Probabilistic latent tensor factorization model for link pattern prediction in multi-relational networks
We address the problem of link prediction in collections of objects connected by multiple relation types,where each type may play a distinct role.While traditional link prediction models are limited to single-type link prediction we attempt here to jointly model and predict the multiple relation types,which we refer to as the link pattern prediction (LPP) problem.For that,we propose a probabilistic latent tensor factorization (PLTF) model and furnish the Bayesian treatment of the probabilistic model to avoid overfitting problem.To learn the proposed model we develop an efficient Markov chain Monte Carlo (MCMC) sampling method.Extensive experiments on several real world multi-relational datasets demonstrate the significant improvements of our model over several state-of-the-art methods.
link pattern prediction latent tensor factorization Gibbs sampling multi-relational networks
GAO Sheng DENOYER Ludovic GALLINARI Patrick GUO Jun
School of Information and Communication Engineering,Beijing University of Posts and Telecommunicatio Laboratoire d”informatique de Paris 6,Université Pierre et Marie CURIE,Paris 75005,France School of Information and Communication Engineering,Beijing University of Posts and Telecommunicatio
国内会议
黄山
英文
172-181
2012-10-25（万方平台首次上网日期，不代表论文的发表时间）