mlsanityData to 14 Oct 2026

Graph Neural Network Generalization with Gaussian Mixture Model Based Augmentation

arXiv 2411.08638 ↗First posted 13 Nov 2024cs.LG cs.SI stat.APcited by 2

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) have shown great promise in tasks like node and graph classification, but they often struggle to generalize, particularly to unseen or out-of-distribution (OOD) data. These challenges are exacerbated when training data is limited in size or diversity. To address these issues, we introduce a theoretical framework using Rademacher complexity to compute a regret bound on the generalization error and then characterize the effect of data augmentation. This framework informs the design of GRATIN, an efficient graph data augmentation algorithm leveraging the capability of Gaussian Mixture Models (GMMs) to approximate any distribution. Our approach not only outperforms existing augmentation techniques in terms of generalization but also offers improved time complexity, making it highly suitable for real-world applications.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 36 of its 70 references that are in the map. First posted on arXiv 13 Nov 2024.

Builds on

36 of 70 references.

References · 36

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2018How Powerful are Graph Neural Networks?cited by 4,393
  3. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,621
  4. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  5. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  6. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  7. 2020Learning Mesh-Based Simulation with Graph Networkscited by 868
  8. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 728
  9. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 680
  10. 2022DiGress: Discrete Denoising diffusion for graph generationcited by 520
  11. 2022DiffDock: Diffusion Steps, Twists, and Turns for Molecular Dockingcited by 313
  12. 2019A Fair Comparison of Graph Neural Networks for Graph Classificationcited by 244
24 more
  1. 2020Generalization and Representational Limits of Graph Neural Networkscited by 218
  2. 2021Data Augmentation Can Improve Robustnesscited by 194
  3. 2019Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernelscited by 161
  4. 2022G-Mixup: Graph Data Augmentation for Graph Classificationcited by 146
  5. 2020A PAC-Bayesian Approach to Generalization Bounds for Graph Neural Networkscited by 85
  6. 2021OOD-GNN: Out-of-Distribution Generalized Graph Neural Networkcited by 78
  7. 2023FAENet: Frame Averaging Equivariant GNN for Materials Modelingcited by 73
  8. 2020SuperMix: Supervising the Mixing Data Augmentationcited by 58
  9. 2021Learning Theory Can (Sometimes) Explain Generalisation in Graph Neural Networkscited by 51
  10. 2022Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and MLPscited by 42
  11. 2023Towards Understanding the Generalization of Graph Neural Networkscited by 41
  12. 2013Clustering and Community Detection in Directed Networks: A Surveycited by 38
  13. 2022SizeShiftReg: a Regularization Method for Improving Size-Generalization in Graph Neural Networkscited by 37
  14. 2022Higher-order Clustering and Pooling for Graph Neural Networkscited by 26
  15. 2022A Deep Reinforcement Learning Framework For Column Generationcited by 22
  16. 2022Model-Agnostic Augmentation for Accurate Graph Classificationcited by 21
  17. 2022Masking Adversarial Damage: Finding Adversarial Saliency for Robust and Sparse Networkcited by 21
  18. 2023Graph Mixup with Soft Alignmentscited by 15
  19. 2023Fused Gromov-Wasserstein Graph Mixup for Graph-level Classificationscited by 15
  20. 2024Investigating Out-of-Distribution Generalization of GNNs: An Architecture Perspectivecited by 13
  21. 2024A Simple and Yet Fairly Effective Defense for Graph Neural Networkscited by 12
  22. 2024Gegenbauer Graph Neural Networks for Time-varying Signal Reconstructioncited by 12
  23. 2024Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attackscited by 9
  24. 2024Enhancing Size Generalization in Graph Neural Networks through Disentangled Representation Learningcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025PR-CapsNet: Pseudo-Riemannian Capsule Network with Adaptive Curvature Routing for Graph Learningcited by 0
  2. 2026CGRL: Causal-Guided Representation Learning for Node-Level Out-of-Distribution Generalizationcited by 0