research-article

Advancing post-hoc case-based explanation with feature highlighting

AUTHORs:

Mark T. KeaneAuthors Info & Claims

IJCAI '23: Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence

Article No.: 48, Pages 427 - 435

https://doi.org/10.24963/ijcai.2023/48

Published: 19 August 2023 Publication History

Abstract

Explainable AI (XAI) has been proposed as a valuable tool to assist in downstream tasks involving human-AI collaboration. Perhaps the most psychologically valid XAI techniques are case-based approaches which display "whole" exemplars to explain the predictions of black-box AI systems. However, for such post-hoc XAI methods dealing with images, there has been no attempt to improve their scope by using multiple clear feature "parts" of the images to explain the predictions while linking back to relevant cases in the training data, thus allowing for more comprehensive explanations that are faithful to the underlying model. Here, we address this gap by proposing two general algorithms (latent and superpixel-based) which can isolate multiple clear feature parts in a test image, and then connect them to the explanatory cases found in the training data, before testing their effectiveness in a carefully designed user study. Results demonstrate that the proposed approach appropriately calibrates a user's feelings of "correctness" for ambiguous classifications in real world data on the ImageNet dataset, an effect which does not happen when just showing the explanation without feature highlighting.

References

[1]

Julius Adebayo, Justin Gilmer, Michael Muelly, Ian Goodfellow, Moritz Hardt, and Been Kim. Sanity checks for saliency maps. In Proceedings of the 32nd International Conference on Neural Information Processing Systems, pages 9525-9536, 2018.

Digital Library

[2]

Chaofan Chen, Oscar Li, Daniel Tao, Alina Barnett, Cynthia Rudin, and Jonathan K Su. This looks like that: Deep learning for interpretable image recognition. Advances in Neural Information Processing Systems, 32:8930-8941, 2019.

[3]

Jonathan Crabbé, Zhaozhi Qian, Fergus Imrie, and Mihaela van der Schaar. Explaining latent representations with a corpus of examples. Advances in Neural Information Processing Systems, 34, 2021.

[4]

Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. Imagenet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pages 248-255, 2009.

[5]

Jon Donnelly, Alina Jade Barnett, and Chaofan Chen. Deformable protopnet: An interpretable image classifier using deformable prototypes. arXiv preprint arXiv:2111.15000, 2021.

[6]

Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. An image is worth 16×16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020.

[7]

Xin Du, Benedicte Legastelois, Bhargavi Ganesh, Ajitha Rajan, Hana Chockler, Vaishak Belle, Stuart Anderson, and Subramanian Ramamoorthy. Vision checklist: Towards testable error analysis of image models to help system designers interrogate model capabilities. arXiv preprint arXiv:2201.11674, 2022.

[8]

Yash Goyal, ZiyanWu, Jan Ernst, Dhruv Batra, Devi Parikh, and Stefan Lee. Counterfactual visual explanations. In International Conference on Machine Learning, pages 2376-2384. PMLR, 2019.

[9]

Kazuaki Hanawa, Sho Yokoi, Satoshi Hara, and Kentaro Inui. Evaluation of similarity-based explanations. In Proceedings of the Ninth International Conference on Learning Representations, 2021.

[10]

Sara Hooker, Dumitru Erhan, Pieter-Jan Kindermans, and Been Kim. A benchmark for interpretability methods in deep neural networks. Advances in Neural Information Processing Systems, 32:9737-9748, 2019.

[11]

Jeya Vikranth Jeyakumar, Joseph Noor, Yu-Hsi Cheng, Luis Garcia, and Mani Srivastava. How can i explain this to you? an empirical study of deep neural network explanation methods. Advances in Neural Information Processing Systems, 33, 2020.

[12]

Eoin M Kenny and Mark T Keane. Twin-systems to explain artificial neural networks using case-based reasoning: Comparative tests of feature-weighting methods in ann-cbr twins for xai. In Twenty-Eighth International Joint Conferences on Artifical Intelligence (IJCAI), Macao, 10-16 August 2019, pages 2708- 2715, 2019.

[13]

Eoin M Kenny and Mark T Keane. Explaining deep learning using examples: Optimal feature weighting methods for twin systems using post-hoc, explanation-by-example in xai. Knowledge-Based Systems, 233:107530, 2021.

Digital Library

[14]

Eoin M Kenny, Mycal Tucker, and Julie Shah. Towards interpretable deep reinforcement learning with human-friendly prototypes. In The Eleventh International Conference on Learning Representations.

[15]

Eoin M Kenny, Courtney Ford, Molly Quinn, and Mark T Keane. Explaining black-box classifiers using post-hoc explanations-by-example: The effect of explanations and error-rates in xai user studies. Artificial Intelligence, page 103459, 2021.

[16]

Been Kim, Cynthia Rudin, and Julie A Shah. The bayesian case model: A generative approach for case-based reasoning and prototype classification. In Advances in neural information processing systems, pages 1952-1960, 2014.

Digital Library

[17]

David Leake and David McSherry. Introduction to the special issue on explanation in case-based reasoning. The Artificial Intelligence Review, 24(2):103, 2005.

Digital Library

[18]

Nicolas Papernot and Patrick McDaniel. Deep k-nearest neighbors: Towards confident, interpretable and robust deep learning. arXiv preprint arXiv:1803.04765, 2018.

[19]

Badri Patro and Vinay P Namboodiri. Differential attention for visual question answering. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 7680-7688, 2018.

[20]

Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. Why should i trust you?: Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pages 1135-1144. ACM, 2016.

Digital Library

[21]

Cynthia Rudin, Chaofan Chen, Zhi Chen, Haiyang Huang, Lesia Semenova, and Chudi Zhong. Interpretable machine learning: Fundamental principles and 10 grand challenges. Statistics Surveys, 16:1- 85, 2022.

[22]

Dawid Rymarczyk, Lukasz Struski, Michał Górszczak, Koryna Łewandowska, Jacek Tabor, and Bartosz Zieliński. Interpretable image classification with differentiable prototypes assignment. arXiv e-prints, pages arXiv-2112, 2021.

[23]

Peter Welinder, Steve Branson, Takeshi Mita, Catherine Wah, Florian Schroff, Serge Belongie, and Pietro Perona. Caltech-ucsd birds 200. In Computation & Neural Systems Technical Report. 2010-001. California Institute of Technology, Pasadena, CA., 2010.

[24]

Christian W Werner and Gerd Rehkämper. Categorization of multidimensional geometrical figures by chickens (gallus gallus f. domestica): fit of basic assumptions from exemplar, feature and prototype theory. Animal Cognition, 4(1):37-48, 2001.

[25]

Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba. Learning deep features for discriminative localization. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2921-2929, 2016.

[26]

Yilun Zhou, Serena Booth, Marco Tulio Ribeiro, and Julie Shah. Do feature attribution methods correctly attribute features? In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 9623-9633, 2022.

Cited By

Kenny EHuang WOh ANaumann TGloberson ASaenko KHardt MLevine S(2023)The utility of "even if..." semifactual explanation to optimise positive outcomesProceedings of the 37th International Conference on Neural Information Processing Systems10.5555/3666122.3668424(52907-52935)Online publication date: 10-Dec-2023
https://dl.acm.org/doi/10.5555/3666122.3668424

Index Terms

Advancing post-hoc case-based explanation with feature highlighting
1. Computing methodologies
  1. Artificial intelligence
  2. Machine learning
2. Human-centered computing

Index terms have been assigned to the content through auto-classification.

Recommendations

Gaining insight through case-based explanation

Traditional explanation strategies in machine learning have been dominated by rule and decision tree based approaches. Case-based explanations represent an alternative approach which has inherent advantages in terms of transparency and user ...
Explanation in Case-Based Reasoning---Perspectives and Goals

We present an overview of different theories of explanation from the philosophy and cognitive science communities. Based on these theories, as well as models of explanation from the knowledge-based systems area, we present a framework for explanation in ...
Using Case-Based Reasoning for Capturing Expert Knowledge on Explanation Methods
Case-Based Reasoning Research and Development
Abstract
Model-agnostic methods in eXplainable Artificial Intelligence (XAI) propose isolating the explanation system from the AI model architecture, typically Machine Learning or black-box models. Existing XAI libraries offer a good number of explanation ...

Comments

Information & Contributors

Information

Published In

cover image Guide Proceedings

IJCAI '23: Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence

August 2023

7242 pages

ISBN:978-1-956792-03-4

Editor:
Edith Elkind

Copyright © 2023 International Joint Conferences on Artificial Intelligence.

Sponsors

International Joint Conferences on Artifical Intelligence (IJCAI)

Publisher

Unknown publishers

Publication History

Published: 19 August 2023

Qualifiers

Research-article
Research
Refereed limited

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 15 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Kenny EHuang WOh ANaumann TGloberson ASaenko KHardt MLevine S(2023)The utility of "even if..." semifactual explanation to optimise positive outcomesProceedings of the 37th International Conference on Neural Information Processing Systems10.5555/3666122.3668424(52907-52935)Online publication date: 10-Dec-2023
https://dl.acm.org/doi/10.5555/3666122.3668424

View Options

View options

Media

Figures

Other

Tables

View Table of Contents