Fractal Graph Contrastive Learning
Provides a principled global augmentation strategy for graph contrastive learning, improving performance on graph classification tasks, especially in urban traffic analysis.
FractalGCL introduces a renormalisation-based augmentation and fractal-dimension-aware contrastive loss for graph contrastive learning, achieving a 61% runtime reduction via a Gaussian surrogate and outperforming the next-best method on urban traffic tasks by 4.51 percentage points in average accuracy.
Graph Contrastive Learning (GCL) relies on semantically consistent graph augmentations, but common local perturbations provide limited control over global structural consistency, motivating a more principled global augmentation strategy. We therefore propose Fractal Graph Contrastive Learning (FractalGCL), a theory-motivated framework that constructs a renormalisation-based augmented graph and introduces a fractal-dimension-aware contrastive loss that penalises unreliable positive views and reweights negative-pair repulsion by finite-scale box-counting discrepancies. However, computing these discrepancies introduces substantial overhead, so we derive and justify a Gaussian surrogate that avoids repeated box-counting on renormalised graphs, yielding about a $61\%$ runtime reduction. Experiments show that FractalGCL serves as an effective frozen-pretraining tool on MalNet-Tiny, achieves strong performance on the standard TUDataset benchmarks, and outperforms the next-best method on real-world urban traffic tasks by $4.51$ percentage points in average accuracy. Code is available at https://anonymous.4open.science/r/FractalGCL-0511/.