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

TL;DR

This paper introduces an attention-based multi-view network representation learning framework that effectively combines multiple types of node proximities to produce robust embeddings, outperforming existing methods.

Contribution

It proposes a novel multi-view learning approach with an attention mechanism to enhance collaboration among views for better node representations.

Findings

Outperforms state-of-the-art single-view methods

Effective in real-world multi-view networks

Attention mechanism improves view collaboration

Abstract

Learning distributed node representations in networks has been attracting increasing attention recently due to its effectiveness in a variety of applications. Existing approaches usually study networks with a single type of proximity between nodes, which defines a single view of a network. However, in reality there usually exists multiple types of proximities between nodes, yielding networks with multiple views. This paper studies learning node representations for networks with multiple views, which aims to infer robust node representations across different views. We propose a multi-view representation learning approach, which promotes the collaboration of different views and lets them vote for the robust representations. During the voting process, an attention 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-the-art approaches for network representation learning with a single view and other competitive approaches with multiple views.