Conflict-Aware Client Selection for Multi-Server Federated Learning

TL;DR

This paper introduces RL CRP, a decentralized reinforcement learning approach that predicts and mitigates client selection conflicts in multi-server federated learning, enhancing training efficiency and reducing communication costs.

Contribution

It proposes a novel conflict risk prediction model combined with a fairness-aware reward mechanism for optimized client selection in multi-server federated learning.

Findings

Reduces inter-server client conflicts effectively.

Improves convergence speed of federated learning.

Decreases overall communication costs.

Abstract

Federated learning (FL) has emerged as a promising distributed machine learning (ML) that enables collaborative model training across clients without exposing raw data, thereby preserving user privacy and reducing communication costs. Despite these benefits, traditional single-server FL suffers from high communication latency due to the aggregation of models from a large number of clients. While multi-server FL distributes workloads across edge servers, overlapping client coverage and uncoordinated selection often lead to resource contention, causing bandwidth conflicts and training failures. To address these limitations, we propose a decentralized reinforcement learning with conflict risk prediction, named RL CRP, to optimize client selection in multi-server FL systems. Specifically, each server estimates the likelihood of client selection conflicts using a categorical hidden Markov model based on its sparse historical client selection sequence. Then, a fairness-aware reward mechanism is incorporated to promote long-term client participation for minimizing training latency and resource contention. Extensive experiments demonstrate that the proposed RL-CRP framework effectively reduces inter-server conflicts and significantly improves training efficiency in terms of convergence speed and communication cost.