Learning the Network of Graphs for Graph Neural Networks

TL;DR

This paper introduces GL-GNN, a novel graph neural network that learns the network of graphs and important features to address unknown graphs and noisy data in graph-structured applications.

Contribution

GL-GNN is the first model to learn multiple relation graphs and a network of graphs simultaneously, effectively handling unknown graphs and noisy features and connections.

Findings

Outperforms 14 baseline methods on seven datasets with unknown graphs.

Achieves better accuracy than baseline methods when graphs are known.

Capable of selecting important features and graph edges from datasets.

Abstract

Graph neural networks (GNNs) have achieved great success in many scenarios with graph-structured data. However, in many real applications, there are three issues when applying GNNs: graphs are unknown, nodes have noisy features, and graphs contain noisy connections. Aiming at solving these problems, we propose a new graph neural network named as GL-GNN. Our model includes multiple sub-modules, each sub-module selects important data features and learn the corresponding key relation graph of data samples when graphs are unknown. GL-GNN further obtains the network of graphs by learning the network of sub-modules. The learned graphs are further fused using an aggregation method over the network of graphs. Our model solves the first issue by simultaneously learning multiple relation graphs of data samples as well as a relation network of graphs, and solves the second and the third issue by selecting important data features as well as important data sample relations. We compare our method with 14 baseline methods on seven datasets when the graph is unknown and 11 baseline methods on two datasets when the graph is known. The results show that our method achieves better accuracies than the baseline methods and is capable of selecting important features and graph edges from the dataset. Our code will be publicly available at \url{https://github.com/Looomo/GL-GNN}.