A Note about: Local Explanation Methods for Deep Neural Networks lack Sensitivity to Parameter Values

Mukund Sundararajan, Ankur Taly

Type: Preprint

Publication Date: 2018-01-01

Citations: 11

DOI: https://doi.org/10.48550/arxiv.1806.04205

View Publication

Locations

arXiv (Cornell University) - View
DataCite API - View

Similar Works

Action	Title	Year	Authors
+	Local Explanation Methods for Deep Neural Networks Lack Sensitivity to Parameter Values	2018	Julius Adebayo Justin Gilmer Ian Goodfellow Been Kim
+	Local Explanation Methods for Deep Neural Networks Lack Sensitivity to Parameter Values	2018	Julius Adebayo Justin Gilmer Ian Goodfellow Been Kim
+	Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations	2022	Alexander Binder Leander Weber Sebastian Lapuschkin Grégoire Montavon Klaus‐Robert Müller Wojciech Samek
+ PDF Chat	Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations	2023	Alexander Binder Leander Weber Sebastian Lapuschkin Grégoire Montavon Klaus‐Robert Müller Wojciech Samek
+	Better Understanding Differences in Attribution Methods via Systematic Evaluations	2023	Sukrut Rao Moritz Böhle Bernt Schiele
+	Boundary Attributions Provide Normal (Vector) Explanations.	2021	Zifan Wang Matt Fredrikson Anupam Datta
+ PDF Chat	Towards Better Understanding Attribution Methods	2022	Sukrut Rao Moritz Böhle Bernt Schiele
+	Towards Better Understanding Attribution Methods	2022	Sukrut Rao Moritz Böhle Bernt Schiele
+	Guided Integrated Gradients: An Adaptive Path Method for Removing Noise	2021	Andrei Kapishnikov Subhashini Venugopalan Besim Avci Ben Wedin Michael Terry Tolga Bolukbasi
+	Guided Integrated Gradients: An Adaptive Path Method for Removing Noise	2021	Andrei Kapishnikov Subhashini Venugopalan Besim Avci Ben Wedin Michael Terry Tolga Bolukbasi
+ PDF Chat	Guided Integrated Gradients: an Adaptive Path Method for Removing Noise	2021	Andrei Kapishnikov Subhashini Venugopalan Besim Avci Ben Wedin Michael Terry Tolga Bolukbasi
+	Towards Better Visualizing the Decision Basis of Networks via Unfold and Conquer Attribution Guidance	2023	Jung-Ho Hong Woo-Jeoung Nam Kyu-Sung Jeon Seong‐Whan Lee
+	Towards Better Visualizing the Decision Basis of Networks via Unfold and Conquer Attribution Guidance	2023	Jung-Ho Hong Woo-Jeoung Nam Kyu-Sung Jeon Seong‐Whan Lee
+	Axiomatic Attribution for Deep Networks	2017	Mukund Sundararajan Ankur Taly Qiqi Yan
+	Axiomatic Attribution for Deep Networks	2017	Mukund Sundararajan Ankur Taly Qiqi Yan
+	A Rigorous Study of Integrated Gradients Method and Extensions to Internal Neuron Attributions	2022	Daniel Lundström Tianjian Huang Meisam Razaviyayn
+ PDF Chat	Explaining Deep Neural Networks by Leveraging Intrinsic Methods	2024	Biagio La Rosa
+	On Gradient-like Explanation under a Black-box Setting: When Black-box Explanations Become as Good as White-box	2023	Yi Cai Gerhard Wunder
+ PDF Chat	Visualization of Supervised and Self-Supervised Neural Networks via Attribution Guided Factorization	2021	Shir Gur Ameen Ali Lior Wolf
+	A-FMI: Learning Attributions from Deep Networks via Feature Map Importance	2021	An Zhang Xiang Wang Chengfang Fang Jie Shi Xiangnan He Tat‐Seng Chua Zehua Chen

Works That Cite This (7)

Action	Title	Year	Authors
+	Explaining Explanations: Axiomatic Feature Interactions for Deep Networks	2020	Joseph D. Janizek Pascal Sturmfels Su‐In Lee
+ PDF Chat	XRAI: Better Attributions Through Regions	2019	Andrei Kapishnikov Tolga Bolukbasi Fernanda Viégas Michael Terry
+	GANMEX: One-vs-One Attributions Guided by GAN-based Counterfactual Explanation Baselines	2020	Sheng-Min Shih Pin-Ju Tien Zohar Karnin
+ PDF Chat	Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations	2023	Alexander Binder Leander Weber Sebastian Lapuschkin Grégoire Montavon Klaus‐Robert Müller Wojciech Samek
+	XRAI: Better Attributions Through Regions	2019	Andrei Kapishnikov Tolga Bolukbasi Fernanda Viégas Michael Terry
+	Local Explanation Methods for Deep Neural Networks Lack Sensitivity to Parameter Values	2018	Julius Adebayo Justin Gilmer Ian Goodfellow Been Kim
+ PDF Chat	Towards Improved Input Masking for Convolutional Neural Networks	2023	Sriram Balasubramanian Soheil Feizi

Works Cited by This (8)

Action	Title	Year	Authors
+	Striving for Simplicity: The All Convolutional Net	2014	Jost Tobias Springenberg Alexey Dosovitskiy Thomas Brox Martin Riedmiller
+	How to Explain Individual Classification Decisions	2009	David Baehrens Timon Schroeter Stefan Harmeling Motoaki Kawanabe Katja Hansen Klaus‐Robert Müller
+	Axiomatic Attribution for Deep Networks	2017	Mukund Sundararajan Ankur Taly Qiqi Yan
+	Learning Important Features Through Propagating Activation Differences	2017	Avanti Shrikumar Peyton Greenside Anshul Kundaje
+	Local Explanation Methods for Deep Neural Networks Lack Sensitivity to Parameter Values	2018	Julius Adebayo Justin Gilmer Ian Goodfellow Been Kim
+	Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers	2016	Alexander Binder Grégoire Montavon Sebastian Bach Klaus‐Robert Müller Wojciech Samek
+	Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps	2013	Karen Simonyan Andrea Vedaldi Andrew Zisserman
+	A Unified Approach to Interpreting Model Predictions	2017	Scott Lundberg Su‐In Lee