Federated Learning in Temporal Heterogeneity

Junghwan Lee

Federated Learning in Temporal Heterogeneity

Machine Learning 2023-09-19 v1

Authors: Junghwan Lee

Abstract

In this work, we explored federated learning in temporal heterogeneity across clients. We observed that global model obtained by \texttt{FedAvg} trained with fixed-length sequences shows faster convergence than varying-length sequences. We proposed methods to mitigate temporal heterogeneity for efficient federated learning based on the empirical observation.

Keywords

federated learning temporal graph machine learning theory

Cite

@article{arxiv.2309.09381,
  title  = {Federated Learning in Temporal Heterogeneity},
  author = {Junghwan Lee},
  journal= {arXiv preprint arXiv:2309.09381},
  year   = {2023}
}

Related papers

View all related →