Communication-Efficient Federated Learning via Robust Distributed Mean Estimation

Advanced search
Browse by:

Department | Year

UCL Theses | Latest

Deposit your research

Communication-Efficient Federated Learning via Robust Distributed Mean Estimation

Vargaftik, Shay; Basat, Ran Ben; Portnoy, Amit; Mendelson, Gal; Ben-Itzhak, Yaniv; Mitzenmacher, Michael; (2022) Communication-Efficient Federated Learning via Robust Distributed Mean Estimation. In: Proceedings of the 39th International Conference on Machine Learning. (pp. pp. 21984-22014). PMLR Green open access

Preview

Text
vargaftik22a.pdf - Other
Download (1MB) | Preview

Abstract

Distributed Mean Estimation (DME) is a central building block in federated learning, where clients send local gradients to a parameter server for averaging and updating the model. Due to communication constraints, clients often use lossy compression techniques to compress the gradients, resulting in estimation inaccuracies. DME is more challenging when clients have diverse network conditions, such as constrained communication budgets and packet losses. In such settings, DME techniques often incur a significant increase in the estimation error leading to degraded learning performance. In this work, we propose a robust DME technique named EDEN that naturally handles heterogeneous communication budgets and packet losses. We derive appealing theoretical guarantees for EDEN and evaluate it empirically. Our results demonstrate that EDEN consistently improves over state-of-the-art DME techniques.

Type:	Proceedings paper
Title:	Communication-Efficient Federated Learning via Robust Distributed Mean Estimation
Event:	39th International Conference on Machine Learning (ICML 2022)
Open access status:	An open access version is available from UCL Discovery
Publisher version:	https://proceedings.mlr.press/v162/vargaftik22a.ht...
Language:	English
Additional information:	This version is the version of record. For information on re-use, please refer to the publisher's terms and conditions.
UCL classification:	UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science UCL > Provost and Vice Provost Offices > UCL BEAMS UCL
URI:	https://discovery.ucl.ac.uk/id/eprint/10152892