{"type":"ScholarlyArticle","title":"Advancing Post-Hoc Case-Based Explanation with Feature Highlighting","authors":[{"name":"Eoin M. Kenny","slug":"eoin-m-kenny","given":"Eoin M.","family":"Kenny","affiliation":"CSAIL , Massachusetts Institute of Technology"},{"name":"Eoin Delaney","slug":"eoin-delaney","given":"Eoin","family":"Delaney","affiliation":"University College Dublin; VistaMilk SFI Research Centre"},{"name":"Mark T. Keane","slug":"mark-t-keane","given":"Mark T.","family":"Keane","affiliation":"University College Dublin; Insight Centre for Data Analytics; VistaMilk SFI Research Centre"}],"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.","doi":"10.24963/ijcai.2023/48","url":"https://ijcai.org/proceedings/2023/48","pdf":"https://ijcai.org/proceedings/2023/0048.pdf","markdown":"https://ijcai.org/proceedings/2023/48.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/48","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"AI Ethics, Trust, Fairness","track":"Main Track","number":48,"pages":{"first":427,"last":435},"keywords":["Knowledge Representation and Reasoning: KRR: Case-based reasoning","AI Ethics, Trust, Fairness: ETF: Explainability and interpretability"],"videos":[],"references":[{"position":1,"raw":"[Adebayo et al., 2018] 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.","title":"Sanity checks for saliency maps","authors":"Julius Adebayo, Justin Gilmer, Michael Muelly, Ian Goodfellow, Moritz Hardt, Been Kim","year":"2018","venue":"Proceedings of the 32nd International Conference on Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chen et al., 2019] 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.","title":"This looks like that: Deep learning for interpretable image recognition","authors":"Chen","year":"2019","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Crabbé et al., 2021] Jonathan Crabbé, Zhaozhi Qian, Fer- gus Imrie, and Mihaela van der Schaar. Explaining latent representations with a corpus of examples. Advances in Neural Information Processing Systems, 34, 2021.","title":"Explaining latent representations with a corpus of examples","authors":"Jonathan Crabbé, Zhaozhi Qian, Fergus Imrie, Mihaela Van Der Schaar","year":"2021","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Deng et al., 2009] 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.","title":"Imagenet: A large-scale hierarchical image database","authors":"Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, Li Fei-Fei","year":"2009","venue":"IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Donnelly et al., 2021] Jon Donnelly, Alina Jade Barnett, and Chaofan Chen. Deformable protopnet: An inter- pretable image classifier using deformable prototypes. arXiv preprint arXiv:2111.15000, 2021.","title":"Deformable protopnet: An interpretable image classifier using deformable prototypes","authors":"Donnelly","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Dosovitskiy et al., 2020] Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Min- derer, Georg Heigold, Sylvain Gelly, et al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020.","title":"An image is worth 16x16 words: Transformers for image recognition at scale","authors":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Du et al., 2022] Xin Du, Benedicte Legastelois, Bhargavi Ganesh, Ajitha Rajan, Hana Chockler, Vaishak Belle, Stu- art Anderson, and Subramanian Ramamoorthy. Vision checklist: Towards testable error analysis of image mod- els to help system designers interrogate model capabilities. arXiv preprint arXiv:2201.11674, 2022.","title":"Vision checklist: Towards testable error analysis of image models to help system designers interrogate model capabilities","authors":"Xin Du, Benedicte Legastelois, Bhargavi Ganesh, Ajitha Rajan, Hana Chockler, Vaishak Belle, Stuart Anderson, Subramanian Ramamoorthy","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Goyal et al., 2019] Yash Goyal, Ziyan Wu, Jan Ernst, Dhruv Batra, Devi Parikh, and Stefan Lee. Counterfactual vi- sual explanations. In International Conference on Ma- chine Learning, pages 2376-2384. PMLR, 2019.","title":"Counterfactual visual explanations","authors":"Yash Goyal, Ziyan Wu, Jan Ernst, Dhruv Batra, Devi Parikh, Stefan Lee","year":"2019","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hanawa et al., 2021] Kazuaki Hanawa, Sho Yokoi, Satoshi Hara, and Kentaro Inui. Evaluation of similarity-based ex- planations. In Proceedings of the Ninth International Con- ference on Learning Representations, 2021.","title":"Evaluation of similarity-based explanations","authors":"Kazuaki Hanawa, Sho Yokoi, Satoshi Hara, Kentaro Inui","year":"2021","venue":"Proceedings of the Ninth International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Hooker et al., 2019] Sara Hooker, Dumitru Erhan, Pieter- Jan Kindermans, and Been Kim. A benchmark for in- terpretability methods in deep neural networks. Advances in Neural Information Processing Systems, 32:9737-9748, 2019.","title":"A benchmark for interpretability methods in deep neural networks","authors":"Sara Hooker, Dumitru Erhan, Pieter-Jan Kindermans, Been Kim","year":"2019","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Jeyakumar et al., 2020] 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.","title":"How can i explain this to you? an empirical study of deep neural network explanation methods","authors":"Jeya Vikranth, Jeyakumar, Joseph Noor, Yu-Hsi Cheng, Luis Garcia, Mani Srivastava","year":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Kenny and Keane, 2019] Eoin M Kenny and Mark T Keane. Twin-systems to explain artificial neural networks us- ing case-based reasoning: Comparative tests of feature- weighting methods in ann-cbr twins for xai. In Twenty- Eighth International Joint Conferences on Artifical Intel- ligence (IJCAI), Macao, 10-16 August 2019, pages 2708- 2715, 2019.","title":"Twin-systems to explain artificial neural networks using case-based reasoning: Comparative tests of featureweighting methods in ann-cbr twins for xai","authors":"M Eoin, Mark T Kenny, Keane","year":"2019","venue":"Twenty-Eighth International Joint Conferences on Artifical Intelligence (IJCAI)","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Kenny and Keane, 2021] Eoin M Kenny and Mark T Keane. Explaining deep learning using examples: Optimal fea- ture weighting methods for twin systems using post-hoc, explanation-by-example in xai. Knowledge-Based Sys- tems, 233:107530, 2021.","title":"Explaining deep learning using examples: Optimal feature weighting methods for twin systems using post-hoc, explanation-by-example in xai","authors":"M Eoin, Mark T Kenny, Keane","year":"2021","venue":"Knowledge-Based Systems","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"Kenny et al., ] Eoin M Kenny, Mycal Tucker, and Julie Shah. Towards interpretable deep reinforcement learning with human-friendly prototypes. In The Eleventh Interna- tional Conference on Learning Representations.","title":"Towards interpretable deep reinforcement learning with human-friendly prototypes","authors":"Kenny","year":null,"venue":"The Eleventh International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Kenny et al., 2021] Eoin M Kenny, Courtney Ford, Molly Quinn, and Mark T Keane. Explaining black-box classi- fiers using post-hoc explanations-by-example: The effect of explanations and error-rates in xai user studies. Artifi- cial Intelligence, page 103459, 2021.","title":"Explaining black-box classifiers using post-hoc explanations-by-example: The effect of explanations and error-rates in xai user studies","authors":"M Eoin, Courtney Kenny, Molly Ford, Mark T Quinn, Keane","year":"2021","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Kim et al., 2014] 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.","title":"The bayesian case model: A generative approach for case-based reasoning and prototype classification","authors":"Kim","year":"2014","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Leake and McSherry, 2005] David Leake and David McSh- erry. Introduction to the special issue on explanation in case-based reasoning. The Artificial Intelligence Review, 24(2):103, 2005.","title":"Introduction to the special issue on explanation in case-based reasoning","authors":"Mcsherry Leake, David Leake, David Mcsherry","year":"2005","venue":"The Artificial Intelligence Review","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Papernot and McDaniel, 2018] Nicolas Papernot and Patrick McDaniel. Deep k-nearest neighbors: Towards confident, interpretable and robust deep learning. arXiv preprint arXiv:1803.04765, 2018.","title":"Deep k-nearest neighbors: Towards confident, interpretable and robust deep learning","authors":"Nicolas Papernot, Patrick Mcdaniel","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Patro and Namboodiri, 2018] Badri Patro and Vinay P Namboodiri. Differential attention for visual question an- swering. In Proceedings of the IEEE conference on com- puter vision and pattern recognition, pages 7680-7688, 2018.","title":"Differential attention for visual question answering","authors":"Badri Patro, P Vinay, Namboodiri","year":"2018","venue":"Proceedings of the IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Ribeiro et al., 2016] Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. Why should i trust you?: Explain- ing the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowl- edge discovery and data mining, pages 1135-1144. ACM, 2016.","title":"Why should i trust you?: Explaining the predictions of any classifier","authors":"Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin","year":"2016","venue":"Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Rudin et al., 2022] Cynthia Rudin, Chaofan Chen, Zhi Chen, Haiyang Huang, Lesia Semenova, and Chudi Zhong. Interpretable machine learning: Fundamental prin- ciples and 10 grand challenges. Statistics Surveys, 16:1- 85, 2022.","title":"Interpretable machine learning: Fundamental principles and 10 grand challenges","authors":"Cynthia Rudin, Chaofan Chen, Zhi Chen, Haiyang Huang, Lesia Semenova, Chudi Zhong","year":"2022","venue":"Statistics Surveys","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Rymarczyk et al., 2021] Dawid Rymarczyk, Łukasz Struski, Michał Górszczak, Koryna Lewandowska, Jacek Tabor, and Bartosz Zieliński. Interpretable image classi- fication with differentiable prototypes assignment. arXiv e-prints, pages arXiv-2112, 2021.","title":"Interpretable image classification with differentiable prototypes assignment","authors":"Dawid Rymarczyk, Łukasz Struski, Michał Górszczak, Koryna Lewandowska, Jacek Tabor, Bartosz Zieliński","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Welinder et al., 2010] 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.","title":"Caltech-ucsd birds 200","authors":"Peter Welinder, Steve Branson, Takeshi Mita, Catherine Wah, Florian Schroff, Serge Belongie, Pietro Perona","year":"2010","venue":"Computation & Neural Systems Technical Report. 2010-001","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Werner and Rehkämper, 2001] Christian W Werner and Gerd Rehkämper. Categorization of multidimensional ge- ometrical figures by chickens (gallus gallus f. domestica): fit of basic assumptions from exemplar, feature and proto- type theory. Animal Cognition, 4(1):37-48, 2001.","title":"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","authors":"Rehkämper Werner","year":"2001","venue":"Animal Cognition","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zhou et al., 2016] Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba. Learning deep features for discriminative localization. In Proceed- ings of the IEEE conference on computer vision and pat- tern recognition, pages 2921-2929, 2016.","title":"Learning deep features for discriminative localization","authors":"Zhou","year":"2016","venue":"Proceedings of the IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zhou et al., 2022] 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.","title":"Do feature attribution methods correctly attribute features","authors":"Yilun Zhou, Serena Booth, Marco Tulio Ribeiro, Julie Shah","year":"2022","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}