Pith. sign in

REVIEW 1 cited by

Causal Analysis of Shapley Values: Conditional vs. Marginal

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 2409.06157 v1 pith:HPC2NW5W submitted 2024-09-10 cs.GT cs.LGstat.MEstat.ML

classification cs.GTcs.LGstat.MEstat.ML
keywords causalconditionalapproachmarginalshapleyvaluesdifferentalong
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Shapley values, a game theoretic concept, has been one of the most popular tools for explaining Machine Learning (ML) models in recent years. Unfortunately, the two most common approaches, conditional and marginal, to calculating Shapley values can lead to different results along with some undesirable side effects when features are correlated. This in turn has led to the situation in the literature where contradictory recommendations regarding choice of an approach are provided by different authors. In this paper we aim to resolve this controversy through the use of causal arguments. We show that the differences arise from the implicit assumptions that are made within each method to deal with missing causal information. We also demonstrate that the conditional approach is fundamentally unsound from a causal perspective. This, together with previous work in [1], leads to the conclusion that the marginal approach should be preferred over the conditional one.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. On Model Extrapolation in Marginal Shapley Values

    stat.ML 2024-12 conditional novelty 5.0 of 10

    Stratifying marginal Shapley by feature region avoids off-manifold extrapolation and, with a causal direction and a chosen reference constant, reproduces causal Shapley values on a linear spline and an insurance example.

Pith tools