{"type":"ScholarlyArticle","title":"Cutting the Black Box: Conceptual Interpretation of a Deep Neural Net with Multi-Modal Embeddings and Multi-Criteria Decision Aid","authors":[{"name":"Nicolas Atienza","slug":"nicolas-atienza","given":"Nicolas","family":"Atienza","affiliation":"Thales Research and Technology , Palaiseau , France; Industrial AI Laboratory SINCLAIR , Saclay , France; LISN CNRS-INRIA , Université Paris-Saclay , France"},{"name":"Roman Bresson","slug":"roman-bresson","given":"Roman","family":"Bresson","affiliation":"Thales Research and Technology , Palaiseau , France; Industrial AI Laboratory SINCLAIR , Saclay , France; KTH Royal Institute of Technology , Stockholm , Sweden"},{"name":"Cyriaque Rousselot","slug":"cyriaque-rousselot","given":"Cyriaque","family":"Rousselot","affiliation":"LISN CNRS-INRIA , Université Paris-Saclay , France"},{"name":"Philippe Caillou","slug":"philippe-caillou","given":"Philippe","family":"Caillou","affiliation":"LISN CNRS-INRIA , Université Paris-Saclay , France"},{"name":"Johanne Cohen","slug":"johanne-cohen","given":"Johanne","family":"Cohen","affiliation":"LISN CNRS-INRIA , Université Paris-Saclay , France"},{"name":"Christophe Labreuche","slug":"christophe-labreuche","given":"Christophe","family":"Labreuche","affiliation":"Thales Research and Technology , Palaiseau , France; Industrial AI Laboratory SINCLAIR , Saclay , France"},{"name":"Michele Sebag","slug":"michele-sebag","given":"Michèle","family":"Sebag","affiliation":"LISN CNRS-INRIA , Université Paris-Saclay , France"}],"abstract":"This paper tackles the concept-based explanation of neural models in computer vision, building upon the state of the art in Multi-Criteria Decision Aid (MCDA).\r\nThe novelty of the approach is to leverage multi-modal embeddings from CLIP to bridge the gap between pixel-based and concept-based representations. The proposed Cut the Black Box (CB2) approach disentangles the latent representation of a trained pixel-based neural net, referred to as teacher model, along a 3-step process. Firstly, the pixel-based representation of the samples is mapped onto a conceptual representation using multi-modal embeddings. Secondly, an interpretable-by-design MCDA student model is trained by distillation from the teacher model, using the  conceptual sample representation. Thirdly, the alignment of the teacher and student latent representations spells out the concepts relevant to explaining the teacher model.\r\nThe empirical validation of the approach on ResNet, VGG, and VisionTransformer on Cifar-10, Cifar-100, Tiny ImageNet, and Fashion-MNIST showcases the effectiveness of the interpretations provided for the teacher models. The analysis reveals that decision-making predominantly relies on few concepts, thereby exposing potential bias in the teacher's decisions.","doi":"10.24963/ijcai.2024/406","url":"https://ijcai.org/proceedings/2024/406","pdf":"https://ijcai.org/proceedings/2024/0406.pdf","markdown":"https://ijcai.org/proceedings/2024/406.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/406","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Machine Learning","track":"Main Track","number":406,"pages":{"first":3669,"last":3678},"keywords":["Machine Learning: ML: Explainable/Interpretable machine learning","Knowledge Representation and Reasoning: KRR: Preference modelling and preference-based reasoning","Machine Learning: ML: Trustworthy machine learning","Computer Vision: CV: Interpretability and transparency"],"videos":[],"references":[{"position":1,"raw":"[Adadi and Berrada, 2018] Amina Adadi and Mohammed Berrada. Peeking inside the black-box: A survey on ex- plainable artificial intelligence (xai). In IEEE Access, 2018.","title":"Amina Adadi and Mohammed Berrada. Peeking inside the black-box: A survey on explainable artificial intelligence (xai)","authors":"Berrada Adadi","year":"2018","venue":"IEEE Access","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bahadori and Heckerman, 2021] Mohammad Taha Ba- hadori and David E. Heckerman. Debiasing concept-based explanations with causal analysis. ICLR, 2021.","title":"Debiasing concept-based explanations with causal analysis","authors":"Heckerman ; Bahadori, Taha Mohammad, David E Bahadori, Heckerman","year":"2021","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bodria et al., 2023] Francesco Bodria, Fosca Giannotti, Riccardo Guidotti, Francesca Naretto, Dino Pedreschi, and Salvatore Rinzivillo. Benchmarking and survey of expla- nation methods for black box models. KDD, 2023.","title":"Benchmarking and survey of explanation methods for black box models","authors":"Francesco Bodria, Fosca Giannotti, Riccardo Guidotti, Francesca Naretto, Dino Pedreschi, Salvatore Rinzivillo","year":"2023","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bresson et al., 2020] Roman Bresson, Johanne Cohen, Eyke Hüllermeier, Christophe Labreuche, and Michèle Se- bag. Neural representation and learning of hierarchical 2- additive Choquet integrals. In IJCAI, 2020.","title":"Neural representation and learning of hierarchical 2additive Choquet integrals","authors":"Bresson","year":"2020","venue":"IJCAI","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Brown et al., 2020] Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhari- wal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Win- ter, Christopher Hesse, Mark Chen, Eric Sigler, Ma- teusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. Language models are few- shot learners. In NeurIPS, 2020.","title":"Language models are fewshot learners","authors":"B Tom, Benjamin Brown, Nick Mann, Melanie Ryder, Jared Subbiah, Prafulla Kaplan, Arvind Dhariwal, Pranav Neelakantan, Girish Shyam, Amanda Sastry, Sandhini Askell, Ariel Agarwal, Gretchen Herbert-Voss, Tom Krueger, Rewon Henighan, Aditya Child, Daniel M Ramesh, Jeffrey Ziegler, Clemens Wu, Christopher Winter, Mark Hesse, Eric Chen, Mateusz Sigler, Scott Litwin, Benjamin Gray, Jack Chess, Christopher Clark, Sam Berner, Alec Mccandlish, Ilya Radford, Dario Sutskever, Amodei","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Bucila et al., 2006] Cristian Bucila, Rich Caruana, and Alexandru Niculescu-Mizil. Model compression. In KDD, 2006.","title":"Model compression","authors":"Cristian Bucila, Rich Caruana, Alexandru Niculescu-Mizil","year":"2006","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Carvalho et al., 2019] Diogo Carvalho, Eduardo Pereira, and Jaime Cardoso. Machine Learning Interpretability: A Survey on Methods and Metrics. In Electronics, 2019.","title":"Machine Learning Interpretability: A Survey on Methods and Metrics","authors":"Diogo Carvalho, Eduardo Pereira, Jaime Cardoso","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Chen et al., 2019] Chaofan Chen, Oscar Li, Chaofan Tao, Alina Jade Barnett, Jonathan Su, and Cynthia Rudin. This looks like that: Deep learning for interpretable image recognition. In NeurIPS, 2019.","title":"This looks like that: Deep learning for interpretable image recognition","authors":"Chen","year":"2019","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Chen et al., 2020] Zhi Chen, Yijie Bei, and Cynthia Rudin. Concept whitening for interpretable image recognition. In Nature Machine Intelligence, 2020.","title":"Concept whitening for interpretable image recognition","authors":"Zhi Chen, Yijie Bei, Cynthia Rudin","year":"2020","venue":"Nature Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Chen et al., 2022] Qi Chen, Chaorui Deng, and Qi Wu. Learning distinct and representative modes for image cap- tioning. NeurIPS, 2022.","title":"Learning distinct and representative modes for image captioning","authors":"Qi Chen, Chaorui Deng, Qi Wu","year":"2022","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Choquet, 1953] G. Choquet. Theory of capacities. Annales de l'Institut Fourier, 1953.","title":"Theory of capacities","authors":"G Choquet","year":"1953","venue":"Annales de l'Institut Fourier","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Crabbé and van der Schaar, 2022] Jonathan Crabbé and Mi- haela van der Schaar. Concept activation regions: A generalized framework for concept-based explanations. NeurIPS, 2022.","title":"Jonathan Crabbé and Mihaela van der Schaar. Concept activation regions: A generalized framework for concept-based explanations","authors":"Van Crabbé, Der Schaar","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Craven and Shavlik, 1995] Mark W. Craven and Jude W. Shavlik. Extracting tree-structured representations of trained networks. In NeurIPS, 1995.","title":"Extracting tree-structured representations of trained networks","authors":"Mark W Craven, Jude W Shavlik","year":"1995","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Dargan et al., 2020] Shaveta Dargan, Munish Kumar, Maruthi Rohit Ayyagari, and Gulshan Kumar. A survey of deep learning and its applications: a new paradigm to machine learning. ACM in Engineering, 2020.","title":"A survey of deep learning and its applications: a new paradigm to machine learning","authors":"Dargan","year":"2020","venue":"ACM in Engineering","doi":null,"url":null,"internal_url":null},{"position":15,"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, Jakob Uszkoreit, and Neil Houlsby. An image is worth 16x16 words: Trans- formers for image recognition at scale. CoRR, 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, Jakob Uszkoreit, Neil Houlsby","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Fan et al., 2023] Wan-Cyuan Fan, Yen-Chun Chen, Dong- Dong Chen, Yu Cheng, Lu Yuan, and Yu-Chiang Frank Wang. Frido: Feature pyramid diffusion for complex scene image synthesis. AAAI, 2023. [Fel et al., 2023] Thomas Fel, Augusting Picard, Louis Bethune, Thibault Boissin, David Vigouroux, Julien Colin, Rémi Cadène, and Thomas Serre. Craft: Concept recursive activation factorization for explainability. CVPR, 2023.","title":"Craft: Concept recursive activation factorization for explainability","authors":"Wan-Cyuan Fan, Yen-Chun Chen, Dong-Dong Chen, Yu Cheng, Lu Yuan, Yu-Chiang Frank Wang, ; Fel","year":"2023","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Gilpin et al., 2018] Leilani H. Gilpin, David Bau, Ben Z. Yuan, Ayesha Bajwa, Michael Specter, and Lalana Kagal. Explaining explanations: An overview of interpretability of machine learning. In DSAA, 2018.","title":"Explaining explanations: An overview of interpretability of machine learning","authors":"Leilani H Gilpin, David Bau, Ben Z Yuan, Ayesha Bajwa, Michael Specter, Lalana Kagal","year":"2018","venue":"DSAA","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Goebel et al., 2018] Randy Goebel, Ajay Chander, Katha- rina Holzinger, Freddy Lecue, Zeynep Akata, Simone Stumpf, Peter Kieseberg, and Andreas Holzinger. Explain- able ai: The new 42? In Machine Learning and Knowledge Extraction, 2018.","title":"Explainable ai: The new 42?","authors":"Randy Goebel, Ajay Chander, Katharina Holzinger, Freddy Lecue, Zeynep Akata, Simone Stumpf, Peter Kieseberg, Andreas Holzinger","year":"2018","venue":"Machine Learning and Knowledge Extraction","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Grabisch and Labreuche, 2010] M. Grabisch and Ch. Labreuche. A decade of application of the Choquet and Sugeno integrals in multi-criteria decision aid. Annals of Operation Research, 2010.","title":"A decade of application of the Choquet and Sugeno integrals in multi-criteria decision aid","authors":"M Grabisch, Ch Labreuche","year":"2010","venue":"Annals of Operation Research","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Grabisch, 1997] Michel Grabisch. K-order additive discrete fuzzy measures and their representation. Fuzzy Sets Syst., 1997.","title":"K-order additive discrete fuzzy measures and their representation","authors":"Michel Grabisch","year":"1997","venue":"Fuzzy Sets Syst","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Guidotti et al., 2018] R. Guidotti, A. Monreale, S. Ruggieri, F. Turini, F. Giannotti, and D. Pedreschi. A survey of methods for explaining black box models. ACM Comput- ing Surveys, 2018.","title":"A survey of methods for explaining black box models","authors":"R Guidotti, A Monreale, S Ruggieri, F Turini, F Giannotti, D Pedreschi","year":"2018","venue":"ACM Computing Surveys","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[He et al., 2016] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recog- nition. In CVPR, 2016.","title":"Deep residual learning for image recognition","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Herin et al., 2023] Margot Herin, Patrice Perny, and Na- taliya Sokolovska. Learning preference models with sparse interactions of criteria. IJCAI, 2023.","title":"Learning preference models with sparse interactions of criteria","authors":"Margot Herin, Patrice Perny, Nataliya Sokolovska","year":"2023","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2023/421"},{"position":24,"raw":"[Hessel et al., 2021] Jack Hessel, Ari Holtzman, Maxwell Forbes, Ronan Le Bras, and Yejin Choi. Clipscore: A reference-free evaluation metric for image captioning. In EMNLP, 2021.","title":"Clipscore: A reference-free evaluation metric for image captioning","authors":"Hessel","year":"2021","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Hinton et al., 2015] Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. Distilling the knowledge in a neural network. In Deep Learning and Representation Learning Wshop, 2015.","title":"Distilling the knowledge in a neural network","authors":"Geoffrey Hinton, Oriol Vinyals, Jeff Dean","year":"2015","venue":"Deep Learning and Representation Learning Wshop","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Huang and Marques-Silva, 2023] Xuanxiang Huang and Joao Marques-Silva. The inadequacy of shapley values for explainability. CoRR, 2023.","title":"The inadequacy of shapley values for explainability","authors":"Marques-Silva ; Huang, Joao Huang, Marques-Silva","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Kim et al., 2018] Been Kim, Martin Wattenberg, Justin Gilmer, Carrie Cai, James Wexler, Fernanda Viegas, et al. Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav). In ICML, 2018.","title":"Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav)","authors":"Kim","year":"2018","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Kingma and Ba, 2015] Diederik P. Kingma and Jimmy Ba. Adam: A method for stochastic optimization. In ICLR, 2015.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2015","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Koh et al., 2020] Pang Wei Koh, Thao Nguyen, Yew Siang Tang, Stephen Mussmann, Emma Pierson, Been Kim, and Percy Liang. Concept bottleneck models. In ICML, 2020.","title":"Concept bottleneck models","authors":"Pang Wei Koh, Thao Nguyen, Siang Yew, Stephen Tang, Emma Mussmann, Been Pierson, Percy Kim, Liang","year":"2020","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Kusters et al., 2020] Ferdinand Kusters, Peter Schichtel, Sheraz Ahmed, and Andreas Dengel. Conceptual expla- nations of neural network prediction for time series. In IJCNN, 2020.","title":"Conceptual explanations of neural network prediction for time series","authors":"Ferdinand Kusters, Peter Schichtel, Sheraz Ahmed, Andreas Dengel","year":"2020","venue":"IJCNN","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Labreuche and Fossier, 2018] Christophe Labreuche and Simon Fossier. Explaining multi-criteria decision aiding models with an extended shapley value. In IJCAI, 2018.","title":"Explaining multi-criteria decision aiding models with an extended shapley value","authors":"Fossier Labreuche, Christophe Labreuche, Simon Fossier","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/46"},{"position":32,"raw":"[Labreuche et al., 2016] Christophe Labreuche, Eyke Hüllermeier, Peter Vojtas, and Ali Fallah Tehrani. On the Identifiability of Models in Multi-Criteria Preference Learning. In DA2PL, 2016.","title":"On the Identifiability of Models in Multi-Criteria Preference Learning","authors":"Christophe Labreuche, Eyke Hüllermeier, Peter Vojtas, Ali Fallah, Tehrani","year":"2016","venue":"DA2PL","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Lundberg and Lee, 2017] Scott M Lundberg and Su-In Lee. A unified approach to interpreting model predictions. NeurIPS, 2017.","title":"A unified approach to interpreting model predictions","authors":"M Scott, Su-In Lundberg, Lee","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Martyn and Kadziński, 2023] Krzysztof Martyn and Miłosz Kadziński. Deep preference learning for multiple criteria decision analysis. EJOR, 2023.","title":"Deep preference learning for multiple criteria decision analysis","authors":"Krzysztof Martyn, Miłosz Kadziński","year":"2023","venue":"EJOR","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Miller, 1995] George A. Miller. Wordnet: A lexical database for english. In Communications of the ACM, 1995.","title":"Wordnet: A lexical database for english","authors":"George A Miller","year":"1995","venue":"Communications of the ACM","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Molnar, 2020] Christophe Molnar. Interpretable machine learning. molnar, 2020.","title":"Interpretable machine learning","authors":"Christophe Molnar","year":"2020","venue":"molnar","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Murdoch et al., 2019] W. James Murdoch, Chandan Singh, Karl Kumbier, Reza Abbasi-Asl, and Bin Yu. Definitions, methods, and applications in interpretable machine learn- ing. PNAS, 2019.","title":"Definitions, methods, and applications in interpretable machine learning","authors":"W James Murdoch, Chandan Singh, Karl Kumbier, Reza Abbasi-Asl, Bin Yu","year":"2019","venue":"PNAS","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Paszke et al., 2019] Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Köpf, Edward Z. Yang, Zach DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. Pytorch: An imperative style, high- performance deep learning library. CoRR, 2019.","title":"Pytorch: An imperative style, highperformance deep learning library","authors":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Köpf, Edward Z Yang, Zach Devito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, Soumith Chintala","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Radford et al., 2021] Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agar- wal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. Learning transferable visual models from natural language supervi- sion. ICML, 2021.","title":"Learning transferable visual models from natural language supervision","authors":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, Ilya Sutskever","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Ramesh et al., 2021] Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. Zero-shot text-to-image generation. In ICML, 2021.","title":"Zero-shot text-to-image generation","authors":"Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, Ilya Sutskever","year":"2021","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":41,"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 KDD, 2016.","title":"why should I trust you?\" explaining the predictions of any classifier","authors":"Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin","year":"2016","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Rozemberczki et al., 2022] Benedek Rozemberczki, Lau- ren Watson, Peter Bayer, Hao-Tsung Yang, Oliver Kiss, Sebastian Nilsson, and Rik Sarkar. The shapley value in machine learning. In IJCAI, 2022.","title":"The shapley value in machine learning","authors":"Lauren Benedek Rozemberczki, Peter Watson, Hao-Tsung Bayer, Oliver Yang, Sebastian Kiss, Rik Nilsson, Sarkar","year":"2022","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2022/778"},{"position":43,"raw":"[Rudin, 2019] Cynthia Rudin. Stop explaining black box machine learning models for high stakes decisions and use interpretable models instead. Nature Machine Intelligence, 2019.","title":"Stop explaining black box machine learning models for high stakes decisions and use interpretable models instead","authors":"Cynthia Rudin","year":"2019","venue":"Nature Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Saharia et al., 2022] Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily Denton, Seyed Kamyar Seyed Ghasemipour, Burcu Karagol Ayan, S. Sara Mahdavi, Rapha Gontijo Lopes, Tim Salimans, Jonathan Ho, David J Fleet, and Mohammad Norouzi. Photorealistic text-to-image diffusion models with deep language understanding. In NeurIPS, 2022.","title":"Photorealistic text-to-image diffusion models with deep language understanding","authors":"Saharia","year":"2022","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":45,"raw":"[Samek et al., 2022] Wojciech Samek, Grégoire Montavon, Andrea Vedaldi, Lars Kai Hansen, and Klaus-Robert Muller, editors. Explainable AI: Interpreting, Explaining and Visualizing Deep Learning. 2022.","title":"Explainable AI: Interpreting, Explaining and Visualizing Deep Learning","authors":null,"year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":46,"raw":"[Selvaraju et al., 2017] Ramprasaath R Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra. Grad-CAM: Visual Explanations From Deep Networks via Gradient-Based Localization. In ICCV, 2017.","title":"Grad-CAM: Visual Explanations From Deep Networks via Gradient-Based Localization","authors":"Michael Ramprasaath R Selvaraju, Abhishek Cogswell, Ramakrishna Das, Devi Vedantam, Dhruv Parikh, Batra","year":"2017","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":47,"raw":"[Simonyan and Zisserman, 2015] Karen Simonyan and An- drew Zisserman. Very deep convolutional networks for large-scale image recognition. In ACPR, 2015.","title":"Very deep convolutional networks for large-scale image recognition","authors":"Karen Simonyan, Andrew Zisserman","year":"2015","venue":"ACPR","doi":null,"url":null,"internal_url":null},{"position":48,"raw":"[Sobrie et al., 2016] Olivier Sobrie, Mohammed El Amine Lazouni, Saïd Mahmoudi, Vincent Mousseau, and Marc Pirlot. A new decision support model for preanes- thetic evaluation. Computer Methods and Programs in Biomedicine, 2016.","title":"A new decision support model for preanesthetic evaluation","authors":"Sobrie","year":"2016","venue":"Computer Methods and Programs in Biomedicine","doi":null,"url":null,"internal_url":null},{"position":49,"raw":"[Speer et al., 2017] Robyn Speer, Joshua Chin, and Cather- ine Havasi. Conceptnet 5.5: An open multilingual graph of general knowledge. In AAAI, 2017.","title":"Conceptnet 5.5: An open multilingual graph of general knowledge","authors":"Speer","year":"2017","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":50,"raw":"[Tehrani et al., 2012] Ali Fallah Tehrani, Weiwei Cheng, Krzysztof Dembczyński, and Eyke Hüllermeier. Learn- ing monotone nonlinear models using the choquet integral. Machine learning, 2012.","title":"Learning monotone nonlinear models using the choquet integral","authors":"Ali Fallah Tehrani, Weiwei Cheng, Krzysztof Dembczyński, Eyke Hüllermeier","year":"2012","venue":"Machine learning","doi":null,"url":null,"internal_url":null},{"position":51,"raw":"[Wang et al., 2021] Jiaxuan Wang, Jenna Wiens, and Scott Lundberg. Shapley flow: A graph-based approach to in- terpreting model predictions. In AISTATS, 2021.","title":"Shapley flow: A graph-based approach to interpreting model predictions","authors":"Wang","year":"2021","venue":"AISTATS","doi":null,"url":null,"internal_url":null},{"position":52,"raw":"[Winter, 2001] E. Winter. The Shapley value, 2001.","title":"The Shapley value","authors":"E Winter","year":"2001","venue":null,"doi":null,"url":null,"internal_url":null},{"position":53,"raw":"[Xiao et al., 2017] Han Xiao, Kashif Rasul, and Roland Vollgraf. Fashion-mnist: a novel image dataset for bench- marking machine learning algorithms. 2017.","title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms","authors":"Han Xiao, Kashif Rasul, Roland Vollgraf","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":54,"raw":"[Yuksekgonul et al., 2023] Mert Yuksekgonul, Maggie Wang, and James Zou. Post-hoc concept bottleneck methods. ICLR, 2023.","title":"Post-hoc concept bottleneck methods","authors":"Mert Yuksekgonul, Maggie Wang, James Zou","year":"2023","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":55,"raw":"[Zopounidis et al., 2015] Constantin Zopounidis, Emilios Galariotis, Michael Doumpos, Stavroula Sarri, and Kostas Andriosopoulos. Multiple criteria decision aiding for fi- nance: An updated bibliographic survey. EJOR, 2015.","title":"Multiple criteria decision aiding for finance: An updated bibliographic survey","authors":"Constantin Zopounidis, Emilios Galariotis, Michael Doumpos, Stavroula Sarri, Kostas Andriosopoulos","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}