{"type":"ScholarlyArticle","title":"Deep Multi-Task Learning with Adversarial-and-Cooperative Nets","authors":[{"name":"Pei Yang","slug":"pei-yang","given":"Pei","family":"Yang","affiliation":"South China University of Technology; Arizona State University"},{"name":"Qi Tan","slug":"qi-tan","given":"Qi","family":"Tan","affiliation":"South China Normal University"},{"name":"Jieping Ye","slug":"jieping-ye","given":"Jieping","family":"Ye","affiliation":"University of Michigan"},{"name":"Hanghang Tong","slug":"hanghang-tong","given":"Hanghang","family":"Tong","affiliation":"Arizona State University"},{"name":"Jingrui He","slug":"jingrui-he","given":"Jingrui","family":"He","affiliation":"Arizona State University"}],"abstract":"In this paper, we propose a deep multi-Task learning model based on Adversarial-and-COoperative nets (TACO). The goal is to use an adversarial-and-cooperative strategy to decouple the task-common and task-specific knowledge, facilitating the fine-grained knowledge sharing among tasks. TACO accommodates multiple game players, i.e., feature extractors, domain discriminator, and tri-classifiers. They play the MinMax games adversarially and cooperatively to distill the task-common and task-specific features, while respecting their discriminative structures. Moreover, it adopts a divide-and-combine strategy to leverage the decoupled multi-view information to further improve the generalization performance of the model. The experimental results show that our proposed method significantly outperforms the state-of-the-art algorithms on the benchmark datasets in both multi-task learning and semi-supervised domain adaptation scenarios.","doi":"10.24963/ijcai.2019/566","url":"https://ijcai.org/proceedings/2019/566","pdf":"https://ijcai.org/proceedings/2019/0566.pdf","markdown":"https://ijcai.org/proceedings/2019/566.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/566","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 M-Z","track":"Main track","number":566,"pages":{"first":4078,"last":4084},"keywords":["Machine Learning: Transfer, Adaptation, Multi-task Learning","Machine Learning: Adversarial Machine Learning"],"videos":[],"references":[{"position":1,"raw":"[Argyriou et al., 2008] Andreas Argyriou, Theodoros Evgeniou, and Massimiliano Pontil. Convex multi-task feature learning. Machine Learning, 73(3):243-272, 2008.","title":"Convex multi-task feature learning","authors":"Andreas Argyriou, Theodoros Evgeniou, Massimiliano Pontil","year":"2008","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Blitzer et al., 2007] John Blitzer, Mark Dredze, and Fernando Pereira. Biographies, bollywood, boom-boxes and blenders: Do- main adaptation for sentiment classification. In ACL, 2007.","title":"Biographies, bollywood, boom-boxes and blenders: Domain adaptation for sentiment classification","authors":"John Blitzer, Mark Dredze, Fernando Pereira","year":"2007","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bousmalis et al., 2016] Konstantinos Bousmalis, George Trigeor- gis, Nathan Silberman, Dilip Krishnan, and Dumitru Erhan. Do- main separation networks. In NIPS, pages 343-351, 2016.","title":"Domain separation networks","authors":"Konstantinos Bousmalis, George Trigeorgis, Nathan Silberman, Dilip Krishnan, Dumitru Erhan","year":"2016","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Caruana, 1993] Rich Caruana. Multitask learning: A knowledge- based source of inductive bias. In ICML, pages 41-48, 1993.","title":"Multitask learning: A knowledgebased source of inductive bias","authors":"Rich Caruana","year":"1993","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chen et al., 2013] Jianhui Chen, Lei Tang, Jun Liu, and Jieping Ye. A convex formulation for learning a shared predictive struc- ture from multiple tasks. IEEE Trans. Pattern Anal. Mach. Intell., 35(5):1025-1038, 2013.","title":"A convex formulation for learning a shared predictive structure from multiple tasks","authors":"Jianhui Chen, Lei Tang, Jun Liu, Jieping Ye","year":"2013","venue":"IEEE Trans. Pattern Anal. Mach. Intell","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Donahue et al., 2014] Jeff Donahue, Yangqing Jia, Oriol Vinyals, Judy Hoffman, Ning Zhang, Eric Tzeng, and Trevor Darrell. De- CAF: A deep convolutional activation feature for generic visual recognition. In ICML, pages 647-655, 2014.","title":"De-CAF: A deep convolutional activation feature for generic visual recognition","authors":"Jeff Donahue, Yangqing Jia, Oriol Vinyals, Judy Hoffman, Ning Zhang, Eric Tzeng, Trevor Darrell","year":"2014","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Ganin and Lempitsky, 2015] Yaroslav Ganin and Victor S. Lem- pitsky. Unsupervised domain adaptation by backpropagation. In ICML, pages 1180-1189, 2015.","title":"Unsupervised domain adaptation by backpropagation","authors":"Yaroslav Ganin, S Victor","year":"2015","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Ghifary et al., 2014] Muhammad Ghifary, W. Bastiaan Kleijn, and Mengjie Zhang. Domain adaptive neural networks for object recognition. In PRICAI, pages 898-904, 2014.","title":"Domain adaptive neural networks for object recognition","authors":"W Muhammad Ghifary, Mengjie Bastiaan Kleijn, Zhang","year":"2014","venue":"PRICAI","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Goodfellow et al., 2014] Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron C. Courville, and Yoshua Bengio. Generative adversari- al nets. In NIPS, pages 2672-2680, 2014.","title":"Generative adversarial nets","authors":"Ian J Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron C Courville, Yoshua Bengio","year":"2014","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Han and Zhang, 2015] Lei Han and Yu Zhang. Learning tree struc- ture in multi-task learning. In KDD, pages 397-406, 2015.","title":"Learning tree structure in multi-task learning","authors":"Zhang ; ] Lei Han, Yu Han, Zhang","year":"2015","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Hoffman et al., 2018] Judy Hoffman, Eric Tzeng, Taesung Park, Jun-Yan Zhu, Phillip Isola, Kate Saenko, Alexei A. Efros, and Trevor Darrell. Cycada: Cycle-consistent adversarial domain adaptation. In ICML, pages 1994-2003, 2018.","title":"Cycada: Cycle-consistent adversarial domain adaptation","authors":"Judy Hoffman, Eric Tzeng, Taesung Park, Jun-Yan Zhu, Phillip Isola, Kate Saenko, Alexei A Efros, Trevor Darrell","year":"2018","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Ji and Ye, 2009] Shuiwang Ji and Jieping Ye. An accelerated gra- dient method for trace norm minimization. In ICML, pages 457- 464, 2009.","title":"Shuiwang Ji and Jieping Ye. An accelerated gradient method for trace norm minimization","authors":"Ji, Ye","year":"2009","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Jia et al., 2014] Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross Girshick, Sergio Guadar- rama, and Trevor Darrell. Caffe: Convolutional architecture for fast feature embedding. arXiv preprint:1408.5093, 2014.","title":"Caffe: Convolutional architecture for fast feature embedding","authors":"Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross Girshick, Sergio Guadarrama, Trevor Darrell","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Krizhevsky et al., 2012] Alex Krizhevsky, Ilya Sutskever, and Ge- offrey E. Hinton. Imagenet classification with deep convolutional neural networks. In NIPS, pages 1106-1114, 2012.","title":"Imagenet classification with deep convolutional neural networks","authors":"Alex Krizhevsky, Ilya Sutskever, Geoffrey E Hinton","year":"2012","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[LeCun et al., 2015] Yann LeCun, Yoshua Bengio, and Geoffrey E. Hinton. Deep learning. Nature, 521(7553):436-444, 2015.","title":"Deep learning","authors":"Yann Lecun, Yoshua Bengio, Geoffrey E Hinton","year":"2015","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Lee et al., 2016] Giwoong Lee, Eunho Yang, and Sung Ju Hwang. Asymmetric multi-task learning based on task relatedness and loss. In ICML, pages 230-238, 2016.","title":"Asymmetric multi-task learning based on task relatedness and loss","authors":"Lee","year":"2016","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Long et al., 2015] Mingsheng Long, Yue Cao, Jianmin Wang, and Michael I. Jordan. Learning transferable features with deep adap- tation networks. In ICML, pages 97-105, 2015.","title":"Learning transferable features with deep adaptation networks","authors":"Mingsheng Long, Yue Cao, Jianmin Wang, Michael I Jordan","year":"2015","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Long et al., 2017a] Mingsheng Long, Zhangjie Cao, Jianmin Wang, and Philip S. Yu. Learning multiple tasks with multilinear relationship networks. In NIPS, pages 1593-1602, 2017.","title":"Learning multiple tasks with multilinear relationship networks","authors":"Long","year":"2017","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Long et al., 2017b] Mingsheng Long, Han Zhu, Jianmin Wang, and Michael I. Jordan. Deep transfer learning with joint adap- tation networks. In ICML, pages 2208-2217, 2017.","title":"Deep transfer learning with joint adaptation networks","authors":"Long","year":"2017","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Pei et al., 2018] Zhongyi Pei, Zhangjie Cao, Mingsheng Long, and Jianmin Wang. Multi-adversarial domain adaptation. In AAAI, 2018.","title":"Multi-adversarial domain adaptation","authors":"Zhongyi Pei, Zhangjie Cao, Mingsheng Long, Jianmin Wang","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Ruder, 2017] Sebastian Ruder. An overview of multi-task learning in deep neural networks. CoRR, abs/1706.05098, 2017.","title":"An overview of multi-task learning in deep neural networks","authors":"Sebastian Ruder","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Saenko et al., 2010] Kate Saenko, Brian Kulis, Mario Fritz, and Trevor Darrell. Adapting visual category models to new domains. In ECCV, pages 213-226, 2010.","title":"Adapting visual category models to new domains","authors":"Saenko","year":"2010","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Simonyan and Zisserman, 2015] Karen Simonyan and Andrew Zisserman. Very deep convolutional networks for large-scale im- age recognition. In ICLR, pages 1106-1114, 2015.","title":"Very deep convolutional networks for large-scale image recognition","authors":"Karen Simonyan, Andrew Zisserman","year":"2015","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Tzeng et al., 2014] Eric Tzeng, Judy Hoffman, Ning Zhang, Kate Saenko, and Trevor Darrell. Deep domain confusion: Maximiz- ing for domain invariance. CoRR, abs/1412.3474, 2014.","title":"Deep domain confusion: Maximizing for domain invariance","authors":"Eric Tzeng, Judy Hoffman, Ning Zhang, Kate Saenko, Trevor Darrell","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Tzeng et al., 2015] Eric Tzeng, Judy Hoffman, Trevor Darrell, and Kate Saenko. Simultaneous deep transfer across domains and tasks. In ICCV, pages 4068-4076, 2015.","title":"Simultaneous deep transfer across domains and tasks","authors":"Eric Tzeng, Judy Hoffman, Trevor Darrell, Kate Saenko","year":"2015","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Tzeng et al., 2017] Eric Tzeng, Judy Hoffman, Kate Saenko, and Trevor Darrell. Adversarial discriminative domain adaptation. In CVPR, pages 2962-2971, 2017.","title":"Adversarial discriminative domain adaptation","authors":"Eric Tzeng, Judy Hoffman, Kate Saenko, Trevor Darrell","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Venkateswara et al., 2017] Hemanth Venkateswara, Jose Eusebio, Shayok Chakraborty, and Sethuraman Panchanathan. Deep hash- ing network for unsupervised domain adaptation. In CVPR, pages 5385-5394, 2017.","title":"Deep hashing network for unsupervised domain adaptation","authors":"Hemanth Venkateswara, Jose Eusebio, Shayok Chakraborty, Sethuraman Panchanathan","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Yang and Hospedales, 2017] Yongxin Yang and Timothy M. Hospedales. Deep multi-task representation learning: A tensor factorisation approach. In ICLR, 2017.","title":"Deep multi-task representation learning: A tensor factorisation approach","authors":"Yang, Hospedales ;, Yongxin Yang, Timothy M Hospedales","year":"2017","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Yang et al., 2017] Pei Yang, Qi Tan, and Jingrui He. Multi-task function-on-function regression with co-grouping structured s- parsity. In KDD, pages 1255-1264, 2017.","title":"Multi-task function-on-function regression with co-grouping structured sparsity","authors":"Pei Yang, Qi Tan, Jingrui He","year":"2017","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Yang et al., 2019] Pei Yang, Qi Tan, Hanghang Tong, and Jingrui He. Task-adversarial co-generative nets. In KDD, 2019.","title":"Task-adversarial co-generative nets","authors":"Pei Yang, Qi Tan, Hanghang Tong, Jingrui He","year":"2019","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Zhang and Yeung, 2010] Yu Zhang and Dit-Yan Yeung. A convex formulation for learning task relationships in multi-task learning. In UAI, pages 733-442, 2010.","title":"A convex formulation for learning task relationships in multi-task learning","authors":"Yu Zhang, Dit-Yan Yeung","year":"2010","venue":"UAI","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zhou et al., 2011] Jiayu Zhou, Jianhui Chen, and Jieping Ye. Clus- tered multi-task learning via alternating structure optimization. In NIPS, pages 702-710, 2011.","title":"Clustered multi-task learning via alternating structure optimization","authors":"Jiayu Zhou, Jianhui Chen, Jieping Ye","year":"2011","venue":"NIPS","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}