IEEE Transactions on Big Data最新文献_第5页

CAPTOR: Cyber Attack Protection via Temporal Online Graph Representation Learning 通过时态在线图表示学习的网络攻击防护

IF 8.1 3区计算机科学

IEEE Transactions on Big Data Pub Date : 2026-04-01 Epub Date: 2025-10-20 DOI: 10.1109/TBDATA.2025.3621145

Bishal Lakha;Janet Layne;Edoardo Serra;Francesco Gullo;Sushil Jajodia

{"title":"CAPTOR: Cyber Attack Protection via Temporal Online Graph Representation Learning","authors":"Bishal Lakha;Janet Layne;Edoardo Serra;Francesco Gullo;Sushil Jajodia","doi":"10.1109/TBDATA.2025.3621145","DOIUrl":"https://doi.org/10.1109/TBDATA.2025.3621145","url":null,"abstract":"Online intrusion detection systems (IDSs), i.e., tools for detecting live cyberattacks in the form of unauthorized access gained to a (networking) system, play a role of paramount importance in the cybersecurity landscape. Among the plethora of existing IDSs, the ones based on temporal graph anomaly detection (TGAD) process a temporal graph representing entities of interest of the underlying system and time-varying relationships among them, and identify anomalous temporal edges in such a graph as potential intrusions. TGAD-based IDSs are superior to various other existing types of IDS for their peculiarities of high generality and powerfulness in data representation and types of cyberattack identifiable. However, existing TGAD-based IDSs are still far from being suitable for real-world settings, due to their severe limitations in efficiently and effectively handling the underlying temporal graphs, which are typically really big. In this paper, we devise CAPTOR (“Cyber Attack Protection via Temporal Online graph Representation learning”), a novel TGAD-based IDS which addresses the limitations of the state of the art. CAPTOR consists of a careful selection and clever combination of graph representation learning (GRL), TGAD, and temporal aggregation of GRL representations (embeddings). These design choices make CAPTOR achieve the best tradeoff between accuracy and scalability in TGAD-based intrusion detection, as testified by extensive experiments on real cybersecurity datasets. As such, with this work we take a significant step forward towards rendering the important TGAD-based IDS technology actually applicable in real-world cybersecurity scenarios.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"12 2","pages":"376-388"},"PeriodicalIF":8.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148505426","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}

引用次数: 0

Proxy-Based Dynamic View Alignment With Cross-View Structure Preservation for Multi-View Clustering 多视图聚类中基于代理的动态视图对齐与交叉视图结构保持

IF 8.1 3区计算机科学

IEEE Transactions on Big Data Pub Date : 2026-04-01 Epub Date: 2025-11-24 DOI: 10.1109/TBDATA.2025.3635898

Xiaoyan Yu;Dazheng Peng;Zhenqiu Shu;Liehuang Zhu

{"title":"Proxy-Based Dynamic View Alignment With Cross-View Structure Preservation for Multi-View Clustering","authors":"Xiaoyan Yu;Dazheng Peng;Zhenqiu Shu;Liehuang Zhu","doi":"10.1109/TBDATA.2025.3635898","DOIUrl":"https://doi.org/10.1109/TBDATA.2025.3635898","url":null,"abstract":"Multi-view clustering aims to fully discover consistent clustering structures across different views, thereby improving the clustering performance. However, they usually lose structural information between different views during multi-view feature integration. Additionally, the misalignment of clustering centers from different views may lead to performance degradation. To tackle these challenges, in this paper, we propose a novel approach, called proxy-based dynamic view alignment with cross-view structure preservation (PDVA-CSP), for multi-view clustering. First, we design a graph aggregation module to explore the structure information between views through graph-based aggregation. Then we propose a proxy-based dynamic alignment strategy based on attention mechanisms to address the misalignment of proxies across views. Finally, we integrate them into an end-to-end learning framework, and then optimize it via a joint reconstruction loss and contrastive learning framework, seamlessly integrating feature extraction, view alignment, and clustering. The experimental results on several multi-view datasets demonstrate that the proposed PDVA-CSP method significantly outperforms other state-of-the-art methods in multi-view clustering tasks.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"12 2","pages":"554-567"},"PeriodicalIF":8.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148506516","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}

引用次数: 0

Bridging the Gaps: A Comprehensive Review of Data Management Capability Maturity Models in the Digital Era 弥合差距：数字时代数据管理能力成熟度模型的全面回顾

IF 8.1 3区计算机科学

IEEE Transactions on Big Data Pub Date : 2026-04-01 Epub Date: 2025-10-13 DOI: 10.1109/TBDATA.2025.3621149

Shuo Yan;Jeff Jones

{"title":"Bridging the Gaps: A Comprehensive Review of Data Management Capability Maturity Models in the Digital Era","authors":"Shuo Yan;Jeff Jones","doi":"10.1109/TBDATA.2025.3621149","DOIUrl":"https://doi.org/10.1109/TBDATA.2025.3621149","url":null,"abstract":"As digital transformation accelerates, organisations are increasingly investing in data management infrastructures and setting related strategic goals. However, expected returns are often not realised due to ineffective data management practices. To address this, Capability Maturity Models (CMMs) have been developed to assess and enhance data management capabilities across areas such as strategy, policy, leadership, culture, processes, and value-added activities. This study presents a Systematic Literature Review (SLR) covering 28 studies published between 2012 and 2022, with an additional snowballing extension up to January 2024 related to data management maturity, encompassing both fully established Capability Maturity Models (CMMs) and conceptually significant contributions. The studies were evaluated based on two main criteria: (1) the application of a Design Science approach, comprising four key steps—problem definition, comparison of existing models, model development, and evaluation; and (2) the comprehensiveness, clarity, and usability of the models, assessed through four sub-criteria. The analysis identified eleven major shortcomings in the existing literature, including limited synthesis of prior work, lack of scientifically grounded iterative development, insufficient validation and verification, and inadequate coverage of the complete data lifecycle—particularly in relation to legal and ISO compliance. Moreover, critical elements such as a Stage 0 for data awareness, transition tables, and practical self-assessment schemes were often missing. These findings underscore the need for a scientifically rigorous and practically applicable CMM that addresses these gaps and offers a holistic framework for advancing data management maturity.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"12 2","pages":"307-320"},"PeriodicalIF":8.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148509100","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}

引用次数: 0

ACJoin: A Low-Latency Multi-Table Join Order Selection Model With Minimum Cost Using Asynchronous Advantage Actor-Critic ACJoin：一个使用异步优势的低延迟多表连接顺序选择模型

IF 8.1 3区计算机科学

IEEE Transactions on Big Data Pub Date : 2026-04-01 Epub Date: 2025-10-07 DOI: 10.1109/TBDATA.2025.3618478

Shaojie Qiao;Chenxu Liu;Nan Han;Kanglei Xu;Ruiwei Gao;Xindong Wu

{"title":"ACJoin: A Low-Latency Multi-Table Join Order Selection Model With Minimum Cost Using Asynchronous Advantage Actor-Critic","authors":"Shaojie Qiao;Chenxu Liu;Nan Han;Kanglei Xu;Ruiwei Gao;Xindong Wu","doi":"10.1109/TBDATA.2025.3618478","DOIUrl":"https://doi.org/10.1109/TBDATA.2025.3618478","url":null,"abstract":"Join order selection is one of the most challenging problems in query optimization and plays an essential role in providing high query performance in Big Data management. Currently, researchers have applied deep reinforcement learning methods, for example, Rejoin and DQ, to join order selection in order to obtain high query performance. However, Rejoin and DQ cannot capture the structural characteristic of the join tree, which may lead to similar encoding structure for different execution plans. To tackle these challenges, we propose a new learning optimizer called ACJoin (asynchronous advantage <bold>A</b>ctor-<bold>C</b>ritic for multi-table <bold>Join</b> order selection). ACJoin employs a new encoding method to capture the structural characteristics of the join tree through integrating GRU (Gated Recurrent Unit). In particular, ACJoin can distinguish different execution plans. It uses A3C (Asynchronous Advantage Actor-Critic) to guide the join order selection and reduce the time taken to find the best query plan with the minimum cost. Compared with existing search strategies, ACJoin can find the globally optimal solution with efficient and stable query performance. Extensive experiments are conducted on the real JOB and the synthetic TPC-H datasets. The results show that ACJoin outperforms the state-of-the-art join order selection methods and DRL (Deep Reinforcement Learning)-based methods in cost and latency.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"12 2","pages":"330-345"},"PeriodicalIF":8.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148505222","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}

引用次数: 0

The Faiss Library 费斯图书馆

IF 8.1 3区计算机科学

IEEE Transactions on Big Data Pub Date : 2026-04-01 Epub Date: 2025-10-13 DOI: 10.1109/TBDATA.2025.3618474

Matthijs Douze;Alexandr Guzhva;Chengqi Deng;Jeff Johnson;Gergely Szilvasy;Pierre-Emmanuel Mazaré;Maria Lomeli;Lucas Hosseini;Hervé Jégou

引用次数: 0

Big Data-Driven UAV Regulatory Compliance: Frameworks, Challenges, and Opportunities 大数据驱动的无人机法规遵从：框架、挑战和机遇

IF 8.1 3区计算机科学

IEEE Transactions on Big Data Pub Date : 2026-04-01 Epub Date: 2025-10-31 DOI: 10.1109/TBDATA.2025.3627501

Nguyen Huu Phuoc Dai;Khaoula Hidawi;Barbara Carminati;Elena Ferrari

引用次数: 0

Generation of Hard SAT Instances and Its Application in Negative Databases for Privacy Enhancement 硬SAT实例的生成及其在负数据库中的应用

IF 8.1 3区计算机科学

IEEE Transactions on Big Data Pub Date : 2026-04-01 Epub Date: 2025-12-04 DOI: 10.1109/TBDATA.2025.3640025

Dongdong Zhao;Pang Chen;Changtian Song;Jianwen Xiang;Junwei Zhou;Zebo Tang;Baogang Song

{"title":"Generation of Hard SAT Instances and Its Application in Negative Databases for Privacy Enhancement","authors":"Dongdong Zhao;Pang Chen;Changtian Song;Jianwen Xiang;Junwei Zhou;Zebo Tang;Baogang Song","doi":"10.1109/TBDATA.2025.3640025","DOIUrl":"https://doi.org/10.1109/TBDATA.2025.3640025","url":null,"abstract":"In recent years, machine learning and deep learning have made remarkable progress and are now widely applied in various fields, including image classification, autonomous driving, natural language processing, and medical diagnosis. However, training these models requires large datasets, which often contain substantial amounts of sensitive personal information, such as medical records and financial details. Without effective privacy protection measures during model training, the risk of sensitive data leakage increases, potentially resulting in severe privacy violations and a loss of trust. As an innovative data representation technique, the Negative Database has proven to be an effective solution in privacy-sensitive domains. Negative databases can be derived from SAT (Boolean Satisfiability Problem) instances, and the hardness of these instances is directly correlated with the level of data protection provided by the Negative Databases. Developing efficient SAT instance generation algorithms to create harder SAT instances can significantly enhance the privacy protection capabilities of the Negative Database. This paper analyzes the hardness conditions of SAT solvers using the Conflict-Driven Clause Learning strategy and proposes a two-stage SAT instance generation algorithm to generate harder SAT instances. These hard instances not only aid in constructing more secure negative databases for enhanced privacy protection but also provide valuable test cases for evaluating and improving SAT solvers.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"12 2","pages":"643-660"},"PeriodicalIF":8.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148509076","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}

引用次数: 0

Visual Question Answer Model Based on Crop Diseases External Knowledge for Smart Agriculture 基于作物病害外部知识的智能农业可视化问答模型

IF 8.1 3区计算机科学

IEEE Transactions on Big Data Pub Date : 2026-04-01 Epub Date: 2025-10-23 DOI: 10.1109/TBDATA.2025.3624953

Yunpeng Zhao;Shansong Wang;Qingtian Zeng;Weijian Ni;Hua Duan;Nengfu Xie;Fengjin Xiao

{"title":"Visual Question Answer Model Based on Crop Diseases External Knowledge for Smart Agriculture","authors":"Yunpeng Zhao;Shansong Wang;Qingtian Zeng;Weijian Ni;Hua Duan;Nengfu Xie;Fengjin Xiao","doi":"10.1109/TBDATA.2025.3624953","DOIUrl":"https://doi.org/10.1109/TBDATA.2025.3624953","url":null,"abstract":"Current crop disease VQA models primarily focus on object counting and detection. However, accurately identifying various disease stages and determining control measures require additional knowledge beyond images, including information about control methods and pathogen details. To address this, the VQA dataset relies on the images and questions to retrieve relevant external knowledge. To realize the VQA task of crop diseases external knowledge, we construct the Visual Question Answer Model Based on Crop Diseases External Knowledge for Smart Agriculture (CDEK). CDEK integrates two categories of external knowledge on 66 common dicotyledonous crop diseases by utilizing large language models and agricultural knowledge repositories to enhance knowledge retrieval. This integration enhances the richness of external knowledge repositories. Enhancing fine-grained image understanding in CDEK through the utilization of Stack Self-Attention (SSA), utilising Cross-Attention and contrastive learning of two external knowledge, with a focus on emphasizing image-related semantic information during training. Finally, an automatic patrol disease detection robot is constructed based on Tensor Processing Unit (TPU) devices and the CDEK model. CDEK achieves an accuracy of 61.7% on the publicly available dataset OK-VQA, surpassing the previous state-of-the-art by 5.1%. Furthermore, we construct the OKiCD-VQA dataset for crop diseases external knowledge and achieve an accuracy of 89.36% using CDEK. A series of ablation experiments are conducted on various modules, the effectiveness of CDEK is demonstrated through extensive experimentation. Contributing solutions to the sustainable development of smart agriculture.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"12 2","pages":"430-446"},"PeriodicalIF":8.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148508559","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}

引用次数: 0

Knockoff-Guided Feature Selection via a Single Pre-Trained Reinforced Agent 通过单个预训练的增强代理进行仿冒引导特征选择

IF 8.1 3区计算机科学

IEEE Transactions on Big Data Pub Date : 2026-04-01 Epub Date: 2025-12-04 DOI: 10.1109/TBDATA.2025.3639973

Xinyuan Wang;Dongjie Wang;Wangyang Ying;Rui Xie;Haifeng Chen;Yanjie Fu

{"title":"Knockoff-Guided Feature Selection via a Single Pre-Trained Reinforced Agent","authors":"Xinyuan Wang;Dongjie Wang;Wangyang Ying;Rui Xie;Haifeng Chen;Yanjie Fu","doi":"10.1109/TBDATA.2025.3639973","DOIUrl":"https://doi.org/10.1109/TBDATA.2025.3639973","url":null,"abstract":"Modern data-driven applications generate vast, complex data that often contain irrelevant, redundant, or noisy features. The task involves selecting the optimal subset of features from a dataset by removing redundant and irrelevant ones to enhance downstream performance. Using reinforcement learning (RL) for feature selection is ideal for data-centric tasks due to its interactive nature, which dynamically adapts to evolving data environments. However, high initial exploration variability, reliance on downstream tasks, and the need to control the false discovery rate bring challenges. To address these issues, we introduce a knockoff-guided RL framework, which uses pseudo-features to control early-stage randomness and matrix reconstruction for unsupervised reward. Our approach is a single-agent RL approach with unsupervised rewards that utilize knockoff information and matrix reconstruction to enhance feature selection without relying on labeled data. The framework integrates three components: the knockoff information to control exploration variability, decision network pre-training to guide RL policy, and matrix reconstruction to guide unsupervised rewards. Extensive experiments are conducted on various datasets across different task types, including classification and regression, demonstrating the superiority of our framework.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"12 2","pages":"625-642"},"PeriodicalIF":8.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148505149","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}

引用次数: 0

A High-Throughput Method for Fabric in Scenarios With Multiple Aborted Transactions 多事务中止场景下Fabric的高吞吐量方法

IF 8.1 3区计算机科学

IEEE Transactions on Big Data Pub Date : 2026-04-01 Epub Date: 2025-12-03 DOI: 10.1109/TBDATA.2025.3639992

Yan Wang;Shushu Ren;Dayu Jia;Aiping Tan;Ziyi Gao

{"title":"A High-Throughput Method for Fabric in Scenarios With Multiple Aborted Transactions","authors":"Yan Wang;Shushu Ren;Dayu Jia;Aiping Tan;Ziyi Gao","doi":"10.1109/TBDATA.2025.3639992","DOIUrl":"https://doi.org/10.1109/TBDATA.2025.3639992","url":null,"abstract":"Hyperledger Fabric is one of the most popular federation chains and is widely used in many fields, such as healthcare, government, and education. However, in practical application scenarios, Fabric faces the challenge of handling a large number of aborted transactions. These transaction failures are primarily caused by read-write conflicts resulting from read-write locks during the execution and validation phases, as well as transaction ordering dependencies in the ordering phase. The frequent occurrence of aborted transactions significantly reduces system throughput, as each failed transaction not only wastes computational resources and network bandwidth but also requires reprocessing. Therefore, this paper proposes a solution called Fabric*, which includes a transaction reordering mechanism, a cache queue mechanism, and a lock-free mechanism. The former two mechanisms are used to abort conflicting transactions early in the ordering phase and to avoid aborting conflicting transactions again. The latter mechanism is used to abort transactions that read obsolete data during the simulation phase. Fabric* reduces abort transactions and increases the throughput of successful transactions in the system. Experimental results show that Fabric* improves throughput by up to about 23.9% and 7.4% over the original Fabric and Fabric++.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"12 2","pages":"584-599"},"PeriodicalIF":8.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148505288","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}

引用次数: 0