Information Sciences最新文献_第2页

SWGCN: Synergy weighted graph convolutional network for multi-behavior recommendation SWGCN：多行为推荐的协同加权图卷积网络

IF 6.8 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2026-02-03 DOI: 10.1016/j.ins.2026.123177

Fangda Chen, Yueyang Wang, Chaoli Lou, Min Gao, Qingyu Xiong

Multi-behavior recommendation paradigms have emerged to capture diverse user activities, forecasting primary conversions (e.g., purchases) by leveraging secondary signals like browsing history. However, current graph-based methods often overlook cross-behavioral synergistic signals and the fine-grained intensity of individual actions. Motivated by the need to overcome these shortcomings, we introduce Synergy Weighted Graph Convolutional Network (SWGCN). SWGCN introduces two novel components: a Target Preference Weigher, which adaptively assigns weights to user-item interactions within each behavior, and a Synergy Alignment Task, which guides its training by leveraging an Auxiliary Preference Valuator. This task prioritizes interactions from synergistic signals that more accurately reflect user preferences. The performance of our model is rigorously evaluated through comprehensive tests on three open-source datasets, specifically Taobao, IJCAI, and Beibei. On the Taobao dataset, SWGCN yields relative gains of 112.49% and 156.36% in terms of Hit Ratio (HR) and Normalized Discounted Cumulative Gain (NDCG), respectively. It also yields consistent gains on IJCAI and Beibei, confirming its robustness and generalizability across various datasets. Our implementation is open-sourced and can be accessed via https://github.com/FangdChen/SWGCN.

多行为推荐模式的出现是为了捕捉不同的用户活动，通过利用浏览历史等次要信号来预测主要转换（例如，购买）。然而，目前基于图的方法往往忽略了跨行为的协同信号和个体行为的细粒度强度。为了克服这些缺点，我们引入了协同加权图卷积网络（SWGCN）。SWGCN引入了两个新组件：一个目标偏好加权器，它自适应地为每个行为中的用户-项目交互分配权重；一个协同对齐任务，它通过利用辅助偏好评估器来指导其训练。该任务优先考虑来自更准确反映用户偏好的协同信号的交互。我们的模型的性能通过三个开源数据集，特别是淘宝，IJCAI和贝贝的综合测试进行了严格的评估。在淘宝数据集上，SWGCN在命中率（HR）和归一化贴现累积增益（NDCG）方面的相对收益分别为112.49%和156.36%。它还在IJCAI和Beibei上产生一致的增益，证实了它在各种数据集上的稳健性和泛化性。我们的实现是开源的，可以通过https://github.com/FangdChen/SWGCN访问。

{"title":"SWGCN: Synergy weighted graph convolutional network for multi-behavior recommendation","authors":"Fangda Chen, Yueyang Wang, Chaoli Lou, Min Gao, Qingyu Xiong","doi":"10.1016/j.ins.2026.123177","DOIUrl":"10.1016/j.ins.2026.123177","url":null,"abstract":"<div><div>Multi-behavior recommendation paradigms have emerged to capture diverse user activities, forecasting primary conversions (e.g., purchases) by leveraging secondary signals like browsing history. However, current graph-based methods often overlook cross-behavioral synergistic signals and the fine-grained intensity of individual actions. Motivated by the need to overcome these shortcomings, we introduce <strong>S</strong>ynergy <strong>W</strong>eighted <strong>G</strong>raph <strong>C</strong>onvolutional <strong>N</strong>etwork (<strong>SWGCN</strong>). SWGCN introduces two novel components: a Target Preference Weigher, which adaptively assigns weights to user-item interactions within each behavior, and a Synergy Alignment Task, which guides its training by leveraging an Auxiliary Preference Valuator. This task prioritizes interactions from synergistic signals that more accurately reflect user preferences. The performance of our model is rigorously evaluated through comprehensive tests on three open-source datasets, specifically Taobao, IJCAI, and Beibei. On the Taobao dataset, SWGCN yields relative gains of 112.49% and 156.36% in terms of Hit Ratio (HR) and Normalized Discounted Cumulative Gain (NDCG), respectively. It also yields consistent gains on IJCAI and Beibei, confirming its robustness and generalizability across various datasets. Our implementation is open-sourced and can be accessed via <span><span>https://github.com/FangdChen/SWGCN</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"739 ","pages":"Article 123177"},"PeriodicalIF":6.8,"publicationDate":"2026-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146191143","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

Neural estimator-based finite-time formation control for manipulator end effectors with obstacle avoidance 基于神经估计的机械臂末端避障有限时间编队控制

IF 6.8 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2026-02-03 DOI: 10.1016/j.ins.2026.123196

Shuangsi Xue , Zihang Guo , Xiaodong Zheng , Hui Cao , Badong Chen

This paper tackles the challenge of formation tracking for multiple manipulator end effectors (MEEs) operating under aggregated perturbations. A neural estimator, which synergistically incorporates a neural network with an extended state, is proposed to achieve real-time identification and compensation of uncertainties and external disturbances, enhancing estimation convergence and precision. Concurrently, an angular artificial potential field (APF) is developed to enable smooth posture adaptation during obstacle avoidance by generating orientation-aware repulsive forces. The distributed controller guarantees the semi-global practical finite-time boundedness (SGPFTB) of formation errors, rigorously validated through Lyapunov-based theoretical proofs. Comparative simulations involving a five-manipulator system demonstrate the framework’s enhanced performance and resilience against obstacles and perturbations.

本文研究了多机械臂末端执行器（MEEs）在聚合扰动下的编队跟踪问题。提出了一种与扩展状态神经网络协同作用的神经估计器，实现了对不确定性和外部干扰的实时识别和补偿，提高了估计的收敛性和精度。同时，开发了一种角度人工势场（APF），通过产生方向感知斥力来实现避障过程中的平滑姿态适应。分布式控制器保证了编队误差的半全局实际有限时间有界性，并通过基于李雅普诺夫的理论证明进行了严格验证。涉及五机械臂系统的比较仿真证明了该框架对障碍物和扰动的增强性能和弹性。

引用次数: 0

Mathematical guarantees for trust region policy optimization 信任域策略优化的数学保证

IF 6.8 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2026-02-03 DOI: 10.1016/j.ins.2026.123190

Li Li , Xiangyu Luo , Xiaoyu Song

Policy gradient methods have achieved remarkable success in reinforcement learning, yet their performance critically depends on the step size selection during policy updates. Inappropriate step sizes can lead to drastic performance degradation or even training collapse. To mitigate this challenge, the trust region mechanism in TRPO formally guarantees stable policy gradient training through a bounded total variation divergence in consecutive policy iterations. This work establishes a tighter performance difference bound for the discounted return

| η (\overset{ˇ}{π}) - L_{π} (\overset{ˇ}{π}) | \leq \frac{2 ϵ γ}{{(1 - γ)}^{2}} α^{2}

, where

α

measures policy divergence and

ϵ

bounds advantage estimation errors. Leveraging mathematical induction, we rigorously analyze the total variation divergence between policy pairs, systematically quantifying the relationship between state advantage disparities and trajectory probability discrepancies. This formal proof reveals the fundamental mechanisms underlying policy improvement constraints, addressing key gaps in the intuitive proof of TRPO theory. Furthermore, our generalized framework demonstrates that any divergence metric satisfying specific axiomatic properties preserves the structural form of the monotonic improvement guarantee. These theoretical advances translate into practical engineering benefits, enabling more precise trust region sizing for safety-critical applications, including autonomous driving, robotic control, and large language model alignment. The tighter bounds provide concrete mathematical guidance for algorithm designers to balance the stability-efficiency tradeoff, minimizing reliance on exhaustive hyperparameter search.

策略梯度方法在强化学习中取得了显著的成功，但其性能严重依赖于策略更新过程中的步长选择。不适当的步长可能导致剧烈的性能下降甚至训练崩溃。为了缓解这一挑战，TRPO中的信任域机制通过连续策略迭代中的有界总变异散度正式保证了策略梯度训练的稳定性。这项工作为贴现收益|η(π ω)−Lπ(π ω)|≤2ϵγ(1−γ)2α2建立了更严格的性能差异界，其中α度量策略分歧和λ界优势估计误差。利用数学归纳法，我们严格分析了政策对之间的总变异差异，系统量化了状态优势差异与轨迹概率差异之间的关系。这一形式化证明揭示了政策改进约束的基本机制，解决了TRPO理论直观证明中的关键空白。进一步，我们的广义框架证明了任何满足特定公理性质的散度度量都保留了单调改进保证的结构形式。这些理论进步转化为实际工程效益，为安全关键应用（包括自动驾驶、机器人控制和大型语言模型对齐）提供更精确的信任区域大小。更严格的边界为算法设计者提供了具体的数学指导，以平衡稳定性和效率的权衡，最大限度地减少对穷举超参数搜索的依赖。

{"title":"Mathematical guarantees for trust region policy optimization","authors":"Li Li , Xiangyu Luo , Xiaoyu Song","doi":"10.1016/j.ins.2026.123190","DOIUrl":"10.1016/j.ins.2026.123190","url":null,"abstract":"<div><div>Policy gradient methods have achieved remarkable success in reinforcement learning, yet their performance critically depends on the step size selection during policy updates. Inappropriate step sizes can lead to drastic performance degradation or even training collapse. To mitigate this challenge, the trust region mechanism in TRPO formally guarantees stable policy gradient training through a bounded total variation divergence in consecutive policy iterations. This work establishes a tighter performance difference bound for the discounted return <span><math><mo>|</mo><mi>η</mi><mo>(</mo><mrow><mover><mi>π</mi><mo>ˇ</mo></mover></mrow><mo>)</mo><mo>−</mo><msub><mi>L</mi><mrow><mi>π</mi></mrow></msub><mo>(</mo><mrow><mover><mi>π</mi><mo>ˇ</mo></mover></mrow><mo>)</mo><mrow><mo>|</mo></mrow><mo>≤</mo><mfrac><mrow><mn>2</mn><mi>ϵ</mi><mi>γ</mi></mrow><msup><mrow><mo>(</mo><mn>1</mn><mo>−</mo><mi>γ</mi><mo>)</mo></mrow><mn>2</mn></msup></mfrac><msup><mi>α</mi><mn>2</mn></msup></math></span>, where <span><math><mi>α</mi></math></span> measures policy divergence and <span><math><mi>ϵ</mi></math></span> bounds advantage estimation errors. Leveraging mathematical induction, we rigorously analyze the total variation divergence between policy pairs, systematically quantifying the relationship between state advantage disparities and trajectory probability discrepancies. This formal proof reveals the fundamental mechanisms underlying policy improvement constraints, addressing key gaps in the intuitive proof of TRPO theory. Furthermore, our generalized framework demonstrates that any divergence metric satisfying specific axiomatic properties preserves the structural form of the monotonic improvement guarantee. These theoretical advances translate into practical engineering benefits, enabling more precise trust region sizing for safety-critical applications, including autonomous driving, robotic control, and large language model alignment. The tighter bounds provide concrete mathematical guidance for algorithm designers to balance the stability-efficiency tradeoff, minimizing reliance on exhaustive hyperparameter search.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"740 ","pages":"Article 123190"},"PeriodicalIF":6.8,"publicationDate":"2026-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146147425","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

Modelling safety distance rule-based automatic emergency braking systems using fuzzy timed petri nets 基于安全距离规则的自动紧急制动系统模糊定时petri网建模

IF 6.8 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2026-02-03 DOI: 10.1016/j.ins.2026.123185

Abdelilah Serji, El Bekkaye Mermri, Mohammed Blej

Automatic Emergency Braking (AEB) systems help prevent or reduce collisions by automatically applying brakes when drivers fail to react in time. This paper proposes a novel approach to model AEB systems using Fuzzy Timed Petri Nets (FTPN), integrating the 3-, 4-, and 5-second rules that define safety distance based on speed and distance. Our approach offers a cost-effective solution for real-time AEB control by modelling deceleration timing relative to vehicle speed and environment. FTPNs combine fuzzy logic with timed Petri nets to capture the uncertainty and timing in AEB scenarios. The proposed system models different rules to determine braking decisions using fuzzy variables such as vehicle speed, front distance, and safety margin. An expert system generates Fuzzy Timed Production Rules (FTPR), which are then converted to FTPNs for accurate modelling. This rule-to-model transformation is essential for system accuracy. Over 1000 models were tested in various scenarios, with top performers achieving critical delays under 0.003 s and over 90% verification success. This research contributes to road safety by enabling vehicles to make timely and informed braking decisions in emergencies.

自动紧急制动（AEB）系统通过在驾驶员未能及时反应时自动刹车来防止或减少碰撞。本文提出了一种使用模糊定时Petri网（FTPN）对AEB系统建模的新方法，该方法集成了基于速度和距离定义安全距离的3秒、4秒和5秒规则。我们的方法通过建模相对于车速和环境的减速时间，为实时AEB控制提供了一种经济有效的解决方案。ftpn将模糊逻辑与定时Petri网相结合，以捕获AEB场景中的不确定性和时序。该系统利用车辆速度、前方距离和安全裕度等模糊变量对不同规则进行建模，以确定制动决策。专家系统生成模糊定时生产规则（FTPR），然后将其转换为ftpn进行精确建模。这种规则到模型的转换对于系统的准确性是必不可少的。在各种场景中测试了超过1000个模型，其中表现最好的模型实现了0.003 s以下的关键延迟，并且验证成功率超过90%。这项研究通过使车辆在紧急情况下及时做出明智的制动决定，有助于道路安全。

{"title":"Modelling safety distance rule-based automatic emergency braking systems using fuzzy timed petri nets","authors":"Abdelilah Serji, El Bekkaye Mermri, Mohammed Blej","doi":"10.1016/j.ins.2026.123185","DOIUrl":"10.1016/j.ins.2026.123185","url":null,"abstract":"<div><div>Automatic Emergency Braking (AEB) systems help prevent or reduce collisions by automatically applying brakes when drivers fail to react in time. This paper proposes a novel approach to model AEB systems using Fuzzy Timed Petri Nets (FTPN), integrating the 3-, 4-, and 5-second rules that define safety distance based on speed and distance. Our approach offers a cost-effective solution for real-time AEB control by modelling deceleration timing relative to vehicle speed and environment. FTPNs combine fuzzy logic with timed Petri nets to capture the uncertainty and timing in AEB scenarios. The proposed system models different rules to determine braking decisions using fuzzy variables such as vehicle speed, front distance, and safety margin. An expert system generates Fuzzy Timed Production Rules (FTPR), which are then converted to FTPNs for accurate modelling. This rule-to-model transformation is essential for system accuracy. Over 1000 models were tested in various scenarios, with top performers achieving critical delays under 0.003 s and over 90% verification success. This research contributes to road safety by enabling vehicles to make timely and informed braking decisions in emergencies.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"739 ","pages":"Article 123185"},"PeriodicalIF":6.8,"publicationDate":"2026-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146191146","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

Space tree-based graph continuous cellular automaton for unit commitment and economic dispatch optimization 基于空间树型图连续元胞自动机的机组投入与经济调度优化

IF 6.8 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2026-02-03 DOI: 10.1016/j.ins.2026.123199

Siyi Zhou , Li’ao Chen , Xingyu Liang , Min Xia , Shi Liang , Jun Liu , Jiayue Hu

Unit Commitment (UC) and Economic Dispatch (ED) are core issues in the power system. In this paper we try to solve both problems jointly: UC-ED problem is a large-scale mixed-integer linear programming (MILP) problem. Algorithms based on mathematical optimization cannot solve large-scale problems, models based on heuristic algorithms tend to fall into local optima, and methods based on deep learning generally cannot directly handle constraint violations. To address UC-ED problem, a new framework: Space tree-based graph continuous cellular automaton (ST-GCCA) has been proposed. It extracts fused features through an autoencoder and decision tree, then uses deep boosted regression trees to generate initial solution of UC-ED problem, and finally employs graph continuous cellular automaton (GCCA) to optimize the solution, achieving economic and secure power system dispatch. Compared with traditional algorithms, it achieves 1400

\times

harmonic mean speedup improvement, making it possible to solve large-scale problems; compared to the most up-to-date AI approaches, it can explicitly handle safety constraints. While achieving speed improvements, it reached economic optimality and, more importantly, achieved zero constraint violations. The experimental results on the IEEE 30-bus and IEEE 118-bus test systems demonstrate our achievements, indicating that ST-GCCA can find the optimal solution to the UC-ED problem.

机组承诺（UC）和经济调度（ED）是电力系统中的核心问题。UC-ED问题是一个大规模混合整数线性规划（MILP）问题。基于数学优化的算法不能解决大规模问题，基于启发式算法的模型容易陷入局部最优，基于深度学习的方法一般不能直接处理约束违规。为了解决UC-ED问题，提出了一个新的框架：基于空间树的图连续元胞自动机（ST-GCCA）。通过自编码器和决策树提取融合特征，然后利用深度增强回归树生成UC-ED问题的初始解，最后利用图连续元胞自动机（GCCA）对解进行优化，实现电力系统经济安全调度。与传统算法相比，实现了1400x的谐波平均加速提升，使解决大规模问题成为可能；与最新的人工智能方法相比，它可以显式地处理安全约束。在提高速度的同时，实现了经济最优，更重要的是，实现了零约束违规。在IEEE 30总线和IEEE 118总线测试系统上的实验结果验证了我们的成果，表明ST-GCCA可以找到UC-ED问题的最优解。

{"title":"Space tree-based graph continuous cellular automaton for unit commitment and economic dispatch optimization","authors":"Siyi Zhou , Li’ao Chen , Xingyu Liang , Min Xia , Shi Liang , Jun Liu , Jiayue Hu","doi":"10.1016/j.ins.2026.123199","DOIUrl":"10.1016/j.ins.2026.123199","url":null,"abstract":"<div><div>Unit Commitment (UC) and Economic Dispatch (ED) are core issues in the power system. In this paper we try to solve both problems jointly: UC-ED problem is a large-scale mixed-integer linear programming (MILP) problem. Algorithms based on mathematical optimization cannot solve large-scale problems, models based on heuristic algorithms tend to fall into local optima, and methods based on deep learning generally cannot directly handle constraint violations. To address UC-ED problem, a new framework: Space tree-based graph continuous cellular automaton (ST-GCCA) has been proposed. It extracts fused features through an autoencoder and decision tree, then uses deep boosted regression trees to generate initial solution of UC-ED problem, and finally employs graph continuous cellular automaton (GCCA) to optimize the solution, achieving economic and secure power system dispatch. Compared with traditional algorithms, it achieves 1400<span><math><mo>×</mo></math></span> harmonic mean speedup improvement, making it possible to solve large-scale problems; compared to the most up-to-date AI approaches, it can explicitly handle safety constraints. While achieving speed improvements, it reached economic optimality and, more importantly, achieved zero constraint violations. The experimental results on the IEEE 30-bus and IEEE 118-bus test systems demonstrate our achievements, indicating that ST-GCCA can find the optimal solution to the UC-ED problem.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"739 ","pages":"Article 123199"},"PeriodicalIF":6.8,"publicationDate":"2026-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146191149","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

Communication-efficient decentralized federated graph learning via knowledge distillation under dual heterogeneity 双异构下基于知识蒸馏的高效通信分散联邦图学习

IF 6.8 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2026-02-02 DOI: 10.1016/j.ins.2026.123192

Guojiang Shen , Xu Guo , Haopeng Yuan , Jiaxin Du , Wenyi Zhang , Y. Neil Qu , Xiangjie Kong

Federated Graph Learning (FGL) integrates the privacy-preserving advantages of federated learning with the structural data modeling capabilities of graph neural networks. To mitigate single points of failure and communication bottlenecks inherent in server-based federated learning, we focus on Decentralized Federated Graph Learning (DFGL), which facilitates efficient distributed training in a peer-to-peer (P2P) manner. However, existing approaches predominantly rely on the direct exchange of gradients or model parameters. Under constrained communication resources and dual heterogeneity (data and model), such approaches often suffer from reduced training efficiency and suboptimal performance. To address these issues, we propose DFedGD, a decentralized federated graph learning framework that integrates graph condensation with knowledge distillation. Specifically, DFedGD extracts representative knowledge by synthesizing condensed subgraphs that approximate the global data distribution within a fully decentralized environment. Clients exchange and learn from condensed subgraphs and logits via a mutual knowledge distillation mechanism, thereby enhancing communication efficiency and privacy preservation while naturally supporting model heterogeneity. Furthermore, an alignment mechanism based on shared anchor samples is incorporated to enforce latent representation consistency, effectively mitigating domain shifts arising from non-IID data distributions. Extensive experiments on three publicly available datasets demonstrate that our framework outperforms competitive baselines.

联邦图学习（FGL）将联邦学习的隐私保护优势与图神经网络的结构数据建模能力相结合。为了缓解基于服务器的联邦学习中固有的单点故障和通信瓶颈，我们专注于分散式联邦图学习（DFGL），它以点对点（P2P）的方式促进了高效的分布式训练。然而，现有的方法主要依赖于梯度或模型参数的直接交换。在通信资源受限和数据和模型双重异构的情况下，这种方法往往存在训练效率降低和性能次优的问题。为了解决这些问题，我们提出了DFedGD，这是一个分散的联邦图学习框架，它集成了图冷凝和知识蒸馏。具体来说，DFedGD通过合成在完全分散的环境中近似全局数据分布的压缩子图来提取代表性知识。客户端通过相互的知识蒸馏机制从压缩的子图和逻辑中交换和学习，从而提高了通信效率和隐私保护，同时自然地支持模型的异构性。此外，采用基于共享锚点样本的对齐机制来增强潜在表示一致性，有效减轻非iid数据分布引起的域偏移。在三个公开可用的数据集上进行的大量实验表明，我们的框架优于竞争性基线。

{"title":"Communication-efficient decentralized federated graph learning via knowledge distillation under dual heterogeneity","authors":"Guojiang Shen , Xu Guo , Haopeng Yuan , Jiaxin Du , Wenyi Zhang , Y. Neil Qu , Xiangjie Kong","doi":"10.1016/j.ins.2026.123192","DOIUrl":"10.1016/j.ins.2026.123192","url":null,"abstract":"<div><div>Federated Graph Learning (FGL) integrates the privacy-preserving advantages of federated learning with the structural data modeling capabilities of graph neural networks. To mitigate single points of failure and communication bottlenecks inherent in server-based federated learning, we focus on Decentralized Federated Graph Learning (DFGL), which facilitates efficient distributed training in a peer-to-peer (P2P) manner. However, existing approaches predominantly rely on the direct exchange of gradients or model parameters. Under constrained communication resources and dual heterogeneity (data and model), such approaches often suffer from reduced training efficiency and suboptimal performance. To address these issues, we propose DFedGD, a decentralized federated graph learning framework that integrates graph condensation with knowledge distillation. Specifically, DFedGD extracts representative knowledge by synthesizing condensed subgraphs that approximate the global data distribution within a fully decentralized environment. Clients exchange and learn from condensed subgraphs and logits via a mutual knowledge distillation mechanism, thereby enhancing communication efficiency and privacy preservation while naturally supporting model heterogeneity. Furthermore, an alignment mechanism based on shared anchor samples is incorporated to enforce latent representation consistency, effectively mitigating domain shifts arising from non-IID data distributions. Extensive experiments on three publicly available datasets demonstrate that our framework outperforms competitive baselines.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"739 ","pages":"Article 123192"},"PeriodicalIF":6.8,"publicationDate":"2026-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146191144","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

Model-based fault-tolerant optimal control of fractional-order singular systems optimized via a novel data-driven approach 基于模型的分数阶奇异系统容错最优控制

IF 6.8 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2026-02-02 DOI: 10.1016/j.ins.2026.123175

Vahid Safari Dehnavi, Masoud Shafiee, Mehdi Mirshahi

This paper presents a novel control framework for fractional-order singular systems (FOSS) that accounts for faults and disturbances. This framework includes four steps: homotopy-based optimal control, fault and disturbance estimation, data-driven optimal control, and data-driven estimation refinement. In the first step, we utilize the iterative homotopy algorithm, the Volterra integral, the Leibniz integral rule, and the boundary condition transformation for optimal control. This algorithm gradually transitions the simple system to the real model with guaranteed stable convergence. The second step simultaneously estimates faults and disturbances by an augmented system. The stability and convergence of the observer are analyzed via Lyapunov theory and linear matrix inequalities (LMI). In the third step, estimation errors and system uncertainties are mitigated by a data-driven approach that utilizes the Lyapunov function. This method utilizes the sampling theorem and is synchronized with the optimal control cost function. In the fourth step, an ant-grasshopper optimization algorithm with the ant’s queen model is designed to estimate uncertainties that have specific patterns. The proposed approach is validated by simulation on a multi-agent system experiencing simultaneous faults and disturbances. In the proposed method, each agent acts as an intelligent entity that interacts with others. This simulation is presented for a near-realistic situation in a biomedical application.

提出了一种考虑故障和扰动的分数阶奇异系统控制框架。该框架包括四个步骤：基于同伦的最优控制、故障和干扰估计、数据驱动的最优控制和数据驱动的估计改进。在第一步中，我们利用迭代同伦算法、Volterra积分、Leibniz积分规则和边界条件变换来进行最优控制。该算法将简单系统逐步过渡到保证稳定收敛的真实模型。第二步同时估计增强系统的故障和干扰。利用李雅普诺夫理论和线性矩阵不等式（LMI）分析了观测器的稳定性和收敛性。在第三步中，利用Lyapunov函数的数据驱动方法减轻了估计误差和系统不确定性。该方法利用了抽样定理，并与最优控制代价函数同步。第四步，利用蚁后模型设计蚁蚱蜢优化算法，对具有特定模式的不确定性进行估计。在一个同时存在故障和干扰的多智能体系统上进行了仿真验证。在提出的方法中，每个代理都充当与其他代理交互的智能实体。该模拟是针对生物医学应用中接近真实的情况提出的。

{"title":"Model-based fault-tolerant optimal control of fractional-order singular systems optimized via a novel data-driven approach","authors":"Vahid Safari Dehnavi, Masoud Shafiee, Mehdi Mirshahi","doi":"10.1016/j.ins.2026.123175","DOIUrl":"10.1016/j.ins.2026.123175","url":null,"abstract":"<div><div>This paper presents a novel control framework for fractional-order singular systems (FOSS) that accounts for faults and disturbances. This framework includes four steps: homotopy-based optimal control, fault and disturbance estimation, data-driven optimal control, and data-driven estimation refinement. In the first step, we utilize the iterative homotopy algorithm, the Volterra integral, the Leibniz integral rule, and the boundary condition transformation for optimal control. This algorithm gradually transitions the simple system to the real model with guaranteed stable convergence. The second step simultaneously estimates faults and disturbances by an augmented system. The stability and convergence of the observer are analyzed via Lyapunov theory and linear matrix inequalities (LMI). In the third step, estimation errors and system uncertainties are mitigated by a data-driven approach that utilizes the Lyapunov function. This method utilizes the sampling theorem and is synchronized with the optimal control cost function. In the fourth step, an ant-grasshopper optimization algorithm with the ant’s queen model is designed to estimate uncertainties that have specific patterns. The proposed approach is validated by simulation on a multi-agent system experiencing simultaneous faults and disturbances. In the proposed method, each agent acts as an intelligent entity that interacts with others. This simulation is presented for a near-realistic situation in a biomedical application.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"739 ","pages":"Article 123175"},"PeriodicalIF":6.8,"publicationDate":"2026-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146191145","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

Machine learning and deep learning techniques for detecting brown spot and narrow brown spot diseases in paddy (Oryza sativa): Algorithms, challenges, and future prospects 水稻褐斑病和窄褐斑病检测的机器学习和深度学习技术：算法、挑战和未来展望

IF 6.8 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2026-02-02 DOI: 10.1016/j.ins.2026.123195

Fredy William Amon, Bhabesh Nath, Dhruba Kumar Bhattacharyya

The reviewed studies demonstrate that host plant resistance is a viable strategy for managing brown spot (BS) disease in paddy. However, challenges such as limited resistant varieties and environmental influences persist. Resistant genotypes like PARC-7 and IRRI-43 show promise, but breeding efforts must prioritise stability, yield, and genotype-environment interactions through multilocation testing. Accurate disease diagnosis, particularly distinguishing BS from narrow brown spot (NBS) based on lesion morphology, is critical for effective management. Meanwhile, AI-based disease monitoring presents opportunities but faces challenges in model selection, balancing accuracy with deployability. While advanced deep learning architectures show potential, issues such as lesion heterogeneity, data scarcity, and real-world variability hinder practical implementation. Future research must focus on robust data collection, improved image processing, lightweight AI models, and enhanced feature extraction to bridge the gap between controlled experiments and field applications. Addressing these challenges will be essential for developing reliable and scalable solutions to support sustainable rice production.

综上所述，寄主植物抗性是防治水稻褐斑病的一种可行策略。然而，诸如有限的抗性品种和环境影响等挑战仍然存在。抗性基因型如PARC-7和IRRI-43显示出希望，但育种工作必须通过多地点测试优先考虑稳定性、产量和基因型与环境的相互作用。准确的疾病诊断，特别是根据病变形态区分BS和窄棕色斑（NBS），对于有效的治疗至关重要。同时，基于人工智能的疾病监测提供了机遇，但在模型选择、平衡准确性和可部署性方面面临挑战。虽然先进的深度学习架构显示出潜力，但病变异质性、数据稀缺性和现实世界的可变性等问题阻碍了实际实施。未来的研究必须集中在稳健的数据收集、改进的图像处理、轻量级的人工智能模型和增强的特征提取上，以弥合控制实验和现场应用之间的差距。应对这些挑战对于制定可靠和可扩展的解决方案以支持可持续水稻生产至关重要。

{"title":"Machine learning and deep learning techniques for detecting brown spot and narrow brown spot diseases in paddy (Oryza sativa): Algorithms, challenges, and future prospects","authors":"Fredy William Amon, Bhabesh Nath, Dhruba Kumar Bhattacharyya","doi":"10.1016/j.ins.2026.123195","DOIUrl":"10.1016/j.ins.2026.123195","url":null,"abstract":"<div><div>The reviewed studies demonstrate that host plant resistance is a viable strategy for managing brown spot (BS) disease in paddy. However, challenges such as limited resistant varieties and environmental influences persist. Resistant genotypes like PARC-7 and IRRI-43 show promise, but breeding efforts must prioritise stability, yield, and genotype-environment interactions through multilocation testing. Accurate disease diagnosis, particularly distinguishing BS from narrow brown spot (NBS) based on lesion morphology, is critical for effective management. Meanwhile, AI-based disease monitoring presents opportunities but faces challenges in model selection, balancing accuracy with deployability. While advanced deep learning architectures show potential, issues such as lesion heterogeneity, data scarcity, and real-world variability hinder practical implementation. Future research must focus on robust data collection, improved image processing, lightweight AI models, and enhanced feature extraction to bridge the gap between controlled experiments and field applications. Addressing these challenges will be essential for developing reliable and scalable solutions to support sustainable rice production.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"739 ","pages":"Article 123195"},"PeriodicalIF":6.8,"publicationDate":"2026-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146191142","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

Weakly supervised object localization via frequency guidance with consistency awareness 带有一致性意识的频率引导弱监督目标定位

IF 6.8 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2026-01-31 DOI: 10.1016/j.ins.2026.123186

Bingfeng Li , Erdong Shi , Boxiang Lv , Qingshan Chen , Jiayu Zhang , Haoran Feng , Shuai Wang

Weakly supervised object localization (WSOL) aims to localize object regions using only image-level labels, avoiding costly bounding box annotations. Recent methods employ foreground prediction map (FPM) to distinguish foreground from background and improve localization completeness. However, FPM-based approaches often rely on background modeling, which can introduce semantic ambiguity due to the inherent uncertainty of background regions. To address this, we propose the Frequency-Guided and Consistency-Aware (FGCA) Network, which enhances foreground modeling without relying on background modeling. FGCA first employs a Wavelet-Frequency Attention Module (WFAM) to decompose features into low- and high-frequency components, selectively enhancing semantic and fine-grained structural information. Subsequently, a consistency-aware optimization framework is introduced to enhance the semantic coherence and structural integrity of the predicted foreground by incorporating complementary constraints from both local and global perspectives. Specifically, the Semantic-Spatial Consistency Loss (SSCL) enforces fine-grained consistency by integrating category-specific discrimination and pixel-level structural smoothness. In parallel, the Foreground-Global Kullback–Leibler Alignment Loss (FG-KL) regularizes the global semantic distribution of the foreground, guiding the network to emphasize contextually relevant object regions while suppressing background-induced noise. Experiments on standard WSOL benchmarks show that FGCA outperforms state-of-the-art methods, particularly in foreground completeness, boundary precision, and semantic consistency.

弱监督对象定位（WSOL）旨在仅使用图像级别的标签来定位对象区域，避免代价高昂的边界框注释。最近的方法采用前景预测图（FPM）来区分前景和背景，提高定位的完整性。然而，基于fpm的方法往往依赖于背景建模，由于背景区域固有的不确定性，这可能会引入语义模糊。为了解决这个问题，我们提出了频率引导和一致性感知（FGCA）网络，它在不依赖背景建模的情况下增强了前景建模。FGCA首先采用小波频率注意模块（WFAM）将特征分解为低频和高频分量，选择性地增强语义和细粒度结构信息。随后，引入一致性感知优化框架，通过从局部和全局角度结合互补约束，增强预测前景的语义一致性和结构完整性。具体来说，语义空间一致性损失（SSCL）通过集成特定类别的区分和像素级的结构平滑来加强细粒度的一致性。同时，前景-全局Kullback-Leibler对齐损失（FG-KL）对前景的全局语义分布进行正则化，引导网络强调上下文相关的目标区域，同时抑制背景引起的噪声。在标准WSOL基准测试上的实验表明，FGCA优于最先进的方法，特别是在前景完整性、边界精度和语义一致性方面。

{"title":"Weakly supervised object localization via frequency guidance with consistency awareness","authors":"Bingfeng Li , Erdong Shi , Boxiang Lv , Qingshan Chen , Jiayu Zhang , Haoran Feng , Shuai Wang","doi":"10.1016/j.ins.2026.123186","DOIUrl":"10.1016/j.ins.2026.123186","url":null,"abstract":"<div><div>Weakly supervised object localization (WSOL) aims to localize object regions using only image-level labels, avoiding costly bounding box annotations. Recent methods employ foreground prediction map (FPM) to distinguish foreground from background and improve localization completeness. However, FPM-based approaches often rely on background modeling, which can introduce semantic ambiguity due to the inherent uncertainty of background regions. To address this, we propose the Frequency-Guided and Consistency-Aware (FGCA) Network, which enhances foreground modeling without relying on background modeling. FGCA first employs a Wavelet-Frequency Attention Module (WFAM) to decompose features into low- and high-frequency components, selectively enhancing semantic and fine-grained structural information. Subsequently, a consistency-aware optimization framework is introduced to enhance the semantic coherence and structural integrity of the predicted foreground by incorporating complementary constraints from both local and global perspectives. Specifically, the Semantic-Spatial Consistency Loss (SSCL) enforces fine-grained consistency by integrating category-specific discrimination and pixel-level structural smoothness. In parallel, the Foreground-Global Kullback–Leibler Alignment Loss (FG-KL) regularizes the global semantic distribution of the foreground, guiding the network to emphasize contextually relevant object regions while suppressing background-induced noise. Experiments on standard WSOL benchmarks show that FGCA outperforms state-of-the-art methods, particularly in foreground completeness, boundary precision, and semantic consistency.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"739 ","pages":"Article 123186"},"PeriodicalIF":6.8,"publicationDate":"2026-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146191065","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

Non-negative transfer space learning based on label release and graph embedding for small sample face recognition 基于标签释放和图嵌入的小样本人脸识别非负迁移空间学习

IF 6.8 1区计算机科学 0 COMPUTER SCIENCE, INFORMATION SYSTEMS

Information Sciences

Pub Date : 2026-01-31 DOI: 10.1016/j.ins.2026.123169

Mengmeng Liao , Jiahao Qin , Yuwei Du

This paper proposes NTLG, a novel method for small-sample facial recognition, addressing two key limitations of traditional approaches: sensitivity to data bias and ineffective use of label information. NTLG introduces three innovations: (1) decomposing complex parameter optimization into simpler subtasks, (2) enhancing inter-class discrimination via label propagation, and (3) improving robustness through feature extraction and data reconstruction. Experiments demonstrate that NTLG significantly boosts accuracy while maintaining efficiency, outperforming state-of-the-art methods in small-sample scenarios.

本文提出了一种用于小样本面部识别的新方法NTLG，解决了传统方法的两个关键局限性：对数据偏差的敏感性和对标签信息的无效使用。NTLG引入了三个创新：(1)将复杂的参数优化分解为更简单的子任务；(2)通过标签传播增强类间判别；(3)通过特征提取和数据重构提高鲁棒性。实验表明，NTLG在保持效率的同时显著提高了准确性，在小样本场景中优于最先进的方法。

引用次数: 0