Graph classification

StellarGraph provides algorithms for graph classification. This folder contains demos to explain how they work and how to use them as part of a TensorFlow Keras data science workflow.

A graph classification task predicts an attribute of each graph in a collection of graphs. For instance, labelling each graph with a categorical class (binary classification or multiclass classification), or predicting a continuous number (regression). It is supervised, where the model is trained using a subset of graphs that have ground-truth labels.

Graph classification can also be done as a downstream task from graph representation learning/embeddings, by training a supervised or semi-supervised classifier against the embedding vectors. StellarGraph provides demos of unsupervised algorithms, some of which include a graph classification downstream task.

Find algorithms and demos for a collection of graphs

This table lists all graph classification demos, including the algorithms trained and the types of graphs used.

demo

algorithm(s)

node features

inductive

GCN Supervised Graph Classification

GCN, mean pooling

yes

yes

DGCNN

DeepGraphCNN

yes

yes

See the demo index for more tasks, and a summary of each algorithm.