RWR-GAE: Random Walk Regularization for Graph Auto Encoders

TL;DR

This paper introduces RWR-GAE, a regularization technique for graph autoencoders using random walks, which improves node embedding quality for clustering and link prediction tasks.

Contribution

It proposes a novel random walk based regularization method for graph autoencoders that enhances embedding quality and outperforms existing models.

Findings

Outperforms state-of-the-art models in node clustering by up to 7.5%.

Achieves state-of-the-art accuracy on link prediction for Cora, Citeseer, and PubMed.

Demonstrates significant improvement over traditional reconstruction loss methods.

Abstract

Node embeddings have become an ubiquitous technique for representing graph data in a low dimensional space. Graph autoencoders, as one of the widely adapted deep models, have been proposed to learn graph embeddings in an unsupervised way by minimizing the reconstruction error for the graph data. However, its reconstruction loss ignores the distribution of the latent representation, and thus leading to inferior embeddings. To mitigate this problem, we propose a random walk based method to regularize the representations learnt by the encoder. We show that the proposed novel enhancement beats the existing state-of-the-art models by a large margin (upto 7.5\%) for node clustering task, and achieves state-of-the-art accuracy on the link prediction task for three standard datasets, cora, citeseer and pubmed. Code available at https://github.com/MysteryVaibhav/DW-GAE.