# Federated Client Selection under Partial Visibility: A POMDP Approach with Spatio-Temporal Attention

arXiv: https://arxiv.org/abs/2605.11752 · HTML: https://mlsanity.com/paper/2605.11752/

## 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 (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [A Theoretical Analysis of Deep Q-Learning](https://mlsanity.com/paper/1901.00137/) (2019)
- [Federated Learning Under Intermittent Client Availability and Time-Varying Communication Constraints](https://mlsanity.com/paper/2205.06730/) (2022)
- [Convergence Analysis of Sequential Federated Learning on Heterogeneous Data](https://mlsanity.com/paper/2311.03154/) (2023)
- [FedFMC: Sequential Efficient Federated Learning on Non-iid Data](https://mlsanity.com/paper/2006.10937/) (2020)
- [Efficient Federated Learning against Heterogeneous and Non-stationary Client Unavailability](https://mlsanity.com/paper/2409.17446/) (2024)
- [Personalized Federated Learning with Attention-based Client Selection](https://mlsanity.com/paper/2312.15148/) (2023)
- [Snake Learning: A Communication- and Computation-Efficient Distributed Learning Framework for 6G](https://mlsanity.com/paper/2405.03372/) (2024)
- [FLASH-RL: Federated Learning Addressing System and Static Heterogeneity using Reinforcement Learning](https://mlsanity.com/paper/2311.06917/) (2023)
- [FedDRL: A Trustworthy Federated Learning Model Fusion Method Based on Staged Reinforcement Learning](https://mlsanity.com/paper/2307.13716/) (2023)
- [FedABC: Attention-Based Client Selection for Federated Learning with Long-Term View](https://mlsanity.com/paper/2507.20871/) (2025)
- [Adaptive Federated Learning Defences via Trust-Aware Deep Q-Networks](https://mlsanity.com/paper/2510.01261/) (2025)
- [EdgeFLow: Serverless Federated Learning via Sequential Model Migration in Edge Networks](https://mlsanity.com/paper/2603.02562/) (2026)

## 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.