Pith. sign in

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

arxiv 2302.08160 v1 pith:IJEPGCDT submitted 2023-02-16 cs.LG cs.AI

classification cs.LGcs.AI
keywords featuresimportancevaluesprovablyshapleyclassifierspredictionpredictions
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. SHAP scores fail pervasively even when Lipschitz succeeds

    cs.LG 2024-12 conditional novelty 6.0 of 10

    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.

  2. The Explanation Game -- Rekindled (Extended Version)

    cs.AI 2025-01 conditional novelty 4.0 of 10

    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.

Pith tools