English
Related papers

Related papers: Explaining individual predictions when features ar…

200 papers

Shapley values, a game theoretic concept, has been one of the most popular tools for explaining Machine Learning (ML) models in recent years. Unfortunately, the two most common approaches, conditional and marginal, to calculating Shapley…

Computer Science and Game Theory · Computer Science 2024-09-11 Ilya Rozenfeld

Shapley effects are a particularly interpretable approach to assessing how a function depends on its various inputs. The existing literature contains various estimators for this class of sensitivity indices in the context of nonparametric…

Methodology · Statistics 2025-05-27 Akira Horiguchi , Matthew T. Pratola

Structural Causal Models (SCM) are a powerful framework for describing complicated dynamics across the natural sciences. A particularly elegant way of interpreting SCMs is do-Shapley, a game-theoretic method of quantifying the average…

Interpretable predictions, where it is clear why a machine learning model has made a particular decision, can compromise privacy by revealing the characteristics of individual data points. This raises the central question addressed in this…

Machine Learning · Computer Science 2020-04-07 Frederik Harder , Matthias Bauer , Mijung Park

Explainable artificial intelligence (XAI) aims to help human decision-makers in understanding complex machine learning (ML) models. One of the hallmarks of XAI are measures of relative feature importance, which are theoretically justified…

Artificial Intelligence · Computer Science 2024-02-12 Joao Marques-Silva , Xuanxiang Huang

The Shapley value is a game-theoretic notion for wealth distribution that is nowadays extensively used to explain complex data-intensive computation, for instance, in network analysis or machine learning. Recent theoretical works show that…

Databases · Computer Science 2022-01-04 Daniel Deutch , Nave Frost , Benny Kimelfeld , Mikaël Monet

As large language models (LLMs) become increasingly prevalent in critical applications, the need for interpretable AI has grown. We introduce TokenSHAP, a novel method for interpreting LLMs by attributing importance to individual tokens or…

Computation and Language · Computer Science 2024-07-23 Roni Goldshmidt , Miriam Horovicz

Predictive black-box models can exhibit high accuracy but their opaque nature hinders their uptake in safety-critical deployment environments. Explanation methods (XAI) can provide confidence for decision-making through increased…

Machine Learning · Statistics 2023-06-27 Lucile Ter-Minassian , Oscar Clivio , Karla Diaz-Ordaz , Robin J. Evans , Chris Holmes

While Explainable Artificial Intelligence (XAI) is increasingly expanding more areas of application, little has been applied to make deep Reinforcement Learning (RL) more comprehensible. As RL becomes ubiquitous and used in critical and…

Artificial Intelligence · Computer Science 2021-10-05 Alexandre Heuillet , Fabien Couthouis , Natalia Díaz-Rodríguez

Shapley values provide model agnostic feature attributions for model outcome at a particular instance by simulating feature absence under a global population distribution. The use of a global population can lead to potentially misleading…

Machine Learning · Computer Science 2021-06-29 Sahra Ghalebikesabi , Lucile Ter-Minassian , Karla Diaz-Ordaz , Chris Holmes

For feature selection and related problems, we introduce the notion of classification game, a cooperative game, with features as players and hinge loss based characteristic function and relate a feature's contribution to Shapley value based…

Machine Learning · Statistics 2021-04-27 Sandhya Tripathi , N. Hemachandra , Prashant Trivedi

The growing adoption of machine learning models for biological sequences has intensified the need for interpretable predictions, with Shapley values emerging as a theoretically grounded standard for model explanation. While effective for…

Machine Learning · Computer Science 2025-05-23 Darin Tsui , Aryan Musharaf , Yigit Efe Erginbas , Justin Singh Kang , Amirali Aghazadeh

We present a novel approach for explaining Gaussian processes (GPs) that can utilize the full analytical covariance structure present in GPs. Our method is based on the popular solution concept of Shapley values extended to stochastic…

Machine Learning · Statistics 2023-05-25 Siu Lun Chau , Krikamol Muandet , Dino Sejdinovic

The Shapley value is a ubiquitous framework for attribution in machine learning, encompassing feature importance, data valuation, and causal inference. However, its exact computation is generally intractable, necessitating efficient…

Machine Learning · Computer Science 2026-02-03 Fabian Fumagalli , Landon Butler , Justin Singh Kang , Kannan Ramchandran , R. Teal Witter

Thanks to its solid theoretical foundation, the SHAP framework is arguably one the most widely utilized frameworks for local explainability of ML models. Despite its popularity, its exact computation is known to be very challenging, proven…

Machine Learning · Computer Science 2024-05-28 Reda Marzouk , Colin de La Higuera

Non-linear kernel methods can be approximated by fast linear ones using suitable explicit feature maps allowing their application to large scale problems. We investigate how convolution kernels for structured data are composed from base…

Machine Learning · Computer Science 2019-11-26 Nils M. Kriege , Marion Neumann , Christopher Morris , Kristian Kersting , Petra Mutzel

We briefly summarize the kernel regression approach, as used recently in materials modelling, to fitting functions, particularly potential energy surfaces, and highlight how the linear algebra framework can be used to both predict and train…

Computational Physics · Physics 2019-02-05 Michele Ceriotti , Michael J. Willatt , Gábor Csányi

A predictive model makes outcome predictions based on some given features, i.e., it estimates the conditional probability of the outcome given a feature vector. In general, a predictive model cannot estimate the causal effect of a feature…

Machine Learning · Computer Science 2023-04-11 Jiuyong Li , Lin Liu , Ziqi Xu , Ha Xuan Tran , Thuc Duy Le , Jixue Liu

Predictions are the currency of a machine learning model, and to understand the model's behavior over segments of a dataset, or over time, is an important problem in machine learning research and practice. There currently is no systematic…

Machine Learning · Computer Science 2021-02-17 Aalok Shanbhag , Avijit Ghosh , Josh Rubin

Machine Learning (ML) is becoming increasingly popular in fluid dynamics. Powerful ML algorithms such as neural networks or ensemble methods are notoriously difficult to interpret. Here, we introduce the novel Shapley Additive Explanations…

Fluid Dynamics · Physics 2022-05-20 Martin Lellep , Jonathan Prexl , Bruno Eckhardt , Moritz Linkmann