One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning

by   Avrim Blum, et al.

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.



There are no comments yet.


page 1

page 2

page 3

page 4


Hierarchically Fair Federated Learning

Federated learning facilitates collaboration among self-interested agent...

Incentive Mechanism Design for Federated Learning: Hedonic Game Approach

Incentive mechanism design is crucial for enabling federated learning. W...

Optimality and Stability in Federated Learning: A Game-theoretic Approach

Federated learning is a distributed learning paradigm where multiple age...

Federated Learning under Importance Sampling

Federated learning encapsulates distributed learning strategies that are...

Optimal Importance Sampling for Federated Learning

Federated learning involves a mixture of centralized and decentralized p...

Dynamic Federated Learning

Federated learning has emerged as an umbrella term for centralized coord...

Model-sharing Games: Analyzing Federated Learning Under Voluntary Participation

Federated learning is a setting where agents, each with access to their ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.