Optimized Federated Multitask Learning in Mobile Edge Networks: A Hybrid Client Selection and Model Aggregation Approach

TL;DR

This paper introduces a clustered federated multitask learning framework for mobile edge networks that improves convergence speed, reduces training time and energy consumption, and provides tailored models to clients through hierarchical clustering and specialized aggregation.

Contribution

It presents a novel hierarchical clustering and model aggregation approach with a two-phase client selection method for federated multitask learning in wireless networks.

Findings

Reduces energy consumption by up to 60%

Enhances convergence speed and training efficiency

Ensures fair and effective client participation

Abstract

We propose clustered federated multitask learning to address statistical challenges in non-independent and identically distributed data across clients. Our approach tackles complexities in hierarchical wireless networks by clustering clients based on data distribution similarities and assigning specialized models to each cluster. These complexities include slower convergence and mismatched model allocation due to hierarchical model aggregation and client selection. The proposed framework features a two-phase client selection and a two-level model aggregation scheme. It ensures fairness and effective participation using greedy and round-robin methods. Our approach significantly enhances convergence speed, reduces training time, and decreases energy consumption by up to 60%, ensuring clients receive models tailored to their specific data needs.