Isometric Graph Neural Networks
This addresses the need for distance-aware node embeddings in graph tasks, offering a novel method to enhance existing GNNs, though it is incremental as it builds on prior GNN techniques.
The paper tackled the problem of generating node representations in graphs that faithfully reflect distances between nodes, proposing Isometric Graph Neural Networks (IGNN) which improved AUC-ROC by up to 43% and Kendall's Tau by up to 400% in experiments.
Many tasks that rely on representations of nodes in graphs would benefit if those representations were faithful to distances between nodes in the graph. Geometric techniques to extract such representations have poor scaling over large graph size, and recent advances in Graph Neural Network (GNN) algorithms have limited ability to reflect graph distance information beyond the first degree neighborhood. To enable this highly desired capability, we propose a technique to learn Isometric Graph Neural Networks (IGNN), which requires changing the input representation space and loss function to enable any GNN algorithm to generate representations that reflect distances between nodes. We experiment with the isometric technique on several GNN architectures for modeling multiple prediction tasks on multiple datasets. In addition to an improvement in AUC-ROC as high as $43\%$ in these experiments, we observe a consistent and substantial improvement as high as 400% in Kendall's Tau (KT), a measure that directly reflects distance information, demonstrating that the learned embeddings do account for graph distances.