Towards better understanding of gradient-based attribution methods for Deep Neural Networks

Marco Ancona, Enea Ceolini, Cengiz Öztireli, Markus Groß

Type: Preprint

Publication Date: 2017-01-01

Citations: 288

DOI: https://doi.org/10.48550/arxiv.1711.06104

View Publication

Locations

arXiv (Cornell University) - View
Zurich Open Repository and Archive (University of Zurich) - View - PDF
Repository for Publications and Research Data (ETH Zurich) - View - PDF
DataCite API - View

Similar Works

Action	Title	Year	Authors
+	Towards better understanding of gradient-based attribution methods for Deep Neural Networks	2017	Marco Ancona Enea Ceolini Cengiz Öztireli Markus Groß
+	A unified view of gradient-based attribution methods for Deep Neural Networks	2017	Marco Ancona Enea Ceolini Cengiz Öztireli Markus Groß
+ PDF Chat	Robust Explainability: A tutorial on gradient-based attribution methods for deep neural networks	2022	Ian E. Nielsen Dimah Dera Ghulam Rasool Ravi P. Ramachandran Nidhal Bouaynaya
+	Four Axiomatic Characterizations of the Integrated Gradients Attribution Method	2023	Daniel Lundström Meisam Razaviyayn
+	Axiomatic Attribution for Deep Networks	2017	Mukund Sundararajan Ankur Taly Qiqi Yan
+	Axiomatic Attribution for Deep Networks	2017	Mukund Sundararajan Ankur Taly Qiqi Yan
+ PDF Chat	Towards More Robust Interpretation via Local Gradient Alignment	2023	Sunghwan Joo SeokHyeon Jeong Juyeon Heo Adrian Weller Taesup Moon
+	On Gradient-like Explanation under a Black-box Setting: When Black-box Explanations Become as Good as White-box	2023	Yi Cai Gerhard Wunder
+	A Rigorous Study of Integrated Gradients Method and Extensions to Internal Neuron Attributions	2022	Daniel Lundström Tianjian Huang Meisam Razaviyayn
+	Attribution Mask: Filtering Out Irrelevant Features By Recursively Focusing Attention on Inputs of DNNs	2021	Jaehong Lee Joon-Hyuk Chang
+	Negative Flux Aggregation to Estimate Feature Attributions	2023	Xin Li Deng Pan Chengyin Li Qiang Yao Dongxiao Zhu
+	Negative Flux Aggregation to Estimate Feature Attributions	2023	Xin Li Deng Pan Chengyin Li Qiang Yao Dongxiao Zhu
+ PDF Chat	Toward Understanding the Disagreement Problem in Neural Network Feature Attribution	2024	Niklas Koenen Marvin Wright
+ PDF Chat	Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach	2024	Lars Nieradzik Henrike Stephani Janis Keuper
+	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
+	Towards More Robust Interpretation via Local Gradient Alignment	2022	Sunghwan Joo Seokhyeon Jeong Juyeon Heo Adrian Weller Taesup Moon
+	MFABA: A More Faithful and Accelerated Boundary-based Attribution Method for Deep Neural Networks	2023	Zhiyu Zhu Huaming Chen J. Z. Zhang Xinyi Wang Zhibo Jin Minhui Xue Dongxiao Zhu Kim‐Kwang Raymond Choo
+	Investigating Saturation Effects in Integrated Gradients.	2020	Vivek Miglani Narine Kokhlikyan Bilal Alsallakh Miguel Vargas Martín Orion Reblitz-Richardson
+	Restricting the Flow: Information Bottlenecks for Attribution	2020	Karl Schulz Leon Sixt Federico Tombari Tim Landgraf
+	Restricting the Flow: Information Bottlenecks for Attribution	2020	Karl Schulz Leon Sixt Federico Tombari Tim Landgraf

Works That Cite This (119)

Action	Title	Year	Authors
+ PDF Chat	Deep learning with photosensor timing information as a background rejection method for the Cherenkov Telescope Array	2021	S. Spencer T. P. Armstrong J. R. Watson S. Mangano Y. Renier G. Cotter
+ PDF Chat	Improvement of variables interpretability in kernel PCA	2023	Mitja Briscik Marie‐Agnès Dillies Sébastien Dejean
+ PDF Chat	Illuminati: Towards Explaining Graph Neural Networks for Cybersecurity Analysis	2022	Haoyu He Yuede Ji H. Howie Huang
+ PDF Chat	TSGB: Target-Selective Gradient Backprop for Probing CNN Visual Saliency	2022	Lin Cheng Pengfei Fang Yanjie Liang Liao Zhang Chunhua Shen Hanzi Wang
+ PDF Chat	Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanations	2021	Wolfgang Stammer Patrick Schramowski Kristian Kersting
+ PDF Chat	AdapLeR: Speeding up Inference by Adaptive Length Reduction	2022	Ali Modarressi Hosein Mohebbi Mohammad Taher Pilehvar
+	Does Your Model Think Like an Engineer? Explainable AI for Bearing Fault Detection with Deep Learning	2023	Thomas Decker Michael Lebacher Volker Tresp
+	Feature perturbation augmentation for reliable evaluation of importance estimators in neural networks	2023	Lennart Brocki Neo Christopher Chung
+	CLEVR-XAI: A benchmark dataset for the ground truth evaluation of neural network explanations	2021	Leila Arras Ahmed Osman Wojciech Samek
+ PDF Chat	A Review on Explainable Artificial Intelligence for Healthcare: Why, How, and When?	2023	Subrato Bharati M. Rubaiyat Hossain Mondal Prajoy Podder

Works Cited by This (0)

Action	Title	Year	Authors