Shapley value: from cooperative game to explainable artificial intelligence

Abstract With the tremendous success of machine learning (ML), concerns about their black-box nature have grown. The issue of interpretability affects trust in ML systems and raises ethical concerns such as algorithmic bias. In recent years, the feature attribution explanation method based on Shapley value has become the mainstream explainable artificial intelligence approach for explaining ML models. This paper provides a comprehensive overview of Shapley value-based attribution methods. We begin by outlining the foundational theory of Shapley value rooted in cooperative game theory and discussing its desirable properties. To enhance comprehension and aid in identifying relevant algorithms, we propose a…

• NN
  National Natural Science Foundation of China

  Award: U1964201
• NK
  National Key Research and Development Program of China

  Award: 2020AAA0108101