REVIEW 2 cited by
The Inadequacy of Shapley Values for Explainability
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
This paper develops a rigorous argument for why the use of Shapley values in explainable AI (XAI) will necessarily yield provably misleading information about the relative importance of features for predictions. Concretely, this paper demonstrates that there exist classifiers, and associated predictions, for which the relative importance of features determined by the Shapley values will incorrectly assign more importance to features that are provably irrelevant for the prediction, and less importance to features that are provably relevant for the prediction. The paper also argues that, given recent complexity results, the existence of efficient algorithms for the computation of rigorous feature attribution values in the case of some restricted classes of classifiers should be deemed unlikely at best.
Forward citations
Cited by 2 Pith papers
-
SHAP scores fail pervasively even when Lipschitz succeeds
SHAP scores can assign zero importance to a relevant feature and nonzero importance to an irrelevant feature, even for Lipschitz-continuous and arbitrarily differentiable regression models.
-
The Explanation Game -- Rekindled (Extended Version)
A characteristic function based on weak abductive explanations yields Shapley values that give zero importance to irrelevant features, and a sample-based algorithm makes the approach practical.
Discussion (0). Continue with ORCID to comment.