{"type":"ScholarlyArticle","title":"Label Enhancement for Label Distribution Learning via Prior Knowledge","authors":[{"name":"Yongbiao Gao","slug":"yongbiao-gao","given":"Yongbiao","family":"Gao","affiliation":"School of Computer Science and Engineering , Southeast University , Nanjing , China"},{"name":"Yu Zhang","slug":"yu-zhang","given":"Yu","family":"Zhang","affiliation":"School of Computer Science and Engineering , Southeast University , Nanjing , China"},{"name":"Xin Geng","slug":"xin-geng","given":"Xin","family":"Geng","affiliation":"School of Computer Science and Engineering , Southeast University , Nanjing , China"}],"abstract":"Label distribution learning (LDL) is a novel machine learning paradigm that gives a description degree of each label to an instance. However, most of training datasets only contain simple logical labels rather than label distributions due to the difficulty of obtaining the label distributions directly. We propose to use the prior knowledge to recover the label distributions. The process of recovering the label distributions from the logical labels is called label enhancement. In this paper, we formulate the label enhancement as a dynamic decision process. Thus, the label distribution is adjusted by a series of actions conducted by a reinforcement learning agent according to sequential state representations. The target state is defined by the prior knowledge. Experimental results show that the proposed approach outperforms the state-of-the-art methods in both age estimation and image emotion recognition.","doi":"10.24963/ijcai.2020/446","url":"https://ijcai.org/proceedings/2020/446","pdf":"https://ijcai.org/proceedings/2020/0446.pdf","markdown":"https://ijcai.org/proceedings/2020/446.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/446","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":446,"pages":{"first":3223,"last":3229},"keywords":["Machine Learning: Multi-instance;Multi-label;Multi-view learning","Machine Learning: Classification","Machine Learning: Deep Reinforcement Learning","Machine Learning Applications: Applications of Reinforcement Learning"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24144/file_24144.m3u8","length_sec":289,"provider":"hls"}],"references":[{"position":1,"raw":"[Bin-Bin et al., 2017] Gao Bin-Bin, Xing Chao, and Geng Xin. Deep label distribution learning with label ambiguity. TIP, 26(6):2825-2838, 2017.","title":"Deep label distribution learning with label ambiguity","authors":"Gao Bin-Bin, Xing Chao, Geng Xin","year":"2017","venue":"TIP","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Edwards et al., 1998] Gareth J. Edwards, Andreas Lanitis, Christopher J Taylor, and Timothy F. Cootes. Statistical face models: Improving specificity. Image Vision Com- puting, 1998.","title":"Statistical face models: Improving specificity","authors":"J Gareth, Andreas Edwards, Christopher J Lanitis, Timothy F Taylor, Cootes","year":"1998","venue":"Image Vision Computing","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Gao et al., 2018] Bin-Bin Gao, Hong-Yu Zhou, Jianxin Wu, and Xin Geng. Age estimation using expectation of label distribution learning. In IJCAI, 2018.","title":"Age estimation using expectation of label distribution learning","authors":"Gao","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/99"},{"position":4,"raw":"[Gayar et al., 2006] Neamat EI Gayar, Friedhelm Schwenker, and Palm. A study of the robustness of knn classifiers trained using soft labels. ANNPR, 2006.","title":"Neamat EI Gayar, Friedhelm Schwenker, and Palm. A study of the robustness of knn classifiers trained using soft labels","authors":"Gayar","year":"2006","venue":"ANNPR","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Geng and Hou, 2015] Xin Geng and Peng Hou. Pre-release prediction of crowd opinion on movies by label distribu- tion learning. In IJCAI, 2015.","title":"Pre-release prediction of crowd opinion on movies by label distribution learning","authors":"Xin Geng, Peng Hou","year":"2015","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2015/494"},{"position":6,"raw":"[Geng, 2016] Xin Geng. Label distribution learning. TKDE, 28(7):1734-1748, 2016.","title":"Label distribution learning","authors":"Xin Geng","year":"2016","venue":"TKDE","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Gibaja and Eva, 2015] Gibaja and Eva. A tutorial on multi- label learning. ACM Computing Surveys, 2015.","title":"Gibaja and Eva. A tutorial on multilabel learning","authors":"Eva Gibaja","year":"2015","venue":"ACM Computing Surveys","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Grigorios and Ioannis, 2006] Tsoumakas Grigorios and Katakis Ioannis. Multi-label classification: An overview. IJDWM, 3(3):1-13, 2006.","title":"Tsoumakas Grigorios and Katakis Ioannis. Multi-label classification: An overview","authors":"Ioannis Grigorios","year":"2006","venue":"IJDWM","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Guo et al., 2009] Guodong Guo, Guowang Mu, Yun Fu, and Thomas S. Huang. Human age estimation using bio- inspired features. In CVPR, 2009.","title":"Human age estimation using bioinspired features","authors":"Guodong Guo, Guowang Mu, Yun Fu, Thomas S Huang","year":"2009","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Hou et al., 2016] Peng Hou, Xin Geng, and Min Ling Zhang. Multi-label manifold learning. In AAAI, 2016.","title":"Multi-label manifold learning","authors":"Peng Hou, Xin Geng, Min Ling Zhang","year":"2016","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Jiang et al., 2006] Xiufeng Jiang, Zhang Yi, and Jian Cheng Lv. Fuzzy svm with a new fuzzy membership func- tion. Neural Computing and Applications, 15(3-4):268- 276, 2006.","title":"Fuzzy svm with a new fuzzy membership function","authors":"Xiufeng Jiang, Zhang Yi, Jian Cheng, Lv","year":"2006","venue":"Neural Computing and Applications","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Lanitis et al., 2002] Andreas Lanitis, Christopher J Taylor, and Timothy F. Cootes. Toward automatic simulation of aging effects on face images. TPAMI, 24(4):442-455, 2002.","title":"Toward automatic simulation of aging effects on face images","authors":"Andreas Lanitis, Christopher J Taylor, Timothy F Cootes","year":"2002","venue":"TPAMI","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Li et al., 2016] Yu Kun Li, Min Ling Zhang, and Xin Geng. Leveraging implicit relative labeling-importance informa- tion for effective multi-label learning. In ICDM, 2016.","title":"Leveraging implicit relative labeling-importance information for effective multi-label learning","authors":"Yu Kun, Li, Min Ling Zhang, Xin Geng","year":"2016","venue":"ICDM","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Ling and Geng, 2017] Miaogen Ling and Xin Geng. Soft video parsing by label distribution learning. In AAAI, 2017.","title":"Soft video parsing by label distribution learning","authors":"Ling, Geng ;, Miaogen Ling, Xin Geng","year":"2017","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Liu et al., 2017] Yujie Liu, Yongbiao Gao, Shihe Feng, and Zongmin Li. Weather-to-garment: Weather-oriented cloth- ing recommendation. In ICME, 2017.","title":"Weather-to-garment: Weather-oriented clothing recommendation","authors":"Yujie Liu, Yongbiao Gao, Shihe Feng, Zongmin Li","year":"2017","venue":"ICME","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Mikels et al., 2005] Joseph A. Mikels, Barbara L. Fredrick- son, and Gregory R. Larkin. A reuter-lorenz. emotional category data on images from the international affective picture system. Behavior research methods, 37(4):626- 630, 2005.","title":"A reuter-lorenz. emotional category data on images from the international affective picture system","authors":"Joseph A Mikels, Barbara L Fredrickson, Gregory R Larkin","year":"2005","venue":"Behavior research methods","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Plutchik, 2001] Plutchik. The nature of emotions. Amer. Scientist, 2001. [Ricanek and Tesafaye, 2006] Karl Ricanek and T. Tesafaye. Morph: A longitudinal image database of normal adult age-progression. In FG, 2006.","title":"Morph: A longitudinal image database of normal adult age-progression","authors":"Plutchik","year":"2001","venue":"The nature of emotions","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Silver et al., 2016] David Silver, Aja Huang, Thore Grae- pel, and Demis Hassabis. Mastering the game of go with deep neural networks and tree search. Nature, 529(7587):484-489, 2016.","title":"Mastering the game of go with deep neural networks and tree search","authors":"David Silver, Aja Huang, Thore Graepel, Demis Hassabis","year":"2016","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Simonyan and Zisserman, 2014] Karen Simonyan and An- drew Zisserman. Very deep convolutional networks for large-scale image recognition. Computer Science, 2014.","title":"Very deep convolutional networks for large-scale image recognition","authors":"Karen Simonyan, Andrew Zisserman","year":"2014","venue":"Computer Science","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Su and Geng, 2019] Kai. Su and Xin. Geng. Soft facial landmark detection by label distribution learning. In AAAI, 2019.","title":"Soft facial landmark detection by label distribution learning","authors":"Kai Su, Xin Geng","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Sutton and Barto, 2018] Richard S. Sutton and Andrew G. Barto. Reinforcement learning: An introduction. MIT Press, 2018.","title":"Reinforcement learning: An introduction","authors":"Richard S Sutton, Andrew G Barto","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Wang et al., 2015] Ziyu Wang, Nando De Freitas, and Marc Lanctot. Dueling network architectures for deep reinforce- ment learning. In ICML, 2015.","title":"Dueling network architectures for deep reinforcement learning","authors":"Ziyu Wang, Nando De Freitas, Marc Lanctot","year":"2015","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Xin et al., 2013] Geng Xin, Yin Chao, and Zhou Zhi-Hua. Facial age estimation by learning from label distributions. TPAMI, 35(10):2401-2412, 2013.","title":"Facial age estimation by learning from label distributions","authors":"Geng Xin, Yin Chao, Zhou Zhi-Hua","year":"2013","venue":"TPAMI","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Xu et al., 2018] Ning Xu, An Tao, and Xin Geng. Label en- hancement for label distribution learning. In IJCAI, 2018.","title":"Label enhancement for label distribution learning","authors":"Ning Xu, An Tao, Xin Geng","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/406"},{"position":25,"raw":"[Yan et al., 2005] Shuicheng Yan, Dong Xu, Benyu Zhang, and Hong Jiang Zhang. Graph embedding: A general framework for dimensionality reduction. In CVPR, 2005.","title":"Graph embedding: A general framework for dimensionality reduction","authors":"Shuicheng Yan, Dong Xu, Benyu Zhang, Hong Jiang Zhang","year":"2005","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Yang et al., 2017a] Jufeng Yang, Dongyu She, and Ming Sun. Joint image emotion classification and distribution learning via deep convolutional neural network. In IJCAI, 2017.","title":"Joint image emotion classification and distribution learning via deep convolutional neural network","authors":"Yang","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/456"},{"position":27,"raw":"[Yang et al., 2017b] Jufeng Yang, Ming Sun, and Xiaoxiao Sun. Learning visual sentiment distributions via augment- ed conditional probability neural network. In AAAI, 2017.","title":"Learning visual sentiment distributions via augmented conditional probability neural network","authors":"Yang","year":"2017","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Yi and Wu, 2019] Kun Yi and Jianxin Wu. Probabilistic end-to-end noise correction for learning with noisy labels. In CVPR, 2019.","title":"Probabilistic end-to-end noise correction for learning with noisy labels","authors":"Yi, Wu ; ] Kun Yi, Jianxin Wu","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Zhang and Zhou, 2014] Min Ling Zhang and Zhi Hua Zhou. A review on multi-label learning algorithms. TKDE, 26(8):1819-1837, 2014.","title":"A review on multi-label learning algorithms","authors":"Zhou ; ] Zhang, Ling Min, Zhi Hua Zhang, Zhou","year":"2014","venue":"TKDE","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Zhang et al., 2015] Zhaoxiang Zhang, Wang Mo, and Geng Xin. Crowd counting in public video surveillance by label distribution learning. Neurocomputing, 2015.","title":"Crowd counting in public video surveillance by label distribution learning","authors":"Zhang","year":"2015","venue":"Neurocomputing","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Zhao et al., 2018] Sicheng Zhao, Hongxun Yao, Gao Yue, and Tat Seng Chua. Stackdrl: Stacked deep reinforcement learning for fine-grained visual categorization. In IJCAI, 2018.","title":"Stackdrl: Stacked deep reinforcement learning for fine-grained visual categorization","authors":"Sicheng Zhao, Hongxun Yao, Gao Yue, Tat Seng, Chua","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/103"},{"position":32,"raw":"[Zhou and Zhang, 2006] Zhi-Hua Zhou and Min Ling Zhang. Multi-instance multi-label learning with applica- tion to scene classification. In NIPS, 2006.","title":"Multi-instance multi-label learning with application to scene classification","authors":"Zhang ; ] Zhi-Hua Zhou, Min Ling Zhou, Zhang","year":"2006","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Zhou et al., 2016] Deyu Zhou, Xuan Zhang, Yin Zhou, Quan Zhao, and Xin Geng. Emotion distribution learning from texts. In EMNLP, 2016.","title":"Emotion distribution learning from texts","authors":"Deyu Zhou, Xuan Zhang, Yin Zhou, Quan Zhao, Xin Geng","year":"2016","venue":"EMNLP","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}