Problems with Shapley-value-based explanations as feature importance measures
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. We also draw on additional literature to argue that Shapley values do not provide explanations which suit human-centric goals of explainability.
Code (0)
등록된 구현이 없습니다.
Tasks
Feature ImportanceSimilar Papers 제목 키워드 기반
CAGE: Causality-Aware Shapley Value for Global Explanations
As Artificial Intelligence (AI) is having more influence on our everyday lives, it becomes important that AI-based decisions are transparent and explainable. As a consequence, the field of eXplainable AI (or XAI) has bec…
Feature ImportanceShapley Residuals: Quantifying the limits of the Shapley value for explanations
Popular feature importance techniques compute additive approximations to nonlinear models by first defining a cooperative game describing the value of different subsets of the model's features, then calculating the resul…
AttributeFeature ImportanceAttention Flows are Shapley Value Explanations
Shapley Values, a solution to the credit assignment problem in cooperative game theory, are a popular type of explanation in machine learning, having been used to explain the importance of features, embeddings, and even …
Shapley values for feature selection: The good, the bad, and the axioms
The Shapley value has become popular in the Explainable AI (XAI) literature, thanks, to a large extent, to a solid theoretical foundation, including four "favourable and fair" axioms for attribution in transferable utili…
Explainable Artificial Intelligence (XAI)feature selectionJoint Shapley values: a measure of joint feature importance
The Shapley value is one of the most widely used measures of feature importance partly as it measures a feature's average effect on a model's prediction. We introduce joint Shapley values, which directly extend Shapley's…
Feature Importance