Node regression pipelines

This feature is in the alpha tier. For more information on feature tiers, see API Tiers.

Node Regression is a common machine learning task applied to graphs: training models to predict node property values. Concretely, Node Regression models are used to predict the value of node property based on other node properties. During training, the property to predict is referred to as the target property.

In GDS, we have Node Regression pipelines which offer an end-to-end workflow, from feature extraction to predicting node property values. The training pipelines reside in the pipeline catalog. When a training pipeline is executed, a regression model is created and stored in the model catalog.

A training pipeline is a sequence of two phases:

1. The graph is augmented with new node properties in a series of steps.

2. The augmented graph is used for training a node regression model.

This segment is divided into the following pages:

• Configuring the pipeline

• Training the pipeline

• Applying a trained model for prediction