One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning
This addresses the challenge of maintaining sustainable collaborations in federated learning by incorporating game theory, though it is incremental as it builds on existing federated learning frameworks.
The paper tackles the problem of designing collaboration protocols in federated learning that account for agents' incentives to balance learning objectives with low sampling burdens, introducing stable and envy-free equilibria and characterizing their properties, existence, and computation.
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.