{"type":"ScholarlyArticle","title":"Adaptive Graph Guided Embedding for Multi-label Annotation","authors":[{"name":"Lichen Wang","slug":"lichen-wang","given":"Lichen","family":"Wang","affiliation":"College of Computer & Information Science , Northeastern University , Boston , USA"},{"name":"Zhengming Ding","slug":"zhengming-ding","given":"Zhengming","family":"Ding","affiliation":"College of Computer & Information Science , Northeastern University , Boston , USA"},{"name":"Yun Fu","slug":"yun-fu","given":"Yun","family":"Fu","affiliation":"‡ Department of Electrical & Computer Engineering , Northeastern University , Boston , USA"}],"abstract":"Multi-label annotation is challenging since a large amount of well-labeled training data are required to achieve promising performance. However, providing such data is expensive while unlabeled data are widely available. To this end, we propose a novel Adaptive Graph Guided Embedding (AG2E) approach for multi-label annotation in a semi-supervised fashion, which utilizes limited labeled data associating with large-scale unlabeled data to facilitate learning performance. Specifically, a multi-label propagation scheme and an effective embedding are jointly learned to seek a latent space where unlabeled instances tend to be well assigned multiple labels. Furthermore, a locality structure regularizer is designed to preserve the intrinsic structure and enhance the multi-label annotation. We evaluate our model in both conventional multi-label learning and zero-shot learning scenario. Experimental results demonstrate that our approach outperforms other compared state-of-the-art methods.","doi":"10.24963/ijcai.2018/388","url":"https://ijcai.org/proceedings/2018/388","pdf":"https://ijcai.org/proceedings/2018/0388.pdf","markdown":"https://ijcai.org/proceedings/2018/388.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/388","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Machine Learning","track":"Main track","number":388,"pages":{"first":2798,"last":2804},"keywords":["Machine Learning: Machine Learning","Machine Learning: Multi-instance;Multi-label;Multi-view learning"],"videos":[],"references":[{"position":1,"raw":"[Antol et al., 2014] Stanislaw Antol, C Lawrence Zitnick, and Devi Parikh. Zero-shot learning via visual abstraction. In ECCV, pages 401-416, 2014.","title":"Zero-shot learning via visual abstraction","authors":"Antol","year":"2014","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Boutell et al., 2004] Matthew R Boutell, Jiebo Luo, Xipeng Shen, and Christopher M Brown. Learning multi-label scene classification. PR, 37(9):1757-1771, 2004.","title":"Learning multi-label scene classification","authors":"Jiebo Matthew R Boutell, Xipeng Luo, Christopher M Shen, Brown","year":"2004","venue":"PR","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Boyd et al., 2011] Stephen Boyd, Neal Parikh, Eric Chu, Borja Peleato, and Jonathan Eckstein. Distributed opti- mization and statistical learning via the alternating direc- tion method of multipliers. Foundations and Trends in Ma- chine Learning, 3(1):1-122, 2011.","title":"Distributed optimization and statistical learning via the alternating direction method of multipliers","authors":"Stephen Boyd, Neal Parikh, Eric Chu, Borja Peleato, Jonathan Eckstein","year":"2011","venue":"Foundations and Trends in Machine Learning","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Briggs et al., 2013] F Briggs, Huang Yonghong, R Raich, et al. New methods for acoustic classification of multi- ple simultaneous bird species in a noisy environment. In MLSP, pages 1-8, 2013.","title":"New methods for acoustic classification of multiple simultaneous bird species in a noisy environment","authors":"Huang Briggs, Yonghong, Raich","year":"2013","venue":"MLSP","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chen et al., 2013] Minmin Chen, Alice Zheng, et al. Fast image tagging. In ICML, pages 1274-1282, 2013.","title":"Fast image tagging","authors":"Minmin Chen, Alice Zheng","year":"2013","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Coppersmith and Winograd, 1987] Don Coppersmith and Shmuel Winograd. Matrix multiplication via arithmetic progressions. In STC, pages 1-6, 1987.","title":"Don Coppersmith and Shmuel Winograd. Matrix multiplication via arithmetic progressions","authors":"Winograd Coppersmith","year":"1987","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Ding and Fu, 2014] Zhengming Ding and Yun Fu. Low- rank common subspace for multi-view learning. In ICDM, pages 110-119. IEEE, 2014.","title":"Lowrank common subspace for multi-view learning","authors":"Zhengming Ding, Yun Fu","year":"2014","venue":"ICDM","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Ding et al., 2017] Zhengming Ding, Ming Shao, and Yun Fu. Low-rank embedded ensemble semantic dictionary for zero-shot learning. In CVPR, pages 2050-2058, 2017.","title":"Low-rank embedded ensemble semantic dictionary for zero-shot learning","authors":"Zhengming Ding, Ming Shao, Yun Fu","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Godbole and Sarawagi, 2004] Shantanu Godbole and Sunita Sarawagi. Discriminative methods for multi- labeled classification. In PAKDD, pages 22-30, 2004.","title":"Discriminative methods for multilabeled classification","authors":"Shantanu Godbole, Sunita Sarawagi","year":"2004","venue":"PAKDD","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Guillaumin et al., 2009] Matthieu Guillaumin, Thomas Mensink, Jakob Verbeek, et al. Tagprop: Discriminative metric learning in nearest neighbor models for image auto-annotation. In ICCV, pages 309-316, 2009.","title":"Tagprop: Discriminative metric learning in nearest neighbor models for image auto-annotation","authors":"Matthieu Guillaumin, Thomas Mensink, Jakob Verbeek","year":"2009","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Guo et al., 2016] Baolin Guo, Chenping Hou, Feiping Nie, and Dongyun Yi. Semi-supervised multi-label dimension- ality reduction. In ICDM, pages 919-924, 2016.","title":"Semi-supervised multi-label dimensionality reduction","authors":"Baolin Guo, Chenping Hou, Feiping Nie, Dongyun Yi","year":"2016","venue":"ICDM","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Lampert et al., 2009] Christoph H Lampert, Hannes Nick- isch, and Stefan Harmeling. Learning to detect unseen ob- ject classes by between-class attribute transfer. In CVPR, pages 951-958, 2009.","title":"Learning to detect unseen object classes by between-class attribute transfer","authors":"Hannes Christoph H Lampert, Stefan Nickisch, Harmeling","year":"2009","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Lampert et al., 2014] Christoph H Lampert, Hannes Nick- isch, and Stefan Harmeling. Attribute-based classification for zero-shot visual object categorization. IEEE TPAMI, 36(3):453-465, 2014.","title":"Attribute-based classification for zero-shot visual object categorization","authors":"Hannes Christoph H Lampert, Stefan Nickisch, Harmeling","year":"2014","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Liu and Tsang, 2015] Weiwei Liu and Ivor Tsang. On the optimality of classifier chain for multi-label classification. In NIPS, pages 712-720, 2015.","title":"On the optimality of classifier chain for multi-label classification","authors":"Tsang Liu, Weiwei Liu, Ivor Tsang","year":"2015","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Liu et al., 2006] Jing Liu, Mingjing Li, Wei-Ying Ma, et al. An adaptive graph model for automatic image annotation. In ACM SIGMM, pages 61-70, 2006.","title":"An adaptive graph model for automatic image annotation","authors":"Jing Liu, Mingjing Li, Wei-Ying Ma","year":"2006","venue":"ACM SIGMM","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Liu et al., 2017] Weiwei Liu, Ivor W Tsang, and Klaus- Robert Müller. An easy-to-hard learning paradigm for multiple classes and multiple labels. JMLR, pages 3300- 3337, 2017.","title":"An easy-to-hard learning paradigm for multiple classes and multiple labels","authors":"Weiwei Liu, Ivor W Tsang, Klaus-Robert Müller","year":"2017","venue":"JMLR","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Liu et al., 2018] Weiwei Liu, Donna Xu, Ivor Tsang, and Wenjie Zhang. Metric learning for multi-output tasks. IEEE TPAMI, 2018.","title":"Metric learning for multi-output tasks","authors":"Weiwei Liu, Donna Xu, Ivor Tsang, Wenjie Zhang","year":"2018","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Merris, 1994] Russell Merris. Laplacian matrices of graphs: a survey. Linear algebra and its applications, pages 143- 176, 1994.","title":"Laplacian matrices of graphs: a survey","authors":"Russell Merris","year":"1994","venue":"Linear algebra and its applications","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Ng et al., 2001] Andrew Y Ng, Michael I Jordan, Yair Weiss, et al. On spectral clustering: Analysis and an al- gorithm. In NIPS, volume 14, pages 849-856, 2001.","title":"On spectral clustering: Analysis and an algorithm","authors":"Y Andrew, Michael I Ng, Yair Jordan, Weiss","year":"2001","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Nie et al., 2012] Feiping Nie, Dong Xu, and Xuelong Li. Initialization independent clustering with actively self- training method. IEEE TSMC, 42(1):17-27, 2012.","title":"Initialization independent clustering with actively selftraining method","authors":"Nie","year":"2012","venue":"IEEE TSMC","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Nie et al., 2016] Feiping Nie, Wei Zhu, and Xuelong Li. Unsupervised feature selection with structured graph op- timization. In AAAI, pages 1302-1308, 2016.","title":"Unsupervised feature selection with structured graph optimization","authors":"Nie","year":"2016","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Nie et al., 2017] Feiping Nie, Guohao Cai, and Xuelong Li. Multi-view clustering and semi-supervised classification with adaptive neighbours. pages 2408-2414. AAAI, 2017.","title":"Multi-view clustering and semi-supervised classification with adaptive neighbours","authors":"Nie","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Patterson and Hays, 2012] Genevieve Patterson and James Hays. Sun attribute database: Discovering, annotating, and recognizing scene attributes. In CVPR, pages 2751-2758, 2012.","title":"Sun attribute database: Discovering, annotating, and recognizing scene attributes","authors":"Genevieve Patterson, James Hays","year":"2012","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Simonyan and Zisserman, 2014] Karen Simonyan and An- drew Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.","title":"Very deep convolutional networks for large-scale image recognition","authors":"Karen Simonyan, Andrew Zisserman","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Sindhwani and Belkin, 2005] Vikas Sindhwani and Mikhail Belkin. Beyond the point cloud: from transductive to semi-supervised learning. In ICML, pages 824-831, 2005.","title":"Beyond the point cloud: from transductive to semi-supervised learning","authors":"Belkin Sindhwani, Vikas Sindhwani, Mikhail Belkin","year":"2005","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Trohidis et al., 2008] Konstantinos Trohidis, Grigorios Tsoumakas, George Kalliris, and Ioannis P Vlahavas. Multi-label classification of music into emotions. In ISMIR, pages 325-330, 2008.","title":"Multi-label classification of music into emotions","authors":"Konstantinos Trohidis, Grigorios Tsoumakas, George Kalliris, Ioannis P Vlahavas","year":"2008","venue":"ISMIR","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Wah et al., 2011] C. Wah, S. Branson, P. Welinder, P. Per- ona, and S. Belongie. The Caltech-UCSD Birds-200-2011 Dataset. Technical report, 2011.","title":"The Caltech-UCSD Birds-200-2011 Dataset","authors":"C Wah, S Branson, P Welinder, P Perona, S Belongie","year":"2011","venue":null,"doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Wang et al., 2018] Lichen Wang, Zhengming Ding, and Yun Fu. Learning transferable subspace for human mo- tion segmentation. In AAAI, 2018.","title":"Learning transferable subspace for human motion segmentation","authors":"Wang","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Wu et al., 2015] Baoyuan Wu, Siwei Lyu, and Bernard Ghanem. Ml-mg: multi-label learning with missing labels using a mixed graph. In ICCV, pages 4157-4165, 2015.","title":"Ml-mg: multi-label learning with missing labels using a mixed graph","authors":"Wu","year":"2015","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Zha et al., 2009] Zheng-Jun Zha, Tao Mei, Jingdong Wang, Zengfu Wang, and Xian-Sheng Hua. Graph-based semi- supervised learning with multiple labels. JVCIR, pages 97 -103, 2009.","title":"Graph-based semisupervised learning with multiple labels","authors":"Zheng-Jun Zha, Tao Mei, Jingdong Wang, Zengfu Wang, Xian-Sheng Hua","year":"2009","venue":"JVCIR","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Zhu et al., 2003] Xiaojin Zhu, Zoubin Ghahramani, et al. Semi-supervised learning using gaussian fields and har- monic functions. In ICML, pages 912-919, 2003.","title":"Semi-supervised learning using gaussian fields and harmonic functions","authors":"Xiaojin Zhu, Zoubin Ghahramani","year":"2003","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zhu, 2005] Xiaojin Zhu. Semi-supervised learning litera- ture survey. 2005.","title":"Semi-supervised learning literature survey","authors":"Xiaojin Zhu","year":"2005","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}