Information Sciences最新文献_第9页

Partition-based differentially private synthetic data generation 基于分区的差异私有合成数据生成

IF 6.8 1区计算机科学

Information Sciences Pub Date : 2025-09-12 DOI: 10.1016/j.ins.2025.122675

Meifan Zhang , Dihang Deng , Lihua Yin

引用次数: 0

Byzantine-resilient federated learning with dynamic scoring matrix and variant PBFT consensus under differential privacy 差分隐私下具有动态评分矩阵和可变PBFT一致性的拜占庭弹性联邦学习

IF 6.8 1区计算机科学

Information Sciences Pub Date : 2025-09-12 DOI: 10.1016/j.ins.2025.122682

Wentai Yang , Xian Xu , Kai Yu , Guoqiang Li

{"title":"Byzantine-resilient federated learning with dynamic scoring matrix and variant PBFT consensus under differential privacy","authors":"Wentai Yang , Xian Xu , Kai Yu , Guoqiang Li","doi":"10.1016/j.ins.2025.122682","DOIUrl":"10.1016/j.ins.2025.122682","url":null,"abstract":"<div><div>The increasing concerns regarding data privacy exacerbate the challenges associated with “data silos”. Federated learning (FL) effectively addresses these issues by facilitating distributed machine learning without necessitating direct data exchange. However, the dependence on a central server in conventional FL architectures exacerbates privacy risks and limits cross-domain data sharing. Existing blockchain-based FL frameworks often employ static consensus protocols, such as classical Practical Byzantine Fault Tolerance (PBFT), which typically rely on fixed weight aggregation strategies. While these methods simplify implementation, they fail to adaptively adjust aggregation weights according to heterogeneous privacy budgets. Attempts to implement adaptive weight aggregation often require achieving consensus for each individual weight, significantly reducing efficiency and creating scalability challenges in large-scale networks. To address these gaps, we propose DSM-PBFT, a variant PBFT consensus enhanced with dynamic scoring matrices (DSM), which enables parallelized validation of multiple models while adaptively adjusting aggregation weights based on differential privacy budgets. Our noise-aware aggregation mechanism dynamically reweights models through cross-validation of accuracy, F1 score, and loss-transformed metrics, effectively decoupling privacy guarantees from model utility degradation. Security analyses affirm the robustness of this framework against Byzantine attacks, with experimental results on MNIST, FashionMNIST and CIFAR-10 demonstrating superior model accuracy across diverse privacy budgets while effectively curbing accuracy degradation under attack scenarios.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"723 ","pages":"Article 122682"},"PeriodicalIF":6.8,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Distributed data-driven event-triggered secure consensus control of MASs: A global preset-time performance constraint method 分布式数据驱动事件触发的质量安全共识控制：一种全局预置时间性能约束方法

IF 6.8 1区计算机科学

Information Sciences Pub Date : 2025-09-11 DOI: 10.1016/j.ins.2025.122672

Run-Ze Chen , Xiang-Gui Guo , Yuan-Xin Li

{"title":"Distributed data-driven event-triggered secure consensus control of MASs: A global preset-time performance constraint method","authors":"Run-Ze Chen , Xiang-Gui Guo , Yuan-Xin Li","doi":"10.1016/j.ins.2025.122672","DOIUrl":"10.1016/j.ins.2025.122672","url":null,"abstract":"<div><div>This paper addresses the distributed data-driven event-triggered secure consensus control issue for model-free multi-agent systems (MASs) under sensor faults and denial-of-service (DoS) attacks, while satisfying prescribed performance constraints. First, a global preset-time performance function (PTPF) is constructed to guarantee the global stability of model-free MASs within the preset time. The proposed PTPF ensures that the preset time remains unaffected by variations in the sampling period. Second, a proportional-integral-derivative (PID) sliding surface is designed to enhance MAS performance regulation, while a novel generalized fuzzy hyperbolic model (GFHM) is constructed to eliminate the dependency on fault information and achieve high-accuracy estimation of unknown fault signals. Third, a hybrid event-triggered mechanism integrating both dynamic and memory features is developed to optimize communication resource utilization while guaranteeing robust performance at extremes. Furthermore, an event-triggered secure control scheme leveraging the memory feature is proposed to reduce communication overhead while avoiding the dangerous open-loop scenario, where control inputs must be zeroed under DoS attacks as in the existing methods. Finally, the stability proof together with simulations confirms the feasibility of the control strategy.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"723 ","pages":"Article 122672"},"PeriodicalIF":6.8,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107072","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Reinforced Heterogeneous Graphlet Design for Knowledge Graph Representation Learning 面向知识图表示学习的增强异构石墨烯设计

IF 6.8 1区计算机科学

Information Sciences Pub Date : 2025-09-11 DOI: 10.1016/j.ins.2025.122670

Jibing Gong , Yuting Lin , Yi Zhao , Tianyu Lin , Xiaohan Fang , Xinchao Feng , Jiquan Peng

{"title":"Reinforced Heterogeneous Graphlet Design for Knowledge Graph Representation Learning","authors":"Jibing Gong , Yuting Lin , Yi Zhao , Tianyu Lin , Xiaohan Fang , Xinchao Feng , Jiquan Peng","doi":"10.1016/j.ins.2025.122670","DOIUrl":"10.1016/j.ins.2025.122670","url":null,"abstract":"<div><div>Knowledge graphs (KGs) are practical tools that represent and integrate plentiful structural and semantic information in mainstream industrial scenarios. Despite their potential, the heterogeneity and complexity of KGs pose a formidable obstacle, especially for graph representation learning. Most existing KG embedding models omit dynamic high-order connectivity patterns to gain insights into heterogeneous networks and heavily rely on handcrafted patterns to handle complex semantic relationships, which limits their capability to adaptively capture the nuanced and intricate relationships of KGs in different tasks. To fill this gap, we present Reinforced Heterogeneous Graphlet Design (ReHGD)—a model designed for KGs that focuses on the adaptive design of typed graphlets (heterogeneous chains and motifs) through a cooperative multi-agent reinforcement learning algorithm. This task-driven approach can learn discriminative graph representations tailored to specific downstream tasks. Specifically, ReHGD engages in the creation of typed graphlets through a two-stage process: it (1) establishes a reinforced chain design module to generate chains without predefined rules and (2) employs a buffer-aware sampling technique to derive episodic chains from prior experiences. Subsequently, motifs are deduced through the application of commute count and Hadamard product operations to the episodic chain-based subgraphs. In the final step toward learning graph representations, ReHGD undertakes chain and motif aggregations. Experimental results and analyses reveal that ReHGD outperforms strong baselines on three real-world graph data and practical tasks.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"723 ","pages":"Article 122670"},"PeriodicalIF":6.8,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107075","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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 semi-heterogeneous ensemble forecasting method for stock returns based on sentiment analysis 基于情绪分析的股票收益半异质集合预测方法

IF 6.8 1区计算机科学

Information Sciences Pub Date : 2025-09-11 DOI: 10.1016/j.ins.2025.122655

Xiao Zhang , Peide Liu , Jing Feng

{"title":"A semi-heterogeneous ensemble forecasting method for stock returns based on sentiment analysis","authors":"Xiao Zhang , Peide Liu , Jing Feng","doi":"10.1016/j.ins.2025.122655","DOIUrl":"10.1016/j.ins.2025.122655","url":null,"abstract":"<div><div>With the growing influence of investor sentiment on market dynamics, sentiment analysis has emerged as an effective tool for enhancing financial forecasting models. This study proposes a diversity-enhanced semi-heterogeneous ensemble forecasting framework that integrates sentiment analysis into the forecasting of stock index returns. A supervised stock market sentiment index set is constructed, in which prior knowledge regarding term importance is integrated into the data augmentation process. This enables higher weights to be assigned to sentiment-related terms with superior predictive capacity, thereby allowing the model to prioritize more informative features and enhance its forecasting performance. A series of diverse base models are generated through the integration of multiple attention-PCA techniques and forecasting algorithms based on variable perturbation strategies. These base models are subsequently combined through a suite of ensemble strategies, forming a semi-heterogeneous ensemble model for forecasting S&P 500 returns. The experiment results demonstrate that the proposed approaches significantly outperform benchmark methods, with notable improvements in both accuracy and diversity.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"723 ","pages":"Article 122655"},"PeriodicalIF":6.8,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Improved query specialization for transformer-based visual relationship detection 改进了基于转换器的可视化关系检测的查询专门化

IF 6.8 1区计算机科学

Information Sciences Pub Date : 2025-09-10 DOI: 10.1016/j.ins.2025.122668

Jongha Kim , Jihwan Park , Jinyoung Park , Jinyoung Kim , Sehyung Kim , Hyunwoo J. Kim

{"title":"Improved query specialization for transformer-based visual relationship detection","authors":"Jongha Kim , Jihwan Park , Jinyoung Park , Jinyoung Kim , Sehyung Kim , Hyunwoo J. Kim","doi":"10.1016/j.ins.2025.122668","DOIUrl":"10.1016/j.ins.2025.122668","url":null,"abstract":"<div><div>Visual Relationship Detection (VRD) has significantly advanced with Transformer-based architectures. However, we identify two fundamental drawbacks in conventional label assignment methods used for training Transformer-based VRD models, where ground-truth (GT) annotations are matched to model predictions. In conventional assignment, queries are trained to detect all relations rather than specializing in specific ones, resulting in ‘unspecialized’ queries. Also, each ground-truth (GT) annotation is assigned to only one prediction under conventional assignment, suppressing other near-correct predictions by labeling them as ‘no relation’. To address these issues, we introduce a novel method called Groupwise Query <strong>Spe</strong>ci<strong>a</strong>lization and <strong>Q</strong>uality-Aware Multi-Assignment (SpeaQ). Groupwise Query Specialization clusters queries and relations into exclusive groups, promoting specialization by assigning a set of relations only to a corresponding query group. Quality-Aware Multi-Assignment enhances training signals by allowing multiple predictions closely matching the GT to be positively assigned. Additionally, we introduce dynamic query reallocation, which transfers queries from high- to low-performing groups for balanced training. Experimental results demonstrate that SpeaQ+, combining SpeaQ with dynamic query reallocation, consistently improves performance across seven baseline models on five benchmarks without additional inference cost.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"723 ","pages":"Article 122668"},"PeriodicalIF":6.8,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107068","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

ConvDiff: Multi-scale spatio-temporal convolutional networks with latent diffusion models for dynamic system modeling ConvDiff：用于动态系统建模的具有潜在扩散模型的多尺度时空卷积网络

IF 6.8 1区计算机科学

Information Sciences Pub Date : 2025-09-10 DOI: 10.1016/j.ins.2025.122656

Yuyang Zhao , Yuhan Wu , Yongmei Wang

{"title":"ConvDiff: Multi-scale spatio-temporal convolutional networks with latent diffusion models for dynamic system modeling","authors":"Yuyang Zhao , Yuhan Wu , Yongmei Wang","doi":"10.1016/j.ins.2025.122656","DOIUrl":"10.1016/j.ins.2025.122656","url":null,"abstract":"<div><div>In the modeling of spatio-temporal dynamic systems, tasks such as fluid dynamics, weather forecasting, and traffic flow prediction face highly complex spatio-temporal dependencies and nonlinear dynamics. These characteristics make it challenging for traditional physical models and data-driven methods to balance accuracy and computational efficiency. To address these challenges, we propose a multi-scale spatio-temporal convolutional network named ConvDiff, optimized specifically for dynamic system modeling tasks by integrating a latent space denoising diffusion model. ConvDiff effectively captures complex spatio-temporal features and handles uncertainties in physical systems by introducing multi-scale convolutional modules combined with a physics-guided diffusion mechanism. Specifically, our model incorporates eight temporal modules and four spatial modules, using a hierarchical convolutional and diffusion structure to capture the intricate dynamics of physical systems. The experiments involved different spatio-temporal data, such as those from TaxiBJ and the Navier-Stokes dataset. According to the findings, ConvDiff demonstrates substantial improvements in essential performance indicators. For example, in the TaxiBJ dataset, ConvDiff obtained a mean squared deviation of 0.29 and a PSNR value of 40.31, outperforming the best-performing models. Moreover, on the Navier-Stokes dataset, ConvDiff reduced the MSE by 51.15% compared to the best baseline model. These results indicate that ConvDiff effectively captures complex spatio-temporal dependencies and improves prediction accuracy, particularly in physics-driven dynamic systems. Our code is available at <span><span>https://github.com/Ray-zyy/ConvDiff</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"723 ","pages":"Article 122656"},"PeriodicalIF":6.8,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107573","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Subsequence heterogeneity contrastive learning for time series anomaly detection 时间序列异常检测的子序列异质性对比学习

IF 6.8 1区计算机科学

Information Sciences Pub Date : 2025-09-10 DOI: 10.1016/j.ins.2025.122680

Zhibin Zhang , Xiaohong Zhang , Qiang Li , Chun Huang , Tao Yin , Meng Yan

{"title":"Subsequence heterogeneity contrastive learning for time series anomaly detection","authors":"Zhibin Zhang , Xiaohong Zhang , Qiang Li , Chun Huang , Tao Yin , Meng Yan","doi":"10.1016/j.ins.2025.122680","DOIUrl":"10.1016/j.ins.2025.122680","url":null,"abstract":"<div><div>Time series anomaly detection is widely applied across various real-world scenarios. Recently, contrastive learning has shown remarkable ability in learning discriminative representations for detecting anomalies. However, most existing contrastive-based methods rely on complex contrastive mechanisms and specially designed model architectures, which make it difficult to maintain efficiency and flexibility across various application scenarios. To address this limitation, we introduce Subsequence-Heterogeneity that defined as the discrepancies in variation patterns and statistical characteristics between subsequences obtained through fixed-interval sampling, which are more pronounced in anomalous sequences than in normal ones. It can serve as a natural discrimination criterion and eliminate the need for complex contrastive mechanisms and specialized model architectures. Specifically, we adopt an efficient temporal hierarchical masking strategy with linear complexity to construct two branches for learning representations at different granularities. The Subsequence-Heterogeneity Contrastive Learning (SHCL) is implemented with different neural networks and enables flexible application to anomaly detection across diverse scenarios. Experiments on eight benchmark datasets demonstrate that SHCL not only achieves state-of-the-art performance with reduced time and resource costs but also significantly improves the ability of different neural networks to distinguish normal from anomalous patterns. The source code is publicly available at <span><span>https://github.com/Zhangzzbzzb/SHCL/</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"723 ","pages":"Article 122680"},"PeriodicalIF":6.8,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107070","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Escrow-free attribute based signature with constant-size for the internet of things 无托管的基于属性的签名与恒定大小的物联网

IF 6.8 1区计算机科学

Information Sciences Pub Date : 2025-09-10 DOI: 10.1016/j.ins.2025.122679

Xudong Liu , Xiaojun Tong , Yihui Wang

引用次数: 0

Energy-related controllability of corona product networks 电晕产品网络的能量相关可控性

IF 6.8 1区计算机科学

Information Sciences Pub Date : 2025-09-09 DOI: 10.1016/j.ins.2025.122654

Qiang Zhang , Junjie Huang , Bo Liu , Housheng Su , Alatancang Chen

引用次数: 0