Ditto: Fair and Robust Federated Learning Through Personalization

Tian Li, Shengyuan Hu, Ahmad Beirami, Virginia Smith
Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6357-6368, 2021.

Abstract

Fairness and robustness are two important concerns for federated learning systems. In this work, we identify that robustness to data and model poisoning attacks and fairness, measured as the uniformity of performance across devices, are competing constraints in statistically heterogeneous networks. To address these constraints, we propose employing a simple, general framework for personalized federated learning, Ditto, that can inherently provide fairness and robustness benefits, and develop a scalable solver for it. Theoretically, we analyze the ability of Ditto to achieve fairness and robustness simultaneously on a class of linear problems. Empirically, across a suite of federated datasets, we show that Ditto not only achieves competitive performance relative to recent personalization methods, but also enables more accurate, robust, and fair models relative to state-of-the-art fair or robust baselines.

Cite this Paper

BibTeX
@InProceedings{pmlr-v139-li21h, title = {Ditto: Fair and Robust Federated Learning Through Personalization}, author = {Li, Tian and Hu, Shengyuan and Beirami, Ahmad and Smith, Virginia}, booktitle = {Proceedings of the 38th International Conference on Machine Learning}, pages = {6357--6368}, year = {2021}, editor = {Meila, Marina and Zhang, Tong}, volume = {139}, series = {Proceedings of Machine Learning Research}, month = {18--24 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v139/li21h/li21h.pdf}, url = {https://proceedings.mlr.press/v139/li21h.html}, abstract = {Fairness and robustness are two important concerns for federated learning systems. In this work, we identify that robustness to data and model poisoning attacks and fairness, measured as the uniformity of performance across devices, are competing constraints in statistically heterogeneous networks. To address these constraints, we propose employing a simple, general framework for personalized federated learning, Ditto, that can inherently provide fairness and robustness benefits, and develop a scalable solver for it. Theoretically, we analyze the ability of Ditto to achieve fairness and robustness simultaneously on a class of linear problems. Empirically, across a suite of federated datasets, we show that Ditto not only achieves competitive performance relative to recent personalization methods, but also enables more accurate, robust, and fair models relative to state-of-the-art fair or robust baselines.} }
Endnote
%0 Conference Paper %T Ditto: Fair and Robust Federated Learning Through Personalization %A Tian Li %A Shengyuan Hu %A Ahmad Beirami %A Virginia Smith %B Proceedings of the 38th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Marina Meila %E Tong Zhang %F pmlr-v139-li21h %I PMLR %P 6357--6368 %U https://proceedings.mlr.press/v139/li21h.html %V 139 %X Fairness and robustness are two important concerns for federated learning systems. In this work, we identify that robustness to data and model poisoning attacks and fairness, measured as the uniformity of performance across devices, are competing constraints in statistically heterogeneous networks. To address these constraints, we propose employing a simple, general framework for personalized federated learning, Ditto, that can inherently provide fairness and robustness benefits, and develop a scalable solver for it. Theoretically, we analyze the ability of Ditto to achieve fairness and robustness simultaneously on a class of linear problems. Empirically, across a suite of federated datasets, we show that Ditto not only achieves competitive performance relative to recent personalization methods, but also enables more accurate, robust, and fair models relative to state-of-the-art fair or robust baselines.
APA
Li, T., Hu, S., Beirami, A. & Smith, V.. (2021). Ditto: Fair and Robust Federated Learning Through Personalization. Proceedings of the 38th International Conference on Machine Learning, in Proceedings of Machine Learning Research 139:6357-6368 Available from https://proceedings.mlr.press/v139/li21h.html.

Related Material