Explaining by Removing: A Unified Framework for Model Explanation

21 November 2020

Papers citing "Explaining by Removing: A Unified Framework for Model Explanation"

50 / 150 papers shown

Title
Fast Shapley Value Estimation: A Unified Approach Borui Zhang Baotong Tian Wenzhao Zheng Jie Zhou Jiwen Lu TDI FAtt 19 0 0 02 Nov 2023
Faithful and Robust Local Interpretability for Textual Predictions Gianluigi Lopardo F. Precioso Damien Garreau OOD 26 4 0 30 Oct 2023
Does Your Model Think Like an Engineer? Explainable AI for Bearing Fault Detection with Deep Learning Thomas Decker Michael Lebacher Volker Tresp 11 9 0 19 Oct 2023
Model-agnostic variable importance for predictive uncertainty: an entropy-based approach Danny Wood Theodore Papamarkou Matt Benatan Richard Allmendinger FAtt UD 38 3 0 19 Oct 2023
Homophone Disambiguation Reveals Patterns of Context Mixing in Speech Transformers Hosein Mohebbi Grzegorz Chrupała Willem H. Zuidema A. Alishahi 28 12 0 15 Oct 2023
The Blame Problem in Evaluating Local Explanations, and How to Tackle it Amir Hossein Akhavan Rahnama ELM FAtt 30 4 0 05 Oct 2023
Explaining Speech Classification Models via Word-Level Audio Segments and Paralinguistic Features Eliana Pastor Alkis Koudounas Giuseppe Attanasio Dirk Hovy Elena Baralis 11 4 0 14 Sep 2023
Statistically Valid Variable Importance Assessment through Conditional Permutations Ahmad Chamma D. Engemann Bertrand Thirion 16 11 0 14 Sep 2023
Circuit Breaking: Removing Model Behaviors with Targeted Ablation Maximilian Li Xander Davies Max Nadeau KELM MU 16 27 0 12 Sep 2023
Insights Into the Inner Workings of Transformer Models for Protein Function Prediction M. Wenzel Erik Grüner Nils Strodthoff ViT 19 7 0 07 Sep 2023
Goodhart's Law Applies to NLP's Explanation Benchmarks Jennifer Hsia Danish Pruthi Aarti Singh Zachary Chase Lipton 28 6 0 28 Aug 2023
Confident Feature Ranking Bitya Neuhof Y. Benjamini FAtt 21 3 0 28 Jul 2023
Argument Attribution Explanations in Quantitative Bipolar Argumentation Frameworks (Technical Report) Xiang Yin Nico Potyka Francesca Toni 18 7 0 25 Jul 2023
Zipper: Addressing degeneracy in algorithm-agnostic inference Geng Chen Yinxu Jia Guanghui Wang Changliang Zou 27 0 0 29 Jun 2023
Increasing Performance And Sample Efficiency With Model-agnostic Interactive Feature Attributions J. Michiels Marina De Vos Johan A. K. Suykens LRM FAtt 11 0 0 28 Jun 2023
Feature Interactions Reveal Linguistic Structure in Language Models Jaap Jumelet Willem H. Zuidema FAtt 11 7 0 21 Jun 2023
On the Robustness of Removal-Based Feature Attributions Christy Lin Ian Covert Su-In Lee 20 12 0 12 Jun 2023
Efficient GNN Explanation via Learning Removal-based Attribution Yao Rong Guanchu Wang Qizhang Feng Ninghao Liu Zirui Liu Enkelejda Kasneci Xia Hu 15 9 0 09 Jun 2023
Explaining Predictive Uncertainty with Information Theoretic Shapley Values David S. Watson Joshua O'Hara Niek Tax Richard Mudd Ido Guy TDI FAtt 26 21 0 09 Jun 2023
Word-Level Explanations for Analyzing Bias in Text-to-Image Models Alexander Lin Lucas Monteiro Paes Sree Harsha Tanneru Suraj Srinivas Himabindu Lakkaraju 22 10 0 03 Jun 2023
Efficient Shapley Values Estimation by Amortization for Text Classification Chenghao Yang Fan Yin He He Kai-Wei Chang Xiaofei Ma Bing Xiang FAtt VLM 18 4 0 31 May 2023
Explaining Deep Learning for ECG Analysis: Building Blocks for Auditing and Knowledge Discovery Patrick Wagner Temesgen Mehari Wilhelm Haverkamp Nils Strodthoff 34 18 0 26 May 2023
Explaining the Uncertain: Stochastic Shapley Values for Gaussian Process Models Siu Lun Chau Krikamol Muandet Dino Sejdinovic FAtt 37 11 0 24 May 2023
A Comparative Study of Methods for Estimating Conditional Shapley Values and When to Use Them Lars Henry Berge Olsen I. Glad Martin Jullum K. Aas FAtt 46 12 0 16 May 2023
The Weighted Möbius Score: A Unified Framework for Feature Attribution Yifan Jiang Shane Steinert-Threlkeld FAtt 25 1 0 16 May 2023
Data-OOB: Out-of-bag Estimate as a Simple and Efficient Data Value Yongchan Kwon James Y. Zou TDI FedML 31 35 0 16 Apr 2023
The XAISuite framework and the implications of explanatory system dissonance Shreyan Mitra Leilani H. Gilpin FAtt 23 1 0 15 Apr 2023
HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation Lu Chen Siyu Lou Keyan Zhang Jin Huang Quanshi Zhang TDI FAtt 14 9 0 04 Apr 2023
A dynamic risk score for early prediction of cardiogenic shock using machine learning Yuxuan Hu Albert Y Lui M. Goldstein Mukund Sudarshan Andrea Tinsay ... G. Fishman J. Hochman S. Katz S. Bernard Rajesh Ranganath 16 2 0 22 Mar 2023
Interpretable Ensembles of Hyper-Rectangles as Base Models A. Konstantinov Lev V. Utkin 30 3 0 15 Mar 2023
Feature Importance: A Closer Look at Shapley Values and LOCO I. Verdinelli Larry A. Wasserman FAtt TDI 31 21 0 10 Mar 2023
iSAGE: An Incremental Version of SAGE for Online Explanation on Data Streams Maximilian Muschalik Fabian Fumagalli Barbara Hammer Eyke Hüllermeier 15 3 0 02 Mar 2023
SHAP-IQ: Unified Approximation of any-order Shapley Interactions Fabian Fumagalli Maximilian Muschalik Patrick Kolpaczki Eyke Hüllermeier Barbara Hammer 32 27 0 02 Mar 2023
Finding the right XAI method -- A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Science P. Bommer M. Kretschmer Anna Hedström Dilyara Bareeva Marina M.-C. Höhne 43 38 0 01 Mar 2023
Don't be fooled: label leakage in explanation methods and the importance of their quantitative evaluation N. Jethani A. Saporta Rajesh Ranganath FAtt 29 10 0 24 Feb 2023
sMRI-PatchNet: A novel explainable patch-based deep learning network for Alzheimer's disease diagnosis and discriminative atrophy localisation with Structural MRI Xin Zhang Liangxiu Han Lianghao Han Haoming Chen Darren Dancey Daoqiang Zhang MedIm 13 4 0 17 Feb 2023
Streamlining models with explanations in the learning loop Francesco Lomuscio P. Bajardi Alan Perotti E. Amparore FAtt 21 0 0 15 Feb 2023
Quantifying Context Mixing in Transformers Hosein Mohebbi Willem H. Zuidema Grzegorz Chrupała A. Alishahi 164 24 0 30 Jan 2023
On the Feasibility of Machine Learning Augmented Magnetic Resonance for Point-of-Care Identification of Disease R. Singhal Mukund Sudarshan Anish Mahishi S. Kaushik L. Ginocchio A. Tong H. Chandarana D. Sodickson Rajesh Ranganath S. Chopra 28 5 0 27 Jan 2023
Multi-dimensional concept discovery (MCD): A unifying framework with completeness guarantees Johanna Vielhaben Stefan Blücher Nils Strodthoff 25 37 0 27 Jan 2023
Don't Lie to Me: Avoiding Malicious Explanations with STEALTH Lauren Alvarez Tim Menzies 21 2 0 25 Jan 2023
Learning to Maximize Mutual Information for Dynamic Feature Selection Ian Covert Wei Qiu Mingyu Lu Nayoon Kim Nathan White Su-In Lee 19 28 0 02 Jan 2023
Calibrating AI Models for Wireless Communications via Conformal Prediction K. Cohen Sangwoo Park Osvaldo Simeone S. Shamai 29 6 0 15 Dec 2022
Explainability as statistical inference Hugo Senetaire Damien Garreau J. Frellsen Pierre-Alexandre Mattei FAtt 19 4 0 06 Dec 2022
Weakly Supervised Learning Significantly Reduces the Number of Labels Required for Intracranial Hemorrhage Detection on Head CT Jacopo Teneggi P. Yi Jeremias Sulam 25 3 0 29 Nov 2022
RecXplainer: Amortized Attribute-based Personalized Explanations for Recommender Systems Sahil Verma Chirag Shah John P. Dickerson Anu Beniwal Narayanan Sadagopan Arjun Seshadri 19 1 0 27 Nov 2022
Shapley Curves: A Smoothing Perspective Ratmir Miftachov Georg Keilbar Wolfgang Karl Härdle FAtt 32 1 0 23 Nov 2022
Trade-off Between Efficiency and Consistency for Removal-based Explanations Yifan Zhang Haowei He Zhiyuan Tan Yang Yuan FAtt 31 3 0 31 Oct 2022
Contrastive Corpus Attribution for Explaining Representations Christy Lin Hugh Chen Chanwoo Kim Su-In Lee SSL 19 8 0 30 Sep 2022
Concept Activation Regions: A Generalized Framework For Concept-Based Explanations Jonathan Crabbé M. Schaar 56 46 0 22 Sep 2022