中文
相关论文

相关论文: On the Computational Tractability of the (Many) Sh…

200 篇论文

Although Shapley additive explanations (SHAP) can be computed in polynomial time for simple models like decision trees, they unfortunately become NP-hard to compute for more expressive black-box models like neural networks - where…

机器学习 · 计算机科学 2026-03-23 Reda Marzouk , Shahaf Bassan , Guy Katz

SHAP explanations are a popular feature-attribution mechanism for explainable AI. They use game-theoretic notions to measure the influence of individual features on the prediction of a machine learning model. Despite a lot of recent…

人工智能 · 计算机科学 2021-02-02 Guy Van den Broeck , Anton Lykov , Maximilian Schleich , Dan Suciu

SHAP (SHapley Additive exPlanations) has become a popular method to attribute the prediction of a machine learning model on an input to its features. One main challenge of SHAP is the computation time. An exact computation of Shapley values…

机器学习 · 统计学 2023-09-06 Linwei Hu , Ke Wang

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…

机器学习 · 计算机科学 2022-12-06 Gabriel Laberge , Yann Pequignot

Shapley additive explanations (SHAP) are widely recognised as computationally intractable for neural networks, since they induce an exponential search space over the input features. In this work, we take a first step towards scaling exact…

机器学习 · 计算机科学 2026-05-26 David Boetius , Shahaf Bassan , Guy Katz , Stefan Leue , Tobias Sutter

Besides accuracy, recent studies on machine learning models have been addressing the question on how the obtained results can be interpreted. Indeed, while complex machine learning models are able to provide very good results in terms of…

机器学习 · 计算机科学 2022-11-07 Guilherme Dean Pelegrina , Leonardo Tomazeli Duarte , Michel Grabisch

Thanks to its solid theoretical foundation, the SHAP framework is arguably one the most widely utilized frameworks for local explainability of ML models. Despite its popularity, its exact computation is known to be very challenging, proven…

机器学习 · 计算机科学 2024-05-28 Reda Marzouk , Colin de La Higuera

Shapley-related techniques have gained attention as both global and local interpretation tools because of their desirable properties. However, their computation using conditional expectations is computationally expensive. Approximation…

机器学习 · 统计学 2022-07-13 Zhipu Zhou , Jie Chen , Linwei Hu

In Machine Learning, the $\mathsf{SHAP}$-score is a version of the Shapley value that is used to explain the result of a learned model on a specific entity by assigning a score to every feature. While in general computing Shapley values is…

人工智能 · 计算机科学 2023-03-31 Marcelo Arenas , Pablo Barceló , Leopoldo Bertossi , Mikaël Monet

In recent years, the Shapley value and SHAP explanations have emerged as one of the most dominant paradigms for providing post-hoc explanations of black-box models. Despite their well-founded theoretical properties, many recent works have…

机器学习 · 计算机科学 2025-02-21 James Enouen , Yan Liu

One of the most popular methods of the machine learning prediction explanation is the SHapley Additive exPlanations method (SHAP). An imprecise SHAP as a modification of the original SHAP is proposed for cases when the class probability…

机器学习 · 计算机科学 2021-06-18 Lev V. Utkin , Andrei V. Konstantinov , Kirill A. Vishniakov

Shapley effects are attracting increasing attention as sensitivity measures. When the value function is the conditional variance, they account for the individual and higher order effects of a model input. They are also well defined under…

统计计算 · 统计学 2021-10-13 Elmar Plischke , Giovanni Rabitti , Emanuele Borgonovo

A very popular model-agnostic technique for explaining predictive models is the SHapley Additive exPlanation (SHAP). The two most popular versions of SHAP are a conditional expectation version and an unconditional expectation version (the…

机器学习 · 计算机科学 2023-07-21 Ronald Richman , Mario V. Wüthrich

Scores based on Shapley values are widely used for providing explanations to classification results over machine learning models. A prime example of this is the influential SHAP-score, a version of the Shapley value that can help explain…

人工智能 · 计算机科学 2021-04-06 Marcelo Arenas , Pablo Barceló Leopoldo Bertossi , Mikaël Monet

In Explainable AI (XAI), Shapley values are a popular model-agnostic framework for explaining predictions made by complex machine learning models. The computation of Shapley values requires estimating non-trivial contribution functions…

机器学习 · 计算机科学 2026-01-27 Lars Henry Berge Olsen , Martin Jullum

Explaining complex or seemingly simple machine learning models is an important practical problem. We want to explain individual predictions from a complex machine learning model by learning simple, interpretable explanations. Shapley values…

机器学习 · 统计学 2020-02-07 Kjersti Aas , Martin Jullum , Anders Løland

When using machine learning techniques in decision-making processes, the interpretability of the models is important. In the present paper, we adopted the Shapley additive explanation (SHAP), which is based on fair profit allocation among…

机器学习 · 计算机科学 2022-03-03 Yasunobu Nohara , Koutarou Matsumoto , Hidehisa Soejima , Naoki Nakashima

Interpretable machine learning has been focusing on explaining final models that optimize performance. The current state-of-the-art is the Shapley additive explanations (SHAP) that locally explains variable impact on individual predictions,…

We introduce a new Shapley value approach for global sensitivity analysis and machine learning explainability. The method is based on the first-order partial derivatives of the underlying function. The computational complexity of the method…

机器学习 · 计算机科学 2023-03-28 Hui Duan , Giray Ökten

Shapley values are model-agnostic methods for explaining model predictions. Many commonly used methods of computing Shapley values, known as off-manifold methods, rely on model evaluations on out-of-distribution input samples. Consequently,…

机器学习 · 统计学 2023-02-28 Muhammad Faaiz Taufiq , Patrick Blöbaum , Lenon Minorics
‹ 上一页 1 2 3 10 下一页 ›