Robust Federated Learning Using ADMM in the Presence of Data Falsifying Byzantines

10/14/2017
by   Qunwei Li, et al.
0

In this paper, we consider the problem of federated (or decentralized) learning using ADMM with multiple agents. We consider a scenario where a certain fraction of agents (referred to as Byzantines) provide falsified data to the system. In this context, we study the convergence behavior of the decentralized ADMM algorithm. We show that ADMM converges linearly to a neighborhood of the solution to the problem under certain conditions. We next provide guidelines for network structure design to achieve faster convergence. Next, we provide necessary conditions on the falsified updates for exact convergence to the true solution. To tackle the data falsification problem, we propose a robust variant of ADMM. We also provide simulation results to validate the analysis and show the resilience of the proposed algorithm to Byzantines.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/28/2021

Communication-Efficient ADMM-based Federated Learning

Federated learning has shown its advances over the last few years but is...
research
04/22/2022

Federated Learning via Inexact ADMM

One of the crucial issues in federated learning is how to develop effici...
research
10/23/2019

Q-GADMM: Quantized Group ADMM for Communication Efficient Decentralized Machine Learning

In this paper, we propose a communication-efficient decentralized machin...
research
11/09/2019

L-FGADMM: Layer-Wise Federated Group ADMM for Communication Efficient Decentralized Deep Learning

This article proposes a communication-efficient decentralized deep learn...
research
06/30/2021

Adaptive Stochastic ADMM for Decentralized Reinforcement Learning in Edge Industrial IoT

Edge computing provides a promising paradigm to support the implementati...
research
02/20/2020

Dynamic Federated Learning

Federated learning has emerged as an umbrella term for centralized coord...
research
04/04/2022

Learning the Proximity Operator in Unfolded ADMM for Phase Retrieval

This paper considers the phase retrieval (PR) problem, which aims to rec...

Please sign up or login with your details

Forgot password? Click here to reset