中文
相关论文

相关论文: Axiomatic characterization of pointwise Shapley de…

200 篇论文

The Shapley value has become a popular method to attribute the prediction of a machine-learning model on an input to its base features. The use of the Shapley value is justified by citing [16] showing that it is the \emph{unique} method…

人工智能 · 计算机科学 2020-02-10 Mukund Sundararajan , Amir Najmi

Despite their ubiquitous use, Shapley value feature attributions can be misleading due to feature interaction in both model and data. We propose an alternative attribution approach, Shapley Sets, which awards value to sets of features.…

机器学习 · 计算机科学 2023-07-06 Torty Sivill , Peter Flach

This paper makes the case for using Shapley value to quantify the importance of random input variables to a function. Alternatives based on the ANOVA decomposition can run into conceptual and computational problems when the input variables…

统计理论 · 数学 2017-03-22 Art B. Owen , Clémentine Prieur

Recent work demonstrated the existence of Boolean functions for which Shapley values provide misleading information about the relative importance of features in rule-based explanations. Such misleading information was broadly categorized…

人工智能 · 计算机科学 2024-02-14 Xuanxiang Huang , Joao Marques-Silva

We extend the well-known Shannon decomposition of Boolean functions to more general classes of functions. Such decompositions, which we call pivotal decompositions, express the fact that every unary section of a function only depends upon…

环与代数 · 数学 2014-06-10 Jean-Luc Marichal , Bruno Teheux

The Shapley value has become popular in the Explainable AI (XAI) literature, thanks, to a large extent, to a solid theoretical foundation, including four "favourable and fair" axioms for attribution in transferable utility games. The…

机器学习 · 计算机科学 2021-02-23 Daniel Fryer , Inga Strümke , Hien Nguyen

We propose a variant of the Shapley value, the group Shapley value, to interpret counterfactual simulations in structural economic models by quantifying the importance of different components. Our framework compares two sets of parameters,…

计量经济学 · 经济学 2024-10-10 Yongchan Kwon , Sokbae Lee , Guillaume A. Pouliot

Shapley values have become one of the go-to methods to explain complex models to end-users. They provide a model agnostic post-hoc explanation with foundations in game theory: what is the worth of a player (in machine learning, a feature…

机器学习 · 计算机科学 2023-06-21 Joran Michiels , Maarten De Vos , Johan Suykens

Game-theoretic formulations of feature importance have become popular as a way to "explain" machine learning models. These methods define a cooperative game between the features of a model and distribute influence among these input elements…

人工智能 · 计算机科学 2020-07-01 I. Elizabeth Kumar , Suresh Venkatasubramanian , Carlos Scheidegger , Sorelle Friedler

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 such as Banzhaf…

数据库 · 计算机科学 2024-04-17 Pratik Karmakar , Mikaël Monet , Pierre Senellart , Stéphane Bressan

We consider an investment process that includes a number of features, each of which can be active or inactive. Our goal is to attribute or decompose an achieved performance to each of these features, plus a baseline value. There are many…

计算金融 · 定量金融 2021-02-12 Nicholas Moehle , Stephen Boyd , Andrew Ang

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

We propose a novel definition of Shapley values with uncertain value functions based on first principles using probability theory. Such uncertain value functions can arise in the context of explainable machine learning as a result of…

机器学习 · 计算机科学 2023-04-03 Raoul Heese , Sascha Mücke , Matthias Jakobs , Thore Gerlach , Nico Piatkowski

In this paper we investigate the problem of quantifying the contribution of each variable to the satisfying assignments of a Boolean function based on the Shapley value. Our main result is a polynomial-time equivalence between computing…

数据库 · 计算机科学 2023-06-27 Ahmet Kara , Dan Olteanu , Dan Suciu

Originally introduced in cooperative game theory, Shapley values have become a very popular tool to explain machine learning predictions. Based on Shapley's fairness axioms, every input (feature component) gets a credit how it contributes…

机器学习 · 统计学 2025-08-19 Michael Mayer , Mario V. Wüthrich

Shapley value is a classic notion from game theory, historically used to quantify the contributions of individuals within groups, and more recently applied to assign values to data points when training machine learning models. Despite its…

机器学习 · 计算机科学 2020-02-28 Amirata Ghorbani , Michael P. Kim , James Zou

SHAP scores represent the proposed use of the well-known Shapley values in eXplainable Artificial Intelligence (XAI). Recent work has shown that the exact computation of SHAP scores can produce unsatisfactory results. Concretely, for some…

机器学习 · 计算机科学 2024-12-20 Olivier Letoffe , Xuanxiang Huang , Joao Marques-Silva

Feature attributions based on the Shapley value are popular for explaining machine learning models; however, their estimation is complex from both a theoretical and computational standpoint. We disentangle this complexity into two factors:…

机器学习 · 计算机科学 2022-07-18 Hugh Chen , Ian C. Covert , Scott M. Lundberg , Su-In Lee

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 computationally very…

机器学习 · 计算机科学 2022-08-29 Arne Gevaert , Yvan Saeys

With the widespread use of sophisticated machine learning models in sensitive applications, understanding their decision-making has become an essential task. Models trained on tabular data have witnessed significant progress in explanations…

机器学习 · 计算机科学 2022-06-16 Aditya Lahiri , Kamran Alipour , Ehsan Adeli , Babak Salimi
‹ 上一页 1 2 3 10 下一页 ›