FILE: A Novel Framework for Predicting Social Status in Signed Networks

Link prediction in signed social networks is challenging because of the existence and imbalance of the three kinds of social status (positive, negative and no-relation). Furthermore, there are a variety types of no-relation status in reality, e.g., strangers and frenemies, which cannot be well distinguished from the other linked status by existing approaches. In this paper, we propose a novel Framework of Integrating both Latent and Explicit features (FILE), to better deal with the norelation status and improve the overall link prediction performance in signed networks. In particular, we design two latent features from latent space and two explicit features by extending social theories, and learn these features for each user via matrix factorization with a specially designed rankingoriented loss function. Experimental results demonstrate the superior of our approach over state-of-the-art methods.

[1]  David Liben-Nowell,et al.  The link-prediction problem for social networks , 2007 .

[2]  Dacheng Tao,et al.  Efficient Latent Link Recommendation in Signed Networks , 2015, KDD.

[3]  Mohammad Al Hasan,et al.  Link prediction using supervised learning , 2006 .

[4]  Lada A. Adamic,et al.  Friends and neighbors on the Web , 2003, Soc. Networks.

[5]  Nitesh V. Chawla,et al.  Vertex collocation profiles: subgraph counting for link analysis and prediction , 2012, WWW.

[6]  W. Bukowski,et al.  Popularity and friendship: Issues in theory, measurement, and outcome. , 1989 .

[7]  Jure Leskovec,et al.  Predicting positive and negative links in online social networks , 2010, WWW '10.

[8]  Svetha Venkatesh,et al.  Towards Discovery of Influence and Personality Traits through Social Link Prediction , 2011, ICWSM.

[9]  Jie Zhang,et al.  Rethinking the Link Prediction Problem in Signed Social Networks , 2017, AAAI.

[10]  Nagarajan Natarajan,et al.  Exploiting longer cycles for link prediction in signed networks , 2011, CIKM '11.

[11]  Christos Faloutsos,et al.  Edge Weight Prediction in Weighted Signed Networks , 2016, 2016 IEEE 16th International Conference on Data Mining (ICDM).

[12]  Jie Zhang,et al.  A Feature-Based Approach for the Redefined Link Prediction Problem in Signed Networks , 2017, ADMA.

[13]  Jure Leskovec,et al.  Signed networks in social media , 2010, CHI.

[14]  Charu C. Aggarwal,et al.  A Survey of Signed Network Mining in Social Media , 2015, ACM Comput. Surv..

[15]  Konstantinos Tserpes,et al.  Predicting Edge Signs in Social Networks Using Frequent Subgraph Discovery , 2014, IEEE Internet Computing.

[16]  Lars Schmidt-Thieme,et al.  BPR: Bayesian Personalized Ranking from Implicit Feedback , 2009, UAI.

[17]  S. Duck,et al.  Personality similarity and the development of friendship: A longitudinal study , 1978 .

[18]  M. Newman.  Clustering and preferential attachment in growing networks. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[19]  Inderjit S. Dhillon,et al.  Low rank modeling of signed networks , 2012, KDD.

[20]  Nitesh V. Chawla,et al.  New perspectives and methods in link prediction , 2010, KDD.

[21]  Charles Elkan,et al.  Link Prediction via Matrix Factorization , 2011, ECML/PKDD.

[22]  Minghua Chen,et al.  Predicting positive and negative links in signed social networks by transfer learning , 2013, WWW.

[23]  Linyuan Lü,et al.  Predicting missing links via local information , 2009, 0901.0553.

[24]  Dongjin Song,et al.  Recommending Positive Links in Signed Social Networks by Optimizing a Generalized AUC , 2015, AAAI.