2021-07-01-acar21a.md

title	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
Debiasing Model Updates for Improving Personalized Federated Training	We propose a novel method for federated learning that is customized specifically to the objective of a given edge device. In our proposed method, a server trains a global meta-model by collaborating with devices without actually sharing data. The trained global meta-model is then personalized locally by each device to meet its specific objective. Different from the conventional federated learning setting, training customized models for each device is hindered by both the inherent data biases of the various devices, as well as the requirements imposed by the federated architecture. We propose gradient correction methods leveraging prior works, and explicitly de-bias the meta-model in the distributed heterogeneous data setting to learn personalized device models. We present convergence guarantees of our method for strongly convex, convex and nonconvex meta objectives. We empirically evaluate the performance of our method on benchmark datasets and demonstrate significant communication savings.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	acar21a	0	Debiasing Model Updates for Improving Personalized Federated Training	21	31	21-31	21	false	Acar, Durmus Alp Emre and Zhao, Yue and Zhu, Ruizhao and Matas, Ramon and Mattina, Matthew and Whatmough, Paul and Saligrama, Venkatesh	given family Durmus Alp Emre Acar given family Yue Zhao given family Ruizhao Zhu given family Ramon Matas given family Matthew Mattina given family Paul Whatmough given family Venkatesh Saligrama	2021-07-01		Proceedings of the 38th International Conference on Machine Learning	139	inproceedings	date-parts 2021 7 1	http://proceedings.mlr.press/v139/acar21a/acar21a.pdf	label link Supplementary PDF http://proceedings.mlr.press/v139/acar21a/acar21a-supp.pdf