English
Related papers

Related papers: Consistency of Feature Attribution in Deep Learnin…

200 papers

Feature selection in machine learning is subject to the intrinsic randomness of the feature selection algorithms (for example, random permutations during MDA). Stability of selected features with respect to such randomness is essential to…

Machine Learning · Computer Science 2020-05-27 Xin Man , Ernest Chan

Interpretability of learning algorithms is crucial for applications involving critical decisions, and variable importance is one of the main interpretation tools. Shapley effects are now widely used to interpret both tree ensembles and…

Machine Learning · Statistics 2022-02-03 Clément Bénard , Gérard Biau , Sébastien da Veiga , Erwan Scornet

An important technique to explore a black-box machine learning (ML) model is called SHAP (SHapley Additive exPlanation). SHAP values decompose predictions into contributions of the features in a fair way. We will show that for a boosted…

Machine Learning · Statistics 2022-08-01 Michael Mayer

Feature attribution methods, which explain an individual prediction made by a model as a sum of attributions for each input feature, are an essential tool for understanding the behavior of complex deep learning models. However, ensuring…

Machine Learning · Computer Science 2020-10-28 Ethan Weinberger , Joseph Janizek , Su-In Lee

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,…

Feature attribution for kernel methods is often heuristic and not individualised for each prediction. To address this, we turn to the concept of Shapley values~(SV), a coalition game theoretical framework that has previously been applied to…

Machine Learning · Statistics 2022-05-27 Siu Lun Chau , Robert Hu , Javier Gonzalez , Dino Sejdinovic

Existing feature attribution methods like SHAP often suffer from global dependence, failing to capture true local model behavior. This paper introduces VARSHAP, a novel model-agnostic local feature attribution method which uses the…

Machine Learning · Computer Science 2025-06-10 Mateusz Gajewski , Mikołaj Morzy , Adam Karczmarz , Piotr Sankowski

Astrochemical modelling of the interstellar medium typically makes use of complex computational codes with parameters whose values can be varied. It is not always clear what the exact nature of the relationship is between these input…

Astrophysics of Galaxies · Physics 2023-09-14 Johannes Heyl , Joshua Butterworth , Serena Viti

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…

Artificial Intelligence · Computer Science 2023-03-31 Marcelo Arenas , Pablo Barceló , Leopoldo Bertossi , Mikaël Monet

Objective: Shapley additive explanations (SHAP) is a popular post-hoc technique for explaining black box models. While the impact of data imbalance on predictive models has been extensively studied, it remains largely unknown with respect…

Machine Learning · Computer Science 2022-06-10 Mingxuan Liu , Yilin Ning , Han Yuan , Marcus Eng Hock Ong , Nan Liu

The problem of explaining the behavior of deep neural networks has recently gained a lot of attention. While several attribution methods have been proposed, most come without strong theoretical foundations, which raises questions about…

Machine Learning · Computer Science 2019-06-24 Marco Ancona , Cengiz Öztireli , Markus Gross

Feature attribution methods, such as SHAP and LIME, explain machine learning model predictions by quantifying the influence of each input component. When applying feature attributions to explain language models, a basic question is defining…

Human-Computer Interaction · Computer Science 2025-09-26 Alan Boyle , Furui Cheng , Vilém Zouhar , Mennatallah El-Assady

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…

Artificial Intelligence · Computer Science 2024-05-21 Olivier Letoffe , Xuanxiang Huang , Nicholas Asher , Joao Marques-Silva

Post-hoc explanations are widely used to justify, contest, and review automated decisions in high-stakes domains such as lending, employment, and healthcare. Among these methods, SHAP is often treated as providing a reliable account of…

Machine Learning · Computer Science 2026-01-27 Hyunseung Hwang , Seungeun Lee , Lucas Rosenblatt , Steven Euijong Whang , Julia Stoyanovich

Feature selection remains a major challenge in medical prediction, where existing approaches such as LASSO often lack robustness and interpretability. We introduce GRASP, a novel framework that couples Shapley value driven attribution with…

Machine Learning · Computer Science 2026-05-01 Yuheng Luo , Shuyan Li , Zhong Cao

Gradient-based attribution methods can aid in the understanding of convolutional neural networks (CNNs). However, the redundancy of attribution features and the gradient saturation problem, which weaken the ability to identify significant…

Computer Vision and Pattern Recognition · Computer Science 2021-04-13 An Zhang , Xiang Wang , Chengfang Fang , Jie Shi , Tat-seng Chua , Zehua Chen

Feature attribution methods identify which features of an input most influence a model's output. Most widely-used feature attribution methods (such as SHAP, LIME, and Grad-CAM) are "class-dependent" methods in that they generate a feature…

Machine Learning · Computer Science 2023-02-28 Neil Jethani , Adriel Saporta , Rajesh Ranganath

We propose and study a framework for quantifying the importance of the choices of parameter values to the result of a query over a database. These parameters occur as constants in logical queries, such as conjunctive queries. In our…

Databases · Computer Science 2024-11-19 Amir Gilad , Martin Grohe , Benny Kimelfeld , Peter Lindner , Christoph Standke

Segmentation is the identification of anatomical regions of interest, such as organs, tissue, and lesions, serving as a fundamental task in computer-aided diagnosis in medical imaging. Although deep learning models have achieved remarkable…

Image and Video Processing · Electrical Eng. & Systems 2025-12-09 Tianyi Ren , Daniel Low , Pittra Jaengprajak , Juampablo Heras Rivera , Jacob Ruzevick , Mehmet Kurt

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.…

Machine Learning · Computer Science 2023-07-06 Torty Sivill , Peter Flach