Revisiting Graph Neural Networks for Link Prediction

by   Muhan Zhang, et al.

Graph neural networks (GNNs) have achieved great success in recent years. Three most common applications include node classification, link prediction, and graph classification. While there is rich literature on node classification and graph classification, GNNs for link prediction is relatively less studied and less understood. Two representative classes of methods exist: GAE and SEAL. GAE (Graph Autoencoder) first uses a GNN to learn node embeddings for all nodes, and then aggregates the embeddings of the source and target nodes as their link representation. SEAL extracts a subgraph around the source and target nodes, labels the nodes in the subgraph, and then uses a GNN to learn a link representation from the labeled subgraph. In this paper, we thoroughly discuss the differences between these two classes of methods, and conclude that simply aggregating node embeddings does not lead to effective link representations, while learning from properly labeled subgraphs around links provides highly expressive and generalizable link representations. Experiments on the recent large-scale OGB link prediction datasets show that SEAL has up to 195 on 3 out of 4 datasets.



There are no comments yet.


page 1

page 2

page 3

page 4


Link Prediction Based on Graph Neural Networks

Traditional methods for link prediction can be categorized into three ma...

Integrating Transductive And Inductive Embeddings Improves Link Prediction Accuracy

In recent years, inductive graph embedding models, viz., graph neural ne...

Graph Learning Network: A Structure Learning Algorithm

Recently, graph neural networks (GNNs) has proved to be suitable in task...

Link Prediction using Graph Neural Networks for Master Data Management

Learning graph representations of n-ary relational data has a number of ...

Interpretable Signed Link Prediction with Signed Infomax Hyperbolic Graph

Signed link prediction in social networks aims to reveal the underlying ...

Modeling Graph Node Correlations with Neighbor Mixture Models

We propose a new model, the Neighbor Mixture Model (NMM), for modeling n...

Revisiting graph neural networks and distance encoding in a practical view

Graph neural networks (GNNs) are widely used in the applications based o...

Code Repositories


An open-source implementation of SEAL for link prediction in open graph benchmark (OGB) datasets.

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.