Node classification

StellarGraph provides numerous algorithms for doing node classification on graphs. This folder contains demos of all of them to explain how they work and how to use them as part of a TensorFlow Keras data science workflow.

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

Node classification can also be done as a downstream task from node representation learning/embeddings, by training a supervised or semi-supervised classifier against the embedding vectors. Unsupervised algorithms that can be used in this manner include random walk-based methods like Metapath2Vec. StellarGraph provides demos of unsupervised algorithms, some of which include a node classification downstream task.

Find algorithms and demos for a graph

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

Demo	Algorithm(s)	Node features	Heterogeneous	Directed	Edge weights	Inductive	Node embeddings
GCN	GCN	yes					yes
Cluster-GCN	Cluster-GCN	yes					yes
RGCN	RGCN	yes	yes, multiple edge types				yes
GAT	GAT	yes					yes
SGC	SGC	yes					yes
PPNP & APPNP	PPNP, APPNP	yes
Attri2Vec	Attri2Vec	yes					yes
GraphSAGE on Cora	GraphSAGE	yes					yes
Inductive GraphSAGE	GraphSAGE	yes				yes	yes
Directed GraphSAGE	GraphSAGE	yes		yes			yes
Node2Vec (keras)	Node2Vec						yes
Node2Vec (gensim)	Node2Vec						yes
Weighted Node2Vec	Node2Vec				yes		yes
GCN, Deep Graph Infomax and fine-tuning	GCN, DeepGraphInfomax, semi-supervised training	yes					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.

Table of contents

• Node classification via node representations with attri2vec
• Node classification with Cluster-GCN
• Node classification with directed GraphSAGE
• Node classification with Graph ATtention Network (GAT)
• Semi-supervised node classification via GCN, Deep Graph Infomax and fine-tuning
• Node classification with Graph Convolutional Network (GCN)
• Inductive node classification and representation learning using GraphSAGE
• Node classification with GraphSAGE
• Node classification with Node2Vec using Stellargraph components
• Node classification with Node2Vec
• Node classification with weighted Node2Vec
• Node classification with Personalised Propagation of Neural Predictions (PPNP) and Approximate PPNP (APPNP)
• Node classification with Relational Graph Convolutional Network (RGCN)
• Node classification with Simplified Graph Convolutions (SGC)