Abstract:Federated learning relies on effective client selection to alleviate the performance degradation caused by data heterogeneity. Most existing methods assume full visibility of all clients at each communication round. However, in large-scale or edge-based deployments, the server can only access a subset of clients due to communication, mobility, or availability constraints, resulting in partial visibility where only a subset of clients is observable for aggregation in each communication round. In this paper, we formulate federated client selection under partial visibility as a Partially Observable Markov Decision Process (POMDP) and propose a Spatial-Temporal attention-based reinforcement learning framework. By integrating historical global models and client identity embeddings, the proposed method captures both the temporal contexts of training and the persistent characteristics of clients. Experimental results across multiple datasets demonstrate that our approach achieves superior performance compared to existing baselines in heterogeneous and partially visible settings, validating its effectiveness in addressing the challenges of incomplete observations in practical federated learning systems.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.11752 [cs.LG] |
| (or arXiv:2605.11752v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.11752 arXiv-issued DOI via DataCite (pending registration) |
From: Qijun Hou [view email]
[v1]
Tue, 12 May 2026 08:28:25 UTC (1,636 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。