Network alignment and link prediction using event-based embedding in aligned heterogeneous dynamic social networks

Abstract

People are associated with multiple social networks to enjoy the exclusive services provided by each. Such users may be well established in some networks but relatively new to others. In order to find their potential connections in any newly entered network, their already existing rich interactions in the neworks where they are well-established can be utilized. We consider two such heterogeneous bibliographic networks where there are common users and propose a novel, event-based embedding algorithm called ABHENE (Alignment Based HEterogeneous Network Embedding) using CNN and transfer learning to construct a target network in a low-dimensional space based on its aligned counterpart. This procedure is repeated for various time slots and the target networks so obtained are fed into an LSTM framework to produce an embedded target network at a future point in time. Using this projected network, the future links among various nodes are predicted. We compare ABHENE with other embedding methods and, from such analysis, it has been found that ABHENE outperforms all its counterparts. Ours is the first work to consider network alignment and link prediction across heterogeneous aligned dynamic social networks. The performance of our link prediction method too surpasses those of other state-of-the-art algorithms. The results highlight the fact that enhanced performance can be achieved by the inclusion of heterogeneity and dynamism in the prediction of future links in partially aligned social networks.