XOR Mixup: Privacy-Preserving Data Augmentation for One-Shot Federated Learning

TL;DR

This paper introduces XorMixup, a privacy-preserving data augmentation method using XOR operations, to improve one-shot federated learning performance on non-IID data by generating synthetic, realistic samples while maintaining privacy.

Contribution

The paper proposes XorMixup, a novel XOR-based data augmentation technique for federated learning, enabling one-shot training with privacy preservation and improved accuracy on non-IID data.

Findings

XorMixFL achieves up to 17.6% higher accuracy than vanilla FL.

The method effectively creates IID datasets from non-IID data.

XorMixup maintains data privacy through XOR-based encoding and decoding.

Abstract

User-generated data distributions are often imbalanced across devices and labels, hampering the performance of federated learning (FL). To remedy to this non-independent and identically distributed (non-IID) data problem, in this work we develop a privacy-preserving XOR based mixup data augmentation technique, coined XorMixup, and thereby propose a novel one-shot FL framework, termed XorMixFL. The core idea is to collect other devices' encoded data samples that are decoded only using each device's own data samples. The decoding provides synthetic-but-realistic samples until inducing an IID dataset, used for model training. Both encoding and decoding procedures follow the bit-wise XOR operations that intentionally distort raw samples, thereby preserving data privacy. Simulation results corroborate that XorMixFL achieves up to 17.6% higher accuracy than Vanilla FL under a non-IID MNIST dataset.