Modeling Heterogeneous Edges to Represent Networks with Graph Auto-Encoder

TL;DR

This paper introduces RGAE, a regularized graph auto-encoder model that effectively captures heterogeneous network structures by leveraging multiple views and regularization techniques, outperforming existing methods.

Contribution

The paper proposes a novel RGAE model with shared and private auto-encoders and regularization loss functions to better learn heterogeneous network representations.

Findings

RGAE outperforms state-of-the-art baselines on real datasets.

Utilizes multiple views to capture diverse relationship types.

Employs regularization to extract consistent and unique information.

Abstract

In the real world, networks often contain multiple relationships among nodes, manifested as the heterogeneity of the edges in the networks. We convert the heterogeneous networks into multiple views by using each view to describe a specific type of relationship between nodes, so that we can leverage the collaboration of multiple views to learn the representation of networks with heterogeneous edges. Given this, we propose a \emph{regularized graph auto-encoders} (RGAE) model, committed to utilizing abundant information in multiple views to learn robust network representations. More specifically, RGAE designs shared and private graph auto-encoders as main components to capture high-order nonlinear structure information of the networks. Besides, two loss functions serve as regularization to extract consistent and unique information, respectively. Concrete experimental results on realistic datasets indicate that our model outperforms state-of-the-art baselines in practical applications.