mlsanityData to 7 Oct 2026

Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labels

arXiv 1902.11038 ↗First posted 28 Feb 2019cs.LG stat.MLcited by 111

Not on the map. Why?

Abstract (arXiv)

Graph Convolutional Networks(GCNs) play a crucial role in graph learning tasks, however, learning graph embedding with few supervised signals is still a difficult problem. In this paper, we propose a novel training algorithm for Graph Convolutional Network, called Multi-Stage Self-Supervised(M3S) Training Algorithm, combined with self-supervised learning approach, focusing on improving the generalization performance of GCNs on graphs with few labeled nodes. Firstly, a Multi-Stage Training Framework is provided as the basis of M3S training method. Then we leverage DeepCluster technique, a popular form of self-supervised learning, and design corresponding aligning mechanism on the embedding space to refine the Multi-Stage Training Framework, resulting in M3S Training Algorithm. Finally, extensive experimental results verify the superior performance of our algorithm on graphs with few labeled nodes under different label rates compared with other state-of-the-art approaches.

Key facts. Cited by 111 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 28; 2022: 31; 2023: 19; 2024: 18; 2025: 11; 2026: 4.

111 papers.

Sort:

  1. 2021Graph Self-Supervised Learning: A Surveycited by 289
  2. 2021Self-Supervised Learning of Graph Neural Networks: A Unified Reviewcited by 184
  3. 2021Self-supervised Learning on Graphs: Contrastive, Generative,or Predictivecited by 136
  4. 2022Data Augmentation for Deep Graph Learning: A Surveycited by 132
  5. 2022How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervisioncited by 102
  6. 2021Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibrationcited by 91
  7. 2024All in One and One for All: A Simple yet Effective Method towards Cross-domain Graph Pretrainingcited by 84
  8. 2022Graph Attention Multi-Layer Perceptroncited by 82
  9. 2021Towards Self-Explainable Graph Neural Networkcited by 75
  10. 2022Simple and Efficient Heterogeneous Graph Neural Networkcited by 71
  11. 2021Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Frameworkcited by 69
  12. 2021MoCL: Data-driven Molecular Fingerprint via Knowledge-aware Contrastive Learning from Molecular Graphcited by 65
38 more
  1. 2022Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labelscited by 63
  2. 2021Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced trainingcited by 54
  3. 2021Molecular Contrastive Learning with Chemical Element Knowledge Graphcited by 50
  4. 2023GSLB: The Graph Structure Learning Benchmarkcited by 49
  5. 2022Confidence May Cheat: Self-Training on Graph Neural Networks under Distribution Shiftcited by 38
  6. 2021FedGL: Federated Graph Learning Framework with Global Self-Supervisioncited by 34
  7. 2021Adaptive Transfer Learning on Graph Neural Networkscited by 31
  8. 2022Self-supervised Heterogeneous Graph Pre-training Based on Structural Clusteringcited by 30
  9. 2022DropMessage: Unifying Random Dropping for Graph Neural Networkscited by 29
  10. 2023Learning on Graphs with Out-of-Distribution Nodescited by 29
  11. 2022Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentationscited by 28
  12. 2021Self-supervised Graph Neural Networks without explicit negative samplingcited by 25
  13. 2021Meta Propagation Networks for Graph Few-shot Semi-supervised Learningcited by 25
  14. 2023Learning Strong Graph Neural Networks with Weak Informationcited by 25
  15. 2022CLNode: Curriculum Learning for Node Classificationcited by 24
  16. 2023Leveraging Large Language Models for Node Generation in Few-Shot Learning on Text-Attributed Graphscited by 23
  17. 2022Modularity-Aware Graph Autoencoders for Joint Community Detection and Link Predictioncited by 22
  18. 2023Data-centric Graph Learning: A Surveycited by 22
  19. 2022CGC: Contrastive Graph Clustering for Community Detection and Trackingcited by 21
  20. 2024Uncertainty in Graph Neural Networks: A Surveycited by 20
  21. 2021X-GOAL: Multiplex Heterogeneous Graph Prototypical Contrastive Learningcited by 19
  22. 2022Informative Pseudo-Labeling for Graph Neural Networks with Few Labelscited by 19
  23. 2021ROD: Reception-aware Online Distillation for Sparse Graphscited by 18
  24. 2021Label-Wise Graph Convolutional Network for Heterophilic Graphscited by 17
  25. 2022Structure-Preserving Graph Representation Learningcited by 17
  26. 2023When to Pre-Train Graph Neural Networks? From Data Generation Perspective!cited by 17
  27. 2021Graph Neural Networks: Methods, Applications, and Opportunitiescited by 16
  28. 2022Defending Graph Convolutional Networks against Dynamic Graph Perturbations via Bayesian Self-supervisioncited by 16
  29. 2021GraphHop: An Enhanced Label Propagation Method for Node Classificationcited by 15
  30. 2021Self-supervised Consensus Representation Learning for Attributed Graphcited by 15
  31. 2022Semi-Supervised Hierarchical Graph Classificationcited by 15
  32. 2023Towards Data-centric Graph Machine Learning: Review and Outlookcited by 15
  33. 2022Learnable Graph Convolutional Network and Feature Fusion for Multi-view Learningcited by 13
  34. 2021CogDL: A Comprehensive Library for Graph Deep Learningcited by 12
  35. 2022Label-Enhanced Graph Neural Network for Semi-supervised Node Classificationcited by 11
  36. 2022Toward Robust Graph Semi-Supervised Learning against Extreme Data Scarcitycited by 11
  37. 2023Deep Insights into Noisy Pseudo Labeling on Graph Datacited by 11
  38. 2021SCR: Training Graph Neural Networks with Consistency Regularizationcited by 10

50 most cited of 111 All 111 (JSON)