Effective Structural Encodings via Local Curvature Profiles

arXiv:2311.14864v2 Announce Type: replace
Abstract: Structural and Positional Encodings can significantly improve the performance of Graph Neural Networks in downstream tasks. Recent literature has begun to systematically investigate differences in the structural properties that these approaches encode, as well as performance trade-offs between them. However, the question of which structural properties yield the most effective encoding remains open. In this paper, we investigate this question from a geometric perspective. We propose a novel structural encoding based on discrete Ricci curvature …

abstract arxiv begun cs.lg differences encode graph graph neural networks however literature networks neural networks performance profiles question stat.ml tasks them trade type via