Measuring and Improving the Use of Graph Information in Graph Neural Networks
This work addresses a fundamental gap in understanding for researchers and practitioners using GNNs, though it appears incremental as it builds on existing GNN frameworks.
The paper tackled the problem of quantifying and improving how much performance graph neural networks (GNNs) gain from graph data by introducing smoothness metrics and a new model, CS-GNN, which achieved better performance than existing methods on real graphs.
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.