{"type":"ScholarlyArticle","title":"Deep Multi-View Concept Learning","authors":[{"name":"Cai Xu","slug":"cai-xu","given":"Cai","family":"Xu","affiliation":"College of Computer Science and Technology , Henan Polytechnic University"},{"name":"Ziyu Guan","slug":"ziyu-guan","given":"Ziyu","family":"Guan","affiliation":"College of Computer Science and Technology , Henan Polytechnic University"},{"name":"Wei Zhao","slug":"wei-zhao","given":"Wei","family":"Zhao","affiliation":"School of Computer Science and Technology , Xidian University"},{"name":"Yunfei Niu","slug":"yunfei-niu","given":"Yunfei","family":"Niu","affiliation":"School of Computer Science and Technology , Xidian University"},{"name":"Quan Wang","slug":"quan-wang","given":"Quan","family":"Wang","affiliation":"‡ State Key Lab of ISN , School of Computer Science and Technology , Xidian University"},{"name":"Zhiheng Wang","slug":"zhiheng-wang","given":"Zhiheng","family":"Wang","affiliation":"School of Computer Science and Technology , Xidian University"}],"abstract":"Multi-view data is common in real-world datasets, where different views describe distinct perspectives. To better summarize the consistent and complementary information in multi-view data, researchers have proposed various multi-view representation learning algorithms, typically based on factorization models. However, most previous methods were focused on shallow factorization models which cannot capture the complex hierarchical information. Although a deep multi-view factorization model has been proposed recently, it fails to explicitly discern consistent and complementary information in multi-view data and does not consider conceptual labels. In this work we present a semi-supervised deep multi-view factorization method, named Deep Multi-view Concept Learning (DMCL). DMCL performs nonnegative factorization of the data hierarchically, and tries to capture semantic structures and explicitly model consistent and complementary information in multi-view data at the highest abstraction level. We develop a block coordinate descent algorithm for DMCL. Experiments conducted on image and document datasets show that DMCL performs well and outperforms baseline methods.","doi":"10.24963/ijcai.2018/402","url":"https://ijcai.org/proceedings/2018/402","pdf":"https://ijcai.org/proceedings/2018/0402.pdf","markdown":"https://ijcai.org/proceedings/2018/402.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/402","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":402,"pages":{"first":2898,"last":2904},"keywords":["Machine Learning: Dimensionality Reduction and Manifold Learning","Machine Learning: Multi-instance;Multi-label;Multi-view learning"],"videos":[],"references":[{"position":1,"raw":"[Amini et al., 2009] Massih Amini, Nicolas Usunier, and Cyril Goutte. Learning from multiple partially observed views-an application to multilingual text categorization. In NIPS, pages 28-36, 2009.","title":"Learning from multiple partially observed views-an application to multilingual text categorization","authors":"Massih Amini, Nicolas Usunier, Cyril Goutte","year":"2009","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bengio and others, 2009] Yoshua Bengio et al. Learning deep architectures for ai. Found. Trends Mach. Learn., 2(1):1-127, 2009.","title":"Learning deep architectures for ai","authors":"Yoshua Bengio","year":"2009","venue":"Found. Trends Mach. Learn","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chaudhuri et al., 2009] Kamalika Chaudhuri, Sham M. Kakade, Karen Livescu, and Karthik Sridharan. Multi- view clustering via canonical correlation analysis. In ICML, pages 129-136, 2009.","title":"Multiview clustering via canonical correlation analysis","authors":"Kamalika Chaudhuri, M Sham, Karen Kakade, Karthik Livescu, Sridharan","year":"2009","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Deng et al., 2009] Jia Deng, Wei Dong, Richard Socher, Li- Jia Li, Kai Li, and Li Fei-Fei. Imagenet: A large-scale hierarchical image database. In CVPR, pages 248-255, 2009.","title":"Imagenet: A large-scale hierarchical image database","authors":"Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, Li Fei-Fei","year":"2009","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Deng et al., 2015] Cheng Deng, Zongting Lv, Wei Liu, Jun- zhou Huang, Dacheng Tao, and Xinbo Gao. Multi-view matrix decomposition: A new scheme for exploring dis- criminative information. In IJCAI, pages 3438-3444, 2015.","title":"Multi-view matrix decomposition: A new scheme for exploring discriminative information","authors":"Cheng Deng, Zongting Lv, Wei Liu, Junzhou Huang, Dacheng Tao, Xinbo Gao","year":"2015","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2015/484"},{"position":6,"raw":"[Guan et al., 2015] Ziyu Guan, Lijun Zhang, Jinye Peng, and Jianping Fan. Multi-view concept learning for data repre- sentation. IEEE TKDE, 27(11):3016-3028, 2015.","title":"Multi-view concept learning for data representation","authors":"Lijun Ziyu Guan, Jinye Zhang, Jianping Peng, Fan","year":"2015","venue":"IEEE TKDE","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Han et al., 2011] Jiawei Han, Jian Pei, and Micheline Kam- ber. Data mining: concepts and techniques. Elsevier, 2011.","title":"Data mining: concepts and techniques","authors":"Jiawei Han, Jian Pei, Micheline Kamber","year":"2011","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hinton and Salakhutdinov, 2006] Geoffrey E Hinton and Ruslan R Salakhutdinov. Reducing the dimensionality of data with neural networks. Science, 313(5786):504-507, 2006.","title":"Reducing the dimensionality of data with neural networks","authors":"Geoffrey E Hinton, Ruslan R Salakhutdinov","year":"2006","venue":"Science","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Lee and Seung, 2001] Daniel D Lee and H Sebastian Seung. Algorithms for non-negative matrix factorization. In NIPS, pages 556-562, 2001.","title":"Algorithms for non-negative matrix factorization","authors":"D Daniel, H Lee, Seung Sebastian","year":"2001","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Li et al., 2016] Yingming Li, Ming Yang, and Zhongfei Zhang. Multi-view representation learning: A survey from shallow methods to deep methods. arXiv preprint arXiv:1610.01206, 2016.","title":"Multi-view representation learning: A survey from shallow methods to deep methods","authors":"Li","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Lin, 2007] Chih-Jen Lin. Projected gradient methods for nonnegative matrix factorization. Neural Comput., 19(10):2756-2779, 2007.","title":"Projected gradient methods for nonnegative matrix factorization","authors":"Lin ; Chih-Jen Lin","year":"2007","venue":"Neural Comput","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Liu et al., 2015] Jing Liu, Yu Jiang, Zechao Li, Zhi-Hua Zhou, and Hanqing Lu. Partially shared latent factor learn- ing with multiview data. IEEE Trans. Neural Netw. Learn. Syst., 26(6):1233-1246, 2015.","title":"Partially shared latent factor learning with multiview data","authors":"Jing Liu, Yu Jiang, Zechao Li, Zhi-Hua Zhou, Hanqing Lu","year":"2015","venue":"IEEE Trans. Neural Netw. Learn. Syst","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Nesterov, 2013] Yu Nesterov. Gradient methods for mini- mizing composite functions. Math. Program., 140(1):125- 161, 2013.","title":"Gradient methods for minimizing composite functions","authors":"Yu Nesterov","year":"2013","venue":"Math. Program","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Ngiam et al., 2011] Jiquan Ngiam, Aditya Khosla, Mingyu Kim, Juhan Nam, Honglak Lee, and Andrew Y Ng. Mul- timodal deep learning. In ICML, pages 689-696, 2011.","title":"Multimodal deep learning","authors":"Ngiam","year":"2011","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Sharma et al., 2017] Pulkit Sharma, Vinayak Abrol, Anil Kumar Sao, Pulkit Sharma, Vinayak Abrol, and Anil Kumar Sao. Deep-sparse-representation-based fea- tures for speech recognition. IEEE Trans. Audio Speech Lang. Process., 25(11):2162-2175, 2017.","title":"Deep-sparse-representation-based features for speech recognition","authors":"Pulkit Sharma, Vinayak Abrol, Anil Kumar Sao, Pulkit Sharma, Vinayak Abrol, Anil Kumar, Sao","year":"2017","venue":"IEEE Trans. Audio Speech Lang. Process","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Song et al., 2015] Hyun Ah Song, Bo-Kyeong Kim, Thanh Luong Xuan, and Soo-Young Lee. Hierarchical feature extraction by multi-layer non-negative matrix factorization network for classification task. Neurocom- puting, 165:63-74, 2015.","title":"Hierarchical feature extraction by multi-layer non-negative matrix factorization network for classification task","authors":"Hyun Ah Song, Bo-Kyeong Kim, Thanh Luong Xuan, Soo-Young Lee","year":"2015","venue":"Neurocomputing","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Srivastava and Salakhutdinov, 2012] Nitish Srivastava and Ruslan R Salakhutdinov. Multimodal learning with deep boltzmann machines. In NIPS, pages 2222-2230, 2012.","title":"Multimodal learning with deep boltzmann machines","authors":"Nitish Srivastava, Ruslan R Salakhutdinov","year":"2012","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Trigeorgis et al., 2017] George Trigeorgis, Konstantinos Bousmalis, Stefanos Zafeiriou, and Björn W Schuller. A deep matrix factorization method for learning attribute representations. IEEE Trans. Pattern Anal. Mach. Intell., 39(3):417-429, 2017.","title":"A deep matrix factorization method for learning attribute representations","authors":"George Trigeorgis, Konstantinos Bousmalis, Stefanos Zafeiriou, Björn W Schuller","year":"2017","venue":"IEEE Trans. Pattern Anal. Mach. Intell","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Wang et al., 2016a] Beidou Wang, Martin Ester, Jiajun Bu, Yu Zhu, Ziyu Guan, and Deng Cai. Which to view: Per- sonalized prioritization for broadcast emails. In WWW, pages 1181-1190, 2016.","title":"Which to view: Personalized prioritization for broadcast emails","authors":"Wang","year":"2016","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Wang et al., 2016b] Beidou Wang, Martin Ester, Yikang Liao, Jiajun Bu, Yu Zhu, Ziyu Guan, and Deng Cai. The million domain challenge: Broadcast email prioritization by cross-domain recommendation. In SIGKDD, pages 1895-1904, 2016.","title":"The million domain challenge: Broadcast email prioritization by cross-domain recommendation","authors":"Wang","year":"2016","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Xu and Sun, 2012] Zhijie Xu and Shiliang Sun. Multi- source transfer learning with multi-view adaboost. In ICONIP, pages 332-339, 2012.","title":"Multisource transfer learning with multi-view adaboost","authors":"Zhijie Xu, Shiliang Sun","year":"2012","venue":"ICONIP","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Yan et al., 2007] Shuicheng Yan, Dong Xu, Benyu Zhang, Hong-Jiang Zhang, Qiang Yang, and Stephen Lin. Graph embedding and extensions: a general framework for di- mensionality reduction. IEEE Trans. Pattern Anal. Mach. Intell., 29(1):40-51, 2007.","title":"Graph embedding and extensions: a general framework for dimensionality reduction","authors":"Shuicheng Yan, Dong Xu, Benyu Zhang, Hong-Jiang Zhang, Qiang Yang, Stephen Lin","year":"2007","venue":"IEEE Trans. Pattern Anal. Mach. Intell","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Zhao et al., 2017] Handong Zhao, Zhengming Ding, and Yun Fu. Multi-view clustering via deep matrix factoriza- tion. In AAAI, pages 2921-2927, 2017.","title":"Multi-view clustering via deep matrix factorization","authors":"Handong Zhao, Zhengming Ding, Yun Fu","year":"2017","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Zong et al., 2017] Linlin Zong, Xianchao Zhang, Long Zhao, Hong Yu, and Qianli Zhao. Multi-view clustering via multi-manifold regularized non-negative matrix factor- ization. Neural Netw., 88:74-89, 2017.","title":"Multi-view clustering via multi-manifold regularized non-negative matrix factorization","authors":"Linlin Zong, Xianchao Zhang, Long Zhao, Hong Yu, Qianli Zhao","year":"2017","venue":"Neural Netw","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}