FedHeN: Federated Learning in Heterogeneous Networks

Durmus Alp Emre Acar, Venkatesh Saligrama
7/7/2022
cs.LGcs.DC

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

NeFL: Nested Model Scaling for Federated Learning with System Heterogeneous Clients

86% match2023

Distributed Learning in Heterogeneous Environment: federated learning with adaptive aggregation and computation reduction

86% match2023

Federated Learning based on Pruning and Recovery

86% match2024

Ampere: Communication-Efficient and High-Accuracy Split Federated Learning

85% match2025

Heterogeneous Federated Learning: State-of-the-art and Research Challenges

85% match1 repo1672023

FedIN: Federated Intermediate Layers Learning for Model Heterogeneity

84% match2023

Cite this paper

@article{acar2022fedhen,
  title  = {FedHeN: Federated Learning in Heterogeneous Networks},
  author = {Durmus Alp Emre Acar and Venkatesh Saligrama},
  year   = {2022},
  eprint = {2207.03031},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2207.03031v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2207.03031.svg)](https://codeofpaper.com/paper/2207.03031)

Discussion