mlsanityData to 14 Oct 2026

Graph Contrastive Learning Meets Graph Meta Learning: A Unified Method for Few-shot Node Tasks

arXiv 2309.10376 ↗First posted 19 Sep 2023cs.LG cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) have become popular in Graph Representation Learning (GRL). One fundamental application is few-shot node classification. Most existing methods follow the meta learning paradigm, showing the ability of fast generalization to few-shot tasks. However, recent works indicate that graph contrastive learning combined with fine-tuning can significantly outperform meta learning methods. Despite the empirical success, there is limited understanding of the reasons behind it. In our study, we first identify two crucial advantages of contrastive learning compared to meta learning, including (1) the comprehensive utilization of graph nodes and (2) the power of graph augmentations. To integrate the strength of both contrastive learning and meta learning on the few-shot node classification tasks, we introduce a new paradigm: Contrastive Few-Shot Node Classification (COLA). Specifically, COLA employs graph augmentations to identify semantically similar nodes, which enables the construction of meta-tasks without the need for label information. Therefore, COLA can utilize all nodes to construct meta-tasks, further reducing the risk of overfitting. Through extensive experiments, we validate the essentiality of each component in our design and demonstrate that COLA achieves new state-of-the-art on all tasks.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 35 of its 43 references that are in the map. First posted on arXiv 19 Sep 2023.

Builds on

35 of 43 references.

References · 35

  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. 2017Inductive Representation Learning on Large Graphscited by 6,320
  6. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  7. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  8. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  9. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  10. 2020Supervised Contrastive Learningcited by 2,829
  11. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  12. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
23 more
  1. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  2. 2018Deep Graph Infomaxcited by 1,106
  3. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  4. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
  5. 2020Contrastive Multi-View Representation Learning on Graphscited by 652
  6. 2020Deep Graph Contrastive Representation Learningcited by 539
  7. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 437
  8. 2017Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Rankingcited by 335
  9. 2019Boosting Few-Shot Visual Learning with Self-Supervisioncited by 140
  10. 2019Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labelscited by 111
  11. 2019Meta-GNN: On Few-shot Node Classification in Graph Meta-learningcited by 105
  12. 2020Graph Prototypical Networks for Few-shot Learning on Attributed Networkscited by 90
  13. 2020Graph Meta Learning via Local Subgraphscited by 89
  14. 2019When Does Self-supervision Improve Few-shot Learning?cited by 78
  15. 2021Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learningcited by 70
  16. 2019Graph Few-shot Learning via Knowledge Transfercited by 63
  17. 2021Pareto Self-Supervised Training for Few-Shot Learningcited by 52
  18. 2022Task-Adaptive Few-shot Node Classificationcited by 43
  19. 2022Graph Few-shot Learning with Task-specific Structurescited by 26
  20. 2022Transductive Linear Probing: A Novel Framework for Few-Shot Node Classificationcited by 24
  21. 2020Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embeddingcited by 19
  22. 2021Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learningcited by 15
  23. 2023Unsupervised Meta-Learning via Few-shot Pseudo-supervised Contrastive Learningcited by 15

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 0; 2025: 2.

3 papers.

  1. 2023One for All: Towards Training One Graph Model for All Classification Taskscited by 243
  2. 2025H4G: Unlocking Faithful Inference for Zero-Shot Graph Learning in Hyperbolic Spacecited by 1
  3. 2025MoEMeta: Mixture-of-Experts Meta Learning for Few-Shot Relational Learningcited by 1