CoRe-GD: A Hierarchical Framework for Scalable Graph Visualization with GNNs

TL;DR

This paper presents CoRe-GD, a scalable GNN-based framework for graph visualization that optimizes stress efficiently through a hierarchical coarsening and un-coarsening process, outperforming existing methods.

Contribution

The paper introduces a novel hierarchical GNN framework with a coarsening strategy and positional rewiring for scalable stress optimization in graph drawing.

Findings

Achieves state-of-the-art performance in graph visualization tasks.

Operates with sub-quadratic runtime, enabling scalability.

Effectively propagates positional information through a new rewiring technique.

Abstract

Graph Visualization, also known as Graph Drawing, aims to find geometric embeddings of graphs that optimize certain criteria. Stress is a widely used metric; stress is minimized when every pair of nodes is positioned at their shortest path distance. However, stress optimization presents computational challenges due to its inherent complexity and is usually solved using heuristics in practice. We introduce a scalable Graph Neural Network (GNN) based Graph Drawing framework with sub-quadratic runtime that can learn to optimize stress. Inspired by classical stress optimization techniques and force-directed layout algorithms, we create a coarsening hierarchy for the input graph. Beginning at the coarsest level, we iteratively refine and un-coarsen the layout, until we generate an embedding for the original graph. To enhance information propagation within the network, we propose a novel positional rewiring technique based on intermediate node positions. Our empirical evaluation demonstrates that the framework achieves state-of-the-art performance while remaining scalable.