Pub Date : 2026-03-02DOI: 10.1109/TETC.2026.3667101
Mina Kato;Xun Yuan;Tiago Koketsu Rodrigues;Fengxiao Tang;Ming Zhao;Nei Kato
Federated learning (FL) relies on timely participation of multiple devices, yet the round time is often dominated by the slowest user under heterogeneous wireless conditions. In multi-base-station (multi-BS) environments with nonlinear concurrent uplink and diverse backhaul capacities, selecting an appropriate set of participants becomes a challenging combinatorial optimization problem. We cast the problem as a round-time–centric optimization with reference-latency-scaled fairness penalties to enforce diversity, cohort size, and BS load balance. To solve it efficiently, we propose a Breakout Local Search (BLS) solver that couples k-opt local refinement with approximate screening and adaptive three-mode perturbations under a wall-clock budget, enabling efficient exploration–exploitation. Extensive simulations under hotspot and throttled-backhaul scenarios show that the proposed method reduces round time by 80–90% compared with particle swarm optimization (PSO) and Random, and by 29–75% compared with Greedy and simulated annealing (SA), while lowering the overall objective by 80–84% relative to PSO and Random and 50–67% relative to Greedy and SA, across various diversity weights and target participant sizes. The results highlight the effectiveness of our BLS method in FL participant selection under realistic and difficult network conditions.
{"title":"Breakout Local Search for Load-Balanced Federated Learning in Multi-BS Networks","authors":"Mina Kato;Xun Yuan;Tiago Koketsu Rodrigues;Fengxiao Tang;Ming Zhao;Nei Kato","doi":"10.1109/TETC.2026.3667101","DOIUrl":"https://doi.org/10.1109/TETC.2026.3667101","url":null,"abstract":"Federated learning (FL) relies on timely participation of multiple devices, yet the round time is often dominated by the slowest user under heterogeneous wireless conditions. In multi-base-station (multi-BS) environments with nonlinear concurrent uplink and diverse backhaul capacities, selecting an appropriate set of participants becomes a challenging combinatorial optimization problem. We cast the problem as a round-time–centric optimization with reference-latency-scaled fairness penalties to enforce diversity, cohort size, and BS load balance. To solve it efficiently, we propose a Breakout Local Search (BLS) solver that couples k-opt local refinement with approximate screening and adaptive three-mode perturbations under a wall-clock budget, enabling efficient exploration–exploitation. Extensive simulations under hotspot and throttled-backhaul scenarios show that the proposed method reduces round time by 80–90% compared with particle swarm optimization (PSO) and Random, and by 29–75% compared with Greedy and simulated annealing (SA), while lowering the overall objective by 80–84% relative to PSO and Random and 50–67% relative to Greedy and SA, across various diversity weights and target participant sizes. The results highlight the effectiveness of our BLS method in FL participant selection under realistic and difficult network conditions.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":"14 1","pages":"364-376"},"PeriodicalIF":5.4,"publicationDate":"2026-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147429294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Among Advanced Persistent Threats in recent years, hackers have combined multiple defense evasion techniques to hide themselves from the detection of traditional antivirus software. For example, the combination of fileless malware and Living Off the Land techniques and abusing legitimate cloud services force the enterprises have gradually adopted the Endpoint Detection and Response (EDR) instead. However, EDR has the disadvantage that this tool may produce massive false alarms. This situation force security maintainer and analysts to be burdened with a large amount of additional analyses. We proposed an anomaly detection system based on graphs. First, we input a provenance graph containing threat intelligence constructed by the normal behaviors of the system. After that, the system learns the potential structured information from the provenance graph for detecting the abnormal behavior of a host. The results show that the proposed system can effectively detect abnormal event logs. Moreover, we reduce the number of false alarms by up to 97.67%. The improvement dramatically reduces the heavy burdens on the security maintainers from the analyses of the records. Furthermore, the performance of the designed system shows that the abnormal detection based on the graph neural network is superior to a traditional neural network.
在近年来的高级持续威胁中，黑客将多种防御规避技术结合起来，以躲避传统杀毒软件的检测。例如，无文件恶意软件与Off the Land技术的结合，以及对合法云服务的滥用，迫使企业逐渐采用端点检测和响应（EDR）代替。然而，EDR的缺点是该工具可能会产生大量的假警报。这种情况迫使安全维护人员和分析人员承担大量额外的分析工作。提出了一种基于图的异常检测系统。首先，我们输入一个包含威胁情报的来源图，该图由系统的正常行为构造而成。然后，系统从来源图中学习到潜在的结构化信息，用于检测主机的异常行为。实验结果表明，该系统能够有效地检测异常事件日志。此外，我们减少了高达97.67%的误报次数。这种改进极大地减轻了安全维护人员在分析记录方面的沉重负担。此外，所设计系统的性能表明，基于图神经网络的异常检测优于传统神经网络。
{"title":"Graph-Based Anomaly APT Attack Detection via Threat Intelligence","authors":"Chun-I Fan;Cheng-Han Shie;Ying-Chan Chang;Tao Ban;Tomohiro Morikawa;Takeshi Takahashi","doi":"10.1109/TETC.2026.3665235","DOIUrl":"https://doi.org/10.1109/TETC.2026.3665235","url":null,"abstract":"Among Advanced Persistent Threats in recent years, hackers have combined multiple defense evasion techniques to hide themselves from the detection of traditional antivirus software. For example, the combination of fileless malware and Living Off the Land techniques and abusing legitimate cloud services force the enterprises have gradually adopted the Endpoint Detection and Response (EDR) instead. However, EDR has the disadvantage that this tool may produce massive false alarms. This situation force security maintainer and analysts to be burdened with a large amount of additional analyses. We proposed an anomaly detection system based on graphs. First, we input a provenance graph containing threat intelligence constructed by the normal behaviors of the system. After that, the system learns the potential structured information from the provenance graph for detecting the abnormal behavior of a host. The results show that the proposed system can effectively detect abnormal event logs. Moreover, we reduce the number of false alarms by up to 97.67%. The improvement dramatically reduces the heavy burdens on the security maintainers from the analyses of the records. Furthermore, the performance of the designed system shows that the abnormal detection based on the graph neural network is superior to a traditional neural network.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":"14 1","pages":"348-363"},"PeriodicalIF":5.4,"publicationDate":"2026-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147429290","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-16DOI: 10.1109/TETC.2026.3662784
Tyler Nicewarner;Ali Allami;Dan Lin
Ensuring efficient task assignment and secure payment in mobile crowdsensing while preserving worker location privacy remains a challenging problem. Existing solutions either rely on expensive encryption schemes, employ blockchain-based verification that incurs high computational and gas costs, or use differential privacy techniques that degrade spatial accuracy. This paper introduces the Privacy-preserving Task Assignment and Payment (PTAP) framework, a lightweight solution built upon secure multi-party computation (SMPC). PTAP employs additive secret sharing and a challenge–response mechanism across three semi-honest servers to achieve anonymous task allocation and payment without blockchain or zero-knowledge proofs. The framework guarantees full unlinkability between worker identities, task locations, and payment records while maintaining accurate location-based assignment and supporting traceability for dispute resolution. Experimental evaluation using the MP-SPDZ framework demonstrates scalability to over 1.5 million workers and 7 million payment tokens. The average end-to-end completion time is approximately 35.4 seconds, with zero gas cost. Compared to the state-of-the-art AVeCQ system (Koutsos et al. 2025), which requires about 13 minutes and 37 MWei per transaction on the Goerli network for only 1,024 users. The results confirm PTAP’s efficiency, scalability, and strong privacy guarantees for large-scale mobile crowdsensing deployments.
在移动众测中，如何在保证员工位置隐私的同时，保证高效的任务分配和安全的支付，仍然是一个具有挑战性的问题。现有的解决方案要么依赖于昂贵的加密方案，要么采用基于区块链的验证，这会产生高昂的计算和天然气成本，要么使用降低空间精度的差分隐私技术。本文介绍了一种基于安全多方计算（SMPC）的轻量级解决方案——保护隐私的任务分配与支付（PTAP）框架。PTAP在三个半诚实服务器之间采用附加秘密共享和挑战响应机制，实现匿名任务分配和支付，无需区块链或零知识证明。该框架保证了工人身份、任务位置和支付记录之间的完全不可链接性，同时保持准确的基于位置的分配，并支持争议解决的可追溯性。使用MP-SPDZ框架的实验评估证明了超过150万工人和700万个支付代币的可扩展性。端到端平均完井时间约为35.4秒，无需耗费任何天然气成本。与最先进的AVeCQ系统（Koutsos et al. 2025）相比，Goerli网络上只有1,024个用户，每笔交易需要大约13分钟和37 MWei。结果证实了PTAP在大规模移动众测部署中的效率、可扩展性和强大的隐私保障。
{"title":"Anonymous Task Assignment and Worker Payment in Mobile Crowdsensing","authors":"Tyler Nicewarner;Ali Allami;Dan Lin","doi":"10.1109/TETC.2026.3662784","DOIUrl":"https://doi.org/10.1109/TETC.2026.3662784","url":null,"abstract":"Ensuring efficient task assignment and secure payment in mobile crowdsensing while preserving worker location privacy remains a challenging problem. Existing solutions either rely on expensive encryption schemes, employ blockchain-based verification that incurs high computational and gas costs, or use differential privacy techniques that degrade spatial accuracy. This paper introduces the Privacy-preserving Task Assignment and Payment (PTAP) framework, a lightweight solution built upon secure multi-party computation (SMPC). PTAP employs additive secret sharing and a challenge–response mechanism across three semi-honest servers to achieve anonymous task allocation and payment without blockchain or zero-knowledge proofs. The framework guarantees full unlinkability between worker identities, task locations, and payment records while maintaining accurate location-based assignment and supporting traceability for dispute resolution. Experimental evaluation using the MP-SPDZ framework demonstrates scalability to over 1.5 million workers and 7 million payment tokens. The average end-to-end completion time is approximately 35.4 seconds, with zero gas cost. Compared to the state-of-the-art AVeCQ system (Koutsos et al. 2025), which requires about 13 minutes and 37 MWei per transaction on the Goerli network for only 1,024 users. The results confirm PTAP’s efficiency, scalability, and strong privacy guarantees for large-scale mobile crowdsensing deployments.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":"14 1","pages":"332-347"},"PeriodicalIF":5.4,"publicationDate":"2026-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11397269","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147429297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-11DOI: 10.1109/TETC.2026.3661199
Andrea Augello;Ashish Gupta;Giuseppe Lo Re;Sajal K. Das
Federated Learning (FL) is a paradigm that enables collaborative machine learning without disclosing the local data of the participants. However, in real-world FL deployment scenarios, some unscrupolous clients may alter the training process to skew the global model towards their local optimum, unfairly prioritizing their data distribution. Their influence can degrade overall model performance for normal clients and reduce fairness in the system. We call this novel category of misbehaving clients “selfish”. This work proposes a Fair and Robust strategy for aggregation in the Federated Learning (FL) server to mitigate the effect of Selfish clients (FairRFL). FairRFL incorporates a novel technique to recover (or estimate) the true updates from selfish clients by using robust statistics, specifically the median of norms. The presented strategy, through the inclusion of the recovered updates in the aggregation process, is robust against selfish behavior. Through extensive empirical evaluations with WISDM-W and CIFAR-10 datasets, we observe that a selfish client can increase the model accuracy on its data by up to 39% and more than quadruple the accuracy variance among clients, which FairRFL can address perfectly and recover performance fairness across normal clients.
{"title":"FairRFL: Fair and Robust Federated Learning in the Presence of Selfish Clients","authors":"Andrea Augello;Ashish Gupta;Giuseppe Lo Re;Sajal K. Das","doi":"10.1109/TETC.2026.3661199","DOIUrl":"https://doi.org/10.1109/TETC.2026.3661199","url":null,"abstract":"Federated Learning (FL) is a paradigm that enables collaborative machine learning without disclosing the local data of the participants. However, in real-world FL deployment scenarios, some unscrupolous clients may alter the training process to skew the global model towards their local optimum, unfairly prioritizing their data distribution. Their influence can degrade overall model performance for normal clients and reduce fairness in the system. We call this novel category of misbehaving clients “selfish”. This work proposes a <bold>Fair</b> and <bold>R</b>obust strategy for aggregation in the <bold>Federated Learning (FL)</b> server to mitigate the effect of Selfish clients (FairRFL). FairRFL incorporates a novel technique to recover (or estimate) the true updates from selfish clients by using robust statistics, specifically the median of norms. The presented strategy, through the inclusion of the recovered updates in the aggregation process, is robust against selfish behavior. Through extensive empirical evaluations with WISDM-W and CIFAR-10 datasets, we observe that a selfish client can increase the model accuracy on its data by up to 39% and more than quadruple the accuracy variance among clients, which FairRFL can address perfectly and recover performance fairness across normal clients.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":"14 1","pages":"316-331"},"PeriodicalIF":5.4,"publicationDate":"2026-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11391495","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147429287","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-10DOI: 10.1109/TETC.2026.3661404
Ama Bandara;Fátima Rodríguez-Galán;Pau Talarn;Elana Pereira de Santana;Evgenii Vinogradov;Peter Haring Bolívar;Eduard Alarcón;Sergi Abadal
The concept of Wireless Network-on-Chip (WNoC) has emerged as a potential solution to address the escalating communication demands of modern computing systems due to its low-latency, versatility, and reconfigurability. However, for WNoC to fulfill its potential, it is essential to establish multiple high-speed wireless links across chips. Unfortunately, the compact and enclosed nature of computing packages introduces significant challenges in the form of Co-Channel Interference (CCI) and Inter-Symbol Interference (ISI), which not only hinder the deployment of multiple spatial channels, but also severely restrict the symbol rate of each individual channel. In this paper, we posit that Time Reversal (TR) could be effective in addressing both impairments in this static scenario, thanks to its spatiotemporal focusing capabilities even in the near-field. Through comprehensive full-wave simulations and bit error rate analysis in multiple chip layouts with multiple frequency bands, we provide evidence that TR can increase the symbol rate by an order of magnitude, enabling the deployment of multiple concurrent links and achieving aggregate speeds exceeding 100 Gb/s. Finally, we evaluate the impact of reducing the sampling rate of the TR filter on the achievable speeds, paving the way to practical TR-based wireless communications at the chip scale.
{"title":"Toward Scalable Multi-Chip Wireless Networks With Near-Field Time Reversal","authors":"Ama Bandara;Fátima Rodríguez-Galán;Pau Talarn;Elana Pereira de Santana;Evgenii Vinogradov;Peter Haring Bolívar;Eduard Alarcón;Sergi Abadal","doi":"10.1109/TETC.2026.3661404","DOIUrl":"https://doi.org/10.1109/TETC.2026.3661404","url":null,"abstract":"The concept of Wireless Network-on-Chip (WNoC) has emerged as a potential solution to address the escalating communication demands of modern computing systems due to its low-latency, versatility, and reconfigurability. However, for WNoC to fulfill its potential, it is essential to establish multiple high-speed wireless links across chips. Unfortunately, the compact and enclosed nature of computing packages introduces significant challenges in the form of Co-Channel Interference (CCI) and Inter-Symbol Interference (ISI), which not only hinder the deployment of multiple spatial channels, but also severely restrict the symbol rate of each individual channel. In this paper, we posit that Time Reversal (TR) could be effective in addressing both impairments in this static scenario, thanks to its spatiotemporal focusing capabilities even in the near-field. Through comprehensive full-wave simulations and bit error rate analysis in multiple chip layouts with multiple frequency bands, we provide evidence that TR can increase the symbol rate by an order of magnitude, enabling the deployment of multiple concurrent links and achieving aggregate speeds exceeding 100 Gb/s. Finally, we evaluate the impact of reducing the sampling rate of the TR filter on the achievable speeds, paving the way to practical TR-based wireless communications at the chip scale.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":"14 1","pages":"303-315"},"PeriodicalIF":5.4,"publicationDate":"2026-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11391496","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147429265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-05DOI: 10.1109/TETC.2025.3633547
{"title":"IEEE Transactions on Emerging Topics in Computing Publication Information","authors":"","doi":"10.1109/TETC.2025.3633547","DOIUrl":"https://doi.org/10.1109/TETC.2025.3633547","url":null,"abstract":"","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":"13 4","pages":"C2-C2"},"PeriodicalIF":5.4,"publicationDate":"2025-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11279973","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145674761","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Multi-view partial multi-label learning deals with scenarios where samples contain heterogeneous features and are associated with both relevant and corrupted labels. Existing methods struggle to effectively capture label-related features through adequate feature interaction while simultaneously integrating inter- and intra-view features. To address these challenges, we propose a robust and scalable framework, Class Activation Specific Features Collaborative Network, designed to handle feature heterogeneity and facilitate comprehensive feature fusion in multi-view partial multi-label learning. The framework integrates label-specific feature extraction with collaborative information propagation through two key components: 1) View-Specific Class Activation Map, which transforms multi-view features into compact class label representations and 2) Class Information Propagation Correction, which refines and propagates accurate class label information by leveraging graph convolutional networks and transformers. Additionally, we introduce a multi-faceted loss function that promotes robust feature learning and architectural stability via consistency-based structural loss, while improving generalization through knowledge distillation. Extensive experiments on benchmark datasets demonstrate that the proposed model significantly outperforms state-of-the-art methods in multi-view partial multi-label learning tasks.
多视图部分多标签学习处理样本包含异构特征并与相关和损坏标签相关联的场景。现有的方法很难通过充分的特征交互来有效地捕获与标签相关的特征，同时集成视图间和视图内的特征。为了解决这些挑战，我们提出了一个强大且可扩展的框架，类激活特定特征协作网络，旨在处理特征异质性并促进多视图部分多标签学习中的全面特征融合。该框架通过两个关键组件将特定于标签的特征提取与协同信息传播集成在一起：1)特定于视图的类激活图（View-Specific Class Activation Map），它将多视图特征转换为紧凑的类标签表示；2)类信息传播校正（Class information propagation Correction），它利用图卷积网络和变压器精炼和传播准确的类标签信息。此外，我们引入了一个多面损失函数，通过基于一致性的结构损失促进鲁棒特征学习和架构稳定性，同时通过知识蒸馏提高泛化。在基准数据集上的大量实验表明，所提出的模型在多视图部分多标签学习任务中显著优于最先进的方法。
{"title":"Multi-View Partial Multi-Label Learning via Class Activation Specific Features Collaborative Learning","authors":"Anhui Tan;Jianhang Xu;Weiping Ding;Jiye Liang;Witold Pedrycz","doi":"10.1109/TETC.2025.3629677","DOIUrl":"https://doi.org/10.1109/TETC.2025.3629677","url":null,"abstract":"Multi-view partial multi-label learning deals with scenarios where samples contain heterogeneous features and are associated with both relevant and corrupted labels. Existing methods struggle to effectively capture label-related features through adequate feature interaction while simultaneously integrating inter- and intra-view features. To address these challenges, we propose a robust and scalable framework, Class Activation Specific Features Collaborative Network, designed to handle feature heterogeneity and facilitate comprehensive feature fusion in multi-view partial multi-label learning. The framework integrates label-specific feature extraction with collaborative information propagation through two key components: 1) View-Specific Class Activation Map, which transforms multi-view features into compact class label representations and 2) Class Information Propagation Correction, which refines and propagates accurate class label information by leveraging graph convolutional networks and transformers. Additionally, we introduce a multi-faceted loss function that promotes robust feature learning and architectural stability via consistency-based structural loss, while improving generalization through knowledge distillation. Extensive experiments on benchmark datasets demonstrate that the proposed model significantly outperforms state-of-the-art methods in multi-view partial multi-label learning tasks.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":"13 4","pages":"1522-1535"},"PeriodicalIF":5.4,"publicationDate":"2025-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145729447","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-11-11DOI: 10.1109/TETC.2025.3629528
Koffka Khan
Federated learning (FL) often suffers from client heterogeneity – differences in data distributions and learning behavior across clients that can degrade the global model’s performance. This paper addresses this challenge with HIFLA (Hilbert-Inspired Federated Learning via Action Principles), a novel approach that leverages variational mechanics. HIFLA formulates the federated training process as the minimization of a global action functional, yielding entropy- regularized Euler–Lagrange dynamics for client and server updates. A key innovation is the introduction of an interaction potential among client models, which mitigates divergence caused by non-i.i.d. data by coupling their updates in the action formulation. Empirically, HIFLA improves model accuracy on heterogeneous FL benchmarks, outperforming standard methods in the presence of statistical heterogeneity. It also demonstrates enhanced robustness against adversarial clients: even when a fraction of participants behave maliciously or send corrupted updates, the HIFLA-based model converges reliably with minimal performance loss. Overall, our results indicate that an action-principle-driven paradigm can effectively tackle client heterogeneity and adversarial robustness in federated learning, paving the way for more resilient and generalizable FL systems.
联邦学习（FL）经常受到客户机异构性的困扰——客户机之间数据分布和学习行为的差异会降低全局模型的性能。本文通过HIFLA （Hilbert-Inspired Federated Learning via Action Principles）解决了这一挑战，HIFLA是一种利用变分机制的新方法。HIFLA将联邦训练过程表述为全局动作函数的最小化，为客户端和服务器更新产生熵-正则化欧拉-拉格朗日动态。一个关键的创新是引入了客户模型之间的交互潜力，这减轻了由非i.d引起的分歧。数据通过在动作公式中耦合它们的更新。从经验上看，HIFLA提高了异构FL基准上的模型准确性，在存在统计异质性的情况下优于标准方法。它还展示了针对对抗性客户端的增强鲁棒性：即使一小部分参与者行为恶意或发送损坏的更新，基于hifl的模型也能以最小的性能损失可靠地收敛。总体而言，我们的研究结果表明，行动原则驱动的范式可以有效地解决联邦学习中的客户异质性和对抗性鲁棒性，为更具弹性和可泛化的FL系统铺平道路。
{"title":"HIFLA: Hilbert-Inspired Federated Learning via Action Principles","authors":"Koffka Khan","doi":"10.1109/TETC.2025.3629528","DOIUrl":"https://doi.org/10.1109/TETC.2025.3629528","url":null,"abstract":"Federated learning (FL) often suffers from client heterogeneity – differences in data distributions and learning behavior across clients that can degrade the global model’s performance. This paper addresses this challenge with HIFLA (Hilbert-Inspired Federated Learning via Action Principles), a novel approach that leverages variational mechanics. HIFLA formulates the federated training process as the minimization of a global action functional, yielding entropy- regularized Euler–Lagrange dynamics for client and server updates. A key innovation is the introduction of an <italic>interaction potential</i> among client models, which mitigates divergence caused by non-i.i.d. data by coupling their updates in the action formulation. Empirically, HIFLA improves model accuracy on heterogeneous FL benchmarks, outperforming standard methods in the presence of statistical heterogeneity. It also demonstrates enhanced robustness against adversarial clients: even when a fraction of participants behave maliciously or send corrupted updates, the HIFLA-based model converges reliably with minimal performance loss. Overall, our results indicate that an action-principle-driven paradigm can effectively tackle client heterogeneity and adversarial robustness in federated learning, paving the way for more resilient and generalizable FL systems.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":"13 4","pages":"1536-1552"},"PeriodicalIF":5.4,"publicationDate":"2025-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145729326","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zeroing neural network (ZNN) with variable convergence parameter has been a research hotspot recently, and it can be divided into two categories: the varying-parameter ZNN (VP-ZNN) model, and the fuzzy-parameter ZNN (FP-ZNN) model. Both of the two models have their own advantages and disadvantages. VP-ZNN models are usually efficient but not intelligent, while FP-ZNN models are usually intelligent but not efficient. Inspired by the classic proportional–integral–derivative (PID) control technology, we proposed a novel proportional-integral-parameter ZNN (PIP-ZNN) model, which is both efficient and intelligent, to solve the quaternion-valued time-varying linear matrix inequalities (QVTV-LMI) problem. Integrated with adaptive convergence parameters (ACP), the PIP-ZNN model dynamically adjusts its convergence in response to error changes and then achieves optimized performance. Compared with FP-ZNN models which are based on fuzzy logic systems, the PID-based PIP-ZNN models are simpler and more efficient. With the incorporation of a robust activation function (RAF), the PIP-ZNN model demonstrates fixed-time stability and robustness in the presence of both attenuated and constant disturbances. Theoretical analyses in this paper establish the fixed-time stability and robustness of the PIP-ZNN model, including an estimation of the upper bound of the settling-time function. Numerical experiments here validate these advanced features further, emphasizing the efficacy and excellent performance of the proposed PIP-ZNN model.
{"title":"A Novel Proportional-Integral-Parameter Zeroing Neural Network and Its Application to the Quaternion-Valued Time-Varying Linear Matrix Inequality","authors":"Jiajie Luo;Jiguang Li;Lin Xiao;Jichun Li;Wenxing Ji;William Holderbaum;Peng Qi","doi":"10.1109/TETC.2025.3629357","DOIUrl":"https://doi.org/10.1109/TETC.2025.3629357","url":null,"abstract":"Zeroing neural network (ZNN) with variable convergence parameter has been a research hotspot recently, and it can be divided into two categories: the varying-parameter ZNN (VP-ZNN) model, and the fuzzy-parameter ZNN (FP-ZNN) model. Both of the two models have their own advantages and disadvantages. VP-ZNN models are usually efficient but not intelligent, while FP-ZNN models are usually intelligent but not efficient. Inspired by the classic proportional–integral–derivative (PID) control technology, we proposed a novel proportional-integral-parameter ZNN (PIP-ZNN) model, which is both efficient and intelligent, to solve the quaternion-valued time-varying linear matrix inequalities (QVTV-LMI) problem. Integrated with adaptive convergence parameters (ACP), the PIP-ZNN model dynamically adjusts its convergence in response to error changes and then achieves optimized performance. Compared with FP-ZNN models which are based on fuzzy logic systems, the PID-based PIP-ZNN models are simpler and more efficient. With the incorporation of a robust activation function (RAF), the PIP-ZNN model demonstrates fixed-time stability and robustness in the presence of both attenuated and constant disturbances. Theoretical analyses in this paper establish the fixed-time stability and robustness of the PIP-ZNN model, including an estimation of the upper bound of the settling-time function. Numerical experiments here validate these advanced features further, emphasizing the efficacy and excellent performance of the proposed PIP-ZNN model.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":"13 4","pages":"1565-1576"},"PeriodicalIF":5.4,"publicationDate":"2025-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145729402","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-11-05DOI: 10.1109/TETC.2025.3626943
Muhammad Ahmad;Manuel Mazzara;Salvatore Distefano;Adil Mehmood Khan;Muhammad Hassaan Farooq Butt;Muhammad Usama;Danfeng Hong
Hyperspectral image (HSI) classification plays a pivotal role in domains such as environmental monitoring, agriculture, and urban planning. Traditional methods, including conventional machine learning and convolutional neural networks (CNNs), often struggle to effectively capture intricate spectral-spatial features and global contextual information. Transformer-based models, while powerful in capturing long-range dependencies, often demand substantial computational resources, posing challenges in scenarios where labeled datasets are limited, as in HSI applications. To overcome such challenges, this work proposes GraphMamba, a hybrid model that combines spectral-spatial token generation, graph-based token prioritization, and cross-attention mechanisms. The model introduces a novel hybridization of state-space modeling and Gated Recurrent Units (GRU), capturing both linear and nonlinear spatial-spectral dynamics. This approach enhances the ability to model complex spatial-spectral relationships while maintaining scalability and computational efficiency across diverse HSI datasets. Through comprehensive experiments, we demonstrate that GraphMamba outperforms existing state-of-the-art models, offering a scalable and robust solution for complex HSI classification tasks.
{"title":"GraphMamba: Graph Tokenization Mamba for Hyperspectral Image Classification","authors":"Muhammad Ahmad;Manuel Mazzara;Salvatore Distefano;Adil Mehmood Khan;Muhammad Hassaan Farooq Butt;Muhammad Usama;Danfeng Hong","doi":"10.1109/TETC.2025.3626943","DOIUrl":"https://doi.org/10.1109/TETC.2025.3626943","url":null,"abstract":"Hyperspectral image (HSI) classification plays a pivotal role in domains such as environmental monitoring, agriculture, and urban planning. Traditional methods, including conventional machine learning and convolutional neural networks (CNNs), often struggle to effectively capture intricate spectral-spatial features and global contextual information. Transformer-based models, while powerful in capturing long-range dependencies, often demand substantial computational resources, posing challenges in scenarios where labeled datasets are limited, as in HSI applications. To overcome such challenges, this work proposes GraphMamba, a hybrid model that combines spectral-spatial token generation, graph-based token prioritization, and cross-attention mechanisms. The model introduces a novel hybridization of state-space modeling and Gated Recurrent Units (GRU), capturing both linear and nonlinear spatial-spectral dynamics. This approach enhances the ability to model complex spatial-spectral relationships while maintaining scalability and computational efficiency across diverse HSI datasets. Through comprehensive experiments, we demonstrate that GraphMamba outperforms existing state-of-the-art models, offering a scalable and robust solution for complex HSI classification tasks.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":"13 4","pages":"1510-1521"},"PeriodicalIF":5.4,"publicationDate":"2025-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145729314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：