Tackling the objective inconsistency problem in heterogeneous federated optimization

Jianyu Wang, Qinghua Liu, Hao Liang, Gauri Joshi, H. Vincent Poor

Research output: Contribution to journalConference articlepeer-review

2 Scopus citations

Abstract

In federated learning, heterogeneity in the clients’ local datasets and computation speeds results in large variations in the number of local updates performed by each client in each communication round. Naive weighted aggregation of such models causes objective inconsistency, that is, the global model converges to a stationary point of a mismatched objective function which can be arbitrarily different from the true objective. This paper provides a general framework to analyze the convergence of heterogeneous federated optimization algorithms. It subsumes previously proposed methods such as FedAvg and FedProx, and provides the first principled understanding of the solution bias and the convergence slowdown due to objective inconsistency. Using insights from this analysis, we propose FedNova, a normalized averaging method that eliminates objective inconsistency while preserving fast error convergence.

Original languageEnglish (US)
JournalAdvances in Neural Information Processing Systems
Volume2020-December
StatePublished - 2020
Event34th Conference on Neural Information Processing Systems, NeurIPS 2020 - Virtual, Online
Duration: Dec 6 2020Dec 12 2020

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Fingerprint

Dive into the research topics of 'Tackling the objective inconsistency problem in heterogeneous federated optimization'. Together they form a unique fingerprint.

Cite this