Explaining individual predictions when features are dependent: More accurate approximations to Shapley values

25 March 2019

Papers citing "Explaining individual predictions when features are dependent: More accurate approximations to Shapley values"

34 / 84 papers shown

Title
Using Shapley Values and Variational Autoencoders to Explain Predictive Models with Dependent Mixed Features Lars Henry Berge Olsen I. Glad Martin Jullum K. Aas TDI FAtt 32 17 0 26 Nov 2021
Decorrelated Variable Importance I. Verdinelli Larry A. Wasserman FAtt 19 18 0 21 Nov 2021
Causal versus Marginal Shapley Values for Robotic Lever Manipulation Controlled using Deep Reinforcement Learning Sindre Benjamin Remman Inga Strümke A. Lekkas CML 17 7 0 04 Nov 2021
Counterfactual Shapley Additive Explanations Emanuele Albini Jason Long Danial Dervovic Daniele Magazzeni 28 49 0 27 Oct 2021
RKHS-SHAP: Shapley Values for Kernel Methods Siu Lun Chau Robert Hu Javier I. González Dino Sejdinovic FAtt 26 16 0 18 Oct 2021
Out-of-Distribution Detection for Medical Applications: Guidelines for Practical Evaluation Karina Zadorozhny P. Thoral Paul Elbers Giovanni Cina OODD OOD 32 12 0 30 Sep 2021
Fast TreeSHAP: Accelerating SHAP Value Computation for Trees Jilei Yang FAtt 38 35 0 20 Sep 2021
Explaining Algorithmic Fairness Through Fairness-Aware Causal Path Decomposition Weishen Pan Sen Cui Jiang Bian Changshui Zhang Fei Wang CML FaML 27 33 0 11 Aug 2021
Sample Observed Effects: Enumeration, Randomization and Generalization Andre F. Ribeiro CML 21 4 0 09 Aug 2021
On Locality of Local Explanation Models Sahra Ghalebikesabi Lucile Ter-Minassian Karla Diaz-Ordaz Chris Holmes FedML FAtt 28 39 0 24 Jun 2021
Synthetic Benchmarks for Scientific Research in Explainable Machine Learning Yang Liu Sujay Khandagale Colin White Willie Neiswanger 37 65 0 23 Jun 2021
Rational Shapley Values David S. Watson 23 20 0 18 Jun 2021
A Framework for Evaluating Post Hoc Feature-Additive Explainers Zachariah Carmichael Walter J. Scheirer FAtt 51 4 0 15 Jun 2021
SHAFF: Fast and consistent SHApley eFfect estimates via random Forests Clément Bénard Gérard Biau Sébastien Da Veiga Erwan Scornet FAtt 38 32 0 25 May 2021
Local Explanations via Necessity and Sufficiency: Unifying Theory and Practice David S. Watson Limor Gultchin Ankur Taly Luciano Floridi 22 63 0 27 Mar 2021
The Shapley Value of coalition of variables provides better explanations Salim I. Amoukou Nicolas Brunel Tangi Salaun FAtt TDI 27 5 0 24 Mar 2021
Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactuals Sainyam Galhotra Romila Pradhan Babak Salimi CML 30 105 0 22 Mar 2021
Ensembles of Random SHAPs Lev V. Utkin A. Konstantinov FAtt 16 20 0 04 Mar 2021
MDA for random forests: inconsistency, and a practical solution via the Sobol-MDA Clément Bénard Sébastien Da Veiga Erwan Scornet 52 49 0 26 Feb 2021
Shapley values for feature selection: The good, the bad, and the axioms D. Fryer Inga Strümke Hien Nguyen FAtt TDI 6 190 0 22 Feb 2021
Explaining by Removing: A Unified Framework for Model Explanation Ian Covert Scott M. Lundberg Su-In Lee FAtt 53 243 0 21 Nov 2020
Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same End R. Mothilal Divyat Mahajan Chenhao Tan Amit Sharma FAtt CML 29 100 0 10 Nov 2020
Feature Removal Is a Unifying Principle for Model Explanation Methods Ian Covert Scott M. Lundberg Su-In Lee FAtt 33 33 0 06 Nov 2020
Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models Tom Heskes E. Sijben I. G. Bucur Tom Claassen FAtt TDI 16 151 0 03 Nov 2020
Shapley Flow: A Graph-based Approach to Interpreting Model Predictions Jiaxuan Wang Jenna Wiens Scott M. Lundberg FAtt 28 88 0 27 Oct 2020
Local Post-Hoc Explanations for Predictive Process Monitoring in Manufacturing Nijat Mehdiyev Peter Fettke 16 11 0 22 Sep 2020
On the Tractability of SHAP Explanations Guy Van den Broeck A. Lykov Maximilian Schleich Dan Suciu FAtt TDI 22 260 0 18 Sep 2020
Explaining predictive models with mixed features using Shapley values and conditional inference trees Annabelle Redelmeier Martin Jullum K. Aas FAtt TDI 11 19 0 02 Jul 2020
Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey Arun Das P. Rad XAI 42 593 0 16 Jun 2020
Explainable AI for a No-Teardown Vehicle Component Cost Estimation: A Top-Down Approach A. Moawad E. Islam Namdoo Kim R. Vijayagopal A. Rousseau Wei Biao Wu 31 5 0 15 Jun 2020
Model-agnostic Feature Importance and Effects with Dependent Features -- A Conditional Subgroup Approach Christoph Molnar Gunnar Konig B. Bischl Giuseppe Casalicchio 33 77 0 08 Jun 2020
An explanation method for Siamese neural networks Lev V. Utkin M. Kovalev E. Kasimov 27 14 0 18 Nov 2019
Feature relevance quantification in explainable AI: A causal problem Dominik Janzing Lenon Minorics Patrick Blobaum FAtt CML 24 279 0 29 Oct 2019
Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability Christopher Frye C. Rowat Ilya Feige 21 180 0 14 Oct 2019