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

arXiv: https://arxiv.org/abs/2011.09907 · HTML: https://mlsanity.com/paper/2011.09907/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Nov 2020.

## Built on by (most cited first, 4 of 4)

- [Line Graph Contrastive Learning for Link Prediction](https://mlsanity.com/paper/2210.13795/) (2022)
- [A Systematic Evaluation of Node Embedding Robustness](https://mlsanity.com/paper/2209.08064/) (2022)
- [Space-Invariant Projection in Streaming Network Embedding](https://mlsanity.com/paper/2303.06293/) (2023)
- [Link prediction on multi-relational graphs from an influence propagation perspective](https://mlsanity.com/paper/2608.05016/) (2026)

## Abstract (arXiv)

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.