Restricting the Flow: Information Bottlenecks for Attribution

2 January 2020

Papers citing "Restricting the Flow: Information Bottlenecks for Attribution"

39 / 39 papers shown

Title
DocVXQA: Context-Aware Visual Explanations for Document Question Answering Mohamed Ali Souibgui Changkyu Choi Andrey Barsky Kangsoo Jung Ernest Valveny Dimosthenis Karatzas 28 0 0 12 May 2025
Class-Dependent Perturbation Effects in Evaluating Time Series Attributions Gregor Baer Isel Grau Chao Zhang Pieter Van Gorp AAML 53 0 0 24 Feb 2025
Narrowing Information Bottleneck Theory for Multimodal Image-Text Representations Interpretability Zhiyu Zhu Zhibo Jin Jiayu Zhang Nan Yang Jiahao Huang Jianlong Zhou Fang Chen 44 0 0 16 Feb 2025
Extending Information Bottleneck Attribution to Video Sequences Veronika Solopova Lucas Schmidt Dorothea Kolossa 47 0 0 28 Jan 2025
Variational Language Concepts for Interpreting Foundation Language Models Hengyi Wang Shiwei Tan Zhiqing Hong Desheng Zhang Hao Wang 34 3 0 04 Oct 2024
Prototypical Self-Explainable Models Without Re-training Srishti Gautam Ahcène Boubekki Marina M.-C. Höhne Michael C. Kampffmeyer 34 2 0 13 Dec 2023
HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation Lu Chen Siyu Lou Keyan Zhang Jin Huang Quanshi Zhang TDI FAtt 22 9 0 04 Apr 2023
Task-specific Fine-tuning via Variational Information Bottleneck for Weakly-supervised Pathology Whole Slide Image Classification Honglin Li Chenglu Zhu Yunlong Zhang Yuxuan Sun Zhongyi Shui Wenwei Kuang S. Zheng L. Yang 69 57 0 15 Mar 2023
Opti-CAM: Optimizing saliency maps for interpretability Hanwei Zhang Felipe Torres R. Sicre Yannis Avrithis Stéphane Ayache 36 22 0 17 Jan 2023
Comparing the Decision-Making Mechanisms by Transformers and CNNs via Explanation Methods Ming-Xiu Jiang Saeed Khorram Li Fuxin FAtt 22 9 0 13 Dec 2022
Interpretability with full complexity by constraining feature information Kieran A. Murphy Danielle Bassett FAtt 35 5 0 30 Nov 2022
Evaluating Feature Attribution Methods for Electrocardiogram J. Suh Jimyeong Kim Euna Jung Wonjong Rhee FAtt 22 2 0 23 Nov 2022
AD-DROP: Attribution-Driven Dropout for Robust Language Model Fine-Tuning Tao Yang Jinghao Deng Xiaojun Quan Qifan Wang Shaoliang Nie 32 3 0 12 Oct 2022
A clinically motivated self-supervised approach for content-based image retrieval of CT liver images Kristoffer Wickstrøm Eirik Agnalt Ostmo Keyur Radiya Karl Øyvind Mikalsen Michael C. Kampffmeyer Robert Jenssen SSL 26 13 0 11 Jul 2022
Variational Distillation for Multi-View Learning Xudong Tian Zhizhong Zhang Cong Wang Wensheng Zhang Yanyun Qu Lizhuang Ma Zongze Wu Yuan Xie Dacheng Tao 26 5 0 20 Jun 2022
Visualizing Deep Neural Networks with Topographic Activation Maps A. Krug Raihan Kabir Ratul Christopher Olson Sebastian Stober FAtt AI4CE 36 3 0 07 Apr 2022
Towards Explainable Evaluation Metrics for Natural Language Generation Christoph Leiter Piyawat Lertvittayakumjorn M. Fomicheva Wei-Ye Zhao Yang Gao Steffen Eger AAML ELM 30 20 0 21 Mar 2022
Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMF Jayneel Parekh Sanjeel Parekh Pavlo Mozharovskyi Florence dÁlché-Buc G. Richard 21 22 0 23 Feb 2022
Improving Subgraph Recognition with Variational Graph Information Bottleneck Junchi Yu Jie Cao Ran He 22 53 0 18 Dec 2021
Automatic Neural Network Pruning that Efficiently Preserves the Model Accuracy Thibault Castells Seul-Ki Yeom 3DV 18 3 0 18 Nov 2021
Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation Jungbeom Lee Jooyoung Choi J. Mok Sungroh Yoon SSeg 220 134 0 13 Oct 2021
The Eval4NLP Shared Task on Explainable Quality Estimation: Overview and Results M. Fomicheva Piyawat Lertvittayakumjorn Wei-Ye Zhao Steffen Eger Yang Gao ELM 24 39 0 08 Oct 2021
Discovery of New Multi-Level Features for Domain Generalization via Knowledge Corruption A. Frikha Denis Krompass Volker Tresp OOD 35 1 0 09 Sep 2021
Translation Error Detection as Rationale Extraction M. Fomicheva Lucia Specia Nikolaos Aletras 21 23 0 27 Aug 2021
Explaining COVID-19 and Thoracic Pathology Model Predictions by Identifying Informative Input Features Ashkan Khakzar Yang Zhang W. Mansour Yuezhi Cai Yawei Li Yucheng Zhang Seong Tae Kim Nassir Navab FAtt 52 17 0 01 Apr 2021
Efficient Explanations from Empirical Explainers Robert Schwarzenberg Nils Feldhus Sebastian Möller FAtt 32 9 0 29 Mar 2021
Explaining Representation by Mutual Information Li Gu SSL FAtt 34 0 0 28 Mar 2021
BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation Jungbeom Lee Jihun Yi Chaehun Shin Sungroh Yoon ISeg 24 172 0 16 Mar 2021
Inserting Information Bottlenecks for Attribution in Transformers Zhiying Jiang Raphael Tang Ji Xin Jimmy J. Lin 38 6 0 27 Dec 2020
Explainable Abstract Trains Dataset Manuel de Sousa Ribeiro L. Krippahl João Leite 13 8 0 15 Dec 2020
Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanations Wolfgang Stammer P. Schramowski Kristian Kersting FAtt 14 107 0 25 Nov 2020
Explaining by Removing: A Unified Framework for Model Explanation Ian Covert Scott M. Lundberg Su-In Lee FAtt 39 241 0 21 Nov 2020
Feature Removal Is a Unifying Principle for Model Explanation Methods Ian Covert Scott M. Lundberg Su-In Lee FAtt 33 33 0 06 Nov 2020
Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers Hanjie Chen Yangfeng Ji AAML VLM 15 63 0 01 Oct 2020
Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking M. Schlichtkrull Nicola De Cao Ivan Titov AI4CE 36 214 0 01 Oct 2020
Local and Global Explanations of Agent Behavior: Integrating Strategy Summaries with Saliency Maps Tobias Huber Katharina Weitz Elisabeth André Ofra Amir FAtt 21 64 0 18 May 2020
Adversarial Attacks and Defenses: An Interpretation Perspective Ninghao Liu Mengnan Du Ruocheng Guo Huan Liu Xia Hu AAML 26 8 0 23 Apr 2020
On Interpretability of Artificial Neural Networks: A Survey Fenglei Fan Jinjun Xiong Mengzhou Li Ge Wang AAML AI4CE 38 300 0 08 Jan 2020
When Explanations Lie: Why Many Modified BP Attributions Fail Leon Sixt Maximilian Granz Tim Landgraf BDL FAtt XAI 13 132 0 20 Dec 2019