{"type":"ScholarlyArticle","title":"Active Discriminative Network Representation Learning","authors":[{"name":"Li Gao","slug":"li-gao","given":"Li","family":"Gao","affiliation":"* Institute of Information Engineering , Chinese Academy of Sciences , Beijing , China; ‡ Macquarie University , Sydney , Australia School of Cyber Security ,"},{"name":"Hong Yang","slug":"hong-yang","given":"Hong","family":"Yang","affiliation":"† Centre for Artificial Intelligence , University of Technology Sydney , Australia Department of Computing ,"},{"name":"Chuan Zhou","slug":"chuan-zhou","given":"Chuan","family":"Zhou","affiliation":"* Institute of Information Engineering , Chinese Academy of Sciences , Beijing , China; ‡ Macquarie University , Sydney , Australia School of Cyber Security ,"},{"name":"Jia Wu","slug":"jia-wu","given":"Jia","family":"Wu","affiliation":"University of Chinese Academy of Sciences , Beijing , China"},{"name":"Shirui Pan","slug":"shirui-pan","given":"Shirui","family":"Pan","affiliation":"† Centre for Artificial Intelligence , University of Technology Sydney , Australia Department of Computing ,"},{"name":"Yue Hu","slug":"yue-hu","given":"Yue","family":"Hu","affiliation":"* Institute of Information Engineering , Chinese Academy of Sciences , Beijing , China; ‡ Macquarie University , Sydney , Australia School of Cyber Security ,"}],"abstract":"Most of current network representation models are learned in unsupervised fashions, which usually lack the capability of discrimination when applied to network analysis tasks, such as node classification. It is worth noting that label information is valuable for learning the discriminative network representations. However, labels of all training nodes are always difficult or expensive to obtain and manually labeling all nodes for training is inapplicable. Different sets of labeled nodes for model learning lead to different network representation results. In this paper, we propose a novel method, termed as ANRMAB, to learn the active discriminative network representations with a multi-armed bandit mechanism in active learning setting. Specifically, based on the networking data and the learned network representations, we design three active learning query strategies. By deriving an effective reward scheme that is closely related to the estimated performance measure of interest, ANRMAB uses a multi-armed bandit mechanism for adaptive decision making to select the most informative nodes for labeling. The updated labeled nodes are then used for further discriminative network representation learning. Experiments are conducted on three public data sets to verify the effectiveness of ANRMAB.","doi":"10.24963/ijcai.2018/296","url":"https://ijcai.org/proceedings/2018/296","pdf":"https://ijcai.org/proceedings/2018/0296.pdf","markdown":"https://ijcai.org/proceedings/2018/296.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/296","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":296,"pages":{"first":2142,"last":2148},"keywords":["Machine Learning Applications: Networks","Machine Learning: Machine Learning"],"videos":[],"references":[{"position":1,"raw":"[Aggarwal et al., 2014] Charu C Aggarwal, Xiangnan Kong, Quanquan Gu, Jiawei Han, and Philip S Yu. Active learn- ing: A survey. 2014.","title":"Active learning: A survey","authors":"Xiangnan Charu C Aggarwal, Quanquan Kong, Jiawei Gu, Philip S Han, Yu","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Auer et al., 2002] Peter Auer, Nicolo Cesa-Bianchi, Yoav Freund, and Robert E Schapire. The nonstochastic mul- tiarmed bandit problem. SIAM journal on computing, 32(1):48-77, 2002.","title":"The nonstochastic multiarmed bandit problem","authors":"Peter Auer, Nicolo Cesa-Bianchi, Yoav Freund, Robert E Schapire","year":"2002","venue":"SIAM journal on computing","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Beygelzimer et al., 2009] Alina Beygelzimer, Sanjoy Das- gupta, and John Langford. Importance weighted active learning. In ICML, pages 49-56, 2009.","title":"Importance weighted active learning","authors":"Alina Beygelzimer, Sanjoy Dasgupta, John Langford","year":"2009","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Beygelzimer et al., 2011] Alina Beygelzimer, John Lang- ford, Lihong Li, Lev Reyzin, and Robert Schapire. Con- textual bandit algorithms with supervised learning guaran- tees. In AISTATS, pages 19-26, 2011.","title":"Contextual bandit algorithms with supervised learning guarantees","authors":"Alina Beygelzimer, John Langford, Lihong Li, Lev Reyzin, Robert Schapire","year":"2011","venue":"AISTATS","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Cai et al., 2017] HongYun Cai, Vincent Wenchen Zheng, and Kevin Chen-Chuan Chang. Active learning for graph embedding. CoRR, abs/1705.05085, 2017.","title":"Active learning for graph embedding","authors":"Cai","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Cai et al., 2018] Hongyun Cai, Vincent W Zheng, and Kevin Chang. A comprehensive survey of graph embed- ding: problems, techniques and applications. IEEE Trans- actions on Knowledge and Data Engineering, 2018.","title":"A comprehensive survey of graph embedding: problems, techniques and applications","authors":"Hongyun Cai, Vincent W Zheng, Kevin Chang","year":"2018","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Cavallari et al., 2017] Sandro Cavallari, Vincent W Zheng, Hongyun Cai, Kevin Chen-Chuan Chang, and Erik Cam- bria. Learning community embedding with community de- tection and node embedding on graphs. In CIKM, pages 377-386, 2017.","title":"Learning community embedding with community detection and node embedding on graphs","authors":"Sandro Cavallari, Hongyun Vincent W Zheng, Kevin Cai, Chang Chen-Chuan, Erik Cambria","year":"2017","venue":"CIKM","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Donmez et al., 2007] Pinar Donmez, Jaime Carbonell, and Paul Bennett. Dual strategy active learning. In ECML, pages 116-127, 2007.","title":"Dual strategy active learning","authors":"Pinar Donmez, Jaime Carbonell, Paul Bennett","year":"2007","venue":"ECML","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Ganti and Gray, 2012] Ravi Ganti and Alexander G. Gray. UPAL: unbiased pool based active learning. In AISTATS, pages 422-431, 2012.","title":"UPAL: unbiased pool based active learning","authors":"Ravi Ganti, Alexander G Gray","year":"2012","venue":"AISTATS","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Gao et al., 2016] Li Gao, Jia Wu, Zhi Qiao, Chuan Zhou, Hong Yang, and Yue Hu. Collaborative social group in- fluence for event recommendation. In CIKM, pages 1941- 1944, 2016.","title":"Collaborative social group influence for event recommendation","authors":"Li Gao, Jia Wu, Zhi Qiao, Chuan Zhou, Hong Yang, Yue Hu","year":"2016","venue":"CIKM","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Gao et al., 2017] Li Gao, Jia Wu, Chuan Zhou, and Yue Hu. Collaborative dynamic sparse topic regression with user profile evolution for item recommendation. In AAAI, pages 1316-1322, 2017.","title":"Collaborative dynamic sparse topic regression with user profile evolution for item recommendation","authors":"Li Gao, Jia Wu, Chuan Zhou, Yue Hu","year":"2017","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Gittins et al., 1989] J. Gittins, K. Glazebrook, R. Weber, J. Gittins, and R. Weber. Multi-armed bandit allocation indices. Journal of the Operational Research Society, 40(12):1158-1159, 1989.","title":"Multi-armed bandit allocation indices","authors":"J Gittins, K Glazebrook, R Weber, J Gittins, R Weber","year":"1989","venue":"Journal of the Operational Research Society","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Hsu and Lin, 2015] Wei-Ning Hsu and Hsuan-Tien Lin. Active learning by learning. In AAAI, pages 2659-2665, 2015.","title":"Active learning by learning","authors":"Lin ; Wei-Ning Hsu, Hsuan-Tien Hsu, Lin","year":"2015","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kingma and Ba, 2014] Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Kipf and Welling, 2016] Thomas N Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016.","title":"Semi-supervised classification with graph convolutional networks","authors":"N Thomas, Max Kipf, Welling","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Konyushkova et al., 2017] Ksenia Konyushkova, Raphael Sznitman, and Pascal Fua. Learning active learning from data. In NIPS, pages 4228-4238, 2017.","title":"Learning active learning from data","authors":"Ksenia Konyushkova, Raphael Sznitman, Pascal Fua","year":"2017","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Maaten and Hinton, 2008] Laurens Van Der Maaten and Geoffrey Hinton. Visualizing data using t-sne. Journal of Machine Learning Research, 9:2579-2605, 2008.","title":"Visualizing data using t-sne","authors":"Hinton Maaten, Laurens Van, Der Maaten, Geoffrey Hinton","year":"2008","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Newman, 2010] Mark Newman. Networks: an introduc- tion. Oxford university press, 2010.","title":"Networks: an introduction","authors":"Mark Newman","year":"2010","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Page et al., 1999] Lawrence Page, Sergey Brin, Rajeev Motwani, and Terry Winograd. The pagerank citation ranking: Bringing order to the web. Technical report, Stan- ford InfoLab, 1999.","title":"The pagerank citation ranking: Bringing order to the web","authors":"Lawrence Page, Sergey Brin, Rajeev Motwani, Terry Winograd","year":"1999","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Perozzi et al., 2014] Bryan Perozzi, Rami Al-Rfou, and Steven Skiena. Deepwalk: online learning of social rep- resentations. In KDD, pages 701-710, 2014.","title":"Deepwalk: online learning of social representations","authors":"Bryan Perozzi, Rami Al-Rfou, Steven Skiena","year":"2014","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Sen et al., 2008] Prithviraj Sen, Galileo Namata, Mustafa Bilgic, Lise Getoor, Brian Gallagher, and Tina Eliassi- Rad. Collective classification in network data. AI Mag- azine, 29(3):93-106, 2008.","title":"Collective classification in network data","authors":"Prithviraj Sen, Galileo Namata, Mustafa Bilgic, Lise Getoor, Brian Gallagher, Tina Eliassi-Rad","year":"2008","venue":"AI Magazine","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Settles and Craven, 2008] Burr Settles and Mark Craven. An analysis of active learning strategies for sequence la- beling tasks. In EMNLP, pages 1070-1079, 2008.","title":"An analysis of active learning strategies for sequence labeling tasks","authors":"Craven ; Burr Settles, Mark Settles, Craven","year":"2008","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Settles, 2010] Burr Settles. Active learning literature sur- vey. University of Wisconsin, Madison, 52(55-66):11, 2010.","title":"Burr Settles. Active learning literature survey","authors":"Settles","year":"2010","venue":"University of Wisconsin","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Stephenson and Zelen, 1989] Karen Stephenson and Mar- vin Zelen. Rethinking centrality: Methods and examples. Social networks, 11(1):1-37, 1989.","title":"Rethinking centrality: Methods and examples","authors":"Zelen Stephenson","year":"1989","venue":"Social networks","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Tu et al., 2016] Cunchao Tu, Weicheng Zhang, Zhiyuan Liu, and Maosong Sun. Max-margin deepwalk: Discrimi- native learning of network representation. In IJCAI, pages 3889-3895, 2016.","title":"Max-margin deepwalk: Discriminative learning of network representation","authors":"Tu","year":"2016","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2016/547"},{"position":26,"raw":"[Vermorel and Mohri, 2005] Joannès Vermorel and Mehryar Mohri. Multi-armed bandit algorithms and empirical eval- uation. In ECML, pages 437-448, 2005.","title":"Joannès Vermorel and Mehryar Mohri. Multi-armed bandit algorithms and empirical evaluation","authors":"Mohri Vermorel","year":"2005","venue":"ECML","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Yang et al., 2016] Zhilin Yang, William Cohen, and Ruslan Salakhudinov. Revisiting semi-supervised learning with graph embeddings. In ICML, pages 40-48, 2016.","title":"Revisiting semi-supervised learning with graph embeddings","authors":"Zhilin Yang, William Cohen, Ruslan Salakhudinov","year":"2016","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhang et al., 2017] Ye Zhang, Matthew Lease, and By- ron C. Wallace. Active discriminative text representation learning. In AAAI, pages 3386-3392, 2017.","title":"Active discriminative text representation learning","authors":"Zhang","year":"2017","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Zhu et al., 2003] Xiaojin Zhu, John Lafferty, and Zoubin Ghahramani. Combining active learning and semi- supervised learning using gaussian fields and harmonic functions. In ICML-workshop, volume 3, 2003.","title":"Combining active learning and semisupervised learning using gaussian fields and harmonic functions","authors":"Xiaojin Zhu, John Lafferty, Zoubin Ghahramani","year":"2003","venue":"ICML-workshop","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}