Generating Perturbation-based Explanations with Robustness to Out-of-Distribution Data

Author:

Qiu Luyu1,Yang Yi2,Cao Caleb Chen2,Zheng Yueyuan3,Ngai Hilary3,Hsiao Janet4,Chen Lei5

Affiliation:

1. Huawei Research Hong Kong, Hong Kong and Hong Kong University of Science and Technology, Hong Kong

2. Huawei Research Hong Kong, Hong Kong

3. Huawei Research Hong Kong, Hong Kong and University of Hong Kong, Hong Kong

4. University of Hong Kong, Hong Kong

5. Hong Kong University of Science and Technology, Hong Kong

Funder

the Hong Kong RIF Project

Theme-based project

Hong Kong ITC ITF grants

Guangdong Basic and Applied Basic Research Foundation

Didi-HKUST joint research lab

National Key Research and Development Program of China Grant

the Hong Kong RGC GRF Project

the Hong Kong AOE Project

the Hong Kong CRF Project

Microsoft Research Asia Collaborative Research Grant

HKUST-NAVER/LINE AI Lab

HKUST-Webank joint research lab grants

China NSFC

Publisher

ACM

Reference42 articles.

1. Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)

2. Chirag Agarwal and Anh Nguyen . 2020. Explaining Image Classifiers by Removing Input Features Using Generative Models . In Computer Vision - ACCV 2020 - 15th Asian Conference on Computer Vision, Kyoto, Japan, November 30 - December 4, 2020 , Revised Selected Papers, Part VI(Lecture Notes in Computer Science, Vol. 12627), Hiroshi Ishikawa, Cheng-Lin Liu, Tomás Pajdla, and Jianbo Shi (Eds.). Springer , 101–118. https://doi.org/10.1007/978-3-030-69544-6_7 10.1007/978-3-030-69544-6_7 Chirag Agarwal and Anh Nguyen. 2020. Explaining Image Classifiers by Removing Input Features Using Generative Models. In Computer Vision - ACCV 2020 - 15th Asian Conference on Computer Vision, Kyoto, Japan, November 30 - December 4, 2020, Revised Selected Papers, Part VI(Lecture Notes in Computer Science, Vol. 12627), Hiroshi Ishikawa, Cheng-Lin Liu, Tomás Pajdla, and Jianbo Shi (Eds.). Springer, 101–118. https://doi.org/10.1007/978-3-030-69544-6_7

3. David Alvarez-Melis and Tommi  S. Jaakkola . 2018 . Towards Robust Interpretability with Self-Explaining Neural Networks. In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018 , NeurIPS 2018, December 3-8, 2018, Montréal, Canada, Samy Bengio, Hanna M. Wallach, Hugo Larochelle, Kristen Grauman, Nicolò Cesa-Bianchi, and Roman Garnett (Eds.). 7786–7795. https://proceedings.neurips.cc/paper/2018/hash/3e9f0fc9b2f89e043bc6233994dfcf76-Abstract.html David Alvarez-Melis and Tommi S. Jaakkola. 2018. Towards Robust Interpretability with Self-Explaining Neural Networks. In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018, Montréal, Canada, Samy Bengio, Hanna M. Wallach, Hugo Larochelle, Kristen Grauman, Nicolò Cesa-Bianchi, and Roman Garnett (Eds.). 7786–7795. https://proceedings.neurips.cc/paper/2018/hash/3e9f0fc9b2f89e043bc6233994dfcf76-Abstract.html

4. Vijay Arya Rachel K. E. Bellamy Pin-Yu Chen Amit Dhurandhar Michael Hind Samuel C. Hoffman Stephanie Houde Q. Vera Liao Ronny Luss Aleksandra Mojsilović Sami Mourad Pablo Pedemonte Ramya Raghavendra John Richards Prasanna Sattigeri Karthikeyan Shanmugam Moninder Singh Kush R. Varshney Dennis Wei and Yunfeng Zhang. 2019. One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques. (2019). https://doi.org/arXiv:1909.03012v2 arXiv:1909.03012 Vijay Arya Rachel K. E. Bellamy Pin-Yu Chen Amit Dhurandhar Michael Hind Samuel C. Hoffman Stephanie Houde Q. Vera Liao Ronny Luss Aleksandra Mojsilović Sami Mourad Pablo Pedemonte Ramya Raghavendra John Richards Prasanna Sattigeri Karthikeyan Shanmugam Moninder Singh Kush R. Varshney Dennis Wei and Yunfeng Zhang. 2019. One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques. (2019). https://doi.org/arXiv:1909.03012v2 arXiv:1909.03012

5. Or Biran and Courtenay V. Cotton. 2017. Explanation and Justification in Machine Learning : A Survey. Or Biran and Courtenay V. Cotton. 2017. Explanation and Justification in Machine Learning : A Survey.

Cited by 12 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3