{"type":"ScholarlyArticle","title":"Learning From Multi-Dimensional Partial Labels","authors":[{"name":"Haobo Wang","slug":"haobo-wang","given":"Haobo","family":"Wang","affiliation":"Key Lab of Intelligent Computing Based Big Data of Zhejiang Province , Zhejiang University; College of Computer Science and Technology , Zhejiang University"},{"name":"Weiwei Liu","slug":"weiwei-liu","given":"Weiwei","family":"Liu","affiliation":"School of Computer Science , Wuhan University"},{"name":"Yang Zhao","slug":"yang-zhao","given":"Yang","family":"Zhao","affiliation":"College of Computer Science and Technology , Zhejiang University"},{"name":"Tianlei Hu","slug":"tianlei-hu","given":"Tianlei","family":"Hu","affiliation":"Key Lab of Intelligent Computing Based Big Data of Zhejiang Province , Zhejiang University; College of Computer Science and Technology , Zhejiang University"},{"name":"Ke Chen","slug":"ke-chen","given":"Ke","family":"Chen","affiliation":"Key Lab of Intelligent Computing Based Big Data of Zhejiang Province , Zhejiang University; College of Computer Science and Technology , Zhejiang University"},{"name":"Gang Chen","slug":"gang-chen","given":"Gang","family":"Chen","affiliation":"Key Lab of Intelligent Computing Based Big Data of Zhejiang Province , Zhejiang University; College of Computer Science and Technology , Zhejiang University"}],"abstract":"Multi-dimensional classification has attracted huge attention from the community. Though most studies consider fully annotated data, in real practice obtaining fully labeled data in MDC tasks is usually intractable. In this paper, we propose a novel learning paradigm: MultiDimensional Partial Label Learning (MDPL) where the ground-truth labels of each instance are concealed in multiple candidate label sets. We first introduce the partial hamming loss for MDPL that incurs a large loss if the predicted labels are not in candidate label sets, and provide an empirical risk minimization (ERM) framework. Theoretically, we rigorously prove the conditions for ERM learnability of MDPL in both independent and dependent cases. Furthermore, we present two MDPL algorithms under our proposed ERM framework. Comprehensive experiments on both synthetic and real-world datasets validate the effectiveness of our proposals.","doi":"10.24963/ijcai.2020/407","url":"https://ijcai.org/proceedings/2020/407","pdf":"https://ijcai.org/proceedings/2020/0407.pdf","markdown":"https://ijcai.org/proceedings/2020/407.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/407","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Machine Learning","track":"Main track","number":407,"pages":{"first":2943,"last":2949},"keywords":["Machine Learning: Multi-instance;Multi-label;Multi-view learning"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/25204/file_25204.m3u8","length_sec":298,"provider":"hls"}],"references":[{"position":1,"raw":"[Arias et al., 2016] Jacinto Arias, José A. Gámez, Thomas D. Nielsen, and José Miguel Puerta. A scalable pairwise class interaction framework for multidimensional classification. Int. J. Approx. Reasoning, 68:194-210, 2016.","title":"A scalable pairwise class interaction framework for multidimensional classification","authors":"Jacinto Arias, José A Gámez, Thomas D Nielsen, José Miguel, Puerta","year":"2016","venue":"Int. J. Approx. Reasoning","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Barutc ¸uoglu et al., 2006] Zafer Barutc ¸uoglu, Robert E. Schapire, and Olga G. Troyanskaya. Hierarchical multi-label prediction of gene function. Bioinformatics, 22(7):830-836, 2006.","title":"Hierarchical multi-label prediction of gene function","authors":"Zafer Barutc ¸uoglu, Robert E Schapire, Olga G Troyanskaya","year":"2006","venue":"Bioinformatics","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Batal et al., 2013] Iyad Batal, Charmgil Hong, and Milos Hauskrecht. An efficient probabilistic framework for multi-dimensional classification. In CIKM, pages 2417- 2422, 2013.","title":"An efficient probabilistic framework for multi-dimensional classification","authors":"Batal","year":"2013","venue":"CIKM","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Benjumeda et al., 2018] Marco Benjumeda, Concha Bielza, and Pedro Larrañaga. Tractability of most probable expla- nations in multidimensional bayesian network classifiers. Int. J. Approx. Reasoning, 93:74-87, 2018.","title":"Tractability of most probable explanations in multidimensional bayesian network classifiers","authors":"Marco Benjumeda, Concha Bielza, Pedro Larrañaga","year":"2018","venue":"Int. J. Approx. Reasoning","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chapelle et al., 2002] Olivier Chapelle, Jason Weston, and Bernhard Schölkopf. Cluster kernels for semi-supervised learning. In NeurIPS, pages 585-592, 2002.","title":"Cluster kernels for semi-supervised learning","authors":"Chapelle","year":"2002","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Cour et al., 2011] Timothée Cour, Benjamin Sapp, and Ben Taskar. Learning from partial labels. Journal of Machine Learning Research, 12:1501-1536, 2011.","title":"Learning from partial labels","authors":"Timothée Cour, Benjamin Sapp, Ben Taskar","year":"2011","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Denis, 1998] Franc ¸ois Denis. PAC learning from positive statistical queries. In ALT, pages 112-126, 1998.","title":"Franc ¸ois Denis. PAC learning from positive statistical queries","authors":"Denis","year":"1998","venue":"ALT","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Dheeru and Karra Taniskidou, 2017] Dua Dheeru and Efi Karra Taniskidou. UCI machine learning repository, 2017.","title":"Dua Dheeru and Efi Karra Taniskidou. UCI machine learning repository","authors":"Karra Dheeru, Taniskidou","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Fang and Zhang, 2019] Jun-Peng Fang and Min-Ling Zhang. Partial multi-label learning via credible label elicitation. In AAAI, 2019.","title":"Partial multi-label learning via credible label elicitation","authors":"Zhang ; Jun-Peng Fang, Min-Ling Fang, Zhang","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Feng and An, 2019] Lei Feng and Bo An. Partial label learning with self-guided retraining. In AAAI, pages 3542- 3549. AAAI Press, 2019.","title":"Lei Feng and Bo An. Partial label learning with self-guided retraining","authors":"An Feng","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Ishida et al., 2017] Takashi Ishida, Gang Niu, Weihua Hu, and Masashi Sugiyama. Learning from complementary labels. In NeurIPS, pages 5644-5654, 2017.","title":"Learning from complementary labels","authors":"Takashi Ishida, Gang Niu, Weihua Hu, Masashi Sugiyama","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Jia and Zhang, 2019] Bin-Bin Jia and Min-Ling Zhang. Multi-dimensional classification via knn feature augmen- tation. In AAAI, 2019.","title":"Multi-dimensional classification via knn feature augmentation","authors":"Zhang ; Bin-Bin Jia, Min-Ling Jia, Zhang","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Jin and Ghahramani, 2002] Rong Jin and Zoubin Ghahra- mani. Learning with multiple labels. In Suzanna Becker, Sebastian Thrun, and Klaus Obermayer, editors, NeurIPS, pages 897-904. MIT Press, 2002.","title":"Rong Jin and Zoubin Ghahramani","authors":"Jin, Ghahramani","year":"2002","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Khosla et al., 2011] Aditya Khosla, Nityananda Jayadevap- rakash, Bangpeng Yao, and Fei-Fei Li. Novel dataset for fine-grained image categorization: Stanford dogs. In Proc. CVPR Workshop on Fine-Grained Visual Categorization (FGVC), volume 2, 2011.","title":"Novel dataset for fine-grained image categorization: Stanford dogs","authors":"Aditya Khosla, Nityananda Jayadevaprakash, Bangpeng Yao, Fei-Fei Li","year":"2011","venue":"Proc. CVPR Workshop on Fine-Grained Visual Categorization (FGVC)","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Kiryo et al., 2017] Ryuichi Kiryo, Gang Niu, Marthi- nus Christoffel du Plessis, and Masashi Sugiyama. Positive-unlabeled learning with non-negative risk estima- tor. In NeurIPS, pages 1674-1684, 2017.","title":"Positive-unlabeled learning with non-negative risk estimator","authors":"Ryuichi Kiryo, Gang Niu, Marthinus Christoffel Du Plessis, Masashi Sugiyama","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Liu and Dietterich, 2012] Li-Ping Liu and Thomas G. Diet- terich. A conditional multinomial mixture model for su- perset label learning. In NeurIPS, pages 557-565, 2012.","title":"Dietterich. A conditional multinomial mixture model for superset label learning","authors":"Li-Ping Liu, Thomas G","year":"2012","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Liu and Tsang, 2017] Weiwei Liu and Ivor W. Tsang. Mak- ing decision trees feasible in ultrahigh feature and label dimensions. J. Mach. Learn. Res., 18:81:1-81:36, 2017.","title":"Making decision trees feasible in ultrahigh feature and label dimensions","authors":"Tsang Liu, Weiwei Liu, Ivor W Tsang","year":"2017","venue":"J. Mach. Learn. Res","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Liu et al., 2019] Weiwei Liu, Donna Xu, Ivor W. Tsang, and Wenjie Zhang. Metric learning for multi-output tasks. IEEE Trans. Pattern Anal. Mach. Intell., 41(2):408-422, 2019.","title":"Metric learning for multi-output tasks","authors":"Weiwei Liu, Donna Xu, Ivor W Tsang, Wenjie Zhang","year":"2019","venue":"IEEE Trans. Pattern Anal. Mach. Intell","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Lv et al., 2020] Jiaqi Lv, Miao Xu, Lei Feng, Gang Niu, Xin Geng, and Masashi Sugiyama. Progressive identi- fication of true labels for partial-label learning. CoRR, abs/2002.08053, 2020.","title":"Progressive identification of true labels for partial-label learning","authors":"Jiaqi Lv, Miao Xu, Lei Feng, Gang Niu, Xin Geng, Masashi Sugiyama","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Natarajan, 1989] B. K. Natarajan. On learning sets and functions. Machine Learning, 4:67-97, 1989.","title":"On learning sets and functions","authors":"B K Natarajan","year":"1989","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Ortigosa-Hernández et al., 2012] Jonathan Ortigosa- Hernández, Juan Diego Rodríguez, Leandro Alzate, Manuel Lucania, Iñaki Inza, and José Antonio Lozano. Approaching sentiment analysis by using semi-supervised learning of multi-dimensional classifiers. Neurocomput- ing, 92:98-115, 2012.","title":"Approaching sentiment analysis by using semi-supervised learning of multi-dimensional classifiers","authors":"Jonathan Ortigosa-Hernández, Juan Diego Rodríguez, Leandro Alzate, Manuel Lucania, Iñaki Inza, José Antonio Lozano","year":"2012","venue":"Neurocomputing","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Read et al., 2014] Jesse Read, Concha Bielza, and Pedro Larrañaga. Multi-dimensional classification with super- classes. IEEE Trans. Knowl. Data Eng., 26(7):1720-1733, 2014.","title":"Jesse Read, Concha Bielza, and Pedro Larrañaga. Multi-dimensional classification with superclasses","authors":"Read","year":"2014","venue":"IEEE Trans. Knowl. Data Eng","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Shalev-Shwartz and Ben-David, 2014] Shai Shalev- Shwartz and Shai Ben-David. Understanding machine learning: From theory to algorithms. Cambridge university press, 2014.","title":"Understanding machine learning: From theory to algorithms","authors":"Shai Shalev, -Shwartz, Shai Ben-David","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Shen et al., 2018] Xiaobo Shen, Weiwei Liu, Ivor W. Tsang, Quan-Sen Sun, and Yew-Soon Ong. Compact multi-label learning. In AAAI, pages 4066-4073, 2018.","title":"Compact multi-label learning","authors":"Xiaobo Shen, Weiwei Liu, Ivor W Tsang, Quan-Sen, Yew-Soon Sun, Ong","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Simonyan and Zisserman, 2015] Karen Simonyan and An- drew Zisserman. Very deep convolutional networks for large-scale image recognition. In ICLR, 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":26,"raw":"[Tsoumakas et al., 2011] Grigorios Tsoumakas, Ioannis Katakis, and Ioannis P. Vlahavas. Random k-labelsets for multilabel classification. IEEE Trans. Knowl. Data Eng., 23(7):1079-1089, 2011.","title":"Random k-labelsets for multilabel classification","authors":"Grigorios Tsoumakas, Ioannis Katakis, Ioannis P Vlahavas","year":"2011","venue":"IEEE Trans. Knowl. Data Eng","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Wang et al., 2019] Haobo Wang, Weiwei Liu, Yang Zhao, Chen Zhang, Tianlei Hu, and Gang Chen. Discriminative and correlative partial multi-label learning. In Sarit Kraus, editor, IJCAI, pages 3691-3697. ijcai.org, 2019.","title":"Discriminative and correlative partial multi-label learning","authors":"Wang","year":"2019","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2019/512"},{"position":28,"raw":"[Wu and Zhang, 2018] Xuan Wu and Min-Ling Zhang. To- wards enabling binary decomposition for partial label learning. In IJCAI, pages 2868-2874, 2018.","title":"Towards enabling binary decomposition for partial label learning","authors":"Zhang ; ] Wu, Xuan Wu, Min-Ling Zhang","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/398"},{"position":29,"raw":"[Zaragoza et al., 2011] Julio H. Zaragoza, Luis Enrique Su- car, Eduardo F. Morales, Concha Bielza, and Pedro Larrañaga. Bayesian chain classifiers for multidimen- sional classification. In IJCAI, pages 2192-2197, 2011.","title":"Bayesian chain classifiers for multidimensional classification","authors":"Julio H Zaragoza, Luis Enrique Sucar, Eduardo F Morales, Concha Bielza, Pedro Larrañaga","year":"2011","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2011/365"},{"position":30,"raw":"[Zhan and Zhang, 2017] Wang Zhan and Min-Ling Zhang. Inductive semi-supervised multi-label learning with co- training. In KDD, pages 1305-1314, 2017.","title":"Inductive semi-supervised multi-label learning with cotraining","authors":"Wang Zhan, Min-Ling Zhang","year":"2017","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Zhao and Guo, 2015] Feipeng Zhao and Yuhong Guo. Semi-supervised multi-label learning with incomplete la- bels. In IJCAI, pages 4062-4068, 2015.","title":"Semi-supervised multi-label learning with incomplete labels","authors":"Guo Zhao, Feipeng Zhao, Yuhong Guo","year":"2015","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2015/570"}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}