# MAB-Based Channel Scheduling for Asynchronous Federated Learning in Non-Stationary Environments

arXiv: https://arxiv.org/abs/2503.01324 · HTML: https://mlsanity.com/paper/2503.01324/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 42 references that are in the map.
- First posted on arXiv 3 Mar 2025.

## Builds on (most cited first, 24 of 24)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (2018)
- [Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification](https://mlsanity.com/paper/1909.06335/) (2019)
- [Data Shapley: Equitable Valuation of Data for Machine Learning](https://mlsanity.com/paper/1904.02868/) (2019)
- [Federated Learning on Non-IID Data Silos: An Experimental Study](https://mlsanity.com/paper/2102.02079/) (2021)
- [Agnostic Federated Learning](https://mlsanity.com/paper/1902.00146/) (2019)
- [Asynchronous Federated Optimization](https://mlsanity.com/paper/1903.03934/) (2019)
- [Collaborative Fairness in Federated Learning](https://mlsanity.com/paper/2008.12161/) (2020)
- [SAFA: a Semi-Asynchronous Protocol for Fast Federated Learning with Low Overhead](https://mlsanity.com/paper/1910.01355/) (2019)
- [An Efficiency-boosting Client Selection Scheme for Federated Learning with Fairness Guarantee](https://mlsanity.com/paper/2011.01783/) (2020)
- [Fair Federated Medical Image Segmentation via Client Contribution Estimation](https://mlsanity.com/paper/2303.16520/) (2023)
- [Blind Federated Edge Learning](https://mlsanity.com/paper/2010.10030/) (2020)
- [A Reputation Mechanism Is All You Need: Collaborative Fairness and Adversarial Robustness in Federated Learning](https://mlsanity.com/paper/2011.10464/) (2020)
- [Age-Based Scheduling Policy for Federated Learning in Mobile Edge Networks](https://mlsanity.com/paper/1910.14648/) (2019)
- [Jamming Attacks and Anti-Jamming Strategies in Wireless Networks: A Comprehensive Survey](https://mlsanity.com/paper/2101.00292/) (2021)
- [Toward Understanding the Impact of Staleness in Distributed Machine Learning](https://mlsanity.com/paper/1810.03264/) (2018)
- [Learning Unknown Service Rates in Queues: A Multi-Armed Bandit Approach](https://mlsanity.com/paper/1604.06377/) (2016)
- [Towards Efficient and Stable K-Asynchronous Federated Learning with Unbounded Stale Gradients on Non-IID Data](https://mlsanity.com/paper/2203.01214/) (2022)
- [Blind Federated Learning via Over-the-Air q-QAM](https://mlsanity.com/paper/2311.04253/) (2023)
- [A General 3D Non-Stationary Wireless Channel Model for 5G and Beyond](https://mlsanity.com/paper/2101.06610/) (2021)
- [A Near-Optimal Change-Detection Based Algorithm for Piecewise-Stationary Combinatorial Semi-Bandits](https://mlsanity.com/paper/1908.10402/) (2019)
- [Regret of Age-of-Information Bandits](https://mlsanity.com/paper/2001.09317/) (2020)
- [Collaborative Learning over Wireless Networks: An Introductory Overview](https://mlsanity.com/paper/2112.05559/) (2021)
- [Learning to Schedule in Non-Stationary Wireless Networks With Unknown Statistics](https://mlsanity.com/paper/2308.02734/) (2023)

## Abstract (arXiv)

Federated learning enables distributed model training across clients without raw data exchange, but in wireless implementations, frequent parameter updates cause high communication overhead. Existing research often assumes known channel state information (CSI) or stationary channels, though practical wireless channels are non-stationary due to fading, user mobility, and attacks, leading to unpredictable transmission failures and exacerbating client staleness, which hampers model convergence. To tackle these challenges, we propose an asynchronous federated learning scheduling framework for non-stationary channels that aims to reduce client staleness while enhancing communication efficiency and fairness. Our framework considers two scenarios: extremely non-stationary and piecewise-stationary channels. Age of Information (AoI) quantifies client staleness under these conditions. We conduct convergence analysis to examine the impact of AoI and per-round client participation on learning performance and formulate the scheduling problem as a multi-armed bandit (MAB) problem. We derive theoretical lower bounds on AoI regret and develop scheduling strategies based on GLR-CUCB and M-exp3 algorithms, including upper bounds on AoI regret. To address imbalanced client updates, we propose an adaptive matching strategy that incorporates marginal utility and fairness considerations. Simulation results show that our algorithm achieves sub-linear AoI regret, accelerates convergence, and promotes fairer aggregation.