Federated Client Selection under Partial Visibility: A POMDP Approach with Spatio-Temporal Attention
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 27 references that are in the map. First posted on arXiv 12 May 2026.
Builds on
17 of 27 references.
References · 17
- 2017Attention Is All You Needcited by 60,361
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2015Deep Reinforcement Learning with Double Q-learningcited by 1,745
- 2019A Theoretical Analysis of Deep Q-Learningcited by 215
- 2022Federated Learning Under Intermittent Client Availability and Time-Varying Communication Constraintscited by 30
- 2023Convergence Analysis of Sequential Federated Learning on Heterogeneous Datacited by 23
- 2020FedFMC: Sequential Efficient Federated Learning on Non-iid Datacited by 17
- 2024Efficient Federated Learning against Heterogeneous and Non-stationary Client Unavailabilitycited by 9
- 2023Personalized Federated Learning with Attention-based Client Selectioncited by 5
- 2024Snake Learning: A Communication- and Computation-Efficient Distributed Learning Framework for 6Gcited by 3
5 more
- 2023FLASH-RL: Federated Learning Addressing System and Static Heterogeneity using Reinforcement Learningcited by 2
- 2023FedDRL: A Trustworthy Federated Learning Model Fusion Method Based on Staged Reinforcement Learningcited by 1
- 2025FedABC: Attention-Based Client Selection for Federated Learning with Long-Term Viewcited by 1
- 2025Adaptive Federated Learning Defences via Trust-Aware Deep Q-Networkscited by 1
- 2026EdgeFLow: Serverless Federated Learning via Sequential Model Migration in Edge Networkscited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Conflict-Aware Client Selection for Multi-Server Federated Learning
- 2026Learning to Sync at the Edge: Client-Side Adaptive Synchronization for Federated Learning
- 2025Adaptive Client Selection via Q-Learning-based Whittle Index in Wireless Federated Learning
- 2024Ranking-based Client Selection with Imitation Learning for Efficient Federated Learning
- 2024On-Demand Model and Client Deployment in Federated Learning with Deep Reinforcement Learning
- 2025Optimized Local Updates in Federated Learning via Reinforcement Learning
- 2025AdRo-FL: Informed and Secure Client Selection for Federated Learning in the Presence of Adversarial Aggregator
- 2024Towards Fast Rates for Federated and Multi-Task Reinforcement Learning