Improving Node Classification by Co-training Node Pair Classification: A Novel Training Framework for General Graph Neural Networks

by   Deli Chen, et al.

Semi-supervised learning is a widely used training framework for graph node classification. However, there are two problems existing in this learning method: (1) the original graph topology may not be perfectly aligned with the node classification task; (2) the supervision information in the training set has not been fully used. To tackle these two problems, we design a new task: node pair classification, to assist in training GNN models for the target node classification task. We further propose a novel training framework named Adaptive Co-training, which jointly trains the node classification and the node pair classification after the optimization of graph topology. Extensive experimental results on four representative GNN models have demonstrated that our proposed training framework significantly outperforms baseline methods across three benchmark graph datasets.


page 1

page 2

page 3

page 4


Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputs

Graph neural networks (GNNs) have received much attention recently becau...

Graph Sanitation with Application to Node Classification

The past decades have witnessed the prosperity of graph mining, with a m...

Dual GNNs: Graph Neural Network Learning with Limited Supervision

Graph Neural Networks (GNNs) require a relatively large number of labele...

Learning Hierarchical Graph Neural Networks for Image Clustering

We propose a hierarchical graph neural network (GNN) model that learns h...

TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classification

Learning unbiased node representations under class-imbalanced graph data...

Preserve, Promote, or Attack? GNN Explanation via Topology Perturbation

Prior works on formalizing explanations of a graph neural network (GNN) ...

A Novel Generalized Artificial Neural Network for Mining Two-Class Datasets

A novel general neural network (GNN) is proposed for two-class data mini...