Pith. sign in

REVIEW 5 cited by

The Shapley Taylor Interaction Index

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 1902.05622 v2 pith:LRL4SEKV submitted 2019-02-14 cs.GT econ.TH

The Shapley Taylor Interaction Index

classification cs.GT econ.TH
keywords shapleyindexmodeltaylorinteractionaxiomfeaturesinteractions
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

The attribution problem, that is the problem of attributing a model's prediction to its base features, is well-studied. We extend the notion of attribution to also apply to feature interactions. The Shapley value is a commonly used method to attribute a model's prediction to its base features. We propose a generalization of the Shapley value called Shapley-Taylor index that attributes the model's prediction to interactions of subsets of features up to some size k. The method is analogous to how the truncated Taylor Series decomposes the function value at a certain point using its derivatives at a different point. In fact, we show that the Shapley Taylor index is equal to the Taylor Series of the multilinear extension of the set-theoretic behavior of the model. We axiomatize this method using the standard Shapley axioms -- linearity, dummy, symmetry and efficiency -- and an additional axiom that we call the interaction distribution axiom. This new axiom explicitly characterizes how interactions are distributed for a class of functions that model pure interaction. We contrast the Shapley-Taylor index against the previously proposed Shapley Interaction index (cf. [9]) from the cooperative game theory literature. We also apply the Shapley Taylor index to three models and identify interesting qualitative insights.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

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

  1. Causal Optimizer Interaction Calculus: Hidden Geometric Relaxation and Identifiable Interventions

    cs.LG 2026-07 conditional novelty 6.0

    Under fixed innovation coupling, finite-horizon optimizers admit minimal pathwise realizations and incidence-identifiable Möbius effects, with a five-term readout transfer from hidden relaxation and a closed reduced-v...

  2. Restricted Dynamic Geometric Complexity: Path-Space Reduction and M\"obius--Jacobi Response

    math.OC 2026-07 conditional novelty 6.0

    RDGC is the least affine-invariant length of an admissible metric path to a Hessian-relative condition target, with global Green and bordered Jacobi–KKT response laws on Hadamard path space.

  3. Interactions Between Crosscoder Features: A Compact Proofs Perspective

    cs.LG 2026-06 unverdicted novelty 6.0

    Derives an interaction measure between crosscoder features from reconstruction error in compact proofs and applies it to produce computationally sparse crosscoders retaining 60% MLP performance with single-feature sel...

  4. Causal Optimizer Interaction Calculus: Hidden Geometric Relaxation and Identifiable Interventions

    cs.LG 2026-07 conditional novelty 5.0

    A modular calculus decomposes optimizer updates into geometric preconditioning plus structured nongeometric mechanisms, with a direction-expressivity theorem showing full SPD geometry captures exactly strict descent d...

  5. Restricted Dynamic Geometric Complexity: Path-Space Reduction and M\"obius--Jacobi Response

    math.OC 2026-07 conditional novelty 5.0

    Restricted dynamic geometric complexity measures the intrinsic affine-invariant path distance from an initial metric to a condition-number target when the metric family is structurally constrained, with exact LMI and ...