Link prediction is the problem of inferring future interactions among existing network members based on available knowledge. Computing similarity between a node pair is a known solution for link prediction. This article proposes some new similarity measures. Some of them use nodes’ recency of activities, some weights of edges and some fusion of both in their calculation. A new definition of recency is provided here. A supervised learning method that applies a range of network properties and nodes similarity measures as its features set is developed here for experiments. The results of the experiments indicate that using proposed similarity measures would improve the performance of the link prediction.
AdamicL.A. and AdarE., Friends and neighbors on the web, Soc Networks25 (2003), 211–230.
2.
BarabâsiA-L, JeongH., NédaZ., RavaszE., SchubertA., VicsekT., Evolution of the social network of scientific collaborations, Phys A Stat Mech its Appl311 (2002), 590–614.
3.
BradleyA.P., The use of the area under the ROC curve in the evaluation of machine learning algorithms, Pattern Recognit30 (1997), 1145–1159.
4.
CsardiG. and NepuszT., The igraph software package for complex network research, Inter Journal Complex Sy (2010), 1695.
5.
CulpM., JohnsonK. and MichailidisG., ada: The R Package Ada for Stochastic Boosting, 2016.
6.
FawcettT., An introduction to ROC analysis, Pattern Recognit Lett27 (2006), 861–874.
7.
FriedmanJ.H., Stochastic gradient boosting, Comput Stat Data Anal38 (2002), 367–378.
8.
Jed WingM.K.C.,
Weston, S., Williams, A., Keefer, C., Engelhardt, A., Cooper, T., Mayer, Z., Kenkel, B., the R Core Team, Benesty, M., Lescarbeau, R., Ziem, A. and Scrucca, L., caret: Classification and Regression Training, 2015.
9.
GetoorL., ParkC. and DiehlC.P., Link mining: A survey, ACM SIGKDD Explor Newsl7 (2005), 3–12.
10.
GoldbergD.S. and RothF.P., Assessing experimentally derived interactions in a small world, Proc Natl Acad Sci100 (2003), 4372–4376.
11.
Al HasanM.,
ChaojiV.,
SalemS. and ZakiM., Link prediction using supervised learning, SDM’06 Work Link Anal Counter-terrorism Secur, 2006.
12.
ItoT., ShimboM., KudoT., MatsumotoY.. Application of kernels to link analysis, Proc Elev ACM SIGKDD Int Conf Knowl Discov data Min (2005), 586–592.
13.
KrebsV.E., Mapping networks of terrorist cells, Connections24 (2002), 43–52.
14.
KuhnM., WestonS. and CoulterN., code for C5.0 by R. Quinlan MCC, C50: C5.0 Decision Trees and Rule-Based Models, 2015.
15.
Liben-NowellD. and KleinbergJ., The link-prediction problem for social networks, J Am Soc Inf Sci Technol58 (2007), 1019–1031.
16.
LichtenwalterR.N., LussierJ.T., ChawlaN.V., New perspectives and methods in link prediction, In: Proc 16th ACM SIGKDD Int Conf Knowl Discov data Min, pp. 243–252.
17.
LiuH., HuZ., HaddadiH. and TianH., Hidden link prediction based on node centrality and weak ties, EPL (Europhysics Lett101 (2013), 18004.
18.
LüL. and ZhouT., Link prediction in weighted networks: The role of weak ties, EPL (Europhysics Lett89 (2010), 18001.
19.
LüL. and ZhouT., Link prediction in complex networks: A survey, Phys A Stat Mech its Appl390 (2011), 1150–1170. doi:10.1016/j.physa.2010.11.027
20.
LuZ., SavasB., TangW., DhillonI.S.. Supervised link prediction using multiple sources, 2010 IEEE Int Conf data Min (2010), 923–928.
21.
MaC., ZhouT. and ZhangH.-F., Playing the role of weak clique property in link prediction: A friend recommendation model, Sci Rep6 (2016).
22.
MohanS., SubramanianM., A New Method of Identifying Individuals’ Roles in Mobile Telecom Subscriber Data for Improved Group Recommendations. Multidiscip Soc Networks Res Springer (2014), 213–227.
23.
MurataT., MoriyasuS.Link prediction of social networks based on weighted proximity measures. Web Intell IEEE/WIC/ACM Int Conf (2007), 85–88.
24.
NewmanM.E.J., Clustering and preferential attachment in growing networks, Phys Rev E64 (2001), 25102.
25.
OpsahlT. and PanzarasaP., Clustering in weighted networks, Soc Networks31 (2009), 155–163.
26.
PapadimitriouA., SymeonidisP. and ManolopoulosY., Fast and accurate link prediction in social networking systems, J Syst Softw85 (2012), 2119–2132. doi:10.1016/j.jss.2012.04.019
27.
PotgieterA., AprilK., CookeR.J.E. and OsunmakindeI.O., Temporality in link prediction: Understanding social complexity, Sprouts Work Pap Inf Syst7 (2007).
28.
PowersD.M., Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation, 2011.
29.
R Core Team, R: A Language and Environment for Statistical Computing, 2015.
30.
RobinX., TurckN., HainardA., TibertiN., LisacekF., SanchezJ.-C. and MiL.M., pROC: An open-source package for R and S+ to analyze and compare ROC curves, BMC Bioinformatics12 (2011), 77.
31.
De SáH.R., PrudêncioR.B.C.. Supervised link prediction in weighted networks. Neural Networks (IJCNN), 2011 Int Jt Conf (2011), 2281–2288.
32.
ShimboM., ItoT., MochihashiD. and MatsumotoY., On the properties of von Neumann kernels for link analysis, Mach Learn75 (2008), 37–67. doi:10.1007/s10994-008-5090-6
33.
VieraA.J. and GarrettJ.M., Understanding interobserver agreement: The kappa statistic, Fam Med37 (2005), 360–363.
34.
WangP., XuB., WuY. and ZhouX., Link prediction in social networks: The state-of-the-art, Sci China Inf Sci58 (2015), 1–38.
35.
YangY., ChawlaN.V., SunY., HanJ.. Predicting Links in Multi-relational and Heterogeneous Networks. ICDM (2012), 755–764.
36.
ZhouT., LüL. and ZhangY.-C., Predicting missing links via local information, Eur Phys J B71 (2009), 623–630.
