中文
相关论文

相关论文: Feature Importance: A Closer Look at Shapley Value…

200 篇论文

Feature importance scores are ubiquitous tools for understanding the predictions of machine learning models. However, many popular attribution methods suffer from high instability due to random sampling. Leveraging novel ideas from…

机器学习 · 统计学 2025-07-08 Jeremy Goldwasser , Giles Hooker

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

A common approach for feature selection is to examine the variable importance scores for a machine learning model, as a way to understand which features are the most relevant for making predictions. Given the significance of feature…

机器学习 · 计算机科学 2021-05-13 Jack Dunn , Luca Mingardi , Ying Daisy Zhuo

The Shapley value, which is arguably the most popular approach for assigning a meaningful contribution value to players in a cooperative game, has recently been used intensively in explainable artificial intelligence. Its meaningfulness is…

机器学习 · 计算机科学 2024-01-31 Patrick Kolpaczki , Viktor Bengs , Maximilian Muschalik , Eyke Hüllermeier

The information decomposition problem requires an additive decomposition of the mutual information between the input and target variables into nonnegative terms. The recently introduced solution to this problem, Information Attribution,…

信息论 · 计算机科学 2022-07-13 Tomáš Kroupa , Sara Vannucci , Tomáš Votroubek

Shapley values underlie one of the most popular model-agnostic methods within explainable artificial intelligence. These values are designed to attribute the difference between a model's prediction and an average baseline to the different…

人工智能 · 计算机科学 2020-11-04 Tom Heskes , Evi Sijben , Ioan Gabriel Bucur , Tom Claassen

Reliability-oriented sensitivity analysis aims at combining both reliability and sensitivity analyses by quantifying the influence of each input variable of a numerical model on a quantity of interest related to its failure. In particular,…

统计理论 · 数学 2022-10-25 Julien Demange-Chryst , François Bachoc , Jérôme Morio

A central goal of eXplainable Artificial Intelligence (XAI) is to assign relative importance to the features of a Machine Learning (ML) model given some prediction. The importance of this task of explainability by feature attribution is…

人工智能 · 计算机科学 2024-05-21 Olivier Letoffe , Xuanxiang Huang , Nicholas Asher , Joao Marques-Silva

Shapley values are today extensively used as a model-agnostic explanation framework to explain complex predictive machine learning models. Shapley values have desirable theoretical properties and a sound mathematical foundation in the field…

机器学习 · 统计学 2022-08-16 Lars Henry Berge Olsen , Ingrid Kristine Glad , Martin Jullum , Kjersti Aas

Data valuation, or the valuation of individual datum contributions, has seen growing interest in machine learning due to its demonstrable efficacy for tasks such as noisy label detection. In particular, due to the desirable axiomatic…

机器学习 · 计算机科学 2022-11-15 Stephanie Schoch , Haifeng Xu , Yangfeng Ji

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

As complex machine learning models continue to find applications in high-stakes decision-making scenarios, it is crucial that we can explain and understand their predictions. Post-hoc explanation methods provide useful insights by…

机器学习 · 统计学 2024-10-16 Beepul Bharti , Paul Yi , Jeremias Sulam

As the decisions made or influenced by machine learning models increasingly impact our lives, it is crucial to detect, understand, and mitigate unfairness. But even simply determining what "unfairness" should mean in a given context is…

机器学习 · 计算机科学 2020-10-16 Tom Begley , Tobias Schwedes , Christopher Frye , Ilya Feige

Explainability in yield prediction helps us fully explore the potential of machine learning models that are already able to achieve high accuracy for a variety of yield prediction scenarios. The data included for the prediction of yields…

机器学习 · 计算机科学 2023-04-17 Florian Huber , Hannes Engler , Anna Kicherer , Katja Herzog , Reinhard Töpfer , Volker Steinhage

Despite the success of complex machine learning algorithms, mostly justified by an outstanding performance in prediction tasks, their inherent opaque nature still represents a challenge to their responsible application. Counterfactual…

机器学习 · 计算机科学 2023-06-13 Bjorge Meulemeester , Raphael Mazzine Barbosa De Oliveira , David Martens

Shapley Values (SV) are widely used in explainable AI, but their estimation and interpretation can be challenging, leading to inaccurate inferences and explanations. As a starting point, we remind an invariance principle for SV and derive…

机器学习 · 统计学 2023-06-01 Salim I. Amoukou , Nicolas J-B. Brunel , Tangi Salaün

The emergence of large language models (LLMs) has opened up exciting possibilities for simulating human behavior and cognitive processes, with potential applications in various domains, including marketing research and consumer behavior…

计算与语言 · 计算机科学 2024-11-13 Behnam Mohammadi

Variable importance in regression analyses is of considerable interest in a variety of fields. There is no unique method for assessing variable importance. However, a substantial share of the available literature employs Shapley values,…

统计方法学 · 统计学 2026-01-05 Sinan Acemoglu , Christian Kleiber , Jörg Urban

Given a model $f$ that predicts a target $y$ from a vector of input features $\pmb{x} = x_1, x_2, \ldots, x_M$, we seek to measure the importance of each feature with respect to the model's ability to make a good prediction. To this end, we…

机器学习 · 计算机科学 2019-10-03 Luke Merrick

The coefficient of determination, the $R^2$, is often used to measure the variance explained by an affine combination of multiple explanatory covariates. An attribution of this explanatory contribution to each of the individual covariates…

统计方法学 · 统计学 2020-08-11 Daniel Fryer , Inga Strumke , Hien Nguyen