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:
Neo4j: Instruction to download.
APOC library plug-in: APOC provides utilities for common procedures and functions in Neo4j. Instruction to download and install APOC.
Graph data science library: This library provides a collection of graph algorithms in Neo4j. Instruction to download and install the data science library.
Py2neo: A client library and toolkit to connect to Neo4j database from within python applications. Install
py2neo
by using pip:pip install stellargraph[neo4j]
orpip install py2neo
. documentation.
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 |
---|---|---|---|---|
Dataset Loading |
||||
GraphSAGE |
Node classification |
yes |
||
GraphSAGE |
Node classification |
yes |
yes |
|
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.