Federated Learning via Plurality Vote

TL;DR

FedVote is a federated learning scheme that uses low-communication-weight voting and quantization to improve robustness, efficiency, and convergence speed in privacy-preserving collaborative machine learning.

Contribution

The paper introduces FedVote, a novel federated learning approach utilizing plurality voting with binary/ternary weights for enhanced resilience and resource efficiency.

Findings

Reduces quantization error compared to direct model update quantization

Converges faster than existing quantization methods

Enhances robustness against Byzantine attacks

Abstract

Federated learning allows collaborative workers to solve a machine learning problem while preserving data privacy. Recent studies have tackled various challenges in federated learning, but the joint optimization of communication overhead, learning reliability, and deployment efficiency is still an open problem. To this end, we propose a new scheme named federated learning via plurality vote (FedVote). In each communication round of FedVote, workers transmit binary or ternary weights to the server with low communication overhead. The model parameters are aggregated via weighted voting to enhance the resilience against Byzantine attacks. When deployed for inference, the model with binary or ternary weights is resource-friendly to edge devices. We show that our proposed method can reduce quantization error and converges faster compared with the methods directly quantizing the model updates.