English
Related papers

Related papers: Feature relevance quantification in explainable AI…

200 papers

Feature attribution methods such as SHapley Additive exPlanations (SHAP) have become instrumental in understanding machine learning models, but their role in guiding model optimization remains underexplored. In this paper, we propose a…

Machine Learning · Computer Science 2025-08-01 Amal Saadallah

Shapley values are extensively used in explainable artificial intelligence (XAI) as a framework to explain predictions made by complex machine learning (ML) models. In this work, we focus on conditional Shapley values for predictive models…

Machine Learning · Statistics 2023-12-07 Lars Henry Berge Olsen

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…

Machine Learning · Computer Science 2023-03-28 Hui Duan , Giray Ökten

Cohort Shapley value is a model-free method of variable importance grounded in game theory that does not use any unobserved and potentially impossible feature combinations. We use it to evaluate algorithmic fairness, using the well known…

Machine Learning · Computer Science 2021-05-20 Masayoshi Mase , Art B. Owen , Benjamin B. Seiler

For neural models to garner widespread public trust and ensure fairness, we must have human-intelligible explanations for their predictions. Recently, an increasing number of works focus on explaining the predictions of neural models in…

Computation and Language · Computer Science 2020-12-15 Oana-Maria Camburu , Eleonora Giunchiglia , Jakob Foerster , Thomas Lukasiewicz , Phil Blunsom

Not all real-world data are labeled, and when labels are not available, it is often costly to obtain them. Moreover, as many algorithms suffer from the curse of dimensionality, reducing the features in the data to a smaller set is often of…

Machine Learning · Computer Science 2022-05-19 Chiara Balestra , Florian Huber , Andreas Mayr , Emmanuel Müller

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…

Machine Learning · Statistics 2023-06-01 Salim I. Amoukou , Nicolas J-B. Brunel , Tangi Salaün

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…

Machine Learning · Computer Science 2021-06-18 Lev V. Utkin , Andrei V. Konstantinov , Kirill A. Vishniakov

Artificial intelligence models and methods commonly lack causal interpretability. Despite the advancements in interpretable machine learning (IML) methods, they frequently assign importance to features which lack causal influence on the…

Machine Learning · Computer Science 2024-01-29 Francisco Nunes Ferreira Quialheiro Simoes , Mehdi Dastani , Thijs van Ommen

Despite their enormous predictive power, machine learning models are often unsuitable for applications in regulated industries such as finance, due to their limited capacity to provide explanations. While model-agnostic frameworks such as…

Machine Learning · Statistics 2025-11-03 Joshua S. Harvey , Guanchao Feng , Sai Anusha Meesala , Tina Zhao , Dhagash Mehta

Shapley values have seen widespread use in machine learning as a way to explain model predictions and estimate the importance of covariates. Accurately explaining models is critical in real-world models to both aid in decision making and to…

Machine Learning · Statistics 2024-08-19 Daniel de Marchi , Michael Kosorok , Scott de Marchi

We study instancewise feature importance scoring as a method for model interpretation. Any such method yields, for each predicted instance, a vector of importance scores associated with the feature vector. Methods based on the Shapley score…

Machine Learning · Computer Science 2018-08-09 Jianbo Chen , Le Song , Martin J. Wainwright , Michael I. Jordan

Explainable AI~(XAI) methods such as SHAP can help discover feature attributions in black-box models. If the method reveals a significant attribution from a ``protected feature'' (e.g., gender, race) on the model output, the model is…

Machine Learning · Computer Science 2024-08-14 Jun Yuan , Aritra Dasgupta

Quantifying the importance of each training point to a learning task is a fundamental problem in machine learning and the estimated importance scores have been leveraged to guide a range of data workflows such as data summarization and…

Machine Learning · Computer Science 2021-04-27 Ruoxi Jia , Fan Wu , Xuehui Sun , Jiacen Xu , David Dao , Bhavya Kailkhura , Ce Zhang , Bo Li , Dawn Song

Data valuation -- quantifying the contribution of individual data sources to certain predictive behaviors of a model -- is of great importance to enhancing the transparency of machine learning and designing incentive systems for data…

Machine Learning · Computer Science 2023-07-28 Zhihong Liu , Hoang Anh Just , Xiangyu Chang , Xi Chen , Ruoxi Jia

Shapley values has established itself as one of the most appropriate and theoretically sound frameworks for explaining predictions from complex machine learning models. The popularity of Shapley values in the explanation setting is probably…

Machine Learning · Statistics 2021-06-24 Martin Jullum , Annabelle Redelmeier , Kjersti Aas

Computing the importance of features in supervised classification tasks is critical for model interpretability. Shapley values are a widely used approach for explaining model predictions, but require direct access to the underlying model,…

Machine Learning · Computer Science 2026-05-18 Joao Fonseca , Julia Stoyanovich

Shapley values originated in cooperative game theory but are extensively used today as a model-agnostic explanation framework to explain predictions made by complex machine learning models in the industry and academia. There are several…

Machine Learning · Statistics 2024-04-15 Lars Henry Berge Olsen , Ingrid Kristine Glad , Martin Jullum , Kjersti Aas

In this article, we provide an axiomatic characterization of feature attribution for multi-output predictors within the Shapley framework. While SHAP explanations are routinely computed independently for each output coordinate, the…

SHAP is a popular method for measuring variable importance in machine learning models. In this paper, we study the algorithm used to estimate SHAP scores and outline its connection to the functional ANOVA decomposition. We use this…

Methodology · Statistics 2022-11-14 Andrew Herren , P. Richard Hahn
‹ Prev 1 4 5 6 7 8 10 Next ›