paper-with-me

Papers

On the Computational Tractability of the (Many) Shapley Values

2025-02-17 · Reda Marzouk, Shahaf Bassan, Guy Katz, Colin de la Higuera

Recent studies have examined the computational complexity of computing Shapley additive explanations (also known as SHAP) across various models and distributions, revealing their tractability or intractability in different settings. However, these studies primarily focused on a specific variant called Conditional SHAP, though many other variants exist and address different limitations. In this work, we analyze the complexity of computing a much broader range of such variants, including Conditional, Interventional, and Baseline SHAP, while exploring both local and global computations. We show that both local and global Interventional and Baseline SHAP can be computed in polynomial time for various ML models under Hidden Markov Model distributions, extending popular algorithms such as TreeSHAP beyond empirical distributions. On the downside, we prove intractability results for these variants over a wide range of neural networks and tree ensembles. We believe that our results emphasize the intricate diversity of computing Shapley values, demonstrating how their complexity is substantially shaped by both the specific SHAP variant, the model type, and the distribution.

📄 PDF Abstract BibTeX arXiv:2502.12295

Code (0)

등록된 구현이 없습니다.

Tasks

Diversity

Methods 이 논문이 사용한 방법론

SHAP 설명 없음

Similar Papers 제목 키워드 기반

Expected Shapley-Like Scores of Boolean Functions: Complexity and Applications to Probabilistic Databases

2024-01-12 · Pratik Karmakar, Mikaël Monet, Pierre Senellart, Stéphane Bressan

Shapley values, originating in game theory and increasingly prominent in explainable AI, have been proposed to assess the contribution of facts in query answering over databases, along with other similar power indices su…

PDD-SHAP: Fast Approximations for Shapley Values using Functional Decomposition

2022-08-26 · Arne Gevaert, Yvan Saeys

Because of their strong theoretical properties, Shapley values have become very popular as a way to explain predictions made by black box models. Unfortuately, most existing techniques to compute Shapley values are compu…

Exactly Computing do-Shapley Values

2026-02-06 · R. Teal Witter, Álvaro Parafita, Tomas Garriga, Maximilian Muschalik 외 arxiv

Structural Causal Models (SCM) are a powerful framework for describing complicated dynamics across the natural sciences. A particularly elegant way of interpreting SCMs is do-Shapley, a game-theoretic method of quantifyi…

groupShapley: Efficient prediction explanation with Shapley values for feature groups

2021-06-23 · Martin Jullum, Annabelle Redelmeier, Kjersti Aas

Shapley values has established itself as one of the most appropriate and theoretically sound frameworks for explaining predictions from complex machine learning models. The popularity of Shapley values in the explanation…

Tractable Shapley Values and Interactions via Tensor Networks

2025-10-25 · Farzaneh Heidari, Chao Li, Guillaume Rabusseau arxiv

We show how to replace the O(2^n) coalition enumeration over n features behind Shapley values and Shapley-style interaction indices with a few-evaluation scheme on a tensor-network (TN) surrogate: TN-SHAP. The key idea i…