English
Related papers

Related papers: Consistency of Feature Attribution in Deep Learnin…

200 papers

This paper studies the robustness of feature attribution methods for deep neural networks. It challenges the current notion of attributional robustness that largely ignores the difference in the model's outputs and introduces a new way of…

Machine Learning · Computer Science 2025-12-09 Panagiota Kiourti , Anu Singh , Preeti Duraipandian , Weichao Zhou , Wenchao Li

Fault detection and diagnosis is significant for reducing maintenance costs and improving health and safety in chemical processes. Convolution neural network (CNN) is a popular deep learning algorithm with many successful applications in…

Machine Learning · Computer Science 2023-07-11 Mengxuan Li , Peng Peng , Min Wang , Hongwei Wang

In order to ensure the reliability of the explanations of machine learning models, it is crucial to establish their advantages and limits and in which case each of these methods outperform. However, the current understanding of when and how…

Machine Learning · Computer Science 2025-02-12 Célia Wafa Ayad , Thomas Bonnier , Benjamin Bosch , Sonali Parbhoo , Jesse Read

Ensuring fairness in machine learning models is critical, particularly in high-stakes domains where biased decisions can lead to serious societal consequences. Existing preprocessing approaches generally lack transparent mechanisms for…

Machine Learning · Computer Science 2026-02-24 Lin Zhu , Yijun Bian , Lei You

Interpretable machine learning offers insights into what factors drive a certain prediction of a black-box system. A large number of interpreting methods focus on identifying explanatory input features, which generally fall into two main…

Machine Learning · Computer Science 2023-06-02 Vy Vo , Van Nguyen , Trung Le , Quan Hung Tran , Gholamreza Haffari , Seyit Camtepe , Dinh Phung

Machine learning methods are emerging as a universal paradigm for constructing correlative structure-property relationships in materials science based on multimodal characterization. However, this necessitates development of methods for…

Machine learning techniques, such as deep learning and ensemble methods, are widely used in various domains due to their ability to handle complex real-world tasks. However, their black-box nature has raised multiple concerns about the…

While shallow decision trees may be interpretable, larger ensemble models like gradient-boosted trees, which often set the state of the art in machine learning problems involving tabular data, still remain black box models. As a remedy, the…

Machine Learning · Computer Science 2024-06-21 Maximilian Muschalik , Fabian Fumagalli , Barbara Hammer , Eyke Hüllermeier

AI explainability improves the transparency of models, making them more trustworthy. Such goals are motivated by the emergence of deep learning models, which are obscure by nature; even in the domain of images, where deep learning has…

Machine Learning · Computer Science 2022-03-01 Anna Arias-Duart , Ferran Parés , Dario Garcia-Gasulla , Victor Gimenez-Abalos

Attribution explanation is a typical approach for explaining deep neural networks (DNNs), inferring an importance or contribution score for each input variable to the final output. In recent years, numerous attribution methods have been…

Machine Learning · Computer Science 2025-08-12 Huiqi Deng , Hongbin Pei , Quanshi Zhang , Mengnan Du

Machine learning transparency calls for interpretable explanations of how inputs relate to predictions. Feature attribution is a way to analyze the impact of features on predictions. Feature interactions are the contextual dependence…

Machine Learning · Statistics 2020-06-22 Michael Tsang , Sirisha Rambhatla , Yan Liu

SHapley Additive exPlanations (SHAP) is a key tool for interpreting decision tree ensembles by assigning contribution values to features. It is widely used in finance, advertising, medicine, and other domains. Two main approaches to SHAP…

Machine Learning · Computer Science 2026-04-14 Alexander Nadel , Ron Wettenstein

A suitable feature representation that can both preserve the data intrinsic information and reduce data complexity and dimensionality is key to the performance of machine learning models. Deeply rooted in algebraic topology, persistent…

Algebraic Topology · Mathematics 2018-11-02 Chi Seng Pun , Kelin Xia , Si Xian Lee

Lack of transparency in AI systems poses challenges in critical real-life applications. It is important to be able to explain the decisions of an AI system to ensure trust on the system. Explainable AI (XAI) algorithms play a vital role in…

Machine Learning · Computer Science 2026-05-15 Sayantani Ghosh , Amit Kumar Das , Amlan Chakrabarti

The SHAP framework provides a principled method to explain the predictions of a model by computing feature importance. Motivated by applications in finance, we introduce the Top-k Identification Problem (TkIP), where the objective is to…

Machine Learning · Computer Science 2023-07-12 Sanjay Kariyappa , Leonidas Tsepenekas , Freddy Lécué , Daniele Magazzeni

In this paper, we investigate the relationship between diversity metrics, accuracy, and resiliency to natural image corruptions of Deep Learning (DL) image classifier ensembles. We investigate the potential of an attribution-based diversity…

Machine Learning · Computer Science 2023-03-17 Rafael Rosales , Pablo Munoz , Michael Paulitsch

Feature attribution methods are widely used for explaining image-based predictions, as they provide feature-level insights that can be intuitively visualized. However, such explanations often vary in their robustness and may fail to…

Computer Vision and Pattern Recognition · Computer Science 2025-09-26 Amr Alkhatib , Stephanie Lowry

Explaining the decisions of an Artificial Intelligence (AI) model is increasingly critical in many real-world, high-stake applications. Hundreds of papers have either proposed new feature attribution methods, discussed or harnessed these…

Computer Vision and Pattern Recognition · Computer Science 2022-07-25 Giang Nguyen , Daeyoung Kim , Anh Nguyen

Visual search, recommendation, and contrastive similarity learning power technologies that impact billions of users worldwide. Modern model architectures can be complex and difficult to interpret, and there are several competing techniques…

Machine Learning · Computer Science 2022-03-17 Mark Hamilton , Scott Lundberg , Lei Zhang , Stephanie Fu , William T. Freeman

Shapley values have emerged as a critical tool for explaining which features impact the decisions made by machine learning models. However, computing exact Shapley values is difficult, generally requiring an exponential (in the feature…