IEEE Transactions on Big Data最新文献

{"title":"Ensemble Approaches for Dynamic Data Stream Classification Under Label Scarcity","authors":"Zhiwen Yu;Siyong Huang;Kaixiang Yang;Jianming Lv;C. L. Philip Chen","doi":"10.1109/TBDATA.2025.3570072","DOIUrl":"https://doi.org/10.1109/TBDATA.2025.3570072","url":null,"abstract":"As data continues to grow exponentially, the importance of online learning across various domains has increased significantly. However, most existing studies assume that the true class label for each incoming data point is readily available, an assumption that is often impractical. To address this issue, this paper introduces a novel algorithm called Density-based Clustering and One-Class Ensemble Active Learning (DCOE-AL). This approach constructs an ensemble model by combining a clustering algorithm with the One-Class Broad Learning System (OCBLS), which represents clusters within the feature space. Furthermore, a new active learning mechanism is developed to enable DCOE-AL to effectively handle challenges associated with concept drift and label scarcity. The proposed method is evaluated on multiple synthetic data streams that exhibit diverse types of concept drift, as well as on several real-world data streams. Comparative evaluations demonstrate that DCOE-AL achieves superior performance while requiring significantly fewer labeled samples.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"11 6","pages":"3047-3060"},"PeriodicalIF":8.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148480912","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":"Patch Based Unsupervised Deep Learning for Retrieval and Part Matching in Large Image Datasets","authors":"Anindita Mukherjee;Jaya Sil;Abhimanyu Sahu;Ananda S. Chowdhury","doi":"10.1109/TBDATA.2025.3594237","DOIUrl":"https://doi.org/10.1109/TBDATA.2025.3594237","url":null,"abstract":"In this paper, we address the dual problems of retrieval and part (Region Of Interest (ROI)) matching, especially in large-scale image datasets. At the heart of our solution lies a patch-based unsupervised deep image representational model, termed a Bag of Variational Deep Embedded Visual Words (BoVDEVW). This model has three main components. Firstly, we extract a set of informative patches based on their entropy values. Secondly, the Variational AutoEncoder (VAE) is used to represent these informative patches in a robust low-dimensional probabilistic latent space. Third, deep embedded clustering is applied to group them. We introduce a composite loss function in this connection, which consists of reconstruction, regularization, and clustering losses, and explicitly show that it is convex. The cluster centers are termed as Variational Deep Embedded Visual Words. Image retrieval is performed by computing the Euclidean distance between a query image and the database images, each being represented as a Bag of Variational Deep Embedded Visual Words (BoVDEVW). The problem of finding ROI(s) in the retrieved images corresponding to ROI(s) in a query image is modeled as a matching problem in a bipartite graph constructed in the probabilistic latent space of the VAE. Comprehensive experimentation on large image datasets, NUS-WIDE and Google Landmarks Dataset (GLD) v2, and medium image datasets, Oxford 5K and Paris 6K clearly shows the efficacy of our proposed solution.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"11 6","pages":"3369-3382"},"PeriodicalIF":8.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148478802","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":"A Cross-Domain Recommendation Model Integrating Users’ Long-Term and Short-Term Interests","authors":"Wanjing Zhao;Yunpeng Xiao;Chaolong Jia;Tun Li;Rong Wang;Qian Li","doi":"10.1109/TBDATA.2025.3558836","DOIUrl":"https://doi.org/10.1109/TBDATA.2025.3558836","url":null,"abstract":"Cross-domain recommendation can combine users’ interests in multiple domains to achieve diversification of recommended content. To solve the problem of complex and changeable interest relationship among different domains, this paper proposes a cross-domain recommendation model integrating user's long-term and short-term interests. First, to solve the problem of different data distributions in different domains, this paper proposes the graph convolutional network with maximum mean discrepancy (MMD), which gradually aligns the feature representation of shared potential space during training to reduce the influence of negative transfer. Second, to solve the problem of different features of items in different domains, considering the advantage of attention mechanism in distinguishing importance, a hierarchical attention mechanism focusing on item features is proposed to build users’ short-term interests in source domain. Finally, aiming at the dynamic influence of users’ long-term and short-term interest, a multi-type interest dynamic aggregation module based on gated network is proposed, which not only integrates users’ preferences in different domains, but also takes into account the characteristics of items to be predicted. Experiments show that the model can effectively capture users’ multi-type interests in source domain and target domain on real data set, so as to improve the recommendation accuracy of target domain.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"11 6","pages":"2841-2855"},"PeriodicalIF":8.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148480887","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":"Using Construction Waste Hauling Trucks’ GPS Data to Classify Earthwork-Related Locations: A Chengdu Case Study","authors":"Lei Yu;Ke Han","doi":"10.1109/TBDATA.2025.3575940","DOIUrl":"https://doi.org/10.1109/TBDATA.2025.3575940","url":null,"abstract":"Earthwork-related locations (ERLs), such as construction sites, earth dumping grounds, and concrete mixing stations, are major sources of urban dust pollution (particulate matter). The effective management of ERLs is crucial and requires timely and efficient tracking of these locations throughout the city. This study aims to identify and classify urban ERLs using GPS trajectory data of over 16,000 construction waste hauling trucks (CWHTs), as well as 58 urban features encompassing geographic, land cover, POI, and transport dimensions. We compare several machine learning models and examine the impact of various spatial-temporal features on classification performance using real-world data in Chengdu, China. The results demonstrate that 77.8% classification accuracy can be achieved with a limited number of features. Implemented in the Alpha MAPS system in Chengdu, this classification framework successfully identified 724 construction sites/earth dumping grounds, 48 concrete mixing stations, and 80 truck parking locations in the city in December 2023, enabling local authorities to manage urban dust pollution at low personnel costs effectively.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"11 6","pages":"3130-3141"},"PeriodicalIF":8.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148478752","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":"PB-TABL: Task Incremental Learning Strategy via Applying Piggyback Architecture on Temporal Attention-Augmented Bilinear Networks for Financial Time-Series Classification","authors":"Reza Paki;Hossein Abbasimehr","doi":"10.1109/TBDATA.2025.3598730","DOIUrl":"https://doi.org/10.1109/TBDATA.2025.3598730","url":null,"abstract":"As financial markets continue to grow and generate vast volumes of data, there is a growing need for models capable of being updated incrementally. In this paper, we present PB-TABL, a novel method for financial time-series forecasting that integrates the piggyback (PB) architecture with Temporal Attention-Augmented Bilinear Networks (TABL). The proposed PB-TABL architecture addresses the challenges of task-incremental learning, including catastrophic forgetting, concept drift, and computational efficiency. By adapting pre-trained models through binary masks, PB-TABL enables efficient reuse of models for new tasks, significantly reducing training time and computational costs. We demonstrate the effectiveness of this approach through extensive experiments on large-scale Limit Order Book (LOB) data, where PB-TABL outperforms baseline models in terms of accuracy, F1 score, and overall computational efficiency. Our contributions include formulating the problem of adapting pre-trained neural networks to new financial data, introducing the PB-TABL architecture, and showing its advantages in handling time-series data with temporal dependencies while mitigating the risks of catastrophic forgetting and model degradation.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"11 6","pages":"3527-3538"},"PeriodicalIF":8.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148479018","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":"FinMem: A Performance-Enhanced LLM Trading Agent With Layered Memory and Character Design","authors":"Yangyang Yu;Haohang Li;Zhi Chen;Yuechen Jiang;Yang Li;Jordan W. Suchow;Denghui Zhang;Khaldoun Khashanah","doi":"10.1109/TBDATA.2025.3593370","DOIUrl":"https://doi.org/10.1109/TBDATA.2025.3593370","url":null,"abstract":"We introduce <sc>FinMem</small>, a novel Large Language Models (LLM)-based agent framework for financial trading, designed to address the need for automated systems that can transform real-time data into executable decisions. <sc>FinMem</small> comprises three core modules: Profile for customizing agent characteristics, Memory for hierarchical financial data assimilation, and Decision-making for converting insights into investment choices. The Memory module, which mimics human traders’ cognitive structure, offers interpretability and real-time tuning while handling the critical timing of various information types. It employs a layered approach to process and prioritize data based on its timeliness and relevance, ensuring that the most recent and impactful information is given appropriate weight in decision-making. <sc>FinMem</small>’s adjustable cognitive span allows retention of critical information beyond human limits, enabling it to balance historical patterns with current market dynamics. This framework facilitates self-evolution of professional knowledge, agile reactions to investment cues, and continuous refinement of trading decisions in financial environments. When compared against advanced algorithmic agents using a large-scale real-world financial dataset, <sc>FinMem</small> demonstrates superior performance across classic metrics like Cumulative Return and Sharpe ratio. Further tuning of the agent’s perceptual span and character setting enhances its trading performance, positioning <sc>FinMem</small> as a cutting-edge solution for automated trading.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"11 6","pages":"3443-3459"},"PeriodicalIF":8.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148479633","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":"Dynamic Modeling and Analysis of Bi-Directional Traffic Flows Through a Deep Spatio-Temporal Graph Neural Network","authors":"Jin Fan;Fu Zhu;Wenchao Weng;Xinyi Zhang;Hanyu Jiang;Hao Tian;Huifeng Wu","doi":"10.1109/TBDATA.2025.3566578","DOIUrl":"https://doi.org/10.1109/TBDATA.2025.3566578","url":null,"abstract":"Accurate traffic flow forecasting is critical for the efficient operation of intelligent transportation systems (ITS), as it directly supports urban management and decision-making. With the increasing complexity of urban traffic, existing models often fail to fully capture the dynamic dependencies between traffic inflows and outflows. Some treat them as a unified process, while others only explore their commonalities. Inflows and outflows exhibit distinct patterns and interactions that require more refined modeling. To improve modeling performance, we propose BiSTGNN, a novel deep spatio-temporal network model which explicitly models bidirectional traffic flows as independent stochastic processes. Our approach leverages the unique temporal and spatial dependencies of each flow direction to distinguish transitions between directions, and integrates them through a composite graph convolution framework, offering a more detailed analysis of the transfer process between flows. Additionally, we introduce an innovative dynamic graph construction method that differentiates the interactions between inflows and outflows, capturing their heterogeneous relationships. Extensive experiments on five real-world traffic datasets demonstrate that our method outperforms state-of-the-art baselines, achieving superior accuracy in predicting both inflows and outflows.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"11 6","pages":"3016-3028"},"PeriodicalIF":8.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148479685","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":"Efficient and Tractable Conflict Detection in Knowledge Graphs via Path Analysis","authors":"Yihan Wang;Qi Song;Ling Zheng;Xiang-Yang Li","doi":"10.1109/TBDATA.2025.3575948","DOIUrl":"https://doi.org/10.1109/TBDATA.2025.3575948","url":null,"abstract":"Knowledge graphs (KGs), which utilize graph structures to represent real-world facts, are pivotal in information retrieval and artificial intelligence. However, heuristic knowledge graph construction methods will produce errors. Some conflicts, such as expression ambiguities, are challenging to detect at triple granularity and require semantic analysis together with other triples. In this paper, we propose an approach for conflict detection at path granularity in large-scale knowledge graphs. It is based on rules on a specific pattern. Different from previous rules, our rules are defined with a ring pattern to extend error detection from triple granularity to path granularity. We prove that indicating whether a triple brings such conflicts only requires dealing with any one of its related ring structures, which can significantly reduce the complexity. We propose <inline-formula><tex-math>$mathsf {RingE}$</tex-math></inline-formula>, a novel Ring Embedding method, to detect ring-pattern conflicts, and <inline-formula><tex-math>$mathsf {DeCon}$</tex-math></inline-formula>, a CONflict DEtection framework suitable for both static and incremental scenes. This framework divides the ring-pattern conflict detection task in KGs into ring discovery and conflict detection. We also design a pruning strategy for ring discovery that reduces the time complexity from the exponential level to the polynomial level. Using real-world graphs, we experimentally verify that our algorithms are effective and feasible for large graphs. Our case study also verifies that <inline-formula><tex-math>$mathsf {DeCon}$</tex-math></inline-formula> can detect real conflicts.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"11 6","pages":"3116-3129"},"PeriodicalIF":8.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148479754","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":"Towards Privacy-Preserving Personalized Federated Relation Classification","authors":"Ning Pang;Xiang Zhao;Weixin Zeng;Zhen Tan;Weidong Xiao","doi":"10.1109/TBDATA.2025.3566576","DOIUrl":"https://doi.org/10.1109/TBDATA.2025.3566576","url":null,"abstract":"Relation classification plays a crucial role in detecting semantic relations between annotated entities within text data, serving as a fundamental tool for knowledge structurization. In recent years, federated learning has emerged as a promising approach for training relation classification models in decentralized settings. Existing methods have focused on developing a robust server model by decoupling model training at the server from direct access to client-side text data, while taking advantage of distributed data sources. However, a significant challenge arises from the heterogeneous nature of client texts, characterized by diverse and skewed distributions of relations, which has limited the practicality of current approaches. In response to this challenge, this study introduces the concept of personalized federated relation classification, aiming to tailor strong client models to adapt to their individual data distributions. To further address the issues stemming from heterogeneous texts, a novel framework, referred to as <inline-formula><tex-math>${sf pFedRC}$</tex-math></inline-formula>, is proposed with several optimized designs. This framework incorporates a knowledge fusion method that leverages a relation-wise weighting mechanism, and a feature augmentation approach utilizing prototypes to adaptively enhance the representations of instances associated with long-tail relations. Although federated learning can safely ensure private data unexposed, it is important to recognize that, from an information theory standpoint, there still exists a possibility for a curious server to deduce private information by analyzing the shared knowledge uploaded by clients. To enhance the privacy guarantees of the personalized federated relation classification system, this work integrates client-level differential privacy mechanism into the federated training process. According to our theoretical analysis, <inline-formula><tex-math>${sf pFedRC}$</tex-math></inline-formula> with client-level differential privacy can realize rigorous privacy guarantees. Experimental evaluations demonstrate the superiority of the proposed <inline-formula><tex-math>${sf pFedRC}$</tex-math></inline-formula> framework over competing baselines in various settings, illustrating that the tailored techniques effectively mitigate the challenges posed by heterogeneous text data while preserving privacy guarantees. This research contributes to the advancement of learning privacy-preserving personalized relation classification models via taking advantages of data from multiple sources.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"11 6","pages":"2972-2986"},"PeriodicalIF":8.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148479608","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":"Self-Representation-Based Generative Graph Neural Networks for End-to-End Link Prediction","authors":"Xingping Xian;Tao Wu;Shaojie Qiao;Chao Wang;Lin Yuan;Yanbing Liu","doi":"10.1109/TBDATA.2025.3566584","DOIUrl":"https://doi.org/10.1109/TBDATA.2025.3566584","url":null,"abstract":"Recently, deep neural networks have revolutionized the field of link prediction, and the state-of-the-art works are typically subgraph-based discriminative methods, which construct features of local subgraphs firstly and predicting potential links via deep learning based binary subgraph classification. However, the discriminative link prediction methods always fail to automatically learn features and perform link prediction, and the performance of them depends on the construction of enclosing subgraphs and the manually-designed features for the subgraphs. To address these issues, we leverage the idea of graph disentangling and propose a novel self-representation-based generative graph neural network framework (GraphLP) for end-to-end link prediction, which learns to extract the latent patterns, i.e., recurring subgraphs, from input graphs via self-supervised learning and reconstruct graphs for link prediction using the subgraphs as structural basis. GraphLP consists of three components: self-representation-based collaborative inference, high-order connectivity computation, and multi-scale pattern fusion. The key idea is to utilize the correlations between the extracted recurring subgraphs on different scales to effectively assist link inference. GraphLP also can effectively exploit the hierarchical organization patterns and incorporate them within the representation procedure, producing robust and accurate results. Compared with traditional methods and state-of-the-art methods, experimental results on public benchmark datasets demonstrate that GraphLP achieves promising performance. Different from the discriminative methods, GraphLP provides a new paradigm for generative neural-network-based link prediction.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"11 6","pages":"2929-2945"},"PeriodicalIF":8.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148479610","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}