Controlling Participation in Federated Learning with Feedback

Michael Cummins, Guner Dilsad Er, Michael Muehlebach
Proceedings of the 7th Annual Learning for Dynamics \& Control Conference, PMLR 283:174-186, 2025.

Abstract

We address the problem of client participation in federated learning, where traditional methods typically rely on a random selection of a small subset of clients for each training round. In contrast, we propose FedBack, a deterministic approach that leverages control-theoretic principles to manage client participation in ADMM-based federated learning. FedBack models client participation as a discrete-time dynamical system and employs an integral feedback controller to adjust each client’s participation rate individually, based on the client’s optimization dynamics. We provide global convergence guarantees for our approach by building on the recent federated learning research. Numerical experiments on federated image classification demonstrate that FedBack achieves up to 50% improvement in communication and computational efficiency over algorithms that rely on a random selection of clients.

Cite this Paper

BibTeX
@InProceedings{pmlr-v283-cummins25a, title = {Controlling Participation in Federated Learning with Feedback}, author = {Cummins, Michael and Er, Guner Dilsad and Muehlebach, Michael}, booktitle = {Proceedings of the 7th Annual Learning for Dynamics \& Control Conference}, pages = {174--186}, year = {2025}, editor = {Ozay, Necmiye and Balzano, Laura and Panagou, Dimitra and Abate, Alessandro}, volume = {283}, series = {Proceedings of Machine Learning Research}, month = {04--06 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v283/main/assets/cummins25a/cummins25a.pdf}, url = {https://proceedings.mlr.press/v283/cummins25a.html}, abstract = {We address the problem of client participation in federated learning, where traditional methods typically rely on a random selection of a small subset of clients for each training round. In contrast, we propose FedBack, a deterministic approach that leverages control-theoretic principles to manage client participation in ADMM-based federated learning. FedBack models client participation as a discrete-time dynamical system and employs an integral feedback controller to adjust each client’s participation rate individually, based on the client’s optimization dynamics. We provide global convergence guarantees for our approach by building on the recent federated learning research. Numerical experiments on federated image classification demonstrate that FedBack achieves up to 50% improvement in communication and computational efficiency over algorithms that rely on a random selection of clients.} }
Endnote
%0 Conference Paper %T Controlling Participation in Federated Learning with Feedback %A Michael Cummins %A Guner Dilsad Er %A Michael Muehlebach %B Proceedings of the 7th Annual Learning for Dynamics \& Control Conference %C Proceedings of Machine Learning Research %D 2025 %E Necmiye Ozay %E Laura Balzano %E Dimitra Panagou %E Alessandro Abate %F pmlr-v283-cummins25a %I PMLR %P 174--186 %U https://proceedings.mlr.press/v283/cummins25a.html %V 283 %X We address the problem of client participation in federated learning, where traditional methods typically rely on a random selection of a small subset of clients for each training round. In contrast, we propose FedBack, a deterministic approach that leverages control-theoretic principles to manage client participation in ADMM-based federated learning. FedBack models client participation as a discrete-time dynamical system and employs an integral feedback controller to adjust each client’s participation rate individually, based on the client’s optimization dynamics. We provide global convergence guarantees for our approach by building on the recent federated learning research. Numerical experiments on federated image classification demonstrate that FedBack achieves up to 50% improvement in communication and computational efficiency over algorithms that rely on a random selection of clients.
APA
Cummins, M., Er, G.D. & Muehlebach, M.. (2025). Controlling Participation in Federated Learning with Feedback. Proceedings of the 7th Annual Learning for Dynamics \& Control Conference, in Proceedings of Machine Learning Research 283:174-186 Available from https://proceedings.mlr.press/v283/cummins25a.html.

Related Material