SOURCE-LINKED INTELLIGENCE

Pathwise Individual Rationality in Federated Learning: A Mechanism-Architecture Co-Design

arXiv · AI, language, vision and robotics · article · Sep 13, 2026 · UTC

Participation in federated learning (FL) comes at a cost. Clients trade off privacy, communication, and compute costs for potentially greater gains in model efficacy. This paper explores this tradeoff under the aegis of individual rationality (IR) versus autarky, the basic game-theoretic requirement that the federation provide utility no worse than local training. Using the above as the design target, we examine pathwise performance of FL, as a per-round bound on cumulative surplus, not just as an asymptotic equilibrium guarantee under different models of client data distribution heterogeneity

Read original source ↗ Open in workspace

recordType

paper

region

Global