Byzantine-Robust Gossip: Insights from a Dual Approach

2024/05/06 by Gaucher, Renaud, Dieuleveut, Aymeric, Hendrikx, Hadrien · 1 citation
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.2405.03449

Abstract

Distributed learning has many computational benefits but is vulnerable to attacks from a subset of devices transmitting incorrect information. This paper investigates Byzantine-resilient algorithms in a decentralized setting, where devices communicate directly in a peer-to-peer manner within a communication network. We leverage the so-called dual approach for decentralized optimization and propose a Byzantine-robust algorithm. We provide convergence guarantees in the average consensus subcase, discuss the potential of the dual approach beyond this subcase, and re-interpret existing algorithms using the dual framework. Lastly, we experimentally show the soundness of our method.

Cited by

• Robust and Efficient Collaborative Learning

Related

• Unified Breakdown Analysis for Byzantine Robust Gossip
• Byzantine-Resilient Federated Learning via Distributed Optimization
• Byzantine-Robust Decentralized Learning via ClippedGossip
• Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
• BRIDGE: Byzantine-resilient Decentralized Gradient Descent