Over-the-Air Fair Federated Learning via Multi-Objective Optimization

TL;DR

This paper introduces OTA-FFL, a novel over-the-air federated learning algorithm that uses multi-objective optimization to enhance fairness among clients, leveraging over-the-air computation for efficient gradient aggregation.

Contribution

It proposes a new fair federated learning method using over-the-air computation and multi-objective optimization with adaptive weighting, along with analytical solutions for efficient implementation.

Findings

OTA-FFL outperforms existing methods in fairness and robustness.

The approach effectively balances client performance disparities.

Analytical solutions enable efficient over-the-air aggregation.

Abstract

In federated learning (FL), heterogeneity among the local dataset distributions of clients can result in unsatisfactory performance for some, leading to an unfair model. To address this challenge, we propose an over-the-air fair federated learning algorithm (OTA-FFL), which leverages over-the-air computation to train fair FL models. By formulating FL as a multi-objective minimization problem, we introduce a modified Chebyshev approach to compute adaptive weighting coefficients for gradient aggregation in each communication round. To enable efficient aggregation over the multiple access channel, we derive analytical solutions for the optimal transmit scalars at the clients and the de-noising scalar at the parameter server. Extensive experiments demonstrate the superiority of OTA-FFL in achieving fairness and robust performance compared to existing methods.