English
Related papers

Related papers: Evaluating and Aggregating Feature-based Model Exp…

200 papers

The Shapley value is one of the most widely used measures of feature importance partly as it measures a feature's average effect on a model's prediction. We introduce joint Shapley values, which directly extend Shapley's axioms and…

Machine Learning · Statistics 2022-02-11 Chris Harris , Richard Pymar , Colin Rowat

Feature attributions based on the Shapley value are popular for explaining machine learning models; however, their estimation is complex from both a theoretical and computational standpoint. We disentangle this complexity into two factors:…

Machine Learning · Computer Science 2022-07-18 Hugh Chen , Ian C. Covert , Scott M. Lundberg , Su-In Lee

It is becoming increasingly important to explain complex, black-box machine learning models. Although there is an expanding literature on this topic, Shapley values stand out as a sound method to explain predictions from any type of machine…

Machine Learning · Statistics 2020-07-03 Annabelle Redelmeier , Martin Jullum , Kjersti Aas

Reliability-oriented sensitivity analysis aims at combining both reliability and sensitivity analyses by quantifying the influence of each input variable of a numerical model on a quantity of interest related to its failure. In particular,…

Statistics Theory · Mathematics 2022-10-25 Julien Demange-Chryst , François Bachoc , Jérôme Morio

Explainability in AI is crucial for model development, compliance with regulation, and providing operational nuance to predictions. The Shapley framework for explainability attributes a model's predictions to its input features in a…

Machine Learning · Computer Science 2021-12-21 Christopher Frye , Damien de Mijolla , Tom Begley , Laurence Cowton , Megan Stanley , Ilya Feige

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

This paper studies the problem of estimating the contributions of features to the prediction of a specific instance by a machine learning model and the overall contribution of a feature to the model. The causal effect of a feature…

Machine Learning · Computer Science 2022-06-24 Jiuyong Li , Ha Xuan Tran , Thuc Duy Le , Lin Liu , Kui Yu , Jixue Liu

We take inspiration from the study of human explanation to inform the design and evaluation of interpretability methods in machine learning. First, we survey the literature on human explanation in philosophy, cognitive science, and the…

Artificial Intelligence · Computer Science 2021-09-21 David Alvarez-Melis , Harmanpreet Kaur , Hal Daumé , Hanna Wallach , Jennifer Wortman Vaughan

We present a principle-based analysis of contribution functions for quantitative bipolar argumentation graphs that quantify the contribution of one argument to another. The introduced principles formalise the intuitions underlying different…

Artificial Intelligence · Computer Science 2024-06-17 Timotheus Kampik , Nico Potyka , Xiang Yin , Kristijonas Čyras , Francesca Toni

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

Feature modeling is a widely used formalism to characterize a set of products (also called configurations). As a manual elaboration is a long and arduous task, numerous techniques have been proposed to reverse engineer feature models from…

Software Engineering · Computer Science 2015-02-17 Guillaume Bécan , Razieh Behjati , Arnaud Gotlieb , Mathieu Acher

Computing the importance of features in supervised classification tasks is critical for model interpretability. Shapley values are a widely used approach for explaining model predictions, but require direct access to the underlying model,…

Machine Learning · Computer Science 2026-05-18 Joao Fonseca , Julia Stoyanovich

Feature attributions and counterfactual explanations are popular approaches to explain a ML model. The former assigns an importance score to each input feature, while the latter provides input examples with minimal changes to alter the…

Machine Learning · Computer Science 2021-06-01 Ramaravind Kommiya Mothilal , Divyat Mahajan , Chenhao Tan , Amit Sharma

Researchers in explainable artificial intelligence have developed numerous methods for helping users understand the predictions of complex supervised learning models. By contrast, explaining the $\textit{uncertainty}$ of model outputs has…

Machine Learning · Statistics 2023-11-01 David S. Watson , Joshua O'Hara , Niek Tax , Richard Mudd , Ido Guy

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 construction can contribute to comprehensibility and performance of machine learning models. Unfortunately, it usually requires exhaustive search in the attribute space or time-consuming human involvement to generate meaningful…

Machine Learning · Computer Science 2023-01-24 Boštjan Vouk , Matej Guid , Marko Robnik-Šikonja

Feature-based explanations, using perturbations or gradients, are a prevalent tool to understand decisions of black box machine learning models. Yet, differences between these methods still remain mostly unknown, which limits their…

Machine Learning · Computer Science 2025-04-18 Fabian Fumagalli , Maximilian Muschalik , Eyke Hüllermeier , Barbara Hammer , Julia Herbinger

Being able to interpret, or explain, the predictions made by a machine learning model is of fundamental importance. This is especially true when there is interest in deploying data-driven models to make high-stakes decisions, e.g. in…

Machine Learning · Computer Science 2019-10-01 An-phi Nguyen , María Rodríguez Martínez

We present a novel framework for estimation and inference with the broad class of universal approximators. Estimation is based on the decomposition of model predictions into Shapley values. Inference relies on analyzing the bias and…

Machine Learning · Statistics 2024-12-06 Andreas Joseph

While many methods purport to explain predictions by highlighting salient features, what aims these explanations serve and how they ought to be evaluated often go unstated. In this work, we introduce a framework to quantify the value of…