Contrastive representation learning on dynamic networks

Pengfei Jiao, Hongjiang Chen, Huijun Tang, Qing Bao, Long Zhang, Zhidong Zhao, Huaming Wu

Abstract: Highlights•We propose a novel approach to dynamic network representation learning by applying contrastive learning.•DNCL design dynamic contrastive objective to capture the temporal and topological features of dynamic networks.•DNCL’s objective consists of inter-snapshot contrast and intra-snapshot contrast.•DNCL achieves state-of-the-art performance compared with the base-lines on tasks.