Neo4j

StellarGraph provides various algorithms that can be run on graphs in Neo4j. This folder contains demos of all of them to explain how to connect to Neo4j and how to run these algorithms as part of a TensorFlow Keras data science workflow.

Required Installations:

Warning

All functionalities demonstrated in the notebooks below are still experimental. They have not been tested thoroughly and the implementation might be dramatically changed.

Find algorithms and demos for a graph

This table lists all Neo4j demos, including the algorithms trained, the types of graph used, and the tasks demonstrated.

Demo

Algorithm(s)

Task

Node features

Directed

Load Cora

Dataset Loading

GraphSAGE

GraphSAGE

Node classification

yes

Directed GraphSAGE

GraphSAGE

Node classification

yes

yes

Cluster-GCN

Cluster-GCN

Node classification

yes

See the root README or each algorithm’s documentation for the relevant citation(s). See the demo index for more tasks, and a summary of each algorithm.

There is also a demonstration of loading data into memory from Neo4j. This allows using any StellarGraph algorithm on data from Neo4j.