2024-04-18-bao24a.md

title	software	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
BOBA: Byzantine-Robust Federated Learning with Label Skewness	https://github.com/baowenxuan/BOBA	In federated learning, most existing robust aggregation rules (AGRs) combat Byzantine attacks in the IID setting, where client data is assumed to be independent and identically distributed. In this paper, we address label skewness, a more realistic and challenging non-IID setting, where each client only has access to a few classes of data. In this setting, state-of-the-art AGRs suffer from selection bias, leading to significant performance drop for particular classes; they are also more vulnerable to Byzantine attacks due to the increased variation among gradients of honest clients. To address these limitations, we propose an efficient two-stage method named BOBA. Theoretically, we prove the convergence of BOBA with an error of the optimal order. Our empirical evaluations demonstrate BOBA’s superior unbiasedness and robustness across diverse models and datasets when compared to various baselines.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	bao24a	0	{BOBA}: Byzantine-Robust Federated Learning with Label Skewness	892	900	892-900	892	false	Bao, Wenxuan and Wu, Jun and He, Jingrui	given family Wenxuan Bao given family Jun Wu given family Jingrui He	2024-04-18		Proceedings of The 27th International Conference on Artificial Intelligence and Statistics	238	inproceedings	date-parts 2024 4 18	https://proceedings.mlr.press/v238/bao24a/bao24a.pdf