECG) signal diagnosis and analysis methods through deep learning, two major hurdles still limit their clinical adoption: the lack of versatility in processing ECG signals with diverse configurations, and the inadequate detection of risk signals due to sample imbalances. Addressing these challenges, we introduce <underline>V</u>ers<underline>A</u>tile and <underline>R</u>isk-<underline>S</u>ensitive cardiac diagnosis (VARS), an innovative approach that employs a graph-based representation to uniformly model heterogeneous ECG signals. VARS stands out by transforming ECG signals into versatile graph structures that capture critical diagnostic features, irrespective of signal diversity in the lead count, sampling frequency, and duration. This graph-centric formulation also enhances diagnostic sensitivity, enabling precise localization and identification of abnormal ECG patterns that often elude standard analysis methods. To facilitate representation transformation, our approach integrates denoising reconstruction with contrastive learning to preserve raw ECG information while highlighting pathognomonic patterns. We rigorously evaluate the efficacy of VARS on three distinct ECG datasets, encompassing a range of structural variations. The results demonstrate that VARS not only consistently surpasses existing state-of-the-art models across all these datasets but also exhibits substantial improvement in identifying risk signals. Additionally, VARS offers interpretability by pinpointing the exact waveforms that lead to specific model outputs, thereby assisting clinicians in making informed decisions. These findings suggest that our VARS will likely emerge as an invaluable tool for comprehensive cardiac health assessment.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"12 2","pages":"600-611"},"PeriodicalIF":8.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148505291","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"RDNet: Rotate-Groundtruth Augmentation and Decoupled Attention HEAD for 3D Object Detection","authors":"Zhenchang Xia;Guanqun Zheng;Shengwu Xiong;Junyin Wang;Jianqun Cui;Yanan Chang;Chenghu Du;Jia Wu","doi":"10.1109/TBDATA.2025.3624947","DOIUrl":"https://doi.org/10.1109/TBDATA.2025.3624947","url":null,"abstract":"LiDAR is one of the most important sensors in the field of autonomous driving and allows for better and more accurate perception of the changes in the surrounding environment. Most of the existing 3D object detection methods use data augmentation and feature fusion enhancement to improve the performance of detection, but the majority of the methods ignore the handling of sample imbalance problems during data augmentation. Also, the designed feature fusion and enhancement methods were not well suited to work with the enhancement methods. To this end, we developed a combined method involving data augmentation and feature enhancement. The designed approach has two main objectives: 1) to address the problem of unbalanced sample distribution in detection scenes through data augmentation, and 2) to enhance feature perception using a special feature enhancement module. Our proposed method solves the problem of class imbalance by directly increasing the number of pedestrian samples in the scene through mixed data augmentation, i.e., RG-Aug. In addition, we introduce the Decoupling and Attention Fusion module (DAF), which combines classification headers with high-level features and prediction branches with low-level features. Leverage data features between different layers of features to get a more robust feature representation. Finally, the multi-scale pyramid attention enhancement module is designed to achieve feature enhancement of multi-scale features by means of attention to improve the detection ability of small objects in the scene, especially the detection ability of pedestrians. Our method can achieve 1.57%, 2.16%, and 2.05% performance improvement on the KITTI dataset for Easy, Mod, and Hard samples, respectively. Furthermore, for the detection of pedestrians, our method has a significant competitive advantage over other state-of-the-art techniques with a mAP of 73.42%.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"12 2","pages":"389-402"},"PeriodicalIF":8.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148507368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Probability-Guided Contrastive Learning for Long-Tailed Domain Generalization","authors":"Mengzhu Wang;Houcheng Su;Shanshan Wang;Nan Yin;Long Lan;Liang Yang;Li Shen","doi":"10.1109/TBDATA.2025.3624965","DOIUrl":"https://doi.org/10.1109/TBDATA.2025.3624965","url":null,"abstract":"After training on a specific source domain, models can leverage domain generalization (DG) techniques to achieve superior and broader performance on new, unseen target domains. Existing DG often utilizes contrastive learning to learn domain-invariant features. The goal of contrastive learning is to learn effective representations of data, causing samples from the same category to cluster together in feature space, while samples from different categories are dispersed. Traditional contrastive learning is limited to a finite set of contrastive pairs for DG. To handle this problem, we consider sampling from an infinite number of contrastive pairs using a mixture of von Mises-Fisher (vMF) distributions on the unit hypersphere. We propose a novel method called Probability-guided Contrastive Learning (PgCL), which selects contrastive pairs based on estimated data distributions of samples from each category in feature space. Additionally, we derive the exact analytical formula for the expected contrastive loss. We conduct an empirical investigation of the error bounds of PgCL and demonstrate its performance by comparing it with several leading methods across a range of DG datasets. The code is available at <uri>https://github.com/dreamkily/PgCL</uri>.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"12 2","pages":"416-429"},"PeriodicalIF":8.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148505838","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Taylor-Sensus Network: Embracing Noise to Enlighten Uncertainty for Scientific Data","authors":"Guangxuan Song;Dongmei Fu;Zhongwei Qiu;Jintao Meng;Dawei Zhang","doi":"10.1109/TBDATA.2025.3624982","DOIUrl":"https://doi.org/10.1109/TBDATA.2025.3624982","url":null,"abstract":"Uncertainty estimation is vital for machine learning with scientific data. Although existing methods effectively address inherent model uncertainty, they frequently overlook explicit modeling of complex noise in data devoid of temporal or spatial dependencies. This gap is especially challenging in structured scientific data, where such dependencies are commonly lacking. To address these challenges in scientific research, we propose the Taylor-Sensus Network (TSNet). TSNet innovatively uses a Taylor series expansion to model complex, heteroscedastic noise and proposes a deep Taylor block for aware noise distribution. TSNet includes a noise-aware contrastive learning module and a data density perception module for aleatoric and epistemic uncertainty. Additionally, an uncertainty combination operator is used to integrate these uncertainties, and the network is trained using a novel heteroscedastic mean square error loss. TSNet demonstrates superior performance over mainstream and state-of-the-art methods in experiments, highlighting its potential in scientific research and noise resistance.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"12 2","pages":"460-474"},"PeriodicalIF":8.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148506957","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Lightweight Scope Integration Network for Rail Surface Defect Detection","authors":"Wujie Zhou;Yue Wu;Fangfang Qiang;Weiqing Yan","doi":"10.1109/TBDATA.2025.3618444","DOIUrl":"https://doi.org/10.1109/TBDATA.2025.3618444","url":null,"abstract":"Rail-surface defect detection (RSDD) is a key technology for ensuring the safety and efficiency of railroad transportation. Existing models enhance the robustness in complex scenarios by using complementary information from visible light (RGB) image and depth data. However, incorporating depth data increases the computational complexity, which consumes more resources, increases the risk of overfitting, and decreases the model efficiency. Optimizing and streamlining multimodal data processing remains challenging. To address this issue and enable fast and accurate RSDD, this study introduces a novel lightweight scope integration network (LSINet). This method efficiently and precisely fuses the features using a lightweight double-context-aware module and refines the image quality using an adaptive Markov field smoothing module in a hierarchical decoding process. A lightweight two-dimensional scanning method that captures long-range dependencies and improves computational efficiency. We integrate this approach with local range extremes to enhance the multimodal feature fusion. Furthermore, to refine the defect edges and improve the detection accuracy, we integrate the Markov random field module into the defect segmentation and optimization using its ability to model interpixel spatial correlation, particularly for small and ambiguous defects. In designing the model, we focused on optimizing the number of parameters (e.g., computational resources). Experimental evaluations using various rail surface images demonstrated that the proposed method enhanced the defect detection accuracy and recall while reaching fast detection speeds. According to extensive experiments conducted using the industrial RGB-D dataset (i.e., NEU RSDDS-AUG), LSINet outperformed 15 state-of-the-art methods with only 27.6 million parameters.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"12 2","pages":"321-329"},"PeriodicalIF":8.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148504852","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SARF: Sparsity-Aware Reconstruction Framework for Large-Scale Datasets","authors":"Agustin Zuniga;Huber Flores;Ngoc Thi Nguyen;Pan Hui;Sasu Tarkoma;Petteri Nurmi","doi":"10.1109/TBDATA.2025.3639968","DOIUrl":"https://doi.org/10.1109/TBDATA.2025.3639968","url":null,"abstract":"Large-scale datasets, particularly those collected from smart devices and Internet of Things sensors, usually exhibit significant temporal and spatial sparsity, resulting in high amounts of missing data. Unless addressed in the analysis, this sparsity can result in substantial gaps and biases as well as limit the generalizability of conclusions drawn from such data. To address this challenge in data quality, we contribute the Sparsity-Aware Reconstruction Framework (SARF) as a novel and unified data fusion and reconstruction framework that enhances data quality and addresses sparsity. SARF analyzes datasets, partitioning the data into segments with similar characteristics, and reconstructs the data in each segment individually by selecting a reconstruction technique that is tailored to the internal temporal-spatial characteristics of the dataset. Through extensive experiments on two representative datasets – mobile application measurements and IoT sensor data from low-cost air quality sensors – we demonstrate that the targeted adaptation of reconstruction strategies employed by SARF significantly enhances the quality of reconstructed data. Our results show the robustness of SARF’s performance across spatiotemporal variations, outperforming current state-of-the-art methods by margins up to 68% on average (74% for compressive sensing, 53% for convolutional sparse coding, 78% for deep learning). These findings underscore SARF’s potential to enhance data-driven insights across multiple domains, paving the way for more robust analyses of sparsity-affected datasets.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"12 2","pages":"612-624"},"PeriodicalIF":8.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11278075","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148505146","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}