Transfer Learning to Infer Social Ties across Heterogeneous Networks

ACM Trans. Inf. Syst., Volume 34, Issue 2, 2016.

Cited by: 33|Bibtex|Views120|Links
EI
Keywords:
triad factor graphinterpersonal tieLinear Threshold Modelsocial statusMaximum UncertaintyMore(20+)
Weibo:
We show that the proposed model can significantly improve the performance for inferring social ties across different networks compared with several alternative methods

Abstract:

Interpersonal ties are responsible for the structure of social networks and the transmission of information through these networks. Different types of social ties have essentially different influences on people. Awareness of the types of social ties can benefit many applications, such as recommendation and community detection. For example...More

Code:

Data:

0
Introduction
  • Interpersonal ties generally fall into three categories: strong, weak, or absent.
  • Among the 150, you may have five intimate friends, 15 family members, 35 colleagues, and other acquaintances [Goncalves et al 2011].
  • In a mobile communication network, interpersonal ties can be roughly classified into four types: family, colleague, friend, and acquaintance.
  • There is little doubt that behaviors in the email network are governed by the different types of relationships between senders and receivers
Highlights
  • In social networks, interpersonal ties generally fall into three categories: strong, weak, or absent
  • We present an influence propagation method based on the idea from the Linear Threshold Model (LTM) in Kempe et al [2003]
  • Another and more important contribution of our work to this field is that we systematically investigate various social theories and design a principled methodology to combine those social theories into a probabilistic graphical model
  • We investigate the problem of inferring the type of social relationships across heterogeneous networks
  • We show that the proposed model can significantly improve the performance for inferring social ties across different networks compared with several alternative methods
  • Through the observation analysis on six different types of networks, our study reveals several interesting phenomena
Methods
  • The authors compare the following methods for predicting the type of social relationships.

    SVM: Similar to the logistic regression model used in Leskovec et al [2010a], SVM uses attributes associated with each relationship as features to train a classification model and employs the classification model to predict relationships’ labels in the test dataset.
  • The authors compare the following methods for predicting the type of social relationships.
  • SVM: Similar to the logistic regression model used in Leskovec et al [2010a], SVM uses attributes associated with each relationship as features to train a classification model and employs the classification model to predict relationships’ labels in the test dataset.
  • CRF: It trains a conditional random field [Lafferty et al 2001] with attributes associated with each relationship and correlations between relationships.
Results
  • The proposed framework is very general and can be applied to many different networks.
  • The authors consider six different networks: Epinions, Slashdot, MobileU, MobileD, Coauthor, and Enron.
  • On the first three networks (Epinions, Slashdot, and MobileU), the goal is to predict undirected relationships, while on the other three networks (MobileD, Coauthor, and Enron), the goal is to predict directed relationships
Conclusion
  • CONCLUSION AND FUTURE WORK

    In this article, the authors investigate the problem of inferring the type of social relationships across heterogeneous networks.
  • The authors study how to accurately infer social ties in a target network with only few labeled relationships by leveraging information from a source network.
  • The model incorporates social theories into a semisupervised learning framework, which is used to transfer supervised information from the source network to help infer social ties in the target network.
  • The authors show that the proposed model can significantly improve the performance for inferring social ties across different networks compared with several alternative methods.
  • Through the observation analysis on six different types of networks, the study reveals several interesting phenomena
Summary
  • Introduction:

    Interpersonal ties generally fall into three categories: strong, weak, or absent.
  • Among the 150, you may have five intimate friends, 15 family members, 35 colleagues, and other acquaintances [Goncalves et al 2011].
  • In a mobile communication network, interpersonal ties can be roughly classified into four types: family, colleague, friend, and acquaintance.
  • There is little doubt that behaviors in the email network are governed by the different types of relationships between senders and receivers
  • Methods:

    The authors compare the following methods for predicting the type of social relationships.

    SVM: Similar to the logistic regression model used in Leskovec et al [2010a], SVM uses attributes associated with each relationship as features to train a classification model and employs the classification model to predict relationships’ labels in the test dataset.
  • The authors compare the following methods for predicting the type of social relationships.
  • SVM: Similar to the logistic regression model used in Leskovec et al [2010a], SVM uses attributes associated with each relationship as features to train a classification model and employs the classification model to predict relationships’ labels in the test dataset.
  • CRF: It trains a conditional random field [Lafferty et al 2001] with attributes associated with each relationship and correlations between relationships.
  • Results:

    The proposed framework is very general and can be applied to many different networks.
  • The authors consider six different networks: Epinions, Slashdot, MobileU, MobileD, Coauthor, and Enron.
  • On the first three networks (Epinions, Slashdot, and MobileU), the goal is to predict undirected relationships, while on the other three networks (MobileD, Coauthor, and Enron), the goal is to predict directed relationships
  • Conclusion:

    CONCLUSION AND FUTURE WORK

    In this article, the authors investigate the problem of inferring the type of social relationships across heterogeneous networks.
  • The authors study how to accurately infer social ties in a target network with only few labeled relationships by leveraging information from a source network.
  • The model incorporates social theories into a semisupervised learning framework, which is used to transfer supervised information from the source network to help infer social ties in the target network.
  • The authors show that the proposed model can significantly improve the performance for inferring social ties across different networks compared with several alternative methods.
  • Through the observation analysis on six different types of networks, the study reveals several interesting phenomena
Tables
  • Table1: Statistics of Six Datasets
  • Table2: Prediction Accuracy between Homogeneous Networks
  • Table3: Features Defined in Relationship eij (or (vi , vj )) and vk ∈ {vi , vj } in Enron (Email Counts) [<a class="ref-link" id="cDiehl_et+al_2007_a" href="#rDiehl_et+al_2007_a">Diehl et al 2007</a>]
  • Table4: Data Transferred in Distributed Learning Algorithm
  • Table5: Performance Comparison of Different Methods for Predicting Directed Relationships (the Source End Has a Higher Social Status Than the Target End)
  • Table6: Features Defined in Relationship eij (or (vi , vj )) in Coauthor (Pi Denotes a Set of Papers Published by Author vi [Tang et al 2011])
  • Table7: Efficient Performance When Training TranFG on Different Networks (Minute)
  • Table8: Features Defined in Relationship eij (or (vi , vj )) in MobileD The dataset is a mobile network of enterprise, in which we try to infer manager-subordinate relationships between users
  • Table9: Performance Comparison of Different Methods for Predicting Friendships (or Trustful Relationships)
  • Table10: Features Defined on Relationship eij (or (vi , vj )) in Epinions/Slashdot [<a class="ref-link" id="cLeskovec_et+al_2010_a" href="#rLeskovec_et+al_2010_a">Leskovec et al 2010a</a>]
Download tables as Excel
Related work
  • Inferring Social Ties. Inferring social ties is an important problem in social network analysis. Liben-Nowell et al [2007] presented an unsupervised method for link prediction. They studied different algorithms and found that the Katz algorithm 7:35

    can achieve the best performance. Xiang et al [2010] developed a latent variable model to estimate relationship strength from interaction activity and user similarity. Backstrom et al [2011] proposed a supervised random walk algorithm to estimate the strength of social relationships. Leskovec et al [2010a] employed a logistic regression model to predict positive and negative relationships in online social networks. Hopcroft et al [2011] studied the extent to which the formation of a reciprocal relationship can be predicted in a dynamic network. However, most existing works focus on predicting and recommending unknown relationships in social networks but ignore the types of relationships.
Funding
  • Tang is supported by the National High-Tech R&D Program (No 2014AA015103), National Basic Research Program of China (No 2014CB340506, No 2012CB316006), Natural Science Foundation of China (No 61222212), National Social Science Foundation of China (No 13&ZD190), and a Huawei Research Grant
  • Kleinberg has been supported in part by a Google Research Grant, a Yahoo Research Alliance Grant, and NSF grants IIS-0910664, CCF-0910940, and IIS-1016099
Reference
  • Lada A. Adamic and Eytan Adar. 200Friends and neighbors on the web. Social Networks 25 (2001), 211–230.
    Google ScholarLocate open access versionFindings
  • Rie Kubota Ando and Tong Zhang. 2005. A framework for learning predictive structures from multiple tasks and unlabeled data. Journal of Machine Learning Research 6 (2005), 1817–1853.
    Google ScholarLocate open access versionFindings
  • Andreas Argyriou, Theodoros Evgeniou, and Massimiliano Pontil. 2006. Multi-task feature learning. In Proceedings of the 18th Neural Information Processing Systems (NIPS’06). 41–48.
    Google ScholarLocate open access versionFindings
  • Andreas Argyriou, Andreas Maurer, and Massimiliano Pontil. 2008. An algorithm for transfer learning in a heterogeneous environment. In Proceedings of 2008 European Conference on Machine Learning and Knowledge Discovery in Databases (ECML/PKDD’08). 71–85.
    Google ScholarLocate open access versionFindings
  • Lars Backstrom and Jure Leskovec. 2011. Supervised random walks: Predicting and recommending links in social networks. In Proceedings of the 4th ACM International Conference on Web Search and Web Data Mining (WSDM’11). 635–644.
    Google ScholarLocate open access versionFindings
  • Albert-Laszlo Barabasi and Reka Albert. 1999. Emergence of scaling in random networks. Science 286, 5439 (1999), 509–512.
    Google ScholarLocate open access versionFindings
  • John Blitzer, Ryan McDonald, and Fernando Pereira. 2006. Domain adaptation with structural correspondence learning. In Proceedings of Conference on Empirical Methods in Natural Language Processing (EMNLP’06). 120–128.
    Google ScholarLocate open access versionFindings
  • Ronald S. Burt. 1992. Structural Holes: The Social Structure of Competition. Harvard University Press. Bin Cao, Nathan Nan Liu, and Qiang Yang. 2010. Transfer learning for collective link prediction in multiple heterogenous domains. In Proceedings of the 27th International Conference on Machine Learning (ICML’10). 159–166. Wei Chen, Yajun Wang, and Siyu Yang. 2009. Efficient influence maximization in social networks. In Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’09). 199–207. Corinna Cortes and Vladimir Vapnik. 1995. Support-vector networks. Machine Learning 20 (1995), 273–297.
    Google ScholarLocate open access versionFindings
  • David J. Crandall, Lars Backstrom, Dan Cosley, Daniel Huttenlocher Siddharth Suri, and Jon Kleinberg. 2010. Inferring social ties from geographic coincidences. Proceedings of the National Academy of Science 107 (Dec. 2010), 22436–22441. Wenyuan Dai, Yuqiang Chen, Gui-Rong Xue, Qiang Yang, and Yong Yu. 2008. Translated learning: Transfer learning across different feature spaces. In Proceedings of the 22nd Annual Conference on Neural Information Processing Systems (NIPS’08). 353–360. Wenyuan Dai, Guirong Xue, Qiang Yang, and Yong Yu. 2007a. Co-clustering based classification for out-ofdomain documents. In Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’07). 210–21Wenyuan Dai, Qiang Yang, Gui-Rong Xue, and Yong Yu. 2007b. Boosting for transfer learning. In Proceedings of the 24th International Conference on Machine Learning (ICML’07). 193–200.
    Google ScholarLocate open access versionFindings
  • James A. Davis and Samuel Leinhardt. 1972. The structure of positive interpersonal relations in small groups. In Sociological Theories in Progress, J. Berger (Ed.). Vol. 2. Houghton Mifflin, 218–251.
    Google ScholarLocate open access versionFindings
  • Christopher P. Diehl, Galileo Namata, and Lise Getoor. 2007. Relationship identification for social network discovery. In Proceedings of the 24th National Conference on Artificial Intelligence and 9th Conference on Innovative Applications of Artificial Intelligence (AAAI’07). 546–552.
    Google ScholarLocate open access versionFindings
  • Yuxiao Dong, Jie Tang, Nitesh V. Chawla, Tiancheng Lou, Yang Yang, and Bai Wang. 2015. Inferring social status and rich club effects in enterprise communication networks. PLOS One 10, 3 (2015), e0119446.
    Google ScholarLocate open access versionFindings
  • Yuxiao Dong, Jie Tang, Sen Wu, Jilei Tian, Nitesh V. Chawla, Jinghai Rao, and Huanhuan Cao. 2012. Link prediction and recommendation across heterogeneous social networks. In Proceedings of the 12th International Conference on Data Mining (ICDM’12). 181–190.
    Google ScholarLocate open access versionFindings
  • Yuxiao Dong, Jing Zhang, Jie Tang, Nitesh V. Chawla, and Bai Wang. 2015. CoupledLP: Link prediction in coupled networks. In Proceedings of the 21nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’15). 199–208.
    Google ScholarLocate open access versionFindings
  • Nathan Eagle, Alex (Sandy) Pentland, and David Lazer. 2009. Inferring social network structure using mobile phone data. Proceedings of the National Academy of Science 106, 36 (2009), 15274–15278.
    Google ScholarLocate open access versionFindings
  • David Easley and Jon Kleinberg. 2010.
    Google ScholarFindings
  • Jing Gao, Wei Fan, Jing Jian, and Jiawei Han. 2008. Knowledge transfer via multiple model local structure mapping. In Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’08). 283–291.
    Google ScholarLocate open access versionFindings
  • Lise Getoor and Ben Taskar. 2007. Introduction to Statistical Relational Learning. MIT Press.
    Google ScholarFindings
  • Malcolm Gladwell. 2001. The Tipping Point - How Little Things Make a Big Difference (New York, NY: Little Brown, 2000); G. Khermouch and J. Green, Buzz Marketing: Suddenly This Stealth Strategy Is Hot – but It’s Still Fraught with Risk. Business Week (2001), 50.
    Google ScholarLocate open access versionFindings
  • Bruno Goncalves, Nicola Perra, and Alessandro Vespignani. 2011. Modeling users’ activity on twitter networks: Validation of dunbar’s number. PLoS ONE 6 (08 2011), e22656.
    Google ScholarLocate open access versionFindings
  • Mark Granovetter. 1973. The strength of weak ties. American Journal of Sociology 78, 6 (1973), 1360–1380.
    Google ScholarLocate open access versionFindings
  • R. Guha, Ravi Kumar, Prabhakar Raghavan, and Andrew Tomkins. 2004. Propagation of trust and distrust. In Proceedings of the 13th International Conference on World Wide Web (WWW’04). 403–412.
    Google ScholarLocate open access versionFindings
  • J. M. Hammersley and P. Clifford. 1971. Markov field on finite graphs and lattices. Unpublished manuscript (1971).
    Google ScholarFindings
  • John Hopcroft, Tiancheng Lou, and Jie Tang. 2011. Who will follow you back? Reciprocal relationship prediction. In Proceedings of the 20th ACM International Conference on Information and Knowledge Management (CIKM’11). 1137–1146.
    Google ScholarLocate open access versionFindings
  • Tony Jebara. 2004. Multi-task feature and kernel selection for svms. In Proceedings of the 21th International Conference on Machine Learning (ICML’04). 55–62.
    Google ScholarLocate open access versionFindings
  • George Karypis and Vipin Kumar. 1998. MeTis: Unstrctured Graph Partitioning and Sparse Matrix Ordering System, Version 4.0. http://glaros.dtc.umn.edu/gkhome/fetch/sw/metis/manual.pdf.
    Findings
  • Elihu Katz. 1957. The two-step flow of communication: An up-to-date report on an hypothesis. Public Opinion Quarterly 21, 1 (1957), 61–78.
    Google ScholarLocate open access versionFindings
  • Elihu Katz and Paul Felix Lazarsfeld. 1955. Personal Influence. The Free Press, New York, USA.
    Google ScholarFindings
  • Leo Katz. 1953. A new status index derived from sociometric analysis. Psychometrika 18, 1 (1953), 39–43. David Kempe, Jon Kleinberg, and Eva Tardos. 2003. Maximizing the spread of influence through a social network. In Proceedings of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’03). 137–146.
    Google ScholarLocate open access versionFindings
  • Nikos Komodakis, Nikos Paragios, and Georgios Tziritas. 2011. MRF energy minimization and beyond via dual decomposition. IEEE Transactions on Pattern Analalysis and Machine Intelligence 33, 3 (2011), 531–552.
    Google ScholarLocate open access versionFindings
  • David Krackhardt. 1992. The strength of strong ties: The importance of philos in organizations. Networks and Organizations: Structure, Form, and Action 216 (1992), 239.
    Google ScholarLocate open access versionFindings
  • Frank R. Kschischang, Brendan J. Frey, and Hans andrea Loeliger. 2001. Factor graphs and the sum-product algorithm. IEEE Transactions on Information Theory 47 (2001), 498–519.
    Google ScholarLocate open access versionFindings
  • John D. Lafferty, Andrew McCallum, and Fernando C. N. Pereira. 2001. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In Proceedings of the 18th International Conference on Machine Learning (ICML’01). 282–289.
    Google ScholarLocate open access versionFindings
  • Steffen L. Lauritzen. 1996. Graphical Models. Oxford University Press, Oxford.
    Google ScholarFindings
  • Paul Felix Lazarsfeld, Bernard Berelson, and Hazel Gaudet. 1944. The People’s Choice: How the Voter Makes up his Mind in a Presidential Campaign. Columbia University Press, New York, NY, USA.
    Google ScholarFindings
  • Su-In Lee, Vassil Chatalbashev, David Vickrey, and Daphne Koller. 2007. Learning a meta-level prior for feature relevance from multiple related tasks. In Proceedings of the 24th International Conference on Machine Learning (ICML’07). 489–496.
    Google ScholarLocate open access versionFindings
  • Jure Leskovec, Daniel Huttenlocher, and Jon Kleinberg. 2010a. Predicting positive and negative links in online social networks. In Proceedings of the 19th International Conference on World Wide Web (WWW’10). 641–650.
    Google ScholarLocate open access versionFindings
  • Jure Leskovec, Daniel Huttenlocher, and Jon Kleinberg. 2010b. Signed networks in social media. In Proceedings of the 28th International Conference on Human Factors in Computing Systems (CHI’10). 1361–1370.
    Google ScholarLocate open access versionFindings
  • Xuejun Liao, Ya Xue, and Lawrence Carin. 2005. Logistic regression with an auxiliary data source. In Proceedings of the 22th International Conference on Machine Learning (ICML’05). 505–512.
    Google ScholarLocate open access versionFindings
  • David Liben-Nowell and Jon M. Kleinberg. 2007. The link-prediction problem for social networks. Journal of the American Society for Information Science and Technology 58, 7 (2007), 1019–1031.
    Google ScholarLocate open access versionFindings
  • Ryan Lichtenwalter, Jake T. Lussier, and Nitesh V. Chawla. 2010. New perspectives and methods in link prediction. In Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’10). 243–252.
    Google ScholarLocate open access versionFindings
  • Xiao Ling, Guirong Xue, Wenyuan Dai, Yun Jiang, Qiang Yang, and Yong Yu. 2008. Can Chinese web pages be classified with english data source? In Proceeding of the 17th International Conference on World Wide Web (WWW’08). 969–978.
    Google ScholarLocate open access versionFindings
  • Tiancheng Lou and Jie Tang. 2013. Mining structural hole spanners through information diffusion in social networks. In Proceedings of the 22th International Conference on World Wide Web (WWW’13). 837–848.
    Google ScholarLocate open access versionFindings
  • Tiancheng Lou, Jie Tang, John Hopcroft, Zhanpeng Fang, and Xiaowen Ding. 2013. Learning to predict reciprocity and triadic closure in social networks. ACM Transactions on Knowledge Discovery from Data 7, 2 (2013), Article No. 5.
    Google ScholarLocate open access versionFindings
  • Julian McAuley and Jure Leskovec. 2014. Discovering social circles in ego networks. ACM Transactions on Knowledge Discovery from Data (TKDD) 8, 1 (2014), 4.
    Google ScholarLocate open access versionFindings
  • Kevin P. Murphy, Yair Weiss, and Michael I. Jordan. 1999. Loopy belief propagation for approximate inference: An empirical study. In Proceedings of the 15th Conference on Uncertainty in Artificial Intelligence (UAI’99). 467–475.
    Google ScholarLocate open access versionFindings
  • G. L. Nemhauser, L. A. Wolsey, and M. L. Fisher. 1978. An analysis of approximations for maximizing submodular set functions. Mathematical Programming 14, 1 (1978), 265–294.
    Google ScholarLocate open access versionFindings
  • M. E. J. Newman. 2001. Clustering and preferential attachment in growing networks. Physical Reviews E 64, 2 (2001), 025102.
    Google ScholarLocate open access versionFindings
  • Lawrence Page, Sergey Brin, Rajeev Motwani, and Terry Winograd. 1999. The PageRank Citation Ranking: Bringing Order to the Web. Technical Report SIDL-WP-1999-0120. Stanford University.
    Google ScholarFindings
  • Sinno Jialin Pan and Qiang Yang. 2010. A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering 22, 10 (Oct. 2010), 1345 –1359.
    Google ScholarLocate open access versionFindings
  • Maayan Roth, Assaf Ben-David, David Deutscher, Guy Flysher, Ilan Horn, Ari Leichtberg, Naty Leiser, Yossi Matias, and Ron Merom. 2010. Suggesting friends using the implicit social graph. In Proceedings of the 16th International Conference on Knowledge Discovery and Data Mining (KDD’10). 233–242.
    Google ScholarLocate open access versionFindings
  • Burr Settles and Mark Craven. 2008. An analysis of active learning strategies for sequence labeling tasks. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’08). 1070–1079.
    Google ScholarLocate open access versionFindings
  • Xiaoxiao Shi, Wei Fan, and Jiangtao Ren. 2008. Actively transfer domain knowledge. In Proceedings of 2008 European Conference on Machine Learning and Knowledge Discovery in Databases (ECML/PKDD’08). 342–357.
    Google ScholarLocate open access versionFindings
  • Xiaodan Song, Yun Chi, Koji Hino, and Belle L. Tseng. 2007. Identifying opinion leaders in the blogosphere. In Proceedings of the 15th ACM International Conference on Information and Knowledge Management (CIKM’06). 971–974.
    Google ScholarLocate open access versionFindings
  • Chenhao Tan, Lillian Lee, Jie Tang, Long Jiang, Ming Zhou, and Ping Li. 2011. User-level sentiment analysis incorporating social networks. In Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’11). 1397–1405.
    Google ScholarLocate open access versionFindings
  • Chenhao Tan, Jie Tang, Jimeng Sun, Quan Lin, and Fengjiao Wang. 2010. Social action tracking via noise tolerant time-varying factor graphs. In Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’10). 1049–1058.
    Google ScholarLocate open access versionFindings
  • Jie Tang, Tiancheng Lou, and Jon Kleinberg. 2012. Inferring social ties across heterogeneous networks. In Proceedings of the 5th ACM International Conference on Web Search and Data Mining (WSDM’12). 743–752.
    Google ScholarLocate open access versionFindings
  • Jie Tang, Jimeng Sun, Chi Wang, and Zi Yang. 2009. Social influence analysis in large-scale networks. In Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’09). 807–816.
    Google ScholarLocate open access versionFindings
  • Jie Tang, Jing Zhang, Limin Yao, Juanzi Li, Li Zhang, and Zhong Su. 2008. ArnetMiner: Extraction and mining of academic social networks. In Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’08). 990–998.
    Google ScholarLocate open access versionFindings
  • Lei Tang and Huan Liu. 2011. Leveraging social media networks for classification. Data Mining and Knowledge Discovery 23, 3 (2011), 447–478.
    Google ScholarLocate open access versionFindings
  • Wenbin Tang, Honglei Zhuang, and Jie Tang. 2011. Learning to Infer Social Ties in Large Networks. In Proceedings of 2011 European Conference on Machine Learning and Knowledge Discovery in Databases (ECML/PKDD’11). 381–397.
    Google ScholarLocate open access versionFindings
  • Benjamin Taskar, Ming Fai Wong, Pieter Abbeel, and Daphne Koller. 2003. Link prediction in relational data. In Proceedings of the 15th Neural Information Processing Systems (NIPS’03).
    Google ScholarLocate open access versionFindings
  • Martin J. Wainwright and Michael I. Jordan. 2008. Graphical models, exponential families, and variational inference. Foundational Trends in Machine Learning 1, 1–2 (Jan. 2008), 1–305.
    Google ScholarLocate open access versionFindings
  • Chi Wang, Jiawei Han, Yuntao Jia, Jie Tang, Duo Zhang, Yintao Yu, and Jingyi Guo. 2010. Mining advisoradvisee relationships from research publication networks. In Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’10). 203–212.
    Google ScholarLocate open access versionFindings
  • Liaoruo Wang, Tiancheng Lou, Jie Tang, and John Hopcroft. 2011. Detecting community kernels in large social networks. In Proceedings of 2011 IEEE International Conference on Data Mining (ICDM’11). 784–793.
    Google ScholarLocate open access versionFindings
  • Wim Wiegerinck. 2000. Variational approximations between mean field theory and the junction tree algorithm. In Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence (UAI’00). 626–633.
    Google ScholarLocate open access versionFindings
  • Shaomei Wu, J. M. Hofman, W. A. Mason, and D. J. Watts. 2011. Who says what to whom on twitter. In Proceedings of the 20th International Conference on World Wide Web (WWW’11). 705–714.
    Google ScholarLocate open access versionFindings
  • Rongjing Xiang, Jennifer Neville, and Monica Rogati. 2010. Modeling relationship strength in online social networks. In Proceedings of the 19th International Conference on World Wide Web (WWW’10). 981–990.
    Google ScholarLocate open access versionFindings
  • Eric P. Xing, Michael I. Jordan, and Stuart Russell. 2003. A generalized mean field algorithm for variational inference in exponential families. In Proceedings of 19th Conference on Uncertainty in Artificial Intelligence (UAI’03). 583–591.
    Google ScholarLocate open access versionFindings
  • Yang Yang, Yizhou Sun, Jie Tang, Bo Ma, and Juanzi Li. 2015. Entity matching across heterogeneous sources. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’15). 1395–1404.
    Google ScholarLocate open access versionFindings
  • Zi Yang, Jingyi Guo, Keke Cai, Jie Tang, Juanzi Li, Li Zhang, and Zhong Su. 2010. Understanding retweeting behaviors in social networks. In Proceedings of the 19th ACM Conference on Information and Knowledge Management (CIKM’10). 1633–1636.
    Google ScholarLocate open access versionFindings
  • Jiawei Zhang, Xiangnan Kong, and Philip S. Yu. 2013. Predicting social links for new users across aligned heterogeneous social networks. In ICDM’13. 1289–1294.
    Google ScholarLocate open access versionFindings
  • Yutao Zhang, Jie Tang, Zhilin Yang, Jian Pei, and Philip Yu. 2015. COSNET: Connecting heterogeneous social networks with local and global consistency. In KDD’15. 1485–1494.
    Google ScholarLocate open access versionFindings
  • Honglei Zhuang, Jie Tang, Wenbin Tang, Tiancheng Lou, Alvin Chin, and Xia Wang. 2012. Actively learning to infer social ties. Data Mining and Knowledge Discovery 25, 2 (2012), 270–297.
    Google ScholarLocate open access versionFindings
  • Received June 2014; revised January 2015; accepted March 2015
    Google ScholarFindings
Your rating :
0

 

Tags
Comments