On the Convergence of the Shapley Value in Parametric Bayesian Learning Games
This work addresses the problem of fair contribution measurement in collaborative machine learning for participants, though it is incremental as it builds on existing Shapley value theory.
The paper tackles the problem of measuring contributions in parametric Bayesian learning games by establishing the convergence of the Shapley value to a limiting game based on Fisher information, enabling an asymptotically fair online collaborative learning framework without costly computations.
Measuring contributions is a classical problem in cooperative game theory where the Shapley value is the most well-known solution concept. In this paper, we establish the convergence property of the Shapley value in parametric Bayesian learning games where players perform a Bayesian inference using their combined data, and the posterior-prior KL divergence is used as the characteristic function. We show that for any two players, under some regularity conditions, their difference in Shapley value converges in probability to the difference in Shapley value of a limiting game whose characteristic function is proportional to the log-determinant of the joint Fisher information. As an application, we present an online collaborative learning framework that is asymptotically Shapley-fair. Our result enables this to be achieved without any costly computations of posterior-prior KL divergences. Only a consistent estimator of the Fisher information is needed. The effectiveness of our framework is demonstrated with experiments using real-world data.