mlsanityData to 14 Oct 2026

Fractal Graph Contrastive Learning

arXiv 2505.11356 ↗First posted 16 May 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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/.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 36 of its 67 references that are in the map. First posted on arXiv 16 May 2025.

Builds on

36 of 67 references.

References · 36

  1. 2018How Powerful are Graph Neural Networks?cited by 4,393
  2. 2016Variational Graph Auto-Encoderscited by 1,382
  3. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,273
  4. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  5. 2018Deep Graph Infomaxcited by 1,106
  6. 2019Strategies for Pre-training Graph Neural Networkscited by 971
  7. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 728
  8. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 680
  9. 2020GCC: Graph Contrastive Coding for Graph Neural Network Pre-Trainingcited by 463
  10. 2019InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximizationcited by 441
  11. 2021Graph Self-Supervised Learning: A Surveycited by 289
  12. 2021Graph Contrastive Learning Automatedcited by 287
24 more
  1. 2017graph2vec: Learning Distributed Representations of Graphscited by 230
  2. 2021Adversarial Graph Augmentation to Improve Graph Contrastive Learningcited by 200
  3. 2021Self-Supervised Learning of Graph Neural Networks: A Unified Reviewcited by 184
  4. 2022SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentationcited by 171
  5. 2021Self-supervised Learning on Graphs: Contrastive, Generative,or Predictivecited by 136
  6. 2024Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spacescited by 134
  7. 2022Towards Unsupervised Deep Graph Structure Learningcited by 114
  8. 2019Unsupervised Attributed Multiplex Network Embeddingcited by 95
  9. 2021ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learningcited by 72
  10. 2021Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learningcited by 70
  11. 2021MoCL: Data-driven Molecular Fingerprint via Knowledge-aware Contrastive Learning from Molecular Graphcited by 65
  12. 2022Let Invariant Rationale Discovery Inspire Graph Contrastive Learningcited by 57
  13. 2024Towards Graph Contrastive Learning: A Survey and Beyondcited by 26
  14. 2025Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellencecited by 26
  15. 2023Data Scarcity in Recommendation Systems: A Surveycited by 17
  16. 2022Graph Contrastive Learning with Personalized Augmentationcited by 14
  17. 2023Rethinking Dimensional Rationale in Graph Contrastive Learning from Causal Perspectivecited by 13
  18. 2024Graph Domain Adaptation: Challenges, Progress and Prospectscited by 11
  19. 2021Label Contrastive Coding based Graph Neural Network for Graph Classificationcited by 10
  20. 2022Localized Contrastive Learning on Graphscited by 10
  21. 2022Graph Neural Network-based Android Malware Classification with Jumping Knowledgecited by 9
  22. 2023Learning Large Graph Property Prediction via Graph Segment Trainingcited by 9
  23. 2024Heterogeneous Graph Neural Networks with Post-hoc Explanations for Multi-modal and Explainable Land Use Inferencecited by 3
  24. 2022Towards a Better Understanding of the Characteristics of Fractal Networkscited by 2

Built on by

Not cited yet.