Measuring and Improving the Use of Graph Information in Graph Neural Networks

Abstract

Graph neural networks (GNNs) have been widely used for representation learning on graph data. However, there is limited understanding on how much performance GNNs actually gain from graph data. This paper introduces a context-surrounding GNN framework and proposes two smoothness metrics to measure the quantity and quality of information obtained from graph data. A new GNN model, called CS-GNN, is then designed to improve the use of graph information based on the smoothness values of a graph. CS-GNN is shown to achieve better performance than existing methods in different types of real graphs.

This paper has been published in ICLR 2020. Code and Dataset can be found here: https://github.com/yifan-h/CS-GNN

References in corpus (2)

• Variational Graph Auto-Encoders
• Utilizing Edge Features in Graph Neural Networks via Variational Information Maximization

Cited by in corpus (9)

• Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters
• How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision
• Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?
• Graph Representation Learning Beyond Node and Homophily
• CommPOOL: An Interpretable Graph Pooling Framework for Hierarchical Graph Representation Learning
• PSGR: Pixel-wise Sparse Graph Reasoning for COVID-19 Pneumonia Segmentation in CT Images
• LEReg: Empower Graph Neural Networks with Local Energy Regularization
• Eigen-GNN: A Graph Structure Preserving Plug-in for GNNs
• CoRGi: Content-Rich Graph Neural Networks with Attention