English
Related papers

Related papers: Impossibility Theorems for Feature Attribution

200 papers

Deep neural networks are often considered opaque systems, prompting the need for explainability methods to improve trust and accountability. Existing approaches typically attribute test-time predictions either to input features (e.g.,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Aziz Bacha , Thomas George

We propose an empirical measure of the approximate accuracy of feature importance estimates in deep neural networks. Our results across several large-scale image classification datasets show that many popular interpretability methods…

Machine Learning · Computer Science 2019-11-06 Sara Hooker , Dumitru Erhan , Pieter-Jan Kindermans , Been Kim

A multitude of explainability methods and associated fidelity performance metrics have been proposed to help better understand how modern AI systems make decisions. However, much of the current work has remained theoretical -- without much…

Computer Vision and Pattern Recognition · Computer Science 2023-02-01 Julien Colin , Thomas Fel , Remi Cadene , Thomas Serre

Training the deep neural networks that dominate NLP requires large datasets. These are often collected automatically or via crowdsourcing, and may exhibit systematic biases or annotation artifacts. By the latter we mean spurious…

Computation and Language · Computer Science 2022-03-29 Pouya Pezeshkpour , Sarthak Jain , Sameer Singh , Byron C. Wallace

Deep learning models for semantics are generally evaluated using naturalistic corpora. Adversarial methods, in which models are evaluated on new examples with known semantic properties, have begun to reveal that good performance at these…

Computation and Language · Computer Science 2021-07-27 Atticus Geiger , Ignacio Cases , Lauri Karttunen , Chris Potts

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

Numerous works propose post-hoc, model-agnostic explanations for learning to rank, focusing on ordering entities by their relevance to a query through feature attribution methods. However, these attributions often weakly correlate or…

Information Retrieval · Computer Science 2025-02-25 Tanya Chowdhury , Yair Zick , James Allan

Attribution maps are one of the most established tools to explain the functioning of computer vision models. They assign importance scores to input features, indicating how relevant each feature is for the prediction of a deep neural…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Robin Hesse , Simone Schaub-Meyer , Stefan Roth

Using feature attributions for post-hoc explanations is a common practice to understand and verify the predictions of opaque machine learning models. Despite the numerous techniques available, individual methods often produce inconsistent…

Machine Learning · Computer Science 2024-06-10 Thomas Decker , Ananta R. Bhattarai , Jindong Gu , Volker Tresp , Florian Buettner

For machine learning models to be reliable and trustworthy, their decisions must be interpretable. As these models find increasing use in safety-critical applications, it is important that not just the model predictions but also their…

Machine Learning · Computer Science 2023-12-19 Sandesh Kamath , Sankalp Mittal , Amit Deshpande , Vineeth N Balasubramanian

Attribution methods have been developed to explain the decision of a machine learning model on a given input. We use the Integrated Gradient method for finding attributions to define the causal neighborhood of an input by incrementally…

Feature attribution is essential for interpreting deep learning models, particularly in time-series domains such as healthcare, biometrics, and human-AI interaction. However, standard attribution methods, such as Integrated Gradients or…

Machine Learning · Computer Science 2025-09-25 Benedikt W. Hosp

Feature attribution analysis is critical for interpreting machine learning models and supporting reliable data-driven decisions. However, feature attribution measures often exhibit stochastic variation: different train--test splits, random…

Machine Learning · Statistics 2026-05-15 Lanxin Xiang , Liang Shi , Youhui Ye , Boyu Jiang , Dawei Zhou , Feng Guo

Predictive uncertainties in classification tasks are often a consequence of model inadequacy or insufficient training data. In popular applications, such as image processing, we are often required to scrutinise these uncertainties by…

Machine Learning · Computer Science 2022-11-10 Iker Perez , Piotr Skalski , Alec Barns-Graham , Jason Wong , David Sutton

Attribution methods have been developed to understand the decision-making process of machine learning models, especially deep neural networks, by assigning importance scores to individual features. Existing attribution methods often built…

Machine Learning · Statistics 2021-04-14 Huiqi Deng , Na Zou , Mengnan Du , Weifu Chen , Guocan Feng , Xia Hu

We study the attribution problem [28] for deep networks applied to perception tasks. For vision tasks, attribution techniques attribute the prediction of a network to the pixels of the input image. We propose a new technique called…

Computer Vision and Pattern Recognition · Computer Science 2020-04-09 Shawn Xu , Subhashini Venugopalan , Mukund Sundararajan

In recent years, neural networks have demonstrated their remarkable ability to discern intricate patterns and relationships from raw data. However, understanding the inner workings of these black box models remains challenging, yet crucial…

Machine Learning · Statistics 2024-04-18 Niklas Koenen , Marvin N. Wright

Fully Connected Neural Networks (FCNNs) are often regarded as simple and intuitive architectures, yet they serve as the foundation for more complex models. Nonetheless, the lack of consensus on their interpretability continues to pose…

Machine Learning · Computer Science 2026-05-18 Thodoris Lymperopoulos , Denia Kanellopoulou

Feature attribution methods explain black-box machine learning (ML) models by assigning importance scores to input features. These methods can be computationally expensive for large ML models. To address this challenge, there has been…

Computers and Society · Computer Science 2024-05-31 Lucas Monteiro Paes , Dennis Wei , Flavio P. Calmon

Feature attribution methods promise to identify which input features matter for a model output. In generative language models, however, it is often unclear what should count as a feature in the first place. In autoregressive language…

Machine Learning · Computer Science 2026-05-25 Giang Nguyen