Graph Inference Representation: Learning Graph Positional Embeddings with Anchor Path Encoding

Abstract

Learning node representations that incorporate information from graph structure benefits wide range of tasks on graph. The majority of existing graph neural networks (GNNs) have limited power in capturing position information for a given node. The idea of positioning nodes with selected anchors has been exploited, yet mainly relying on explicit labeling of distance information. Here we propose Graph Inference Representation (GIR), an anchor based GNN model encoding path information related to pre-selected anchors for each node. Abilities to get position-aware embeddings are theoretically and experimentally investigated on GIR and its core variants. Further, the complementarity between GIRs and typical GNNs is demonstrated. We show that GIRs get outperformed results in position-aware scenarios, and performances on typical GNNs could be improved by fusing GIR embeddings.

12 pages, 5 figures

References in corpus (5)

• Finding community structure in networks using the eigenvectors of matrices
• Nonoptimal Component Placement, but Short Processing Paths, due to Long-Distance Projections in Neural Systems
• Position-aware Graph Neural Networks
• Gated Multimodal Units for Information Fusion
• Graph Inference Learning for Semi-supervised Classification