Training methods

Node Classification Pipelines, Node Regression Pipelines, and Link Prediction Pipelines are trained using supervised machine learning methods. These methods have several hyperparameters that one can set to influence the training. The objective of this page is to give a brief overview of the methods, as well as advice on how to tune their hyperparameters.

For instructions on how to add model candidates, see the sections Adding model candidates (Node Classification), Adding model candidates (Node Regression), and Adding model candidates (Link Prediction). During training, auto-tuning is carried out to select a best candidate and the best values for its hyper-parameters.

The training methods currently support in the Neo4j Graph Data Science library are:

Classification

Regression