mlsanityData to 14 Oct 2026

Coarse-to-Fine Contrastive Learning on Graphs

arXiv 2212.06423 ↗First posted 13 Dec 2022cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Inspired by the impressive success of contrastive learning (CL), a variety of graph augmentation strategies have been employed to learn node representations in a self-supervised manner. Existing methods construct the contrastive samples by adding perturbations to the graph structure or node attributes. Although impressive results are achieved, it is rather blind to the wealth of prior information assumed: with the increase of the perturbation degree applied on the original graph, 1) the similarity between the original graph and the generated augmented graph gradually decreases; 2) the discrimination between all nodes within each augmented view gradually increases. In this paper, we argue that both such prior information can be incorporated (differently) into the contrastive learning paradigm following our general ranking framework. In particular, we first interpret CL as a special case of learning to rank (L2R), which inspires us to leverage the ranking order among positive augmented views. Meanwhile, we introduce a self-ranking paradigm to ensure that the discriminative information among different nodes can be maintained and also be less altered to the perturbations of different degrees. Experiment results on various benchmark datasets verify the effectiveness of our algorithm compared with the supervised and unsupervised models.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 37 of its 63 references that are in the map. First posted on arXiv 13 Dec 2022.

Builds on

37 of 63 references.

References · 37

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  6. 2017Inductive Representation Learning on Large Graphscited by 6,320
  7. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  8. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  9. 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
  10. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,845
  11. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,838
  12. 2014DeepWalk: Online Learning of Social Representationscited by 1,547
25 more
  1. 2019Contrastive Multiview Codingcited by 1,301
  2. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,273
  3. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  4. 2018Deep Graph Infomaxcited by 1,106
  5. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  6. 2015Image-based Recommendations on Styles and Substitutescited by 706
  7. 2020Self-supervised Learning: Generative or Contrastivecited by 694
  8. 2020Contrastive Multi-View Representation Learning on Graphscited by 652
  9. 2020Contrastive Learning with Hard Negative Samplescited by 628
  10. 2019Multi-scale Attributed Node Embeddingcited by 548
  11. 2020Deep Graph Contrastive Representation Learningcited by 539
  12. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  13. 2020GCC: Graph Contrastive Coding for Graph Neural Network Pre-Trainingcited by 463
  14. 2019InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximizationcited by 441
  15. 2020Graph Representation Learning via Graphical Mutual Information Maximizationcited by 217
  16. 2021Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learningcited by 177
  17. 2019Analyzing and Improving Representations with the Soft Nearest Neighbor Losscited by 95
  18. 2021Graph Barlow Twins: A self-supervised representation learning framework for graphscited by 85
  19. 2021Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learningcited by 70
  20. 2020Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learningcited by 43
  21. 2020Multi-Label Contrastive Learning for Abstract Visual Reasoningcited by 24
  22. 2019Fast Haar Transforms for Graph Neural Networkscited by 20
  23. 2021Towards Robust Graph Contrastive Learningcited by 16
  24. 2020NCGNN: Node-Level Capsule Graph Neural Network for Semisupervised Classificationcited by 9
  25. 2022Contrastive Brain Network Learning via Hierarchical Signed Graph Pooling Modelcited by 8

Built on by

Not cited yet.