mlsanityData to 14 Oct 2026

G-Mixup: Graph Data Augmentation for Graph Classification

arXiv 2202.07179 ↗First posted 15 Feb 2022cs.LG cs.AIcited by 146

Not on the map. Why?

Abstract (arXiv)

This work develops mixup for graph data. Mixup has shown superiority in improving the generalization and robustness of neural networks by interpolating features and labels between two random samples. Traditionally, Mixup can work on regular, grid-like, and Euclidean data such as image or tabular data. However, it is challenging to directly adopt Mixup to augment graph data because different graphs typically: 1) have different numbers of nodes; 2) are not readily aligned; and 3) have unique typologies in non-Euclidean space. To this end, we propose G-Mixup to augment graphs for graph classification by interpolating the generator (i.e., graphon) of different classes of graphs. Specifically, we first use graphs within the same class to estimate a graphon. Then, instead of directly manipulating graphs, we interpolate graphons of different classes in the Euclidean space to get mixed graphons, where the synthetic graphs are generated through sampling based on the mixed graphons. Extensive experiments show that G-Mixup substantially improves the generalization and robustness of GNNs.

Key facts. Cited by 146 papers in the map (data through 14 Oct 2026). Builds on 37 of its 74 references that are in the map. First posted on arXiv 15 Feb 2022.

Builds on

37 of 74 references.

References · 37

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  5. 2017Inductive Representation Learning on Large Graphscited by 6,320
  6. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  7. 2018How Powerful are Graph Neural Networks?cited by 4,393
  8. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  9. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  10. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
  11. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  12. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 787
25 more
  1. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 680
  2. 2019Graph U-Netscited by 492
  3. 2018Deep Learning on Graphs: A Surveycited by 393
  4. 2020Data Augmentation for Graph Neural Networkscited by 203
  5. 2021Adversarial Graph Augmentation to Improve Graph Contrastive Learningcited by 200
  6. 2020How Does Mixup Help With Robustness and Generalization?cited by 193
  7. 2018Adaptive Sampling Towards Fast Graph Representation Learningcited by 180
  8. 2018MixUp as Locally Linear Out-Of-Manifold Regularizationcited by 158
  9. 2019Augmenting Data with Mixup for Sentence Classification: An Empirical Studycited by 125
  10. 2021Accurate Learning of Graph Representations with Graph Multiset Poolingcited by 120
  11. 2020Graphon Neural Networks and the Transferability of Graph Neural Networkscited by 118
  12. 2020Towards Deeper Graph Neural Networks with Differentiable Group Normalizationcited by 114
  13. 2013Stochastic blockmodel approximation of a graphon: Theory and consistent estimationcited by 39
  14. 2014A Consistent Histogram Estimator for Exchangeable Graph Modelscited by 37
  15. 2020Learning Graphons via Structured Gromov-Wasserstein Barycenterscited by 37
  16. 2020GraphCrop: Subgraph Cropping for Graph Classificationcited by 31
  17. 2021Graph Transplant: Node Saliency-Guided Graph Mixup with Local Structure Preservationcited by 30
  18. 2022Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentationscited by 28
  19. 2020Data Augmentation for Graph Classificationcited by 22
  20. 2017Centrality measures for graphons: Accounting for uncertainty in networkscited by 17
  21. 2019How Robust Are Graph Neural Networks to Structural Noise?cited by 15
  22. 2022Geometric Graph Representation Learning via Maximizing Rate Reductioncited by 9
  23. 2020The Laplacian Spectrum of Large Graphs Sampled from Graphonscited by 8
  24. 2021Data Augmentation for Graph Convolutional Network on Semi-Supervised Classificationcited by 7
  25. 2021Training Graph Neural Networks by Graphon Estimationcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 17; 2023: 46; 2024: 44; 2025: 26; 2026: 13.

146 papers.

Sort:

By area:

  1. 2023Data-centric Artificial Intelligence: A Surveycited by 203
  2. 2022Data Augmentation for Deep Graph Learning: A Surveycited by 133
  3. 2022Out-Of-Distribution Generalization on Graphs: A Surveycited by 97
  4. 2022A Generalization of ViT/MLP-Mixer to Graphscited by 93
  5. 2023Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modelingcited by 64
  6. 2022Graph Data Augmentation for Graph Machine Learning: A Surveycited by 62
  7. 2023Structural Re-weighting Improves Graph Domain Adaptationcited by 45
  8. 2024A Comprehensive Survey on Data Augmentationcited by 40
  9. 2022Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shiftcited by 38
  10. 2022A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainabilitycited by 31
  11. 2024Pairwise Alignment Improves Graph Domain Adaptationcited by 25
  12. 2024Improved Generalization of Weight Space Networks via Augmentationscited by 24
38 more
  1. 2023Data-centric Graph Learning: A Surveycited by 22
  2. 2022Automated Data Augmentations for Graph Classificationcited by 20
  3. 2024A Survey on Mixup Augmentations and Beyondcited by 20
  4. 2023The Benefits of Mixup for Feature Learningcited by 19
  5. 2023Data-Centric Learning from Unlabeled Graphs with Diffusion Modelcited by 19
  6. 2023Rayleigh Quotient Graph Neural Networks for Graph-level Anomaly Detectioncited by 19
  7. 2023GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned Expertscited by 19
  8. 2024Hypergraph-based Multi-View Action Recognition using Event Camerascited by 19
  9. 2025GraphMaster: Automated Graph Synthesis via LLM Agents in Data-Limited Environmentscited by 19
  10. 2023When to Pre-Train Graph Neural Networks? From Data Generation Perspective!cited by 18
  11. 2023Pseudo-Bag Mixup Augmentation for Multiple Instance Learning-Based Whole Slide Image Classificationcited by 18
  12. 2023MixupExplainer: Generalizing Explanations for Graph Neural Networks with Data Augmentationcited by 18
  13. 2023Graph Invariant Learning with Subgraph Co-mixup for Out-Of-Distribution Generalizationcited by 18
  14. 2024Subgraph Pooling: Tackling Negative Transfer on Graphscited by 17
  15. 2024A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptationcited by 17
  16. 2025Pave Your Own Path: Graph Gradual Domain Adaptation on Fused Gromov-Wasserstein Geodesicscited by 17
  17. 2024Modality-Aware Integration with Large Language Models for Knowledge-based Visual Question Answeringcited by 16
  18. 2023Graph Mixup with Soft Alignmentscited by 15
  19. 2023Fused Gromov-Wasserstein Graph Mixup for Graph-level Classificationscited by 15
  20. 2023Towards Data-centric Graph Machine Learning: Review and Outlookcited by 15
  21. 2022GraphTTA: Test Time Adaptation on Graph Neural Networkscited by 14
  22. 2023Semi-Supervised Graph Imbalanced Regressioncited by 14
  23. 2023Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networkscited by 14
  24. 2022GraphMAD: Graph Mixup for Data Augmentation using Data-Driven Convex Clusteringcited by 13
  25. 2023Over-training with Mixup May Hurt Generalizationcited by 13
  26. 2023Fine-tuning Graph Neural Networks by Preserving Graph Generative Patternscited by 13
  27. 2025GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuningcited by 13
  28. 2022SA-MLP: Distilling Graph Knowledge from GNNs into Structure-Aware MLPcited by 12
  29. 2022RSC: Accelerating Graph Neural Networks Training via Randomized Sparse Computationscited by 12
  30. 2023Improving Expressivity of GNNs with Subgraph-specific Factor Embedded Normalizationcited by 12
  31. 2023Chasing Fairness in Graphs: A GNN Architecture Perspectivecited by 12
  32. 2023Contrastive Meta-Learning for Few-shot Node Classificationcited by 11
  33. 2022Data Augmentation on Graphs: A Technical Surveycited by 10
  34. 2023Graph Structure and Feature Extrapolation for Out-of-Distribution Generalizationcited by 10
  35. 2024A Graph is Worth K Words: Euclideanizing Graph using Pure Transformercited by 10
  36. 2023R-Mixup: Riemannian Mixup for Biological Networkscited by 9
  37. 2023RegExplainer: Generating Explanations for Graph Neural Networks in Regression Taskscited by 9
  38. 2023Graph Out-of-Distribution Generalization with Controllable Data Augmentationcited by 9

50 most cited of 146 All 146 (JSON)