English
Related papers

Related papers: Impossibility Theorems for Feature Attribution

200 papers

Iterative refinement -- start with a random guess, then iteratively improve the guess -- is a useful paradigm for representation learning because it offers a way to break symmetries among equally plausible explanations for the data. This…

Machine Learning · Computer Science 2023-01-03 Michael Chang , Thomas L. Griffiths , Sergey Levine

Post-hoc global/local feature attribution methods are progressively being employed to understand the decisions of complex machine learning models. Yet, because of limited amounts of data, it is possible to obtain a diversity of models with…

Machine Learning · Computer Science 2024-01-01 Gabriel Laberge , Yann Pequignot , Alexandre Mathieu , Foutse Khomh , Mario Marchand

The field of explainable artificial intelligence (XAI) attempts to develop methods that provide insight into how complicated machine learning methods make predictions. Many methods of explanation have focused on the concept of feature…

Machine Learning · Computer Science 2024-03-13 Kurt Butler , Guanchao Feng , Petar M. Djuric

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

As deep vision models' popularity rapidly increases, there is a growing emphasis on explanations for model predictions. The inherently explainable attribution method aims to enhance the understanding of model behavior by identifying the…

Computer Vision and Pattern Recognition · Computer Science 2024-08-07 Xianren Zhang , Dongwon Lee , Suhang Wang

This paper develops a rigorous argument for why the use of Shapley values in explainable AI (XAI) will necessarily yield provably misleading information about the relative importance of features for predictions. Concretely, this paper…

Machine Learning · Computer Science 2023-02-17 Xuanxiang Huang , Joao Marques-Silva

Evaluation of generative models is mostly based on the comparison between the estimated distribution and the ground truth distribution in a certain feature space. To embed samples into informative features, previous works often use…

Machine Learning · Computer Science 2022-12-15 Junghyuk Lee , Jun-Hyuk Kim , Jong-Seok Lee

Recent work has shown great promise in explaining neural network behavior. In particular, feature attribution methods explain which features were most important to a model's prediction on a given input. However, for many tasks, simply…

Machine Learning · Computer Science 2020-07-01 Joseph D. Janizek , Pascal Sturmfels , Su-In Lee

Interpretability analysis methods for artificial intelligence models, such as LIME and SHAP, are widely used, though they primarily serve as post-model for analyzing model outputs. While it is commonly believed that the transparency and…

General Finance · Quantitative Finance 2025-02-28 Yan Zhang , Lin Chen , Yixiang Tian

Explaining machine learning (ML) predictions has become crucial as ML models are increasingly deployed in high-stakes domains such as healthcare. While SHapley Additive exPlanations (SHAP) is widely used for model interpretability, it fails…

Machine Learning · Computer Science 2025-09-03 Woon Yee Ng , Li Rong Wang , Siyuan Liu , Xiuyi Fan

Graph Neural Networks (GNNs) achieve strong performance on node classification tasks but remain difficult to interpret, particularly with respect to which input features drive their predictions. Existing global GNN explainers operate at the…

Machine Learning · Computer Science 2026-05-06 Rishi Raj Sahoo , Subhankar Mishra

Feature attribution explains Artificial Intelligence (AI) at the instance level by providing importance scores of input features' contributions to model prediction. Integrated Gradients (IG) is a prominent path attribution method for deep…

Computer Vision and Pattern Recognition · Computer Science 2024-06-18 Yue Zhuo , Zhiqiang Ge

The Shapley value has become a popular method to attribute the prediction of a machine-learning model on an input to its base features. The use of the Shapley value is justified by citing [16] showing that it is the \emph{unique} method…

Artificial Intelligence · Computer Science 2020-02-10 Mukund Sundararajan , Amir Najmi

Deep learning models have achieved state-of-the-art performance in many classification tasks. However, most of them cannot provide an interpretation for their classification results. Machine learning models that are interpretable are…

Machine Learning · Computer Science 2021-11-04 Miles Q. Li , Benjamin C. M. Fung , Adel Abusitta

A barrier to the wider adoption of neural networks is their lack of interpretability. While local explanation methods exist for one prediction, most global attributions still reduce neural network decisions to a single set of features. In…

Machine Learning · Computer Science 2019-02-08 Mark Ibrahim , Melissa Louie , Ceena Modarres , John Paisley

We present the findings of the Machine Learning Model Attribution Challenge. Fine-tuned machine learning models may derive from other trained models without obvious attribution characteristics. In this challenge, participants identify the…

Machine Learning · Computer Science 2023-02-20 Elizabeth Merkhofer , Deepesh Chaudhari , Hyrum S. Anderson , Keith Manville , Lily Wong , João Gante

Feature attribution methods have become a staple method to disentangle the complex behavior of black box models. Despite their success, some scholars have argued that such methods suffer from a serious flaw: they do not allow a reliable…

Neural networks outperform kernel methods, sometimes by orders of magnitude, e.g. on staircase functions. This advantage stems from the ability of neural networks to learn features, adapting their hidden representations to better capture…

Machine Learning · Computer Science 2025-07-29 Niclas Alexander Göring , Charles London , Abdurrahman Hadi Erturk , Chris Mingard , Yoonsoo Nam , Ard A. Louis

The recent increase in the deployment of machine learning models in critical domains such as healthcare, criminal justice, and finance has highlighted the need for trustworthy methods that can explain these models to stakeholders. Feature…

Machine Learning · Computer Science 2021-10-04 Angeline Yasodhara , Azin Asgarian , Diego Huang , Parinaz Sobhani

A common assumption about neural networks is that they can learn an appropriate internal representations on their own, see e.g. end-to-end learning. In this work we challenge this assumption. We consider two simple tasks and show that the…

Machine Learning · Computer Science 2019-11-19 Krisztian Buza