FedHeN: Federated Learning in Heterogeneous Networks

We propose a novel training recipe for federated learning with heterogeneous networks where each device can have different architectures. We introduce training with a side objective to the devices of higher complexities to jointly train different architectures in a federated setting. We empirically...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-07
Main Authors: Durmus Alp Emre Acar, Saligrama, Venkatesh
Format: Article
Language:English
Subjects:
Federated learning
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose a novel training recipe for federated learning with heterogeneous networks where each device can have different architectures. We introduce training with a side objective to the devices of higher complexities to jointly train different architectures in a federated setting. We empirically show that our approach improves the performance of different architectures and leads to high communication savings compared to the state-of-the-art methods.
ISSN:2331-8422