A Primal-Dual Algorithm for Hybrid Federated Learning

Tom Overman, Garrett Blum, Diego Klabjan

Research output: Contribution to journalConference articlepeer-review

1 Scopus citations

Abstract

Very few methods for hybrid federated learning, where clients only hold subsets of both features and samples, exist. Yet, this scenario is extremely important in practical settings. We provide a fast, robust algorithm for hybrid federated learning that hinges on Fenchel Duality. We prove the convergence of the algorithm to the same solution as if the model is trained centrally in a variety of practical regimes. Furthermore, we provide experimental results that demonstrate the performance improvements of the algorithm over a commonly used method in federated learning, FedAvg, and an existing hybrid FL algorithm, HyFEM. We also provide privacy considerations and necessary steps to protect client data.

Original languageEnglish (US)
Pages (from-to)14482-14489
Number of pages8
JournalProceedings of the AAAI Conference on Artificial Intelligence
Volume38
Issue number13
DOIs
StatePublished - Mar 25 2024
Event38th AAAI Conference on Artificial Intelligence, AAAI 2024 - Vancouver, Canada
Duration: Feb 20 2024Feb 27 2024

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'A Primal-Dual Algorithm for Hybrid Federated Learning'. Together they form a unique fingerprint.

Cite this