Geodesic Graph Neural Network for Efficient Graph Representation LearningDownload PDF

Published: 31 Oct 2022, Last Modified: 12 Jan 2023NeurIPS 2022 AcceptReaders: Everyone
Keywords: Graph Learning, Geodesic, Graph Neural Network, GNN, Fast Inference
Abstract: Graph Neural Networks (GNNs) have recently been applied to graph learning tasks and achieved state-of-the-art (SOTA) results. However, many competitive methods run GNNs multiple times with subgraph extraction and customized labeling to capture information that is hard for normal GNNs to learn. Such operations are time-consuming and do not scale to large graphs. In this paper, we propose an efficient GNN framework called Geodesic GNN (GDGNN) that requires only one GNN run and injects conditional relationships between nodes into the model without labeling. This strategy effectively reduces the runtime of subgraph methods. Specifically, we view the shortest paths between two nodes as the spatial graph context of the neighborhood around them. The GNN embeddings of nodes on the shortest paths are used to generate geodesic representations. Conditioned on the geodesic representations, GDGNN can generate node, link, and graph representations that carry much richer structural information than plain GNNs. We theoretically prove that GDGNN is more powerful than plain GNNs. We present experimental results to show that GDGNN achieves highly competitive performance with SOTA GNN models on various graph learning tasks while taking significantly less time.
TL;DR: We leverage the geodesic information between nodes to develope a generic Graph Neural Network framework that is both efficient and effective.
Supplementary Material: pdf
21 Replies