Topological link prediction

This chapter provides explanations and examples for each of the link prediction algorithms in the Neo4j Graph Data Science library.

Link prediction algorithms help determine the closeness of a pair of nodes using the topology of the graph. The computed scores can then be used to predict new relationships between them.

The following algorithms use only the topology of the graph to make predictions about relationships between nodes. To make predictions also utilizing node properties one can use the machine learning based methods Link prediction and Link prediction pipelines.

The Neo4j GDS library includes the following link prediction algorithms, grouped by quality tier: