{"type":"ScholarlyArticle","title":"Partial Optimal Transport Based Out-of-Distribution Detection for Open-Set Semi-Supervised Learning","authors":[{"name":"Yilong Ren","slug":"yilong-ren","given":"Yilong","family":"Ren","affiliation":"School of Artificial Intelligence and Data Science , University of Science and Technology of China; Data Darkness Lab , MIRACLE Center , Suzhou Institute for Advanced Research , USTC"},{"name":"Chuanwen Feng","slug":"chuanwen-feng","given":"Chuanwen","family":"Feng","affiliation":"School of Computer Science , University of Science and Technology of China (USTC); Data Darkness Lab , MIRACLE Center , Suzhou Institute for Advanced Research , USTC"},{"name":"Xike Xie","slug":"xike-xie","given":"Xike","family":"Xie","affiliation":"School of Biomedical Engineering , University of Science and Technology of China (USTC); Data Darkness Lab , MIRACLE Center , Suzhou Institute for Advanced Research , USTC"},{"name":"S. Kevin Zhou","slug":"s-kevin-zhou","given":"S. Kevin","family":"Zhou","affiliation":"School of Biomedical Engineering , University of Science and Technology of China (USTC); Data Darkness Lab , MIRACLE Center , Suzhou Institute for Advanced Research , USTC; Key Laboratory of Precision and Intelligent Chemistry , USTC"}],"abstract":"Semi-supervised learning (SSL) is a machine learning paradigm that utilizes both labeled and unlabeled data to enhance the performance of learning tasks. However, SSL methods operate under the assumption that the label spaces of labeled and unlabeled data are identical, which may not hold in open-world applications. In such scenarios, the unlabeled data may contain novel categories that were not presented in the labeled training data, essentially outliers. This specific challenge is referred to as the Open-set Semi-supervised Learning (OSSL) problem. In OSSL, a pivotal concern is the detection of out-of-distribution (OOD) samples within unlabeled data. Existing methods often struggle to provide effective OOD detection strategies, especially when dealing with datasets comprising a large number of training categories. In response to this challenge, we model the OOD detection problem in OSSL as a partial optimal transport (POT) problem. With POT theory, we devise a mass score function to measure the likelihood of a sample being an outlier, which enables a binary classifier for OOD detection. Further, we put forward an OOD loss, enabling the seamless integration of the binary classifier and off-the-shelf SSL methods under OSSL settings, all within an end-to-end training framework. We extensively evaluate our proposal under various datasets and OSSL configurations, consistently demonstrating the superior performance of our proposal. Codes are available at https://github.com/ryl0427/Code_for_POT_OSSL.","doi":"10.24963/ijcai.2024/536","url":"https://ijcai.org/proceedings/2024/536","pdf":"https://ijcai.org/proceedings/2024/0536.pdf","markdown":"https://ijcai.org/proceedings/2024/536.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/536","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":536,"pages":{"first":4851,"last":4859},"keywords":["Machine Learning: ML: Semi-supervised learning","Machine Learning: ML: Optimization","Machine Learning: ML: Robustness"],"videos":[],"references":[{"position":1,"raw":"[Bauschke and Lewis, 2000] Heinz H Bauschke and Adrian S Lewis. Dykstras algorithm with bregman projec- tions: A convergence proof. Optimization, 48(4):409-427, 2000.","title":"Dykstras algorithm with bregman projections: A convergence proof","authors":"H Heinz, Adrian S Bauschke, Lewis","year":"2000","venue":"Optimization","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Benamou et al., 2015] Jean-David Benamou, Guillaume Carlier, Marco Cuturi, Luca Nenna, and Gabriel Peyré. Iterative bregman projections for regularized transporta- tion problems. SIAM Journal on Scientific Computing, 37(2):A1111-A1138, 2015.","title":"Iterative bregman projections for regularized transportation problems","authors":"Jean-David Benamou, Guillaume Carlier, Marco Cuturi, Luca Nenna, Gabriel Peyré","year":"2015","venue":"SIAM Journal on Scientific Computing","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Berthelot et al., 2019] David Berthelot, Nicholas Carlini, Ian Goodfellow, Nicolas Papernot, Avital Oliver, and Colin A Raffel. Mixmatch: A holistic approach to semi- supervised learning. Advances in neural information pro- cessing systems, 32, 2019.","title":"Mixmatch: A holistic approach to semisupervised learning","authors":"David Berthelot, Nicholas Carlini, Ian Goodfellow, Nicolas Papernot, Avital Oliver, Colin A Raffel","year":"2019","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bickel et al., 2009] Steffen Bickel, Michael Brückner, and Tobias Scheffer. Discriminative learning under covariate shift. Journal of Machine Learning Research, 10(9), 2009.","title":"Discriminative learning under covariate shift","authors":"Steffen Bickel, Michael Brückner, Tobias Scheffer","year":"2009","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Caffarelli and McCann, 2010] Luis A Caffarelli and Robert J McCann. Free boundaries in optimal trans- port and monge-ampere obstacle problems. Annals of mathematics, pages 673-730, 2010.","title":"Free boundaries in optimal transport and monge-ampere obstacle problems","authors":"A Luis, Robert J Caffarelli, Mccann","year":"2010","venue":"Annals of mathematics","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Caruana, 1997] Rich Caruana. Multitask learning. Machine learning, 28:41-75, 1997.","title":"Multitask learning","authors":"Caruana","year":"1997","venue":"Machine learning","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Chapel et al., 2020] Laetitia Chapel, Mokhtar Z Alaya, and Gilles Gasso. Partial optimal tranport with applications on positive-unlabeled learning. Advances in Neural Informa- tion Processing Systems, 33:2903-2913, 2020.","title":"Partial optimal tranport with applications on positive-unlabeled learning","authors":"Laetitia Chapel, Gilles Mokhtar Z Alaya, Gasso","year":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Chen et al., 2020] Yanbei Chen, Xiatian Zhu, Wei Li, and Shaogang Gong. Semi-supervised learning under class distribution mismatch. In Proceedings of the AAAI Con- ference on Artificial Intelligence, volume 34, pages 3569- 3576, 2020.","title":"Semi-supervised learning under class distribution mismatch","authors":"Chen","year":"2020","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Courty et al., 2014] Nicolas Courty, Remi Flamary, Alain Rakotomamonjy, and Devis Tuia. Optimal transport for domain adaptation. In NIPS 2014, Workshop on Optimal Transport and Machine Learning, 2014.","title":"Optimal transport for domain adaptation","authors":"Nicolas Courty, Remi Flamary, Alain Rakotomamonjy, Devis Tuia","year":"2014","venue":"NIPS 2014, Workshop on Optimal Transport and Machine Learning","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Cuturi, 2013] Marco Cuturi. Sinkhorn distances: Light- speed computation of optimal transport. Advances in neu- ral information processing systems, 26, 2013.","title":"Sinkhorn distances: Lightspeed computation of optimal transport","authors":"Marco Cuturi","year":"2013","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Dykstra, 1983] Richard L Dykstra. An algorithm for re- stricted least squares regression. Journal of the American Statistical Association, 78(384):837-842, 1983.","title":"An algorithm for restricted least squares regression","authors":"Richard L Dykstra","year":"1983","venue":"Journal of the American Statistical Association","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Fan et al., 2023] Yue Fan, Anna Kukleva, Dengxin Dai, and Bernt Schiele. Ssb: Simple but strong baseline for boost- ing performance of open-set semi-supervised learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 16068-16078, 2023.","title":"Ssb: Simple but strong baseline for boosting performance of open-set semi-supervised learning","authors":"Anna Yue Fan, Dengxin Kukleva, Bernt Dai, Schiele","year":"2023","venue":"Proceedings of the IEEE/CVF International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Feng et al., 2023] Chuanwen Feng, Yilong Ren, and Xike Xie. Ot-filter: An optimal transport filter for learning with noisy labels. In Proceedings of the IEEE/CVF Confer- ence on Computer Vision and Pattern Recognition, pages 16164-16174, 2023.","title":"Ot-filter: An optimal transport filter for learning with noisy labels","authors":"Feng","year":"2023","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Figalli and Glaudo, 2021] Alessio Figalli and Federico Glaudo. An invitation to optimal transport, Wasserstein distances, and gradient flows. 2021.","title":"An invitation to optimal transport, Wasserstein distances, and gradient flows","authors":"Alessio Figalli, Federico Glaudo","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Guo et al., 2020] Lan-Zhe Guo, Zhen-Yu Zhang, Yuan Jiang, Yu-Feng Li, and Zhi-Hua Zhou. Safe deep semi- supervised learning for unseen-class unlabeled data. In International Conference on Machine Learning, pages 3897-3906. PMLR, 2020.","title":"Safe deep semisupervised learning for unseen-class unlabeled data","authors":"Lan-Zhe Guo, Zhen-Yu Zhang, Yuan Jiang, Yu-Feng Li, Zhi-Hua Zhou","year":"2020","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":16,"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":17,"raw":"[He et al., 2022] Rundong He, Zhongyi Han, Xiankai Lu, and Yilong Yin. Safe-student for safe deep semi- supervised learning with unseen-class unlabeled data. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14585-14594, 2022.","title":"Safe-student for safe deep semisupervised learning with unseen-class unlabeled data","authors":"He","year":"2022","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Hendrycks and Gimpel, 2016] Dan Hendrycks and Kevin Gimpel. A baseline for detecting misclassified and out-of- distribution examples in neural networks. arXiv preprint arXiv:1610.02136, 2016.","title":"A baseline for detecting misclassified and out-ofdistribution examples in neural networks","authors":"Gimpel Hendrycks, Dan Hendrycks, Kevin Gimpel","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Huang et al., 2021] Junkai Huang, Chaowei Fang, Weikai Chen, Zhenhua Chai, Xiaolin Wei, Pengxu Wei, Liang Lin, and Guanbin Li. Trash to treasure: Harvesting ood data with cross-modal matching for open-set semi-supervised learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 8310-8319, 2021.","title":"Trash to treasure: Harvesting ood data with cross-modal matching for open-set semi-supervised learning","authors":"Huang","year":"2021","venue":"Proceedings of the IEEE/CVF International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Laine and Aila, 2016] Samuli Laine and Timo Aila. Tem- poral ensembling for semi-supervised learning. arXiv preprint arXiv:1610.02242, 2016.","title":"Temporal ensembling for semi-supervised learning","authors":"Laine, Aila ;, Samuli Laine, Timo Aila","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Lee and others, 2013] Dong-Hyun Lee et al. Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In Workshop on challenges in representation learning, ICML, volume 3, page 896.","title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","authors":"Dong-Hyun Lee","year":null,"venue":"Workshop on challenges in representation learning","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Lee et al., 2018] Kimin Lee, Kibok Lee, Honglak Lee, and Jinwoo Shin. A simple unified framework for detect- ing out-of-distribution samples and adversarial attacks. Advances in neural information processing systems, 31, 2018.","title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","authors":"Lee","year":"2018","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Li et al., 2023] Zekun Li, Lei Qi, Yinghuan Shi, and Yang Gao. Iomatch: Simplifying open-set semi-supervised learning with joint inliers and outliers utilization. In Pro- ceedings of the IEEE/CVF International Conference on Computer Vision, pages 15870-15879, 2023.","title":"Iomatch: Simplifying open-set semi-supervised learning with joint inliers and outliers utilization","authors":"Li","year":"2023","venue":"Proceedings of the IEEE/CVF International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Liu et al., 2020] Weitang Liu, Xiaoyun Wang, John Owens, and Yixuan Li. Energy-based out-of-distribution detec- tion. Advances in neural information processing systems, 33:21464-21475, 2020.","title":"Energy-based out-of-distribution detection","authors":"Weitang Liu, Xiaoyun Wang, John Owens, Yixuan Li","year":"2020","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Lu et al., 2023] Fan Lu, Kai Zhu, Wei Zhai, Kecheng Zheng, and Yang Cao. Uncertainty-aware optimal trans- port for semantically coherent out-of-distribution detec- tion. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3282- 3291, 2023.","title":"Uncertainty-aware optimal transport for semantically coherent out-of-distribution detection","authors":"Fan Lu, Kai Zhu, Wei Zhai, Kecheng Zheng, Yang Cao","year":"2023","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Ma et al., 2023] Qiankun Ma, Jiyao Gao, Bo Zhan, Yun- peng Guo, Jiliu Zhou, and Yan Wang. Rethinking safe semi-supervised learning: Transferring the open-set prob- lem to a close-set one. In Proceedings of the IEEE/CVF In- ternational Conference on Computer Vision, pages 16370- 16379, 2023.","title":"Rethinking safe semi-supervised learning: Transferring the open-set problem to a close-set one","authors":"Ma","year":"2023","venue":"Proceedings of the IEEE/CVF International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Saito et al., 2021] Kuniaki Saito, Donghyun Kim, and Kate Saenko. Openmatch: Open-set consistency regularization for semi-supervised learning with outliers. arXiv preprint arXiv:2105.14148, 2021.","title":"Openmatch: Open-set consistency regularization for semi-supervised learning with outliers","authors":"Kuniaki Saito, Donghyun Kim, Kate Saenko","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Sohn et al., 2020] Kihyuk Sohn, David Berthelot, Nicholas Carlini, Zizhao Zhang, Han Zhang, Colin A Raffel, Ekin Dogus Cubuk, Alexey Kurakin, and Chun-Liang Li. Fixmatch: Simplifying semi-supervised learning with con- sistency and confidence. Advances in neural information processing systems, 33:596-608, 2020.","title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","authors":"Sohn","year":"2020","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Sun et al., 2022] Yiyou Sun, Yifei Ming, Xiaojin Zhu, and Yixuan Li. Out-of-distribution detection with deep nearest neighbors, 2022.","title":"Out-of-distribution detection with deep nearest neighbors","authors":"Yiyou Sun, Yifei Ming, Xiaojin Zhu, Yixuan Li","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Tarvainen and Valpola, 2017] Antti Tarvainen and Harri Valpola. Mean teachers are better role models: Weight- averaged consistency targets improve semi-supervised deep learning results. Advances in neural information pro- cessing systems, 30, 2017.","title":"Mean teachers are better role models: Weightaveraged consistency targets improve semi-supervised deep learning results","authors":"Valpola Tarvainen, Antti Tarvainen, Harri Valpola","year":"2017","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Villani, 2008] C Villani. Optimal transport, old and new. notes for the 2005 saint-flour summer school. Grundlehren der mathematischen Wissenschaften [Fundamental Prin- ciples of Mathematical Sciences]. Springer, 3, 2008.","title":"Optimal transport, old and new. notes for the 2005 saint-flour summer school","authors":"Villani","year":"2008","venue":"Grundlehren der mathematischen Wissenschaften","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Villani, 2021] Cédric Villani. Topics in optimal transporta- tion, volume 58. American Mathematical Soc., 2021.","title":"Topics in optimal transportation","authors":"Cédric Villani, Villani","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Wang et al., 2023] Yu Wang, Pengchong Qiao, Chang Liu, Guoli Song, Xiawu Zheng, and Jie Chen. Out-of- distributed semantic pruning for robust semi-supervised learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 23849- 23858, 2023.","title":"Out-ofdistributed semantic pruning for robust semi-supervised learning","authors":"Yu Wang, Pengchong Qiao, Chang Liu, Guoli Song, Xiawu Zheng, Jie Chen","year":"2023","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Xie et al., 2020] Qizhe Xie, Zihang Dai, Eduard Hovy, Minh-Thang Luong, and Quoc V. Le. Unsupervised data augmentation for consistency training, 2020.","title":"Unsupervised data augmentation for consistency training","authors":"Xie","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Xu et al., 2020] Renjun Xu, Pelen Liu, Yin Zhang, Fang Cai, Jindong Wang, Shuoying Liang, Heting Ying, and Jianwei Yin. Joint partial optimal transport for open set domain adaptation. In IJCAI, pages 2540-2546, 2020.","title":"Joint partial optimal transport for open set domain adaptation","authors":"Xu","year":"2020","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2020/352"},{"position":36,"raw":"[Yang et al., 2023a] Xiangli Yang, Zixing Song, Irwin King, and Zenglin Xu. A survey on deep semi-supervised learn- ing. IEEE Transactions on Knowledge and Data Engineer- ing, 35(9):8934-8954, September 2023.","title":"A survey on deep semi-supervised learning","authors":"Yang","year":"2023","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Yang et al., 2023b] Yucheng Yang, Xiang Gu, and Jian Sun. Prototypical partial optimal transport for universal domain adaptation. 2023.","title":"Prototypical partial optimal transport for universal domain adaptation","authors":"Yang","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Yu et al., 2020] Qing Yu, Daiki Ikami, Go Irie, and Kiy- oharu Aizawa. Multi-task curriculum framework for open- set semi-supervised learning. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XII 16, pages 438-454. Springer, 2020.","title":"Multi-task curriculum framework for openset semi-supervised learning","authors":"Qing Yu, Daiki Ikami, Go Irie, Kiyoharu Aizawa","year":"2020","venue":"Computer Vision-ECCV 2020: 16th European Conference","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Zagoruyko and Komodakis, 2016] Sergey Zagoruyko and Nikos Komodakis. Wide residual networks. arXiv preprint arXiv:1605.07146, 2016.","title":"Wide residual networks","authors":"Sergey Zagoruyko, Nikos Komodakis","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Zhang et al., 2021] Bowen Zhang, Yidong Wang, Wenxin Hou, Hao Wu, Jindong Wang, Manabu Okumura, and Takahiro Shinozaki. Flexmatch: Boosting semi- supervised learning with curriculum pseudo labeling. Advances in Neural Information Processing Systems, 34:18408-18419, 2021.","title":"Flexmatch: Boosting semisupervised learning with curriculum pseudo labeling","authors":"Bowen Zhang, Yidong Wang, Wenxin Hou, Hao Wu, Jindong Wang, Manabu Okumura, Takahiro Shinozaki","year":"2021","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}