{"type":"ScholarlyArticle","title":"Learning Unforgotten Domain-Invariant Representations for Online Unsupervised Domain Adaptation","authors":[{"name":"Cheng Feng","slug":"cheng-feng","given":"Cheng","family":"Feng","affiliation":"Fujitsu R&D Center , Co. , LTD"},{"name":"Chaoliang Zhong","slug":"chaoliang-zhong","given":"Chaoliang","family":"Zhong","affiliation":"Fujitsu R&D Center , Co. , LTD"},{"name":"Jie Wang","slug":"jie-wang","given":"Jie","family":"Wang","affiliation":"Fujitsu R&D Center , Co. , LTD"},{"name":"Ying Zhang","slug":"ying-zhang","given":"Ying","family":"Zhang","affiliation":"Fujitsu R&D Center , Co. , LTD"},{"name":"Jun Sun","slug":"jun-sun","given":"Jun","family":"Sun","affiliation":"Fujitsu R&D Center , Co. , LTD"},{"name":"Yasuto Yokota","slug":"yasuto-yokota","given":"Yasuto","family":"Yokota","affiliation":"Fujitsu LTD {fengcheng ,"}],"abstract":"Existing unsupervised domain adaptation (UDA) studies focus on transferring knowledge in an offline manner. However, many tasks involve online requirements, especially in real-time systems. In this paper, we discuss Online UDA (OUDA) which assumes that the target samples are arriving sequentially as a small batch. OUDA tasks are challenging for prior UDA methods since online training suffers from catastrophic forgetting which leads to poor generalization. Intuitively, a good memory is a crucial factor in the success of OUDA. We formalize this intuition theoretically with a generalization bound where the OUDA target error can be bounded by the source error, the domain discrepancy distance, and a novel metric on forgetting in continuous online learning. Our theory illustrates the tradeoffs inherent in learning and remembering representations for OUDA. To minimize the proposed forgetting metric, we propose a novel source feature distillation (SFD) method which utilizes the source-only model as a teacher to guide the online training. In the experiment, we modify three UDA algorithms, i.e., DANN, CDAN, and MCC, and evaluate their performance on OUDA tasks with real-world datasets. By applying SFD, the performance of all baselines is significantly improved.","doi":"10.24963/ijcai.2022/410","url":"https://ijcai.org/proceedings/2022/410","pdf":"https://ijcai.org/proceedings/2022/0410.pdf","markdown":"https://ijcai.org/proceedings/2022/410.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/410","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Machine Learning","track":"Main Track","number":410,"pages":{"first":2958,"last":2965},"keywords":["Machine Learning: Learning Theory","Machine Learning: Unsupervised Learning","Machine Learning: Online Learning","Machine Learning: Theory of Deep Learning"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986454","length_sec":76,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984597","length_sec":355,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Ben-David et al., 2007] Shai Ben-David, John Blitzer, Koby Crammer, and Fernando Pereira. Analysis of representations for domain adaptation. In Advances in neural information processing systems, pages 137-144, 2007.","title":"Analysis of representations for domain adaptation","authors":"Shai Ben-David, John Blitzer, Koby Crammer, Fernando Pereira","year":"2007","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Blitzer et al., 2007] John Blitzer, Koby Crammer, Alex Kulesza, Fernando Pereira, and Jennifer Wortman. Learn- ing bounds for domain adaptation. Advances in neural in- formation processing systems, 20, 2007.","title":"Learning bounds for domain adaptation","authors":"John Blitzer, Koby Crammer, Alex Kulesza, Fernando Pereira, Jennifer Wortman","year":"2007","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Ganin et al., 2016] Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, Franc ¸ois Laviolette, Mario Marchand, and Victor Lempitsky. Domain-adversarial training of neural networks. The Journal of Machine Learning Research, 17(1):2096-2030, 2016.","title":"Domain-adversarial training of neural networks","authors":"Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, Mario Franc ¸ois Laviolette, Victor Marchand, Lempitsky","year":"2016","venue":"The Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Hajifar and Sun, 2021] Sahand Hajifar and Hongyue Sun. Online domain adaptation for continuous cross-subject liver viability evaluation based on irregular thermal data. IISE Transactions, pages 1-12, 2021.","title":"Sahand Hajifar and Hongyue Sun. Online domain adaptation for continuous cross-subject liver viability evaluation based on irregular thermal data","authors":"Sun Hajifar","year":"2021","venue":"IISE Transactions","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[He et al., 2016] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recog- nition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770-778, 2016.","title":"Deep residual learning for image recognition","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun","year":"2016","venue":"Proceedings of the IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Jin et al., 2020] Ying Jin, Ximei Wang, Mingsheng Long, and Jianmin Wang. Minimum class confusion for versatile domain adaptation. In European Conference on Computer Vision, pages 464-480. Springer, 2020.","title":"Minimum class confusion for versatile domain adaptation","authors":"Ying Jin, Ximei Wang, Mingsheng Long, Jianmin Wang","year":"2020","venue":"European Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Kirkpatrick et al., 2017] James Kirkpatrick, Razvan Pas- canu, Neil Rabinowitz, Joel Veness, Guillaume Des- jardins, Andrei A Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, et al. Overcom- ing catastrophic forgetting in neural networks. Proceed- ings of the national academy of sciences, 114(13):3521- 3526, 2017.","title":"Overcoming catastrophic forgetting in neural networks","authors":"James Kirkpatrick, Razvan Pascanu, Neil Rabinowitz, Joel Veness, Guillaume Desjardins, Andrei A Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska","year":"2017","venue":"Proceedings of the national academy of sciences","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Long et al., 2017] Mingsheng Long, Zhangjie Cao, Jianmin Wang, and Michael I Jordan. Conditional adversarial do- main adaptation. arXiv preprint arXiv:1705.10667, 2017.","title":"Conditional adversarial domain adaptation","authors":"Mingsheng Long, Zhangjie Cao, Jianmin Wang, Michael I Jordan","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Lopez-Paz and Ranzato, 2017] David Lopez-Paz and Marc'Aurelio Ranzato. Gradient episodic memory for continual learning. Advances in neural information processing systems, 30, 2017.","title":"Gradient episodic memory for continual learning","authors":"David Lopez, - Paz, Marc'aurelio Ranzato","year":"2017","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Maaten and Hinton, 2008] Laurens van der Maaten and Ge- offrey Hinton. Visualizing data using t-sne. Journal of machine learning research, 9(Nov):2579-2605, 2008.","title":"Laurens van der Maaten and Geoffrey Hinton","authors":"Hinton Maaten","year":"2008","venue":"Journal of machine learning research","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Mancini et al., 2018] Massimiliano Mancini, Hakan Karaoguz, Elisa Ricci, Patric Jensfelt, and Barbara Caputo. Kitting in the wild through online domain adap- tation. In 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 1103-1109. IEEE, 2018.","title":"Kitting in the wild through online domain adaptation","authors":"Massimiliano Mancini, Hakan Karaoguz, Elisa Ricci, Patric Jensfelt, Barbara Caputo","year":"2018","venue":"IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Mao et al., 2017] Xudong Mao, Qing Li, Haoran Xie, Ray- mond YK Lau, Zhen Wang, and Stephen Paul Smolley. Least squares generative adversarial networks. In Proceed- ings of the IEEE international conference on computer vi- sion, pages 2794-2802, 2017.","title":"Least squares generative adversarial networks","authors":"Xudong Mao, Qing Li, Haoran Xie, Raymond Yk Lau, Zhen Wang, Stephen Paul Smolley","year":"2017","venue":"Proceedings of the IEEE international conference on computer vision","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[McMahan et al., 2013] H Brendan McMahan, Gary Holt, David Sculley, Michael Young, Dietmar Ebner, Julian Grady, Lan Nie, Todd Phillips, Eugene Davydov, Daniel Golovin, et al. Ad click prediction: a view from the trenches. In Proceedings of the 19th ACM SIGKDD in- ternational conference on Knowledge discovery and data mining, pages 1222-1230, 2013.","title":"Ad click prediction: a view from the trenches","authors":"Gary H Brendan Mcmahan, David Holt, Michael Sculley, Dietmar Young, Julian Ebner, Lan Grady, Todd Nie, Eugene Phillips, Davydov, Daniel Golovin","year":"2013","venue":"Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Moon et al., 2020] JH Moon, Debasmit Das, and CS George Lee. Multi-step online unsupervised domain adaptation. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 41172-41576. IEEE, 2020.","title":"Multi-step online unsupervised domain adaptation","authors":"Moon","year":"2020","venue":"ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Pan and Yang, 2009] Sinno Jialin Pan and Qiang Yang. A survey on transfer learning. IEEE Transactions on knowl- edge and data engineering, 22(10):1345-1359, 2009.","title":"A survey on transfer learning","authors":"Jialin Sinno, Qiang Pan, Yang","year":"2009","venue":"IEEE Transactions on knowledge and data engineering","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Rolnick et al., 2019] David Rolnick, Arun Ahuja, Jonathan Schwarz, Timothy Lillicrap, and Gregory Wayne. Expe- rience replay for continual learning. Advances in Neural Information Processing Systems, 32, 2019.","title":"Experience replay for continual learning","authors":"David Rolnick, Arun Ahuja, Jonathan Schwarz, Timothy Lillicrap, Gregory Wayne","year":"2019","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Saenko et al., 2010] Kate Saenko, Brian Kulis, Mario Fritz, and Trevor Darrell. Adapting visual category models to new domains. In European conference on computer vision, pages 213-226. Springer, 2010.","title":"Adapting visual category models to new domains","authors":"Saenko","year":"2010","venue":"European conference on computer vision","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Shu et al., 2018] Rui Shu, Hung H Bui, Hirokazu Narui, and Stefano Ermon. A dirt-t approach to unsupervised do- main adaptation. arXiv preprint arXiv:1802.08735, 2018.","title":"A dirt-t approach to unsupervised domain adaptation","authors":"Rui Shu, Hung H Bui, Hirokazu Narui, Stefano Ermon","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Tachet des Combes et al., 2020] Remi Tachet des Combes, Han Zhao, Yu-Xiang Wang, and Geoffrey J Gordon. Do- main adaptation with conditional distribution matching and generalized label shift. Advances in Neural Informa- tion Processing Systems, 33, 2020.","title":"Domain adaptation with conditional distribution matching and generalized label shift","authors":"Tachet Des, Combes","year":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Tzeng et al., 2017] Eric Tzeng, Judy Hoffman, Kate Saenko, and Trevor Darrell. Adversarial discriminative domain adaptation. In Proceedings of the IEEE confer- ence on computer vision and pattern recognition, pages 7167-7176, 2017.","title":"Adversarial discriminative domain adaptation","authors":"Eric Tzeng, Judy Hoffman, Kate Saenko, Trevor Darrell","year":"2017","venue":"Proceedings of the IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Venkateswara et al., 2017] Hemanth Venkateswara, Jose Eusebio, Shayok Chakraborty, and Sethuraman Pan- chanathan. Deep hashing network for unsupervised do- main adaptation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 5018- 5027, 2017.","title":"Deep hashing network for unsupervised domain adaptation","authors":"Hemanth Venkateswara, Jose Eusebio, Shayok Chakraborty, Sethuraman Panchanathan","year":"2017","venue":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Zhang et al., 2019] Yuchen Zhang, Tianle Liu, Mingsheng Long, and Michael Jordan. Bridging theory and algorithm for domain adaptation. In International Conference on Machine Learning, pages 7404-7413. PMLR, 2019.","title":"Bridging theory and algorithm for domain adaptation","authors":"Yuchen Zhang, Tianle Liu, Mingsheng Long, Michael Jordan","year":"2019","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Zhao et al., 2019] Han Zhao, Remi Tachet des Combes, Kun Zhang, and Geoffrey J Gordon. On learning invari- ant representation for domain adaptation. arXiv preprint arXiv:1901.09453, 2019.","title":"On learning invariant representation for domain adaptation","authors":"Han Zhao, Remi Tachet Des Combes, Kun Zhang, Geoffrey J Gordon","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}