An Aention-based Collaboration Framework for Multi-View Network Representation Learning

Learning distributed node representations in networks has been a�racting increasing a�ention recently due to its e�ectiveness in a variety of applications. Existing approaches usually study networks with a single type of proximity between nodes, which de�nes a single view of a network. However, in reality there usually exists multiple types of proximities between nodes, yielding networks with multiple views. �is paper studies learning node representations for networks with multiple views, which aims to infer robust node representations across di�erent views. We propose a multi-view representation learning approach, which promotes the collaboration of di�erent views and lets them vote for the robust representations. During the voting process, an a�ention mechanism is introduced, which enables each node to focus on the most informative views. Experimental results on real-world networks show that the proposed approach outperforms existing state-of-theart approaches for network representation learning with a single view and other competitive approaches with multiple views.