Integrating Transductive And Inductive Embeddings Improves Link Prediction Accuracy

TL;DR

This paper demonstrates that combining transductive methods like Node2Vec with inductive GNNs significantly enhances link prediction accuracy in social networks, especially when node features are limited or unavailable.

Contribution

The study shows that using Node2Vec for initial node representations before applying GNNs improves link prediction performance across various models.

Findings

Node2Vec embeddings serve as high-quality features for GNNs.

Combining transductive and inductive techniques boosts LP accuracy.

Method is effective even with limited or no node features.

Abstract

In recent years, inductive graph embedding models, \emph{viz.}, graph neural networks (GNNs) have become increasingly accurate at link prediction (LP) in online social networks. The performance of such networks depends strongly on the input node features, which vary across networks and applications. Selecting appropriate node features remains application-dependent and generally an open question. Moreover, owing to privacy and ethical issues, use of personalized node features is often restricted. In fact, many publicly available data from online social network do not contain any node features (e.g., demography). In this work, we provide a comprehensive experimental analysis which shows that harnessing a transductive technique (e.g., Node2Vec) for obtaining initial node representations, after which an inductive node embedding technique takes over, leads to substantial improvements in link prediction accuracy. We demonstrate that, for a wide variety of GNN variants, node representation vectors obtained from Node2Vec serve as high quality input features to GNNs, thereby improving LP performance.