AI RESEARCH
Fractal Graph Contrastive Learning
arXiv CS.LG
•
ArXi:2505.11356v4 Announce Type: replace Graph Contrastive Learning (GCL) relies on semantically consistent graph augmentations, but common local perturbations provide limited control over global structural consistency, motivating a principled global augmentation strategy. We therefore propose Fractal Graph Contrastive Learning (FractalGCL), a theory-motivated framework that constructs a renormalisation-based augmented graph and