v1v2 (latest)

Interpretation of Neural Networks is Fragile

AAAI Conference on Artificial Intelligence (AAAI), 2017

29 October 2017

Papers citing "Interpretation of Neural Networks is Fragile"

50 / 489 papers shown

Title
Concept-based Explainable Artificial Intelligence: A Survey Eleonora Poeta Gabriele Ciravegna Eliana Pastor Tania Cerquitelli Elena Baralis LRM XAI 238 84 0 20 Dec 2023
CEIR: Concept-based Explainable Image Representation Learning Yan Cui Shuhong Liu Liuzhuozheng Li Zhiyuan Yuan SSL VLM 132 5 0 17 Dec 2023
Rethinking Robustness of Model AttributionsAAAI Conference on Artificial Intelligence (AAAI), 2023 Sandesh Kamath Sankalp Mittal Amit Deshpande Vineeth N. Balasubramanian 206 2 0 16 Dec 2023
CIDR: A Cooperative Integrated Dynamic Refining Method for Minimal Feature Removal ProblemAAAI Conference on Artificial Intelligence (AAAI), 2023 Qian Chen Tao Zhang Dongyang Li Xiaofeng He 410 0 0 13 Dec 2023
TaCo: Targeted Concept Removal in Output Embeddings for NLP via Information Theory and Explainability Fanny Jourdan Louis Bethune Agustin Picard Laurent Risser Nicholas M. Asher 182 0 0 11 Dec 2023
Interpretability Illusions in the Generalization of Simplified Models Dan Friedman Andrew Kyle Lampinen Lucas Dixon Danqi Chen Asma Ghandeharioun 317 19 0 06 Dec 2023
Interpretable Knowledge Tracing via Response Influence-based Counterfactual ReasoningIEEE International Conference on Data Engineering (ICDE), 2023 Jiajun Cui Minghe Yu Bo Jiang Aimin Zhou Jianyong Wang Wei Zhang 249 7 0 01 Dec 2023
Improving Interpretation Faithfulness for Vision TransformersInternational Conference on Machine Learning (ICML), 2023 Lijie Hu Yixin Liu Ninghao Liu Mengdi Huai Lichao Sun Haiyan Zhao 203 12 0 29 Nov 2023
Uncertainty in Additive Feature Attribution methods Abhishek Madaan Tanya Chowdhury Neha Rana James Allan Tanmoy Chakraborty 175 0 0 29 Nov 2023
FocusLearn: Fully-Interpretable, High-Performance Modular Neural Networks for Time SeriesIEEE International Joint Conference on Neural Network (IJCNN), 2023 Qiqi Su Christos Kloukinas Artur dÁvila Garcez AI4TS 317 8 0 28 Nov 2023
Survey on AI Ethics: A Socio-technical PerspectiveInternational Conference on Climate Informatics (ICCI), 2023 Dave Mbiazi Meghana Bhange Maryam Babaei Ivaxi Sheth Patrik Kenfack Samira Ebrahimi Kahou 391 9 0 28 Nov 2023
MRxaI: Black-Box Explainability for Image Classifiers in a Medical Setting Nathan Blake Hana Chockler David A. Kelly Santiago Calderón-Pena Akchunya Chanchal 114 5 0 24 Nov 2023
On the Relationship Between Interpretability and Explainability in Machine Learning Benjamin Leblanc Pascal Germain FaML 390 1 0 20 Nov 2023
Explainability of Vision Transformers: A Comprehensive Review and New Perspectives Rojina Kashefi Leili Barekatain Mohammad Sabokrou Fatemeh Aghaeipoor ViT 262 19 0 12 Nov 2023
SCAAT: Improving Neural Network Interpretability via Saliency Constrained Adaptive Adversarial Training Rui Xu Wenkang Qin Peixiang Huang Hao Wang Lin Luo FAtt AAML 262 3 0 09 Nov 2023
SmoothHess: ReLU Network Feature Interactions via Stein's LemmaNeural Information Processing Systems (NeurIPS), 2023 Max Torop A. Masoomi Davin Hill Kivanc Kose Stratis Ioannidis Jennifer Dy 320 7 0 01 Nov 2023
Corrupting Neuron Explanations of Deep Visual FeaturesIEEE International Conference on Computer Vision (ICCV), 2023 Divyansh Srivastava Tuomas P. Oikarinen Tsui-Wei Weng FAtt AAML 114 3 0 25 Oct 2023
Explanation-based Training with Differentiable Insertion/Deletion Metric-aware RegularizersInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2023 Yuya Yoshikawa Tomoharu Iwata 223 1 0 19 Oct 2023
Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations Shiyuan Huang Siddarth Mamidanna Shreedhar Jangam Yilun Zhou Leilani H. Gilpin LRM MILM ELM 356 107 0 17 Oct 2023
A New Baseline Assumption of Integated Gradients Based on Shaply value Shuyang Liu Zixuan Chen Ge Shi Ji Wang Changjie Fan Yu Xiong Runze Wu Yujing Hu Ze Ji Yang Gao 235 2 0 07 Oct 2023
The Blame Problem in Evaluating Local Explanations, and How to Tackle it Amir Hossein Akhavan Rahnama ELM FAtt 241 7 0 05 Oct 2023
SMOOT: Saliency Guided Mask Optimized Online Training Ali Karkehabadi Houman Homayoun Avesta Sasan AAML 277 21 0 01 Oct 2023
Counterfactual Image Generation for adversarially robust and interpretable Classifiers Rafael Bischof Florian Scheidegger Michael A. Kraus A. Malossi AAML 202 2 0 01 Oct 2023
Faithful Explanations of Black-box NLP Models Using LLM-generated CounterfactualsInternational Conference on Learning Representations (ICLR), 2023 Y. Gat Nitay Calderon Amir Feder Alexander Chapanin Amit Sharma Roi Reichart 380 42 0 01 Oct 2023
Black-box Attacks on Image Activity Prediction and its Natural Language Explanations Alina Elena Baia Valentina Poggioni Andrea Cavallaro AAML 192 1 0 30 Sep 2023
DeepROCK: Error-controlled interaction detection in deep neural networks Winston Chen William Stafford Noble Y. Lu 262 1 0 26 Sep 2023
Concept explainability for plant diseases classificationVISIGRAPP (VISIGRAPP), 2023 Jihen Amara B. König-Ries Sheeba Samuel FAtt 98 2 0 15 Sep 2023
Interpretability is in the Mind of the Beholder: A Causal Framework for Human-interpretable Representation LearningEntropy (Entropy), 2023 Emanuele Marconato Baptiste Caramiaux Stefano Teso 264 19 0 14 Sep 2023
Automatic Concept Embedding Model (ACEM): No train-time concepts, No issue! Rishabh Jain LRM 106 0 0 07 Sep 2023
Goodhart's Law Applies to NLP's Explanation BenchmarksFindings (Findings), 2023 Jennifer Hsia Danish Pruthi Aarti Singh Zachary Chase Lipton 203 7 0 28 Aug 2023
On the Interpretability of Quantum Neural NetworksQuantum Machine Intelligence (QMI), 2023 Lirande Pira C. Ferrie FAtt 188 29 0 22 Aug 2023
FUTURE-AI: International consensus guideline for trustworthy and deployable artificial intelligence in healthcareBritish medical journal (BMJ), 2023 Karim Lekadir Aasa Feragen Abdul Joseph Fofanah Alejandro F Frangi Alena Buyx ... Yi Zeng Yunusa G Mohammed Yves Saint James Aquino Zohaib Salahuddin M. P. Starmans AI4TS 297 206 0 11 Aug 2023
A New Perspective on Evaluation Methods for Explainable Artificial Intelligence (XAI) Timo Speith Markus Langer 205 16 0 26 Jul 2023
Saliency strikes back: How filtering out high frequencies improves white-box explanationsInternational Conference on Machine Learning (ICML), 2023 Sabine Muzellec Thomas Fel Victor Boutin Léo Andéol R. V. Rullen Thomas Serre FAtt 415 3 0 18 Jul 2023
SHAMSUL: Systematic Holistic Analysis to investigate Medical Significance Utilizing Local interpretability methods in deep learning for chest radiography pathology predictionNordic Machine Intelligence (NMI), 2023 Mahbub Ul Alam Jaakko Hollmén Jón R. Baldvinsson R. Rahmani FAtt 424 3 0 16 Jul 2023
On the Connection between Game-Theoretic Feature Attributions and Counterfactual ExplanationsAAAI/ACM Conference on AI, Ethics, and Society (AIES), 2023 Emanuele Albini Sanjay Kariyappa Saumitra Mishra Danial Dervovic Daniele Magazzeni FAtt 250 3 0 13 Jul 2023
Single-Class Target-Specific Attack against Interpretable Deep Learning Systems Eldor Abdukhamidov Mohammed Abuhamad George K. Thiruvathukal Hyoungshick Kim Tamer Abuhmed AAML 187 2 0 12 Jul 2023
Stability Guarantees for Feature Attributions with Multiplicative SmoothingNeural Information Processing Systems (NeurIPS), 2023 Anton Xue Rajeev Alur Eric Wong 313 12 0 12 Jul 2023
Hierarchical Semantic Tree Concept Whitening for Interpretable Image Classification Haixing Dai Lu Zhang Lin Zhao Zihao Wu Zheng Liu ... Yanjun Lyu Changying Li Ninghao Liu Tianming Liu Dajiang Zhu 238 7 0 10 Jul 2023
Robust Ranking Explanations Chao Chen Chenghua Guo Guixiang Ma Ming Zeng Xi Zhang Sihong Xie FAtt AAML 335 0 0 08 Jul 2023
A Vulnerability of Attribution Methods Using Pre-Softmax Scores Miguel A. Lerma Mirtha Lucas FAtt 230 0 0 06 Jul 2023
DARE: Towards Robust Text Explanations in Biomedical and Healthcare ApplicationsAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 Adam Ivankay Mattia Rigotti P. Frossard OOD MedIm 184 1 0 05 Jul 2023
Fixing confirmation bias in feature attribution methods via semantic match Giovanni Cina Daniel Fernandez-Llaneza Ludovico Deponte Nishant Mishra Tabea E. Rober Sandro Pezzelle Iacer Calixto Rob Goedhart cS. .Ilker Birbil FAtt 229 3 0 03 Jul 2023
SHARCS: Shared Concept Space for Explainable Multimodal Learning Gabriele Dominici Pietro Barbiero Lucie Charlotte Magister Pietro Lio Nikola Simidjievski 158 6 0 01 Jul 2023
Verifying Safety of Neural Networks from Topological PerspectivesScience of Computer Programming (SCP), 2023 Zhen Liang Dejin Ren Bai Xue Jing Wang Wenjing Yang Wanwei Liu AAML 212 0 0 27 Jun 2023
Requirements for Explainability and Acceptance of Artificial Intelligence in Collaborative WorkInteracción (HCI), 2023 Sabine Theis Sophie F. Jentzsch Fotini Deligiannaki C. Berro A. Raulf C. Bruder 178 13 0 27 Jun 2023
Evaluating the overall sensitivity of saliency-based explanation methods Harshinee Sriram Cristina Conati AAML XAI FAtt 150 0 0 21 Jun 2023
On the Robustness of Removal-Based Feature AttributionsNeural Information Processing Systems (NeurIPS), 2023 Christy Lin Ian Covert Su-In Lee 361 18 0 12 Jun 2023
A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance EstimationNeural Information Processing Systems (NeurIPS), 2023 Thomas Fel Victor Boutin Mazda Moayeri Rémi Cadène Louis Bethune Léo Andéol Mathieu Chalvidal Thomas Serre FAtt 299 83 0 11 Jun 2023
On Minimizing the Impact of Dataset Shifts on Actionable ExplanationsConference on Uncertainty in Artificial Intelligence (UAI), 2023 Anna P. Meyer Dan Ley Suraj Srinivas Himabindu Lakkaraju FAtt 191 6 0 11 Jun 2023