English
Related papers

Related papers: Succinct Interaction-Aware Explanations

200 papers

Models in the supervised learning framework may capture rich and complex representations over the features that are hard for humans to interpret. Existing methods to explain such models are often specific to architectures and data where the…

Machine Learning · Computer Science 2021-02-25 Akshay Sood , Mark Craven

Generating explanations for neural networks has become crucial for their applications in real-world with respect to reliability and trustworthiness. In natural language processing, existing methods usually provide important features which…

Computation and Language · Computer Science 2020-05-19 Hanjie Chen , Guangtao Zheng , Yangfeng Ji

Detecting anomalies in energy consumption data is crucial for identifying energy waste, equipment malfunction, and overall, for ensuring efficient energy management. Machine learning, and specifically deep learning approaches, have been…

Machine Learning · Computer Science 2025-01-13 Mohammad Noorchenarboo , Katarina Grolinger

While SHAP (SHapley Additive exPlanations) and other feature attribution methods are commonly employed to explain model predictions, their application within information retrieval (IR), particularly for complex outputs such as ranked lists,…

Information Retrieval · Computer Science 2025-05-01 Maria Heuss , Maarten de Rijke , Avishek Anand

Although Shapley additive explanations (SHAP) can be computed in polynomial time for simple models like decision trees, they unfortunately become NP-hard to compute for more expressive black-box models like neural networks - where…

Machine Learning · Computer Science 2026-03-23 Reda Marzouk , Shahaf Bassan , Guy Katz

As machine learning algorithms are deployed ubiquitously to a variety of domains, it is imperative to make these often black-box models transparent. Several recent works explain black-box models by capturing the most influential features…

Among explainability techniques, SHAP stands out as one of the most popular, but often overlooks the causal structure of the problem. In response, do-SHAP employs interventional queries, but its reliance on estimands hinders its practical…

Machine Learning · Computer Science 2026-01-13 Álvaro Parafita , Tomas Garriga , Axel Brando , Francisco J. Cazorla

Originally rooted in game theory, the Shapley Value (SV) has recently become an important tool in machine learning research. Perhaps most notably, it is used for feature attribution and data valuation in explainable artificial intelligence.…

We introduce methods for discovering and applying sparse feature circuits. These are causally implicated subnetworks of human-interpretable features for explaining language model behaviors. Circuits identified in prior work consist of…

Machine Learning · Computer Science 2025-03-28 Samuel Marks , Can Rager , Eric J. Michaud , Yonatan Belinkov , David Bau , Aaron Mueller

With the adoption of machine learning into routine clinical practice comes the need for Explainable AI methods tailored to medical applications. Shapley values have sparked wide interest for locally explaining models. Here, we demonstrate…

Machine Learning · Computer Science 2024-02-02 Lucile Ter-Minassian , Sahra Ghalebikesabi , Karla Diaz-Ordaz , Chris Holmes

Interpreting predictions from tree ensemble methods such as gradient boosting machines and random forests is important, yet feature attribution for trees is often heuristic and not individualized for each prediction. Here we show that…

Machine Learning · Computer Science 2019-03-08 Scott M. Lundberg , Gabriel G. Erion , Su-In Lee

eXplainable artificial intelligence (XAI) methods have emerged to convert the black box of machine learning (ML) models into a more digestible form. These methods help to communicate how the model works with the aim of making ML models more…

Hazard and survival functions are natural, interpretable targets in time-to-event prediction, but their inherent non-additivity fundamentally limits standard additive explanation methods. We introduce Survival Functional Decomposition…

With increasing interest in explaining machine learning (ML) models, the first part of this two-part study synthesizes recent research on methods for explaining global and local aspects of ML models. This study distinguishes explainability…

Machine Learning · Statistics 2022-11-17 Montgomery Flora , Corey Potvin , Amy McGovern , Shawn Handler

One often finds in the literature connections between measures of fairness and measures of feature importance employed to interpret trained classifiers. However, there seems to be no study that compares fairness measures and feature…

Machine Learning · Computer Science 2019-10-15 Juliana Cesaro , Fabio G. Cozman

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

Many important questions about a model cannot be answered just by explaining how much each feature contributes to its output. To answer a broader set of questions, we generalize a popular, mathematically well-grounded explanation technique,…

Machine Learning · Computer Science 2020-06-16 Dillon Bowen , Lyle Ungar

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

Explainable Artificial Intelligence (XAI) has become an increasingly important area of research, particularly as machine learning models are deployed in high-stakes domains. Among various XAI approaches, SHAP (SHapley Additive exPlanations)…

Artificial Intelligence · Computer Science 2026-04-15 Latifa Dwiyanti , Sergio Ryan Wibisono , Hidetaka Nambo

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