arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.01039cs.LGcs.AI
收藏

面向联邦学习的自适应双加权框架通过分布外检测

Adaptive Dual-Weighting Framework for Federated Learning via Out-of-Distribution Detection

School of Software Technology, Zhejiang University(浙江大学软件技术学院);Zhejiang Key Laboratory of Digital-Intelligence Service Technology(浙江省数字智能服务技术重点实验室);School of Information Technology and Artificial Intelligence, Zhejiang University of Finance and Economics(浙江财经大学信息科技与人工智能学院);College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院);School of Intelligent Systems Engineering, Sun Yat-sen University(中山大学智能系统工程学院);Department of Electrical and Computer Engineering, New Jersey Institute of Technology(新泽西理工学院电子与计算机工程系)

Zhiwei Ling, Hailiang Zhao, Chao Zhang, Xiang Ao, Ziqi Wang, Cheng Zhang, Zhen Qin, Xinkui Zhao, Kingsum Chow, Yuanqing Wu, MengChu Zhou

AI总结:

FLood通过分布外检测机制,提出自适应双加权框架,提升联邦学习在非独立同分布数据下的收敛稳定性与泛化能力。

摘要:

联邦学习(FL)通过在大规模分布式服务节点上进行协同模型训练,同时保护数据隐私,成为边缘-云计算环境中智能服务系统的核心。然而,在现实世界的服务导向部署中,由异构用户、设备和应用场景生成的数据本质上是非独立同分布(non-IID)的。这种严重的数据异质性严重削弱了全局模型的收敛稳定性、泛化能力,最终影响服务质量。为了解决这一挑战,我们提出了FLood,一种受分布外检测(OOD)启发的新型FL框架。FLood通过双加权机制动态对抗异质性带来的负面影响,共同管理本地训练和全局聚合。在客户端层面,它通过加重伪OOD样本的监督损失,自适应地重新加权,从而鼓励从分布不一致或具有挑战性的数据中学习更稳健的模型。在服务器层面,它通过根据客户端的OOD置信度分数加权客户端贡献,优化模型聚合,优先考虑具有更高分布一致性客户端的更新,从而增强全局模型的鲁棒性和收敛稳定性。在多个基准测试中,针对多样化的非IID设置进行广泛实验,证明FLood在准确性和泛化能力上均优于现有最先进的FL方法。此外,FLood作为一项正交插件模块:它可以无缝集成到现有FL算法中,在异质性环境下提升其性能,而无需修改其核心优化逻辑。这些特性使FLood成为在现实世界联邦环境中部署可靠智能服务的实用且可扩展的解决方案。

英文摘要:

Federated Learning (FL) enables collaborative model training across large-scale distributed service nodes while preserving data privacy, making it a cornerstone of intelligent service systems in edge-cloud environments. However, in real-world service-oriented deployments, data generated by heterogeneous users, devices, and application scenarios are inherently non-IID. This severe data heterogeneity critically undermines the convergence stability, generalization ability, and ultimately the quality of service delivered by the global model. To address this challenge, we propose FLood, a novel FL framework inspired by out-of-distribution (OOD) detection. FLood dynamically counteracts the adverse effects of heterogeneity through a dual-weighting mechanism that jointly governs local training and global aggregation. At the client level, it adaptively reweights the supervised loss by upweighting pseudo-OOD samples, thereby encouraging more robust learning from distributionally misaligned or challenging data. At the server level, it refines model aggregation by weighting client contributions according to their OOD confidence scores, prioritizing updates from clients with higher in-distribution consistency and enhancing the global model's robustness and convergence stability. Extensive experiments across multiple benchmarks under diverse non-IID settings demonstrate that FLood consistently outperforms state-of-the-art FL methods in both accuracy and generalization. Furthermore, FLood functions as an orthogonal plug-in module: it seamlessly integrates with existing FL algorithms to boost their performance under heterogeneity without modifying their core optimization logic. These properties make FLood a practical and scalable solution for deploying reliable intelligent services in real-world federated environments.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑