LGSep 17, 2023
Federated Learning in Temporal Heterogeneity
arXiv:2309.09381v1h-index: 2
Originality Synthesis-oriented
AI Analysis
This addresses efficiency challenges in federated learning for distributed systems, but appears incremental as it builds on existing methods like FedAvg.
The paper tackled the problem of federated learning under temporal heterogeneity, finding that FedAvg with fixed-length sequences converges faster than with varying-length sequences, and proposed methods to mitigate this issue.
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.