mlsanityData to 7 Oct 2026

Unsupervised Episode Generation for Graph Meta-learning

arXiv 2306.15217 ↗First posted 27 Jun 2023cs.LG cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

We propose Unsupervised Episode Generation method called Neighbors as Queries (NaQ) to solve the Few-Shot Node-Classification (FSNC) task by unsupervised Graph Meta-learning. Doing so enables full utilization of the information of all nodes in a graph, which is not possible in current supervised meta-learning methods for FSNC due to the label-scarcity problem. In addition, unlike unsupervised Graph Contrastive Learning (GCL) methods that overlook the downstream task to be solved at the training phase resulting in vulnerability to class imbalance of a graph, we adopt the episodic learning framework that allows the model to be aware of the downstream task format, i.e., FSNC. The proposed NaQ is a simple but effective unsupervised episode generation method that randomly samples nodes from a graph to make a support set, followed by similarity-based sampling of nodes to make the corresponding query set. Since NaQ is model-agnostic, any existing supervised graph meta-learning methods can be trained in an unsupervised manner, while not sacrificing much of their performance or sometimes even improving them. Extensive experimental results demonstrate the effectiveness of our proposed unsupervised episode generation method for graph meta-learning towards the FSNC task. Our code is available at: https://github.com/JhngJng/NaQ-PyTorch.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 33 of its 52 references that are in the map. First posted on arXiv 27 Jun 2023.

Builds on

33 of 52 references.

References · 33

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  6. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  7. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  8. 2016Matching Networks for One Shot Learningcited by 2,246
  9. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  10. 2019A Closer Look at Few-shot Classificationcited by 679
  11. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
  12. 2019Diffusion Improves Graph Learningcited by 414
21 more
  1. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 368
  2. 2017Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Rankingcited by 332
  3. 2021Large-Scale Representation Learning on Graphs via Bootstrappingcited by 184
  4. 2020Graph-Bert: Only Attention is Needed for Learning Graph Representationscited by 176
  5. 2019Meta-GNN: On Few-shot Node Classification in Graph Meta-learningcited by 105
  6. 2021Augmentation-Free Self-Supervised Learning on Graphscited by 94
  7. 2015Inferring Networks of Substitutable and Complementary Productscited by 91
  8. 2020Graph Prototypical Networks for Few-shot Learning on Attributed Networkscited by 90
  9. 2020Graph Meta Learning via Local Subgraphscited by 89
  10. 2018Unsupervised Learning via Meta-Learningcited by 81
  11. 2018Unsupervised Meta-Learning For Few-Shot Image Classificationcited by 74
  12. 2023Virtual Node Tuning for Few-shot Node Classificationcited by 46
  13. 2022Task-Adaptive Few-shot Node Classificationcited by 43
  14. 2020Unsupervised Meta-Learning through Latent-Space Interpolation in Generative Modelscited by 26
  15. 2022Graph Few-shot Learning with Task-specific Structurescited by 26
  16. 2019Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentationcited by 24
  17. 2022Transductive Linear Probing: A Novel Framework for Few-Shot Node Classificationcited by 24
  18. 2023Robust Mid-Pass Filtering Graph Convolutional Networkscited by 17
  19. 2023Few-shot Node Classification with Extremely Weak Supervisioncited by 14
  20. 2022Relational Self-Supervised Learning on Graphscited by 11
  21. 2023Task-Equivariant Graph Few-shot Learningcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Improving Graph Few-shot Learning with Hyperbolic Space and Denoising Diffusioncited by 0