Neural graph embeddings as explicit low-rank matrix factorization for link prediction

TL;DR

This paper introduces an improved low-rank matrix factorization approach for neural graph embeddings that incorporates information from unlikely node pairs, significantly enhancing link prediction accuracy.

Contribution

It proposes a novel method that includes low-PMI node pairs in graph embedding learning, outperforming baseline methods in link prediction tasks.

Findings

Improved link prediction performance by up to 24.2%.

Incorporating unlikely node pairs enhances embedding quality.

Provides insights for future graph embedding algorithm design.

Abstract

Learning good quality neural graph embeddings has long been achieved by minimizing the point-wise mutual information (PMI) for co-occurring nodes in simulated random walks. This design choice has been mostly popularized by the direct application of the highly-successful word embedding algorithm word2vec to predicting the formation of new links in social, co-citation, and biological networks. However, such a skeuomorphic design of graph embedding methods entails a truncation of information coming from pairs of nodes with low PMI. To circumvent this issue, we propose an improved approach to learning low-rank factorization embeddings that incorporate information from such unlikely pairs of nodes and show that it can improve the link prediction performance of baseline methods from 1.2% to 24.2%. Based on our results and observations we outline further steps that could improve the design of next graph embedding algorithms that are based on matrix factorization.