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

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 this 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. Along this path, clients can remain below their local-training baseline for hundreds of rounds. The natural remedy is to cap each client's per-round contribution so that this shortfall stays bounded, and we prove that it backfires, collapsing learning even at low-to-modest heterogeneity. We then propose a novel design that combines short-term participation guarantees with personalized model evaluation, while maintaining fair incentives and high accuracy. We provide a theoretical basis for this new approach and empirically demonstrate that clients can avoid short-term losses at no accuracy cost beyond the contract it builds on, under moderate to severe data distribution heterogeneity.