Position-aware Graph Neural Networks

TL;DR

Position-aware Graph Neural Networks (P-GNNs) effectively capture node positions within graphs by using anchor nodes and distance-based aggregation, leading to improved performance on tasks like link prediction and community detection.

Contribution

This paper introduces P-GNNs, a novel GNN architecture that incorporates node position information through anchor nodes and distance-based aggregation, enhancing predictive accuracy.

Findings

P-GNNs outperform existing GNNs by up to 66% in ROC AUC.

P-GNNs are scalable and inductive, suitable for large graphs.

They improve tasks like link prediction and community detection.

Abstract

Learning node embeddings that capture a node's position within the broader graph structure is crucial for many prediction tasks on graphs. However, existing Graph Neural Network (GNN) architectures have limited power in capturing the position/location of a given node with respect to all other nodes of the graph. Here we propose Position-aware Graph Neural Networks (P-GNNs), a new class of GNNs for computing position-aware node embeddings. P-GNN first samples sets of anchor nodes, computes the distance of a given target node to each anchor-set,and then learns a non-linear distance-weighted aggregation scheme over the anchor-sets. This way P-GNNs can capture positions/locations of nodes with respect to the anchor nodes. P-GNNs have several advantages: they are inductive, scalable,and can incorporate node feature information. We apply P-GNNs to multiple prediction tasks including link prediction and community detection. We show that P-GNNs consistently outperform state of the art GNNs, with up to 66% improvement in terms of the ROC AUC score.