Clustered Federated Learning for Heterogeneous Data (Student Abstract)

AAAI 2023 pp. 16378-16379

doi:10.1609/AAAI.V37I13.27049 /aaai/2023/yu2023aaai-clustered/

Abstract

Federated Learning (FL) aims to achieve a global model via aggregating models from all devices. However, it can diverge when the data on the users’ devices are heterogeneous. To address this issue, we propose a novel clustered FL method (FPFC) based on a nonconvex pairwise fusion penalty. FPFC can automatically identify clusters without prior knowledge of the number of clusters and the set of devices in each cluster. Our method is implemented in parallel, updates only a subset of devices at each communication round, and allows each participating device to perform inexact computation. We also provide convergence guarantees of FPFC for general nonconvex losses. Experiment results demonstrate the advantages of FPFC over existing methods.

PDF AAAI Semantic Scholar

Cite

Text

Yu et al. "Clustered Federated Learning for Heterogeneous Data (Student Abstract)." AAAI Conference on Artificial Intelligence, 2023. doi:10.1609/AAAI.V37I13.27049

Markdown

[Yu et al. "Clustered Federated Learning for Heterogeneous Data (Student Abstract)." AAAI Conference on Artificial Intelligence, 2023.](https://mlanthology.org/aaai/2023/yu2023aaai-clustered/) doi:10.1609/AAAI.V37I13.27049

BibTeX

@inproceedings{yu2023aaai-clustered,
  title     = {{Clustered Federated Learning for Heterogeneous Data (Student Abstract)}},
  author    = {Yu, Xue and Liu, Ziyi and Sun, Yifan and Wang, Wu},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {16378-16379},
  doi       = {10.1609/AAAI.V37I13.27049},
  url       = {https://mlanthology.org/aaai/2023/yu2023aaai-clustered/}
}