C3D-LSTM: a novel convolution-3D-based LSTM for link prediction in dynamic social networks

Abstract

Recently, due to the surge in the use of social networks, link prediction has become an essential technique which could enable service providers to anticipate future friendships between users based on the network structure and personal data so as to enhance consumer loyalty and experience. Undoubtedly, link prediction analysis becomes increasingly difficult when social networks expand quickly, particularly in light of the major advancements in complex social network modelling. Prior studies which predicted social links based on static network settings may have ignored the dynamic variation of networks over time. In this research, an end-to-end model, convolution-3D-based long-short-term memory (abbreviated as C3D-LSTM), is developed to integrate the convolution neural network (CNN) and long-short-term memory (LSTM) network for effective link prediction. We employ 3D convolution to detect subtle patterns in social network snapshots, capturing short-term spatial-temporal features. LSTM layers then interpret these features to model the network's long-term temporal dynamics. To demonstrate its practicability, extensive experiments are conducted to show that C3D-LSTM surpasses current state-of-the-art techniques and delivers remarkable performance.