English
Related papers

Related papers: Triplot: model agnostic measures and visualisation…

200 papers

In this paper, we present a new explainability formalism designed to shed light on how each input variable of a test set impacts the predictions of machine learning models. Hence, we propose a group explainability formalism for trained…

Machine Learning · Statistics 2022-08-12 François Bachoc , Fabrice Gamboa , Max Halford , Jean-Michel Loubes , Laurent Risser

Self-supervised models create representation spaces that lack clear semantic meaning. This interpretability problem of representations makes traditional explainability methods ineffective in this context. In this paper, we introduce a novel…

Computer Vision and Pattern Recognition · Computer Science 2024-06-12 Yavuz Yarici , Kiran Kokilepersaud , Mohit Prabhushankar , Ghassan AlRegib

Variable importance is one of the most widely used measures for interpreting machine learning with significant interest from both statistics and machine learning communities. Recently, increasing attention has been directed toward…

Machine Learning · Statistics 2025-12-22 Xiaohan Wang , Yunzhe Zhou , Giles Hooker

Observational studies of treatment effects require adjustment for confounding variables. However, causal inference methods typically cannot deliver perfect adjustment on all measured baseline variables, and there is often ambiguity about…

Methodology · Statistics 2024-02-16 Lauren D. Liao , Yeyi Zhu , Amanda L. Ngo , Rana F. Chehab , Samuel D. Pimentel

Explainable Artificial Intelligence (XAI) has gained importance in interpreting model predictions. Among leading techniques for XAI, Local Interpretable Model-agnostic Explanations (LIME) is most frequently utilized as it notably helps…

Human-Computer Interaction · Computer Science 2026-02-05 Jeongmin Rhee , Changhee Lee , DongHwa Shin , Bohyoung Kim

Interpretability methods aim to help users build trust in and understand the capabilities of machine learning models. However, existing approaches often rely on abstract, complex visualizations that poorly map to the task at hand or require…

Human-Computer Interaction · Computer Science 2021-07-12 Harini Suresh , Kathleen M. Lewis , John V. Guttag , Arvind Satyanarayan

With now well-recognized non-negligible model selection uncertainty, data analysts should no longer be satisfied with the output of a single final model from a model selection process, regardless of its sophistication. To improve…

Methodology · Statistics 2016-08-03 Chenglong Ye , Yi Yang , Yuhong Yang

Algorithmic approaches to interpreting machine learning models have proliferated in recent years. We carry out human subject tests that are the first of their kind to isolate the effect of algorithmic explanations on a key aspect of model…

Computation and Language · Computer Science 2020-05-06 Peter Hase , Mohit Bansal

As opaque black-box predictive models become more prevalent, the need to develop interpretations for these models is of great interest. The concept of variable importance and Shapley values are interpretability measures that applies to any…

Machine Learning · Statistics 2025-03-10 Zexuan Sun , Garvesh Raskutti

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

Machine learning models can automatically learn complex relationships, such as non-linear and interaction effects. Interpretable machine learning methods such as partial dependence plots visualize marginal feature effects but may lead to…

Machine Learning · Statistics 2022-02-16 Julia Herbinger , Bernd Bischl , Giuseppe Casalicchio

In domains where transparency and trustworthiness are crucial, such as healthcare, rule-based systems are widely used and often preferred over black-box models for decision support systems due to their inherent interpretability. However, as…

Machine Learning · Computer Science 2025-06-18 Christel Sirocchi , Damiano Verda

This paper reviews and advocates against the use of permute-and-predict (PaP) methods for interpreting black box functions. Methods such as the variable importance measures proposed for random forests, partial dependence plots, and…

Methodology · Statistics 2021-10-11 Giles Hooker , Lucas Mentch , Siyu Zhou

Interpretable Machine Learning (IML) methods are used to gain insight into the relevance of a feature of interest for the performance of a model. Commonly used IML methods differ in whether they consider features of interest in isolation,…

Machine Learning · Statistics 2021-04-23 Gunnar König , Christoph Molnar , Bernd Bischl , Moritz Grosse-Wentrup

Quantifying variable importance is essential for answering high-stakes questions in fields like genetics, public policy, and medicine. Current methods generally calculate variable importance for a given model trained on a given dataset.…

Machine Learning · Computer Science 2024-04-03 Jon Donnelly , Srikar Katta , Cynthia Rudin , Edward P. Browne

A new approach to the local and global explanation is proposed. It is based on selecting a convex hull constructed for the finite number of points around an explained instance. The convex hull allows us to consider a dual representation of…

Machine Learning · Computer Science 2024-01-30 Andrei V. Konstantinov , Boris V. Kozlov , Stanislav R. Kirpichenko , Lev V. Utkin

Reliable estimation of feature contributions in machine learning models is essential for trust, transparency and regulatory compliance, especially when models are proprietary or otherwise operate as black boxes. While permutation-based…

Machine Learning · Statistics 2025-12-24 Albert Dorador

Locally interpretable model agnostic explanations (LIME) method is one of the most popular methods used to explain black-box models at a per example level. Although many variants have been proposed, few provide a simple way to produce high…

Machine Learning · Computer Science 2023-10-04 Amit Dhurandhar , Karthikeyan Ramamurthy , Kartik Ahuja , Vijay Arya

Explaining the decision process of machine learning algorithms is nowadays crucial for both model's performance enhancement and human comprehension. This can be achieved by assessing the variable importance of single variables, even for…

Machine Learning · Computer Science 2023-12-19 Ahmad Chamma , Bertrand Thirion , Denis A. Engemann

In the domain of Mobility Data Science, the intricate task of interpreting models trained on trajectory data, and elucidating the spatio-temporal movement of entities, has persistently posed significant challenges. Conventional XAI…

Artificial Intelligence · Computer Science 2023-12-04 Georgios Makridis , Vasileios Koukos , Georgios Fatouros , Dimosthenis Kyriazis