解决联邦学习中数据异构与动态变化问题，提升模型准确性和鲁棒性。
Fed-REACT: Federated Representation Learning for Heterogeneous and Evolving Data
- 分两阶段：先本地学特征表示，再按表示聚类协作训练下游模型。
- 在真实数据集上，准确率和鲁棒性均优于传统联邦学习方法。
- 适合数据分布不均且随时间变化的场景，如跨设备医疗或金融应用。
针对集中式机器学习带来的高资源消耗和隐私问题，联邦学习（FL）成为一种高效替代方案，使客户端在本地数据不共享的前提下协同训练全局模型。然而，在实际部署中，客户端数据分布常随时间演变且存在显著差异，导致标准联邦学习算法性能下降。本文提出Fed-REACT框架，专为异构且动态演化数据设计。该框架采用两阶段机制：第一阶段，各客户端学习本地模型以提取数据特征表示；第二阶段，服务器基于这些表示动态将客户端聚类，并协调各簇内任务特定模型的训练，以支持分类或回归等下游任务。我们对表示学习阶段提供理论分析，并在真实数据集上实证表明，Fed-REACT在准确率和鲁棒性方面均表现更优。
原文摘要 · Abstract (English)
Motivated by the high resource costs and privacy concerns associated with centralized machine learning, federated learning (FL) has emerged as an efficient alternative that enables clients to collaboratively train a global model while keeping their data local. However, in real-world deployments, client data distributions often evolve over time and differ significantly across clients, introducing heterogeneity that degrades the performance of standard FL algorithms. In this work, we introduce Fed-REACT, a federated learning framework designed for heterogeneous and evolving client data. Fed-REACT combines representation learning with evolutionary clustering in a two-stage process: (1) in the first stage, each client learns a local model to extracts feature representations from its data; (2) in the second stage, the server dynamically groups clients into clusters based on these representations and coordinates cluster-wise training of task-specific models for downstream objectives such as classification or regression. We provide a theoretical analysis of the representation learning stage, and empirically demonstrate that Fed-REACT achieves superior accuracy and robustness on real-world datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。