Approximating the Shapley Value without Marginal Contributions
This addresses the scalability problem for researchers and practitioners using Shapley values in explainable AI, though it is incremental as it builds on existing approximation efforts.
The paper tackles the computational inefficiency of exactly computing the Shapley value for explainable AI by proposing SVARM and Stratified SVARM, two parameter-free approximation algorithms that avoid marginal contributions, achieving unmatched theoretical guarantees and competitive empirical results in synthetic games and use cases.
The Shapley value, which is arguably the most popular approach for assigning a meaningful contribution value to players in a cooperative game, has recently been used intensively in explainable artificial intelligence. Its meaningfulness is due to axiomatic properties that only the Shapley value satisfies, which, however, comes at the expense of an exact computation growing exponentially with the number of agents. Accordingly, a number of works are devoted to the efficient approximation of the Shapley value, most of them revolve around the notion of an agent's marginal contribution. In this paper, we propose with SVARM and Stratified SVARM two parameter-free and domain-independent approximation algorithms based on a representation of the Shapley value detached from the notion of marginal contribution. We prove unmatched theoretical guarantees regarding their approximation quality and provide empirical results including synthetic games as well as common explainability use cases comparing ourselves with state-of-the-art methods.