Multi-relational matrix factorization using bayesian personalized ranking for social network data

A key element of the social networks on the internet such as Facebook and Flickr is that they encourage users to create connections between themselves, other users and objects. One important task that has been approached in the literature that deals with such data is to use social graphs to predict user behavior (e.g. joining a group of interest). More specifically, we study the cold-start problem, where users only participate in some relations, which we will call social relations, but not in the relation on which the predictions are made, which we will refer to as target relations. We propose a formalization of the problem and a principled approach to it based on multi-relational factorization techniques. Furthermore, we derive a principled feature extraction scheme from the social data to extract predictors for a classifier on the target relation. Experiments conducted on real world datasets show that our approach outperforms current methods. Categories and Subject Descriptors H.3...

• Type: Journal
• Year: 2012
• Where: WSDM
• Authors: Artus Krohn-Grimberghe, Lucas Drumond, Christoph Freudenthaler, Lars Schmidt-Thieme
• Keywords: Data Mining, Matrix Factorization, Principled Approach, Recommender Systems, WSDM 2012