2021-07-01-blum21a.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
One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning	In recent years, federated learning has been embraced as an approach for bringing about collaboration across large populations of learning agents. However, little is known about how collaboration protocols should take agents’ incentives into account when allocating individual resources for communal learning in order to maintain such collaborations. Inspired by game theoretic notions, this paper introduces a framework for incentive-aware learning and data sharing in federated learning. Our stable and envy-free equilibria capture notions of collaboration in the presence of agents interested in meeting their learning objectives while keeping their own sample collection burden low. For example, in an envy-free equilibrium, no agent would wish to swap their sampling burden with any other agent and in a stable equilibrium, no agent would wish to unilaterally reduce their sampling burden. In addition to formalizing this framework, our contributions include characterizing the structural properties of such equilibria, proving when they exist, and showing how they can be computed. Furthermore, we compare the sample complexity of incentive-aware collaboration with that of optimal collaboration when one ignores agents’ incentives.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	blum21a	0	One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning	1005	1014	1005-1014	1005	false	Blum, Avrim and Haghtalab, Nika and Phillips, Richard Lanas and Shao, Han	given family Avrim Blum given family Nika Haghtalab given family Richard Lanas Phillips given family Han Shao	2021-07-01		Proceedings of the 38th International Conference on Machine Learning	139	inproceedings	date-parts 2021 7 1	http://proceedings.mlr.press/v139/blum21a/blum21a.pdf	label link Supplementary PDF http://proceedings.mlr.press/v139/blum21a/blum21a-supp.pdf