REPA: Client Clustering without Training and Data Labels for Improved Federated Learning in Non-IID Settings

B Radovič, V Pejović - arXiv preprint arXiv:2309.14088, 2023 - arxiv.org
Clustering clients into groups that exhibit relatively homogeneous data distributions
represents one of the major means of improving the performance of federated learning (FL) …
被引用次数：1 相关文章

REPA: Client Clustering without Training and Data Labels for Improved Federated Learning in Non-IID Settings

B Radovič, V Pejović - arXiv e-prints, 2023 - ui.adsabs.harvard.edu
Clustering clients into groups that exhibit relatively homogeneous data distributions
represents one of the major means of improving the performance of federated learning (FL) …