发布求助
文献互助 智能选刊 最新文献

IEEE transactions on neural networks and learning systems最新文献

筛选
英文 中文
DA-PFL: Dynamic Affinity Aggregation in Personalized Federated Learning Under Class Imbalance. 类不平衡下个性化联邦学习的动态亲和聚合。
IF 10.4 1区 计算机科学
IEEE transactions on neural networks and learning systems Pub Date : 2025-09-03 DOI: 10.1109/tnnls.2025.3598818
Xu Yang,Jiyuan Feng,Yongxin Tong,Lingzhi Wang,Songyue Guo,Binxing Fang,Qing Liao
{"title":"DA-PFL: Dynamic Affinity Aggregation in Personalized Federated Learning Under Class Imbalance.","authors":"Xu Yang,Jiyuan Feng,Yongxin Tong,Lingzhi Wang,Songyue Guo,Binxing Fang,Qing Liao","doi":"10.1109/tnnls.2025.3598818","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3598818","url":null,"abstract":"Personalized federated learning (PFL) has become a hot research topic that can learn a personalized learning model for each client. Existing PFL models prefer to aggregate similar clients with similar data distribution to improve the performance of learning models. However, similarity-based PFL methods may exacerbate the class imbalance problem. In this article, we propose a novel dynamic affinity-based PFL (DA-PFL) model to alleviate the class imbalanced problem during federated learning. Specifically, we build an affinity metric from a complementary perspective to guide which clients should be aggregated. We then design a dynamic aggregation strategy that adjusts client aggregation based on the affinity metric in each round, thereby reducing the risk of class imbalance. Extensive experiments demonstrate that the proposed DA-PFL model can significantly improve the accuracy of each client in four real-world datasets with state-of-the-art comparison methods.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"303 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144960182","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
Privacy-Preserving Video Anomaly Detection: A Survey 隐私保护视频异常检测：综述
IF 10.4 1区 计算机科学
IEEE transactions on neural networks and learning systems Pub Date : 2025-09-03 DOI: 10.1109/tnnls.2025.3600252
Yang Liu, Siao Liu, Xiaoguang Zhu, Hao Yang, Jielin Li, Juncen Guo, Liangyu Teng, Dingkang Yang, Yan Wang, Jing Liu
{"title":"Privacy-Preserving Video Anomaly Detection: A Survey","authors":"Yang Liu, Siao Liu, Xiaoguang Zhu, Hao Yang, Jielin Li, Juncen Guo, Liangyu Teng, Dingkang Yang, Yan Wang, Jing Liu","doi":"10.1109/tnnls.2025.3600252","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3600252","url":null,"abstract":"","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"14 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144987699","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
Nesterov Accelerated Gradient Tracking With Adam for Distributed Online Optimization. 基于Adam的Nesterov加速梯度跟踪分布式在线优化。
IF 10.4 1区 计算机科学
IEEE transactions on neural networks and learning systems Pub Date : 2025-09-03 DOI: 10.1109/tnnls.2025.3604059
Yanxu Su,Qingyang Sheng,Xiasheng Shi,Chaoxu Mu,Changyin Sun
{"title":"Nesterov Accelerated Gradient Tracking With Adam for Distributed Online Optimization.","authors":"Yanxu Su,Qingyang Sheng,Xiasheng Shi,Chaoxu Mu,Changyin Sun","doi":"10.1109/tnnls.2025.3604059","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3604059","url":null,"abstract":"This article presents an accelerated distributed optimization algorithm for online optimization problems over large-scale networks. The proposed algorithm's iteration only relies on local computation and communication. To effectively adapt to dynamic changes and achieve a fast convergence rate while maintaining good convergence performance, we design a new algorithm called NGTAdam. This algorithm combines the Nesterov acceleration technique with an adaptive moment estimation method. The convergence of NGTAdam is evaluated by evaluating its dynamic regret through the use of linear system inequality. For online convex optimization problems, we provide an upper bound on the dynamic regret of NGTAdam, which depends on the initial conditions and the time-varying nature of the optimization problem. Moreover, we show that if the time-varying part of this upper bound is sublinear with time, the dynamic regret is also sublinear. Through a variety of numerical experiments, we demonstrate that NGTAdam outperforms state-of-the-art distributed online optimization algorithms.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"32 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144960179","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
Unveiling Group-Specific Distributed Concept Drift: A Fairness Imperative in Federated Learning 揭示群体特定的分布式概念漂移：联邦学习中的公平必要性
IF 10.4 1区 计算机科学
IEEE transactions on neural networks and learning systems Pub Date : 2025-09-01 DOI: 10.1109/tnnls.2025.3601834
Teresa Salazar, João Gama, Helder Araújo, Pedro Henriques Abreu
{"title":"Unveiling Group-Specific Distributed Concept Drift: A Fairness Imperative in Federated Learning","authors":"Teresa Salazar, João Gama, Helder Araújo, Pedro Henriques Abreu","doi":"10.1109/tnnls.2025.3601834","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3601834","url":null,"abstract":"","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"27 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144928064","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
Efficient High-Dimensional Learning With Adaptive Gaussian RBF Networks 基于自适应高斯RBF网络的高效高维学习
IF 10.4 1区 计算机科学
IEEE transactions on neural networks and learning systems Pub Date : 2025-08-28 DOI: 10.1109/tnnls.2025.3601366
Xiaoyu Gao, Xuetao Xie, Jian Wang, Sergey V. Ablameyko, Nikhil R. Pal
{"title":"Efficient High-Dimensional Learning With Adaptive Gaussian RBF Networks","authors":"Xiaoyu Gao, Xuetao Xie, Jian Wang, Sergey V. Ablameyko, Nikhil R. Pal","doi":"10.1109/tnnls.2025.3601366","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3601366","url":null,"abstract":"","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"25 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144915474","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
SSPPI: Cross-Modality Enhanced Protein–Protein Interaction Prediction From Sequence and Structure Perspectives 从序列和结构的角度预测跨模态增强的蛋白质相互作用
IF 10.4 1区 计算机科学
IEEE transactions on neural networks and learning systems Pub Date : 2025-08-28 DOI: 10.1109/tnnls.2025.3599927
Xiangpeng Bi, Wenjian Ma, Huasen Jiang, Weigang Lu, Zhiqiang Wei, Shugang Zhang
{"title":"SSPPI: Cross-Modality Enhanced Protein–Protein Interaction Prediction From Sequence and Structure Perspectives","authors":"Xiangpeng Bi, Wenjian Ma, Huasen Jiang, Weigang Lu, Zhiqiang Wei, Shugang Zhang","doi":"10.1109/tnnls.2025.3599927","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3599927","url":null,"abstract":"","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"38 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144915477","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
Recurrent Network Expansion for Class Incremental Learning 类增量学习的循环网络扩展
IF 10.4 1区 计算机科学
IEEE transactions on neural networks and learning systems Pub Date : 2025-08-27 DOI: 10.1109/tnnls.2025.3601373
Kai Jiang, Xueru Bai, Feng Zhou
{"title":"Recurrent Network Expansion for Class Incremental Learning","authors":"Kai Jiang, Xueru Bai, Feng Zhou","doi":"10.1109/tnnls.2025.3601373","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3601373","url":null,"abstract":"","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"6 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144911232","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
DSPFL: A Deep-Layer Sign Sharing Personalized Federated Learning Scheme for Mitigating Poisoning Attacks 一种缓解投毒攻击的深层签名共享个性化联邦学习方案
IF 10.4 1区 计算机科学
IEEE transactions on neural networks and learning systems Pub Date : 2025-08-27 DOI: 10.1109/tnnls.2025.3601078
Chenhao Xu, Nasrin Sohrabi, Youyang Qu, Hai Dong, Zahir Tari, Xun Yi
{"title":"DSPFL: A Deep-Layer Sign Sharing Personalized Federated Learning Scheme for Mitigating Poisoning Attacks","authors":"Chenhao Xu, Nasrin Sohrabi, Youyang Qu, Hai Dong, Zahir Tari, Xun Yi","doi":"10.1109/tnnls.2025.3601078","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3601078","url":null,"abstract":"","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"22 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144911231","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 Bioinspired Deep Learning Framework for Saliency-Based Image Quality Assessment 基于显著性的图像质量评估的生物启发深度学习框架
IF 10.4 1区 计算机科学
IEEE transactions on neural networks and learning systems Pub Date : 2025-08-26 DOI: 10.1109/tnnls.2025.3598716
Huasheng Wang, Yueran Ma, Hongchen Tan, Xiaochang Liu, Ying Chen, Hantao Liu
{"title":"A Bioinspired Deep Learning Framework for Saliency-Based Image Quality Assessment","authors":"Huasheng Wang, Yueran Ma, Hongchen Tan, Xiaochang Liu, Ying Chen, Hantao Liu","doi":"10.1109/tnnls.2025.3598716","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3598716","url":null,"abstract":"","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"13 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144905929","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
CRL: An Efficient Autonomous Exploration Framework for Large-Scale Environments With Contrastive-Driven Reinforcement Learning 基于对比驱动强化学习的大规模环境的高效自主探索框架
IF 10.4 1区 计算机科学
IEEE transactions on neural networks and learning systems Pub Date : 2025-08-26 DOI: 10.1109/tnnls.2025.3597164
Benke Gao, Hao Chen, Quan Liu, Hanqiang Deng, Jian Huang, Yan-Jun Liu
{"title":"CRL: An Efficient Autonomous Exploration Framework for Large-Scale Environments With Contrastive-Driven Reinforcement Learning","authors":"Benke Gao, Hao Chen, Quan Liu, Hanqiang Deng, Jian Huang, Yan-Jun Liu","doi":"10.1109/tnnls.2025.3597164","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3597164","url":null,"abstract":"","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"3 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144905928","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
首页 上一页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信