Federated Learning in Temporal Heterogeneity

TL;DR

This paper investigates federated learning with clients having different temporal data lengths, finding fixed-length sequences improve convergence, and proposes methods to address heterogeneity for better efficiency.

Contribution

It introduces new methods to mitigate temporal heterogeneity in federated learning, based on empirical observations of sequence length effects.

Findings

Fixed-length sequences lead to faster convergence.

Proposed methods improve federated learning efficiency.

Empirical analysis of sequence length impact.

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.