Problems with Shapley-value-based explanations as feature importance measures

Understand

Game-theoretic formulations of feature importance have become popular as a way to "explain" machine learning models.

• These methods define a cooperative game between the features of a model and distribute influence among these input elements using some form of the game's unique Shapley values.
• Justification for these methods rests on two pillars: their desirable mathematical properties, and their applicability to specific motivations for explanations.
• We show that mathematical problems arise when Shapley values are used for feature importance and that the solutions to mitigate these necessarily induce further complexity, such as the need for causal reasoning.