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

02/18/2020
by   Han Yang, et al.
16

Graph neural networks (GNNs) have received much attention recently because of their excellent performance on graph-based tasks. However, existing research on GNNs focuses on designing more effective models without considering much the quality of the input data itself. In this paper, we propose self-enhanced GNN, which improves the quality of the input data using the outputs of existing GNN models for better performance on semi-supervised node classification. As graph data consist of both topology and node labels, we improve input data quality from both perspectives. For topology, we observe that higher classification accuracy can be achieved when the ratio of inter-class edges (connecting nodes from different classes) is low and propose topology update to remove inter-class edges and add intra-class edges. For node labels, we propose training node augmentation, which enlarges the training set using the labels predicted by existing GNN models. As self-enhanced GNN improves the quality of the input graph data, it is general and can be easily combined with existing GNN models. Experimental results on three well-known GNN models and seven popular datasets show that self-enhanced GNN consistently improves the performance of the three models. The reduction in classification error is 16.2 on average and can be as high as 35.1

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/11/2020

Data Augmentation for Graph Neural Networks

Data augmentation has been widely used to improve generalizability of ma...
research
11/10/2019

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

Semi-supervised learning is a widely used training framework for graph n...
research
04/29/2023

Leveraging Label Non-Uniformity for Node Classification in Graph Neural Networks

In node classification using graph neural networks (GNNs), a typical mod...
research
10/26/2022

TuneUp: A Training Strategy for Improving Generalization of Graph Neural Networks

Despite many advances in Graph Neural Networks (GNNs), their training st...
research
09/03/2020

CAGNN: Cluster-Aware Graph Neural Networks for Unsupervised Graph Representation Learning

Unsupervised graph representation learning aims to learn low-dimensional...
research
04/03/2023

Fair Evaluation of Graph Markov Neural Networks

Graph Markov Neural Networks (GMNN) have recently been proposed to impro...
research
09/29/2021

Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration

Despite Graph Neural Networks (GNNs) have achieved remarkable accuracy, ...

Please sign up or login with your details

Forgot password? Click here to reset