Knowledge Transfer among Heterogeneous Information Networks

Online recommendation systems are becoming more and more popular with the development of web. However, a critical problem of such system is that new users and items are always added to the system with time. How to overcome the data sparseness for such new incoming entities become an important issue. In this paper, we try to reduce the data sparseness in the link prediction problem via involving heterogeneous information network as auxiliary information sources. We developed two models based on the Collective Matrix Factorization (CMF) framework. We also provided a detailed empirical study on how effectively different information networks could help with two real world link prediction tasks. We will report some preliminary results of our current work and also point our several potential research issues.