Feature Removal Is a Unifying Principle for Model Explanation Methods

6 November 2020

Papers citing "Feature Removal Is a Unifying Principle for Model Explanation Methods"

20 / 20 papers shown

Title
CAGE: Causality-Aware Shapley Value for Global Explanations Nils Ole Breuer Andreas Sauter Majid Mohammadi Erman Acar FAtt 29 2 0 17 Apr 2024
SmoothHess: ReLU Network Feature Interactions via Stein's Lemma Max Torop A. Masoomi Davin Hill Kivanc Kose Stratis Ioannidis Jennifer Dy 23 4 0 01 Nov 2023
Faithful Knowledge Graph Explanations for Commonsense Reasoning Weihe Zhai A. Zubiaga 17 0 0 07 Oct 2023
On the Connection between Game-Theoretic Feature Attributions and Counterfactual Explanations Emanuele Albini Shubham Sharma Saumitra Mishra Danial Dervovic Daniele Magazzeni FAtt 38 2 0 13 Jul 2023
Prototype-Based Interpretability for Legal Citation Prediction Chunyan Luo R. Bhambhoria Samuel Dahan Xiao-Dan Zhu ELM AILaw 11 7 0 25 May 2023
Explanations of Black-Box Models based on Directional Feature Interactions A. Masoomi Davin Hill Zhonghui Xu C. Hersh E. Silverman P. Castaldi Stratis Ioannidis Jennifer Dy FAtt 21 17 0 16 Apr 2023
Contrastive Video Question Answering via Video Graph Transformer Junbin Xiao Pan Zhou Angela Yao Yicong Li Richang Hong Shuicheng Yan Tat-Seng Chua ViT 19 35 0 27 Feb 2023
Boundary-Aware Uncertainty for Feature Attribution Explainers Davin Hill A. Masoomi Max Torop S. Ghimire Jennifer Dy FAtt 55 3 0 05 Oct 2022
How explainable are adversarially-robust CNNs? Mehdi Nourelahi Lars Kotthoff Peijie Chen Anh Totti Nguyen AAML FAtt 14 8 0 25 May 2022
Reinforced Causal Explainer for Graph Neural Networks Xiang Wang Y. Wu An Zhang Fuli Feng Xiangnan He Tat-Seng Chua CML 17 46 0 23 Apr 2022
Explainability in Music Recommender Systems Darius Afchar Alessandro B. Melchiorre Markus Schedl Romain Hennequin Elena V. Epure Manuel Moussallam 16 48 0 25 Jan 2022
Deconfounding to Explanation Evaluation in Graph Neural Networks Yingmin Wu Xiang Wang An Zhang Xia Hu Fuli Feng Xiangnan He Tat-Seng Chua FAtt CML 12 14 0 21 Jan 2022
Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models? Thang M. Pham Trung H. Bui Long Mai Anh Totti Nguyen 21 7 0 22 Oct 2021
Shapley variable importance clouds for interpretable machine learning Yilin Ning M. Ong Bibhas Chakraborty B. Goldstein Daniel Ting Roger Vaughan Nan Liu FAtt 11 69 0 06 Oct 2021
Attribution of Predictive Uncertainties in Classification Models Iker Perez Piotr Skalski Alec E. Barns-Graham Jason Wong David Sutton UQCV 14 5 0 19 Jul 2021
The effectiveness of feature attribution methods and its correlation with automatic evaluation scores Giang Nguyen Daeyoung Kim Anh Totti Nguyen FAtt 8 86 0 31 May 2021
Can We Faithfully Represent Masked States to Compute Shapley Values on a DNN? J. Ren Zhanpeng Zhou Qirui Chen Quanshi Zhang FAtt TDI 19 8 0 22 May 2021
Towards Rigorous Interpretations: a Formalisation of Feature Attribution Darius Afchar Romain Hennequin Vincent Guigue FAtt 29 20 0 26 Apr 2021
Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretations N. Jethani Mukund Sudarshan Yindalon Aphinyanagphongs Rajesh Ranganath FAtt 78 70 0 02 Mar 2021
PredDiff: Explanations and Interactions from Conditional Expectations Stefan Blücher Johanna Vielhaben Nils Strodthoff FAtt 17 19 0 26 Feb 2021