{"type":"ScholarlyArticle","title":"Advocacy Learning: Learning through Competition and Class-Conditional Representations","authors":[{"name":"Ian Fox","slug":"ian-fox","given":"Ian","family":"Fox","affiliation":"Department of Computer Science and Engineering , University of Michigan , Ann Arbor , USA"},{"name":"Jenna Wiens","slug":"jenna-wiens","given":"Jenna","family":"Wiens","affiliation":"Department of Computer Science and Engineering , University of Michigan , Ann Arbor , USA"}],"abstract":"We introduce advocacy learning, a novel supervised training scheme for attention-based classification problems. Advocacy learning relies on a framework consisting of two connected networks: 1) N Advocates (one for each class), each of which outputs an argument in the form of an attention map over the input, and 2) a Judge, which predicts the class label based on these arguments. Each Advocate produces a class-conditional representation with the goal of convincing the Judge that the input example belongs to their class, even when the input belongs to a different class.  Applied to several different classification tasks, we show that advocacy learning can lead to small improvements in classification accuracy over an identical supervised baseline. Though a series of follow-up experiments, we analyze when and how such class-conditional representations improve discriminative performance. Though somewhat counter-intuitive, a framework in which subnetworks are trained to competitively provide evidence in support of their class shows promise, in many cases performing on par with standard learning approaches. This provides a foundation for further exploration into competition and class-conditional representations in supervised learning.","doi":"10.24963/ijcai.2019/321","url":"https://ijcai.org/proceedings/2019/321","pdf":"https://ijcai.org/proceedings/2019/0321.pdf","markdown":"https://ijcai.org/proceedings/2019/321.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/321","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Machine Learning A-L","track":"Main track","number":321,"pages":{"first":2315,"last":2321},"keywords":["Machine Learning: Adversarial Machine Learning","Machine Learning: Deep Learning","Machine Learning: Classification","Machine Learning: Transfer, Adaptation, Multi-task Learning"],"videos":[],"references":[{"position":1,"raw":"[Adam et al., 2017] Paszke Adam, Chintala Soumith, Chanan Gregory, Yang Edward, DeVito Zachary, Lin Zeming, Desmaison Alban, Antiga Luca, and Lerer Adam. Automatic Differentiation in PyTorch. In Autodiff Workshop in the Proceedings of Neural Information Processing Systems, 2017.","title":"Automatic Differentiation in PyTorch","authors":"Adam","year":"2017","venue":"Autodiff Workshop in the Proceedings of Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Badrinarayanan et al., 2017] Vijay Badrinarayanan, Alex Kendall, and Roberto Cipolla. Segnet: A deep convolu- tional encoder-decoder architecture for image segmenta- tion. IEEE transactions on pattern analysis and machine intelligence, 39(12):2481-2495, 2017.","title":"Segnet: A deep convolutional encoder-decoder architecture for image segmentation","authors":"Vijay Badrinarayanan, Alex Kendall, Roberto Cipolla","year":"2017","venue":"IEEE transactions on pattern analysis and machine intelligence","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Desautels et al., 2016] Thomas Desautels, Jacob Calvert, Jana Hoffman, Melissa Jay, Yaniv Kerem, Lisa Shieh, David Shimabukuro, Uli Chettipally, Mitchell D Feldman, Chris Barton, David J Wales, and Ritankar Das. Predic- tion of Sepsis in the Intensive Care Unit With Minimal Electronic Health Record Data: A Machine Learning Ap- proach. JMIR Medical Informatics, 4(3), September 2016.","title":"Prediction of Sepsis in the Intensive Care Unit With Minimal Electronic Health Record Data: A Machine Learning Approach","authors":"Thomas Desautels, Jacob Calvert, Jana Hoffman, Melissa Jay, Yaniv Kerem, Lisa Shieh, David Shimabukuro, Uli Chettipally, Chris Mitchell D Feldman, David J Barton, Ritankar Wales, Das","year":"2016","venue":"JMIR Medical Informatics","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Ghosh et al., 2018] Arnab Ghosh, Viveka Kulharia, Vinay P. Namboodiri, Philip H. S. Torr, and Puneet K. Dokania. Multi-Agent Diverse Generative Adversarial Networks. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 8513-8521, 2018.","title":"Multi-Agent Diverse Generative Adversarial Networks","authors":"Arnab Ghosh, Viveka Kulharia, P Vinay, Namboodiri, H S Philip, Puneet K Torr, Dokania","year":"2018","venue":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Goodfellow et al., 2014] Ian Goodfellow, Jean Pouget- Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Gen- erative adversarial nets. In Advances in Neural Informa- tion Processing Systems, pages 2672-2680, 2014.","title":"Generative adversarial nets","authors":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio","year":"2014","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Harutyunyan et al., 2017] Hrayr Harutyunyan, Hrant Khachatrian, David C. Kale, and Aram Galstyan. Mul- titask Learning and Benchmarking with Clinical Time Series Data. arXiv:1703.07771 [cs, stat], March 2017. arXiv: 1703.07771.","title":"Multitask Learning and Benchmarking with Clinical Time Series Data","authors":"Hrayr Harutyunyan, Hrant Khachatrian, David C Kale, Aram Galstyan","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[He et al., 2016] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recog- nition. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.","title":"Deep residual learning for image recognition","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun","year":"2016","venue":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Irving et al., 2018] Geoffrey Irving, Paul Christiano, and Dario Amodei. AI safety via debate. arXiv:1805.00899 [cs, stat], May 2018. arXiv: 1805.00899.","title":"AI safety via debate","authors":"Geoffrey Irving, Paul Christiano, Dario Amodei","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Itti et al., 1998] L. Itti, C. Koch, and E. Niebur. A model of saliency-based visual attention for rapid scene analysis. IEEE Transactions on Pattern Analysis and Machine In- telligence, 20(11):1254-1259, November 1998.","title":"A model of saliency-based visual attention for rapid scene analysis","authors":"L Itti, C Koch, E Niebur","year":"1998","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Johnson et al., 2016] Alistair EW Johnson, Tom J. Pollard, Lu Shen, H. Lehman Li-wei, Mengling Feng, Mohammad Ghassemi, Benjamin Moody, Peter Szolovits, Leo An- thony Celi, and Roger G. Mark. MIMIC-III, a freely ac- cessible critical care database. Scientific data, 3:160035, 2016.","title":"MIMIC-III, a freely accessible critical care database","authors":"E W Alistair, Tom J Johnson, Lu Pollard, H Lehman Shen, Mengling Li-Wei, Mohammad Feng, Benjamin Ghassemi, Peter Moody, Leo Szolovits, Roger G Anthony Celi, Mark","year":"2016","venue":"Scientific data","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kingma and Ba, 2014] Diederik P. Kingma and Jimmy Ba. Adam: A method for stochastic optimization. Interna- tional Conference for Learning Representations, 2014. [Makhzani and Frey, 2015]","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2014","venue":"International Conference for Learning Representations","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"Alireza Makhzani and Bren- dan J. Frey. Winner-take-all autoencoders. In Advances in Neural Information Processing Systems, pages 2791- 2799, 2015.","title":"Winner-take-all autoencoders","authors":"Alireza Makhzani, Brendan J Frey","year":"2015","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Maslove et al., 2017] David M. Maslove, Francois Lamon- tagne, John C. Marshall, and Daren K. Heyland. A path to precision in the ICU. Critical Care, 21(1):79, April 2017.","title":"A path to precision in the ICU","authors":"David M Maslove, Francois Lamontagne, John C Marshall, Daren K Heyland","year":"2017","venue":"Critical Care","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Odena et al., 2016] Augustus Odena, Vincent Dumoulin, and Chris Olah. Deconvolution and checkerboard artifacts. Distill, 2016.","title":"Deconvolution and checkerboard artifacts","authors":"Odena","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Parascandolo et al., 2018] Giambattista Parascandolo, Niki Kilbertus, Mateo Rojas-Carulla, and Bernhard Schölkopf. Learning Independent Causal Mechanisms. In Interna- tional Conference on Machine Learning, pages 4036- 4044, July 2018.","title":"Learning Independent Causal Mechanisms","authors":"Parascandolo","year":"2018","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Ribeiro et al., 2016] Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. \"Why Should I Trust You?\": Ex- plaining the Predictions of Any Classifier. In Proceedings of the 22Nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '16, pages 1135-1144, New York, NY, USA, 2016. ACM. event- place: San Francisco, California, USA.","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, KDD '16","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Ronneberger et al., 2015] Olaf Ronneberger, Philipp Fis- cher, and Thomas Brox. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer- assisted intervention, pages 234-241. Springer, 2015.","title":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. U-net: Convolutional networks for biomedical image segmentation","authors":"Ronneberger","year":"2015","venue":"International Conference on Medical image computing and computerassisted intervention","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Sabour et al., 2017] Sara Sabour, Nicholas Frosst, and Ge- offrey E. Hinton. Dynamic routing between capsules. In Advances in Neural Information Processing Systems, pages 3856-3866, 2017.","title":"Dynamic routing between capsules","authors":"Sara Sabour, Nicholas Frosst, Geoffrey E Hinton","year":"2017","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Silver et al., 2017] David Silver, Julian Schrittwieser, Karen Simonyan, Ioannis Antonoglou, Aja Huang, Arthur Guez, Thomas Hubert, Lucas Baker, Matthew Lai, Adrian Bolton, Yutian Chen, Timothy Lillicrap, Fan Hui, Laurent Sifre, George van den Driessche, Thore Graepel, and Demis Hassabis. Mastering the game of Go without human knowledge. Nature, 550(7676):354-359, October 2017.","title":"Mastering the game of Go without human knowledge","authors":"David Silver, Julian Schrittwieser, Karen Simonyan, Ioannis Antonoglou, Aja Huang, Arthur Guez, Thomas Hubert, Lucas Baker, Matthew Lai, Adrian Bolton, Yutian Chen, Timothy Lillicrap, Fan Hui, Laurent Sifre, George Van Den Driessche, Thore Graepel, Demis Hassabis","year":"2017","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Vaswani et al., 2017] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need. In Advances in neural information processing sys- tems, pages 5998-6008, 2017.","title":"Attention is all you need","authors":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, Illia Polosukhin","year":"2017","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Xiao et al., 2017] Han Xiao, Kashif Rasul, and Roland Vollgraf. Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms. arXiv:1708.07747 [cs, stat], August 2017. arXiv: 1708.07747.","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}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}