mlsanityData to 14 Oct 2026

Improving Graph Few-shot Learning with Hyperbolic Space and Denoising Diffusion

arXiv 2604.27462 ↗First posted 30 Apr 2026cs.LG cs.AIcited by 0

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Graph few-shot learning, which focuses on effectively learning from only a small number of labeled nodes to quickly adapt to new tasks, has garnered significant research attention. Despite recent advances in graph few-shot learning that have demonstrated promising performance, existing methods still suffer from several key limitations. First, during the meta-training phase, these methods typically perform node representation learning in Euclidean space, which often fails to capture the inherently hierarchical structure existing in real-world graph data. Second, during the meta-testing phase, they usually fit an empirical target distribution derived from only a few support samples, even when this distribution significantly deviates from the true underlying distribution. To address these issues, we propose IMPRESS, a novel framework that IMproves graPh few-shot learning with hypeRbolic spacE and denoiSing diffuSion. Specifically, our model learns node representations in a hyperbolic space and enriches the support distribution through denoising diffusion mechanisms. Theoretically, IMPRESS achieves a tighter generalization bound. Empirically, IMPRESS consistently outperforms competitive baselines across multiple benchmark datasets.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 39 of its 47 references that are in the map. First posted on arXiv 30 Apr 2026.

Builds on

39 of 47 references.

References · 39

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  6. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  7. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  8. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  9. 2019Simplifying Graph Convolutional Networkscited by 1,477
  10. 2022Diffusion Models in Vision: A Surveycited by 1,015
  11. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  12. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
27 more
  1. 2017Poincar'e Embeddings for Learning Hierarchical Representationscited by 684
  2. 2018Hyperbolic Neural Networkscited by 402
  3. 2019Hyperbolic Graph Convolutional Neural Networkscited by 402
  4. 2017Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Rankingcited by 335
  5. 2018Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometrycited by 265
  6. 2020Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networkscited by 260
  7. 2022Diffsound: Discrete Diffusion Model for Text-to-sound Generationcited by 257
  8. 2019Hyperbolic Graph Neural Networkscited by 244
  9. 2022ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speechcited by 149
  10. 2021Hyperbolic Deep Neural Networks: A Surveycited by 139
  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. 2023Hyperbolic Deep Learning in Computer Vision: A Surveycited by 73
  15. 2019Graph Few-shot Learning via Knowledge Transfercited by 63
  16. 2023Virtual Node Tuning for Few-shot Node Classificationcited by 46
  17. 2022Task-Adaptive Few-shot Node Classificationcited by 43
  18. 2022Hyperbolic Graph Neural Networks: A Review of Methods and Applicationscited by 40
  19. 2022HICF: Hyperbolic Informative Collaborative Filteringcited by 24
  20. 2022Transductive Linear Probing: A Novel Framework for Few-Shot Node Classificationcited by 24
  21. 2023Few-shot Node Classification with Extremely Weak Supervisioncited by 14
  22. 2023Contrastive Meta-Learning for Few-shot Node Classificationcited by 11
  23. 2023Task-Equivariant Graph Few-shot Learningcited by 8
  24. 2025Enhancing Unsupervised Graph Few-shot Learning via Set Functions and Optimal Transportcited by 6
  25. 2025Dual-level Mixup for Graph Few-shot Learning with Fewer Taskscited by 5
  26. 2025Graph Few-Shot Learning via Adaptive Spectrum Experts and Cross-Set Distribution Calibrationcited by 3
  27. 2023Unsupervised Episode Generation for Graph Meta-learningcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Graffe: Graph Representation Learning via Diffusion Probabilistic Models
  2. 2023Sparse Training of Discrete Diffusion Models for Graph Generation
  3. 2026Principled Latent Diffusion for Graphs via Laplacian Autoencoders
  4. 2025Graph Representation Learning with Diffusion Generative Models
  5. 2025Controllable Graph Generation with Diffusion Models via Inference-Time Tree Search Guidance
  6. 2025Diffusion on Graph: Augmentation of Graph Structure for Node Classification
  7. 2023Directional diffusion models for graph representation learning
  8. 2025Diffusion-Free Graph Generation with Next-Scale Prediction