{"type":"ScholarlyArticle","title":"Positive and Unlabeled Learning with Label Disambiguation","authors":[{"name":"Chuang Zhang","slug":"chuang-zhang","given":"Chuang","family":"Zhang","affiliation":"PCA Lab , the Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education , School of Computer Science and Engineering , Nanjing University of Science and Technology , China"},{"name":"Dexin Ren","slug":"dexin-ren","given":"Dexin","family":"Ren","affiliation":"PCA Lab , the Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education , School of Computer Science and Engineering , Nanjing University of Science and Technology , China"},{"name":"Tongliang Liu","slug":"tongliang-liu","given":"Tongliang","family":"Liu","affiliation":"UBTECH Sydney AI Centre , SCS , FEIT , The University of Sydney , Australia"},{"name":"Jian Yang","slug":"jian-yang","given":"Jian","family":"Yang","affiliation":"PCA Lab , the Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education , School of Computer Science and Engineering , Nanjing University of Science and Technology , China; Jiangsu Key Lab of Image and Video Understanding for Social Security"},{"name":"Chen Gong","slug":"chen-gong","given":"Chen","family":"Gong","affiliation":"PCA Lab , the Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education , School of Computer Science and Engineering , Nanjing University of Science and Technology , China"}],"abstract":"Positive and Unlabeled (PU) learning aims to learn a binary classifier from only positive and unlabeled training data. The state-of-the-art methods usually formulate PU learning as a cost-sensitive learning problem, in which every unlabeled example is simultaneously treated as positive and negative with different class weights. However, the ground-truth label of an unlabeled example should be unique, so the existing models inadvertently introduce the label noise which may lead to the biased classifier and deteriorated performance. To solve this problem, this paper  proposes a novel algorithm dubbed as \"Positive and Unlabeled learning with Label Disambiguation'' (PULD). We first regard all the unlabeled examples in PU learning as ambiguously labeled as positive and negative, and then employ the margin-based label disambiguation strategy, which enlarges the margin of classifier response between the most likely label and the less likely one, to find the unique ground-truth label of each unlabeled example. Theoretically, we derive the generalization error bound of the proposed method by analyzing its Rademacher complexity. Experimentally, we conduct intensive experiments on both benchmark and real-world datasets, and the results clearly demonstrate the superiority of the proposed PULD to the existing PU learning approaches.","doi":"10.24963/ijcai.2019/590","url":"https://ijcai.org/proceedings/2019/590","pdf":"https://ijcai.org/proceedings/2019/0590.pdf","markdown":"https://ijcai.org/proceedings/2019/590.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/590","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":590,"pages":{"first":4250,"last":4256},"keywords":["Machine Learning: Classification","Machine Learning: Semi-Supervised Learning"],"videos":[],"references":[{"position":1,"raw":"[Bartlett and Mendelson, 2002] Peter L Bartlett and Shahar Mendelson. Rademacher and gaussian complexities: Risk bounds and structural results. JMLR, 3(Nov):463-482, 2002.","title":"Rademacher and gaussian complexities: Risk bounds and structural results","authors":"L Peter, Shahar Bartlett, Mendelson","year":"2002","venue":"JMLR","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Belkin et al., 2006] Mikhail Belkin, Partha Niyogi, and Vikas Sindhwani. Manifold regularization: A geometric framework for learning from labeled and unlabeled examples. JMLR, 7(Nov):2399-2434, 2006.","title":"Manifold regularization: A geometric framework for learning from labeled and unlabeled examples","authors":"Mikhail Belkin, Partha Niyogi, Vikas Sindhwani","year":"2006","venue":"JMLR","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Boyd and Vandenberghe, 2004] Stephen Boyd and Lieven Van- denberghe. Convex optimization. Cambridge university press, 2004.","title":"Stephen Boyd and Lieven Vandenberghe","authors":"Vandenberghe Boyd","year":"2004","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen et al., 2018] Ching-Hui Chen, Vishal M Patel, and Rama Chellappa. Learning from ambiguously labeled face images. IEEE T-PAMI, 40(7):1653-1667, 2018.","title":"Learning from ambiguously labeled face images","authors":"Ching-Hui Chen, M Vishal, Rama Patel, Chellappa","year":"2018","venue":"IEEE T-PAMI","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Christoffel et al., 2016] Marthinus Christoffel, Gang Niu, and Masashi Sugiyama. Class-prior estimation for learning from pos- itive and unlabeled data. In ACML, pages 221-236, 2016.","title":"Class-prior estimation for learning from positive and unlabeled data","authors":"Marthinus Christoffel, Gang Niu, Masashi Sugiyama","year":"2016","venue":"ACML","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Cour et al., 2011] Timothee Cour, Ben Sapp, and Ben Taskar. Learning from partial labels. JMLR, 12(May):1501-1536, 2011.","title":"Learning from partial labels","authors":"Timothee Cour, Ben Sapp, Ben Taskar","year":"2011","venue":"JMLR","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Crammer and Singer, 2001] Koby Crammer and Yoram Singer. On the algorithmic implementation of multiclass kernel-based vector machines. JMLR, 2(Dec):265-292, 2001.","title":"On the algorithmic implementation of multiclass kernel-based vector machines","authors":"Koby Crammer, Yoram Singer","year":"2001","venue":"JMLR","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Denis et al., 2005] Franc ¸ois Denis, Rémi Gilleron, and Fabien Letouzey. Learning from positive and unlabeled examples. The- oretical Computer Science, 348(1):70-83, 2005.","title":"Franc ¸ois Denis, Rémi Gilleron, and Fabien Letouzey. Learning from positive and unlabeled examples","authors":"Denis","year":"2005","venue":"Theoretical Computer Science","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Du Plessis et al., 2014] Marthinus C Du Plessis, Gang Niu, and Masashi Sugiyama. Analysis of learning from positive and unla- beled data. In NeurIPS, pages 703-711, 2014.","title":"Analysis of learning from positive and unlabeled data","authors":"Marthinus C Du, Gang Plessis, Masashi Niu, Sugiyama","year":"2014","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Du Plessis et al., 2015] Marthinus Du Plessis, Gang Niu, and Masashi Sugiyama. Convex formulation for learning from posi- tive and unlabeled data. In ICML, pages 1386-1394, 2015.","title":"Convex formulation for learning from positive and unlabeled data","authors":"Marthinus Du Plessis, Gang Niu, Masashi Sugiyama","year":"2015","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Elkan and Noto, 2008] Charles Elkan and Keith Noto. Learning classifiers from only positive and unlabeled data. In SIGKDD, pages 213-220. ACM, 2008.","title":"Learning classifiers from only positive and unlabeled data","authors":"Noto Elkan, Charles Elkan, Keith Noto","year":"2008","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Fan et al., 2008] Rong-En Fan, Kai-Wei Chang, Cho-Jui Hsieh, Xiang-Rui Wang, and Chih-Jen Lin. Liblinear: A library for large linear classification. JMLR, 9(Aug):1871-1874, 2008.","title":"Liblinear: A library for large linear classification","authors":"Rong-En Fan, Kai-Wei Chang, Cho-Jui Hsieh, Xiang-Rui Wang, Chih-Jen Lin","year":"2008","venue":"JMLR","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Feng and An, 2018] Lei Feng and Bo An. Leveraging latent label distributions for partial label learning. In IJCAI, pages 2107- 2113, 2018.","title":"Leveraging latent label distributions for partial label learning","authors":"Lei Feng, Bo An","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/291"},{"position":14,"raw":"[Fu et al., 2016] Guangyuan Fu, Jun Wang, Bo Yang, and Guoxian Yu. Neggoa: negative go annotations selection using ontology structure. Bioinformatics, 32(19):2996-3004, 2016.","title":"Neggoa: negative go annotations selection using ontology structure","authors":"Guangyuan Fu, Jun Wang, Bo Yang, Guoxian Yu","year":"2016","venue":"Bioinformatics","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Gong et al., 2018] Chen Gong, Tongliang Liu, Yuanyan Tang, Jian Yang, Jie Yang, and Dacheng Tao. A regularization approach for instance-based superset label learning. IEEE T-CYB, 48(3):967- 978, 2018.","title":"A regularization approach for instance-based superset label learning","authors":"Chen Gong, Tongliang Liu, Yuanyan Tang, Jian Yang, Jie Yang, Dacheng Tao","year":"2018","venue":"IEEE T-CYB","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Gong et al., 2019a] Chen Gong, Tongliang Liu, Jian Yang, and Dacheng Tao. Large-margin label-calibrated support vector ma- chines for positive and unlabeled learning. IEEE T-NNLS, 2019.","title":"Large-margin label-calibrated support vector machines for positive and unlabeled learning","authors":"Gong","year":"2019","venue":"IEEE T-NNLS","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Gong et al., 2019b] Chen Gong, Hong Shi, Jie Yang, and Jian Yan- ga. Multi-manifold positive and unlabeled learning for visual analysis. IEEE T-CSVT, 2019.","title":"Multi-manifold positive and unlabeled learning for visual analysis","authors":"Gong","year":"2019","venue":"IEEE T-CSVT","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Hong and Luo, 2017] Mingyi Hong and Zhi-Quan Luo. On the linear convergence of the alternating direction method of multi- pliers. Mathematical Programming, 162(1-2):165-199, 2017.","title":"On the linear convergence of the alternating direction method of multipliers","authors":"Mingyi Hong, Zhi-Quan Luo","year":"2017","venue":"Mathematical Programming","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Jin and Ghahramani, 2003] Rong Jin and Zoubin Ghahramani. Learning with multiple labels. In NeurIPS, pages 921-928, 2003.","title":"Learning with multiple labels","authors":"Jin, Ghahramani ; ] Rong, Jin, Zoubin Ghahramani","year":"2003","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Kiryo et al., 2017] Ryuichi Kiryo, Gang Niu, Marthinus C du P- lessis, and Masashi Sugiyama. Positive-unlabeled learning with non-negative risk estimator. In NeurIPS, pages 1675-1685, 2017.","title":"Positive-unlabeled learning with non-negative risk estimator","authors":"Ryuichi Kiryo, Gang Niu, C Marthinus, Masashi Du Plessis, Sugiyama","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Krizhevsky and Hinton, 2009] Alex Krizhevsky and Geoffrey Hinton. Learning multiple layers of features from tiny images. Technical report, Citeseer, 2009.","title":"Learning multiple layers of features from tiny images","authors":"Alex Krizhevsky, Geoffrey Hinton","year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Lee and Liu, 2003] Wee Sun Lee and Bing Liu. Learning with pos- itive and unlabeled examples using weighted logistic regression. In ICML, volume 3, pages 448-455, 2003.","title":"Learning with positive and unlabeled examples using weighted logistic regression","authors":"Lee, Liu ; Wee, Sun Lee, Bing Liu","year":"2003","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Li and Liu, 2003] Xiaoli Li and Bing Liu. Learning to classify texts using positive and unlabeled data. In IJCAI, volume 3, pages 587-592, 2003.","title":"Learning to classify texts using positive and unlabeled data","authors":"Li, Liu ; ] Xiaoli Li, Bing Liu","year":"2003","venue":"IJCAI","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Li et al., 2011] Wenkai Li, Qinghua Guo, and Charles Elkan. A positive and unlabeled learning algorithm for one-class classi- fication of remote-sensing data. IEEE T-GRS, 49(2):717-725, 2011.","title":"A positive and unlabeled learning algorithm for one-class classification of remote-sensing data","authors":"Li","year":"2011","venue":"IEEE T-GRS","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Liu and Tao, 2016] Tongliang Liu and Dacheng Tao. Classifica- tion with noisy labels by importance reweighting. IEEE T-PAMI, 38(3):447-461, 2016.","title":"Tongliang Liu and Dacheng Tao. Classification with noisy labels by importance reweighting","authors":"Tao Liu","year":"2016","venue":"IEEE T-PAMI","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Liu et al., 2002] Bing Liu, Wee Sun Lee, Philip S Yu, and Xiaoli Li. Partially supervised classification of text documents. In ICM- L, volume 2, pages 387-394. Citeseer, 2002.","title":"Partially supervised classification of text documents","authors":"Bing Liu, Wee Sun Lee, Philip S Yu, Xiaoli Li","year":"2002","venue":"ICM-L","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Mohri et al., 2018] Mehryar Mohri, Afshin Rostamizadeh, and Ameet Talwalkar. Foundations of machine learning. MIT press, 2018.","title":"Foundations of machine learning","authors":"Mehryar Mohri, Afshin Rostamizadeh, Ameet Talwalkar","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Netzer et al., 2011] Yuval Netzer, Tao Wang, Adam Coates, A- lessandro Bissacco, Bo Wu, and Andrew Y Ng. Reading digits in natural images with unsupervised feature learning. 2011.","title":"Reading digits in natural images with unsupervised feature learning","authors":"Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Bo Wu, Andrew Y Ng","year":"2011","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Nguyen and Caruana, 2008] Nam Nguyen and Rich Caruana. Classification with partial labels. In SIGKDD, pages 551-559. ACM, 2008.","title":"Classification with partial labels","authors":"Caruana Nguyen, Nam Nguyen, Rich Caruana","year":"2008","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Shi et al., 2018] Hong Shi, Shaojun Pan, Jian Yang, and Chen Gong. Positive and unlabeled learning via loss decomposition and centroid estimation. In IJCAI, pages 2689-2695, 2018.","title":"Positive and unlabeled learning via loss decomposition and centroid estimation","authors":"Shi","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/373"},{"position":31,"raw":"[Wei and Li, 2018] Huihui Wei and Ming Li. Positive and unla- beled learning for detecting software functional clones with ad- versarial training. In IJCAI, pages 2840-2846, 2018.","title":"Positive and unlabeled learning for detecting software functional clones with adversarial training","authors":"Huihui Wei, Ming Li","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/394"},{"position":32,"raw":"[Wu and Zhang, 2018] Xuan Wu and Min-Ling Zhang. Towards enabling binary decomposition for partial label learning. In IJ- CAI, pages 2868-2874, 2018.","title":"Towards enabling binary decomposition for partial label learning","authors":"Zhang ; ] Wu, Xuan Wu, Min-Ling Zhang","year":"2018","venue":"IJ-CAI","doi":null,"url":null,"internal_url":"/proceedings/2018/398"},{"position":33,"raw":"[Youngs et al., 2014] Noah Youngs, Duncan Penfold-Brown, Richard Bonneau, and Dennis Shasha. Negative example selection for protein function prediction: the nogo database. PLoS computational biology, 10(6):e1003644, 2014.","title":"Negative example selection for protein function prediction: the nogo database","authors":"Youngs","year":"2014","venue":"PLoS computational biology","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Youngs et al., 2015] Noah Youngs, Dennis Shasha, and Richard Bonneau. Positive-unlabeled learning in the face of labeling bias. In ICDMW, pages 639-645. IEEE, 2015.","title":"Positive-unlabeled learning in the face of labeling bias","authors":"Youngs","year":"2015","venue":"ICDMW","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Yu and Zhang, 2017] Fei Yu and Min-Ling Zhang. Maximum mar- gin partial label learning. Machine Learning, 106(4):573-593, 2017.","title":"Maximum margin partial label learning","authors":"Yu, Zhang ; ] Fei Yu, Min-Ling Zhang","year":"2017","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Zhou et al., 2004] Dengyong Zhou, Olivier Bousquet, Thomas N Lal, Jason Weston, and Bernhard Schölkopf. Learning with local and global consistency. In NeurIPS, pages 321-328, 2004.","title":"Learning with local and global consistency","authors":"Zhou","year":"2004","venue":"NeurIPS","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}