English
Related papers

Related papers: A Baseline for Shapley Values in MLPs: from Missin…

200 papers

Originating in game theory, Shapley values are widely used for explaining a machine learning model's prediction by quantifying the contribution of each feature's value to the prediction. This requires a scalar prediction as in binary…

Machine Learning · Computer Science 2025-02-13 Paul-Gauthier Noé , Miquel Perelló-Nieto , Jean-François Bonastre , Peter Flach

Shapley values are model-agnostic methods for explaining model predictions. Many commonly used methods of computing Shapley values, known as off-manifold methods, rely on model evaluations on out-of-distribution input samples. Consequently,…

Machine Learning · Statistics 2023-02-28 Muhammad Faaiz Taufiq , Patrick Blöbaum , Lenon Minorics

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

Shapley value is a popular approach for measuring the influence of individual features. While Shapley feature attribution is built upon desiderata from game theory, some of its constraints may be less natural in certain machine learning…

Machine Learning · Computer Science 2022-09-28 Yongchan Kwon , James Zou

With wide application of Artificial Intelligence (AI), it has become particularly important to make decisions of AI systems explainable and transparent. In this paper, we proposed a new Explainable Artificial Intelligence (XAI) method…

Artificial Intelligence · Computer Science 2025-04-01 Chi Zhao , Jing Liu , Elena Parilina

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

The use of algorithm-agnostic approaches is an emerging area of research for explaining the contribution of individual features towards the predicted outcome. Whilst there is a focus on explaining the prediction itself, a little has been…

Machine Learning · Computer Science 2022-11-07 Guilherme Dean Pelegrina , Sajid Siraj

Shapley values, a gold standard for feature attribution in Explainable AI, face two key challenges. First, the canonical Shapley framework assumes that the worth function is additive, yet real-world payoff constructions--driven by…

Machine Learning · Computer Science 2026-03-10 Jialai She

The purported "black box" nature of neural networks is a barrier to adoption in applications where interpretability is essential. Here we present DeepLIFT (Deep Learning Important FeaTures), a method for decomposing the output prediction of…

Computer Vision and Pattern Recognition · Computer Science 2019-10-15 Avanti Shrikumar , Peyton Greenside , Anshul Kundaje

Nonlinear system identification remains an important open challenge across research and academia. Large numbers of novel approaches are seen published each year, each presenting improvements or extensions to existing methods. It is natural,…

Systems and Control · Electrical Eng. & Systems 2024-08-28 Max D. Champneys , Gerben I. Beintema , Roland Tóth , Maarten Schoukens , Timothy J. Rogers

Originally introduced in cooperative game theory, Shapley values have become a very popular tool to explain machine learning predictions. Based on Shapley's fairness axioms, every input (feature component) gets a credit how it contributes…

Machine Learning · Statistics 2025-08-19 Michael Mayer , Mario V. Wüthrich

Note: This paper describes an older version of DeepLIFT. See https://arxiv.org/abs/1704.02685 for the newer version. Original abstract follows: The purported "black box" nature of neural networks is a barrier to adoption in applications…

Machine Learning · Computer Science 2017-04-12 Avanti Shrikumar , Peyton Greenside , Anna Shcherbina , Anshul Kundaje

Estimating feature importance is a significant aspect of explaining data-based models. Besides explaining the model itself, an equally relevant question is which features are important in the underlying data generating process. We present a…

Machine Learning · Computer Science 2021-09-21 Pål Vegard Johnsen , Inga Strümke , Signe Riemer-Sørensen , Andrew Thomas DeWan , Mette Langaas

In Explainable AI (XAI), Shapley values are a popular model-agnostic framework for explaining predictions made by complex machine learning models. The computation of Shapley values requires estimating non-trivial contribution functions…

Machine Learning · Computer Science 2026-01-27 Lars Henry Berge Olsen , Martin Jullum

Unsupervised and supervised learning methods conventionally use kernels to capture nonlinearities inherent in data structure. However experts have to ensure their proposed nonlinearity maximizes variability and capture inherent diversity of…

Machine Learning · Computer Science 2025-07-30 Mojtaba Moattari

Shapley values are among the most popular tools for explaining predictions of blackbox machine learning models. However, their high computational cost motivates the use of sampling approximations, inducing a considerable degree of…

Machine Learning · Statistics 2024-04-11 Jeremy Goldwasser , Giles Hooker

Deep neural networks are vulnerable to adversarial attacks and hard to interpret because of their black-box nature. The recently proposed invertible network is able to accurately reconstruct the inputs to a layer from its outputs, thus has…

Machine Learning · Computer Science 2019-10-16 Juntang Zhuang , Nicha C. Dvornek , Xiaoxiao Li , Junlin Yang , James S. Duncan

Shapley value-based data valuation methods, originating from cooperative game theory, quantify the usefulness of each individual sample by considering its contribution to all possible training subsets. Despite their extensive applications,…

Machine Learning · Computer Science 2024-05-29 Ziao Yang , Han Yue , Jian Chen , Hongfu Liu

Artificial Neural Networks have shown impressive success in very different application cases. Choosing a proper network architecture is a critical decision for a network's success, usually done in a manual manner. As a straightforward…

Artificial Intelligence · Computer Science 2019-04-18 Julian Stier , Gabriele Gianini , Michael Granitzer , Konstantin Ziegler

Machine learning (ML) for transient stability assessment has gained traction due to the significant increase in computational requirements as renewables connect to power systems. To achieve a high degree of accuracy; black-box ML models are…

Systems and Control · Electrical Eng. & Systems 2023-02-14 Robert I. Hamilton , Panagiotis N. Papadopoulos