paper-with-me

홈 › Papers

Understanding Interventional TreeSHAP : How and Why it Works

2022-09-29 · Gabriel Laberge, Yann Pequignot

Shapley values are ubiquitous in interpretable Machine Learning due to their strong theoretical background and efficient implementation in the SHAP library. Computing these values previously induced an exponential cost with respect to the number of input features of an opaque model. Now, with efficient implementations such as Interventional TreeSHAP, this exponential burden is alleviated assuming one is explaining ensembles of decision trees. Although Interventional TreeSHAP has risen in popularity, it still lacks a formal proof of how/why it works. We provide such proof with the aim of not only increasing the transparency of the algorithm but also to encourage further development of these ideas. Notably, our proof for Interventional TreeSHAP is easily adapted to Shapley-Taylor indices and one-hot-encoded features.

📄 PDF Abstract BibTeX arXiv:2209.15123

Code (1)

gablabc/understand_treeshap 공식 구현

Tasks

Interpretable Machine Learning

Methods 이 논문이 사용한 방법론

SHAP 설명 없음

Similar Papers 제목 키워드 기반

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 differe…

Diversity

Fast TreeSHAP: Accelerating SHAP Value Computation for Trees

2021-09-20 · Jilei Yang

SHAP (SHapley Additive exPlanation) values are one of the leading tools for interpreting machine learning models, with strong theoretical guarantees (consistency, local accuracy) and a wide availability of implementation…

BIG-bench Machine LearningComputational Efficiency

Quadrature-TreeSHAP: Depth-Independent TreeSHAP and Shapley Interactions

2026-05-06 · Ron Wettenstein, Rory Mitchell, Peng Yu arxiv

Shapley values are a standard tool for explaining predictions of tree ensembles, with Path-Dependent SHAP being the most widely used variant. Despite substantial progress, existing methods still exhibit trade-offs betwee…

Linear TreeShap

2022-09-16 · Peng Yu, Chao Xu, Albert Bifet, Jesse Read

Decision trees are well-known due to their ease of interpretability. To improve accuracy, we need to grow deep trees or ensembles of trees. These are hard to interpret, offsetting their original benefits. Shapley values …

Beyond TreeSHAP: Efficient Computation of Any-Order Shapley Interactions for Tree Ensembles

2024-01-22 · Maximilian Muschalik, Fabian Fumagalli, Barbara Hammer, Eyke Hüllermeier

While shallow decision trees may be interpretable, larger ensemble models like gradient-boosted trees, which often set the state of the art in machine learning problems involving tabular data, still remain black box mode…

Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)