v1v2 (latest)

Unifying Feature-Based Explanations with Functional ANOVA and Cooperative Game Theory

International Conference on Artificial Intelligence and Statistics (AISTATS), 2024

22 December 2024

Papers citing "Unifying Feature-Based Explanations with Functional ANOVA and Cooperative Game Theory"

44 / 44 papers shown

Title
Exact Shapley Attributions in Quadratic-time for FANOVA Gaussian Processes Majid Mohammadi Krikamol Muandet Ilaria Tiddi A. T. Teije Siu Lun Chau FAtt 181 1 0 20 Aug 2025
Permutation-Free High-Order Interaction Tests Zhaolu Liu Robert L. Peach Mauricio Barahona 232 0 0 06 Jun 2025
Computing Exact Shapley Values in Polynomial Time for Product-Kernel Methods Majid Mohammadi Siu Lun Chau Krikamol Muandet FAtt 426 3 0 22 May 2025
What's Wrong with Your Synthetic Tabular Data? Using Explainable AI to Evaluate Generative Models Jan Kapar Niklas Koenen Martin Jullum 224 1 0 29 Apr 2025
shapiq: Shapley Interactions for Machine LearningNeural Information Processing Systems (NeurIPS), 2024 Maximilian Muschalik Hubert Baniecki Fabian Fumagalli Patrick Kolpaczki Barbara Hammer Eyke Hüllermeier TDI 170 30 0 02 Oct 2024
Efficient and Accurate Explanation Estimation with Distribution Compression Hubert Baniecki Giuseppe Casalicchio Bernd Bischl Przemyslaw Biecek FAtt 366 4 0 26 Jun 2024
KernelSHAP-IQ: Weighted Least-Square Optimization for Shapley InteractionsInternational Conference on Machine Learning (ICML), 2024 Fabian Fumagalli Maximilian Muschalik Patrick Kolpaczki Eyke Hüllermeier Barbara Hammer 271 17 0 17 May 2024
A Guide to Feature Importance Methods for Scientific Inference F. K. Ewald Ludwig Bothmann Marvin N. Wright J. Herbinger Giuseppe Casalicchio Gunnar Konig 227 21 0 19 Apr 2024
Toward Understanding the Disagreement Problem in Neural Network Feature Attribution Niklas Koenen Marvin N. Wright FAtt 177 11 0 17 Apr 2024
Beyond TreeSHAP: Efficient Computation of Any-Order Shapley Interactions for Tree EnsemblesAAAI Conference on Artificial Intelligence (AAAI), 2024 Maximilian Muschalik Fabian Fumagalli Barbara Hammer Eyke Hüllermeier TDI 280 28 0 22 Jan 2024
SHAP-IQ: Unified Approximation of any-order Shapley InteractionsNeural Information Processing Systems (NeurIPS), 2023 Fabian Fumagalli Maximilian Muschalik Patrick Kolpaczki Eyke Hüllermeier Barbara Hammer 458 43 0 02 Mar 2023
From Shapley Values to Generalized Additive Models and backInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2022 Sebastian Bordt U. V. Luxburg FAtt TDI 498 62 0 08 Sep 2022
Unifying local and global model explanations by functional decomposition of low dimensional structuresInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2022 M. Hiabu Josephine T. Meyer Marvin N. Wright FAtt 236 25 0 12 Aug 2022
Algorithms to estimate Shapley value feature attributionsNature Machine Intelligence (Nat. Mach. Intell.), 2022 Hugh Chen Ian Covert Scott M. Lundberg Su-In Lee TDI FAtt 259 329 0 15 Jul 2022
Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc ExplanationsNeural Information Processing Systems (NeurIPS), 2022 Tessa Han Suraj Srinivas Himabindu Lakkaraju FAtt 312 105 0 02 Jun 2022
Faith-Shap: The Faithful Shapley Interaction IndexJournal of machine learning research (JMLR), 2022 Che-Ping Tsai Chih-Kuan Yeh Pradeep Ravikumar TDI 255 67 0 02 Mar 2022
REPID: Regional Effect Plots with implicit Interaction DetectionInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2022 J. Herbinger B. Bischl Giuseppe Casalicchio FAtt 199 19 0 15 Feb 2022
Joint Shapley values: a measure of joint feature importanceInternational Conference on Learning Representations (ICLR), 2021 Chris Harris Richard Pymar C. Rowat FAtt TDI 142 27 0 23 Jul 2021
Sampling Permutations for Shapley Value EstimationJournal of machine learning research (JMLR), 2021 Rory Mitchell Joshua N. Cooper E. Frank G. Holmes 257 160 0 25 Apr 2021
Grouped Feature Importance and Combined Features Effect PlotData mining and knowledge discovery (DMKD), 2021 Quay Au J. Herbinger Clemens Stachl J. Herbinger Giuseppe Casalicchio FAtt 247 56 0 23 Apr 2021
PredDiff: Explanations and Interactions from Conditional ExpectationsArtificial Intelligence (AI), 2021 Stefan Blücher Johanna Vielhaben Nils Strodthoff FAtt 251 22 0 26 Feb 2021
Explaining by Removing: A Unified Framework for Model ExplanationJournal of machine learning research (JMLR), 2020 Ian Covert Scott M. Lundberg Su-In Lee FAtt 349 299 0 21 Nov 2020
How does this interaction affect me? Interpretable attribution for feature interactions Michael Tsang Sirisha Rambhatla Yan Liu FAtt 190 97 0 19 Jun 2020
Model-agnostic Feature Importance and Effects with Dependent Features -- A Conditional Subgroup Approach Christoph Molnar Gunnar Konig J. Herbinger Giuseppe Casalicchio 236 93 0 08 Jun 2020
Explaining Explanations: Axiomatic Feature Interactions for Deep NetworksJournal of machine learning research (JMLR), 2020 Joseph D. Janizek Pascal Sturmfels Su-In Lee FAtt 642 167 0 10 Feb 2020
PyTorch: An Imperative Style, High-Performance Deep Learning LibraryNeural Information Processing Systems (NeurIPS), 2019 Adam Paszke Sam Gross Francisco Massa Adam Lerer James Bradbury ... Sasank Chilamkurthy Benoit Steiner Lu Fang Junjie Bai Soumith Chintala ODL 956 48,233 0 03 Dec 2019
Feature relevance quantification in explainable AI: A causal problemInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2019 Dominik Janzing Lenon Minorics Patrick Blobaum FAtt CML 245 319 0 29 Oct 2019
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter Victor Sanh Lysandre Debut Julien Chaumond Thomas Wolf 1.7K 8,772 0 02 Oct 2019
The many Shapley values for model explanationInternational Conference on Machine Learning (ICML), 2019 Mukund Sundararajan A. Najmi TDI FAtt 246 742 0 22 Aug 2019
Explaining individual predictions when features are dependent: More accurate approximations to Shapley values K. Aas Martin Jullum Anders Løland FAtt TDI 236 761 0 25 Mar 2019
Consistent Individualized Feature Attribution for Tree Ensembles Scott M. Lundberg G. Erion Su-In Lee FAtt TDI 460 1,647 0 12 Feb 2018
Considerations When Learning Additive Explanations for Black-Box Models S. Tan Giles Hooker Paul Koch Albert Gordo R. Caruana FAtt 320 28 0 26 Jan 2018
Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR Sandra Wachter Brent Mittelstadt Chris Russell MLAU 837 2,699 0 01 Nov 2017
SmoothGrad: removing noise by adding noise D. Smilkov Nikhil Thorat Been Kim F. Viégas Martin Wattenberg FAtt ODL 465 2,453 0 12 Jun 2017
A Unified Approach to Interpreting Model Predictions Scott M. Lundberg Su-In Lee FAtt 3.0K 28,723 0 22 May 2017
Learning Important Features Through Propagating Activation Differences Avanti Shrikumar Peyton Greenside A. Kundaje FAtt 542 4,295 0 10 Apr 2017
Axiomatic Attribution for Deep Networks Mukund Sundararajan Ankur Taly Qiqi Yan OOD FAtt 1.3K 7,022 0 04 Mar 2017
Visualizing Deep Neural Network Decisions: Prediction Difference AnalysisInternational Conference on Learning Representations (ICLR), 2017 L. Zintgraf Taco S. Cohen T. Adel Max Welling FAtt 262 726 0 15 Feb 2017
On Shapley value for measuring importance of dependent inputs Art B. Owen Clémentine Prieur FAtt TDI 196 166 0 06 Oct 2016
XGBoost: A Scalable Tree Boosting System Tianqi Chen Carlos Guestrin 1.4K 46,792 0 09 Mar 2016
"Why Should I Trust You?": Explaining the Predictions of Any Classifier Marco Tulio Ribeiro Sameer Singh Carlos Guestrin FAtt FaML 2.2K 19,394 0 16 Feb 2016
Visualizing and Understanding Convolutional NetworksEuropean Conference on Computer Vision (ECCV), 2013 Matthew D. Zeiler Rob Fergus FAtt SSL 1.0K 16,593 0 12 Nov 2013
Variance components and generalized Sobol' indices Art B. Owen 189 122 0 08 May 2012
Generalized Hoeffding-Sobol Decomposition for Dependent Variables -Application to Sensitivity Analysis Gaelle Chastaing Fabrice Gamboa Clémentine Prieur 343 169 0 08 Dec 2011