Unlocking the Potential of Weighting Methods in Federated Learning Through Communication Compression
Valery Parfenov, Daniil Medyakov, Dmitry Bylinkin, Nail Bashirov, Aleksandr Beznosikov
Abstract
Modern machine learning problems are frequently formulated in federated learning domain and incorporate inherently heterogeneous data. Weighting methods operate efficiently in terms of iteration complexity and represent a common direction in this setting. At the same time, they do not address directly the main obstacle in federated and distributed learning -- communication bottleneck. We tackle this issue by incorporating compression into the weighting scheme. We establish the convergence under a convexity assumption, considering both exact and stochastic oracles. Finally, we evaluate the practical performance of the proposed method on real-world problems.
BibTeX
@inproceedings{
parfenov2026unlocking,
title={Unlocking the Potential of Weighting Methods in Federated Learning Through Communication Compression},
author={Valery Parfenov and Daniil Medyakov and Dmitry Bylinkin and Nail Bashirov and Aleksandr Beznosikov},
booktitle={The Fourteenth International Conference on Learning Representations},
year={2026},
url={https://openreview.net/forum?id=zOWljZMbCm}
}