FedMix: Approximation of Mixup under Mean Augmented Federated Learning

TL;DR

FedMix introduces a privacy-preserving data augmentation method for federated learning that improves performance under highly non-iid data distributions by approximating Mixup without sharing raw data.

Contribution

The paper proposes FedMix, a novel augmentation algorithm inspired by Mixup, compatible with Mean Augmented Federated Learning to enhance model performance in heterogeneous data settings.

Findings

Significantly improves accuracy in non-iid federated learning scenarios

Does not require sharing raw local data among clients

Outperforms conventional algorithms on standard benchmarks

Abstract

Federated learning (FL) allows edge devices to collectively learn a model without directly sharing data within each device, thus preserving privacy and eliminating the need to store data globally. While there are promising results under the assumption of independent and identically distributed (iid) local data, current state-of-the-art algorithms suffer from performance degradation as the heterogeneity of local data across clients increases. To resolve this issue, we propose a simple framework, Mean Augmented Federated Learning (MAFL), where clients send and receive averaged local data, subject to the privacy requirements of target applications. Under our framework, we propose a new augmentation algorithm, named FedMix, which is inspired by a phenomenal yet simple data augmentation method, Mixup, but does not require local raw data to be directly shared among devices. Our method shows greatly improved performance in the standard benchmark datasets of FL, under highly non-iid federated settings, compared to conventional algorithms.