paper-with-me

홈 › Papers

TT-FSI: Scalable Faithful Shapley Interactions via Tensor-Train

2026-01-05 · Ungsik Kim, Suwon Lee arxiv

The Faithful Shapley Interaction (FSI) index uniquely satisfies the faithfulness axiom among Shapley interaction indices, but computing FSI requires $O(d^\ell \cdot 2^d)$ time and existing implementations use $O(4^d)$ memory. We present TT-FSI, which exploits FSI's algebraic structure via Matrix Product Operators (MPO). Our main theoretical contribution is proving that the linear operator $v \mapsto \text{FSI}(v)$ admits an MPO representation with TT-rank $O(\ell d)$, enabling an efficient sweep algorithm with $O(\ell^2 d^3 \cdot 2^d)$ time and $O(\ell d^2)$ core storage an exponential improvement over existing methods. Experiments on six datasets ($d=8$ to $d=20$) demonstrate up to 280$\times$ speedup over baseline, 85$\times$ over SHAP-IQ, and 290$\times$ memory reduction. TT-FSI scales to $d=20$ (1M coalitions) where all competing methods fail.

📄 PDF Abstract BibTeX arXiv:2601.01903

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Faith-Shap: The Faithful Shapley Interaction Index

2022-03-02 · Che-Ping Tsai, Chih-Kuan Yeh, Pradeep Ravikumar

Shapley values, which were originally designed to assign attributions to individual players in coalition games, have become a commonly used approach in explainable machine learning to provide attributions to input featur…

Computational Efficiency

Interaction Tensor SHAP

2025-12-05 · Hiroki Hasegawa, Yukihiko Okada arxiv

This study proposes Interaction Tensor SHAP (IT-SHAP), a tensor algebraic formulation of the Shapley Taylor Interaction Index (STII) that makes its computational structure explicit. STII extends the Shapley value to high…

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…

TN-SHAP-G: Graph-Structured Tensor Network Surrogates for Shapley Values and Interactions

2026-06-01 · Farzaneh Heidari, Guillaume Rabusseau arxiv

Shapley values are a widely used tool for attributing importance and interactions among input variables in black-box models, but their computation involves a function defined over an exponentially large space of subsets.…

Beyond Additive Decompositions: Interpretability Through Separability

2026-05-29 · Jinyang Liu, Munir Eberhardt Hiabu arxiv

Interpretable machine learning requires models that are accurate and structurally faithful to the data. Existing explainability methods rely heavily on additive representations (e.g., Generalized Additive Models (GAMs), …

Interpretable Machine Learning