mlsanityData to 7 Oct 2026

Automated Data Augmentations for Graph Classification

arXiv 2202.13248 ↗First posted 26 Feb 2022cs.LG cs.AIcited by 19

Not on the map. Why?

Abstract (arXiv)

Data augmentations are effective in improving the invariance of learning machines. We argue that the core challenge of data augmentations lies in designing data transformations that preserve labels. This is relatively straightforward for images, but much more challenging for graphs. In this work, we propose GraphAug, a novel automated data augmentation method aiming at computing label-invariant augmentations for graph classification. Instead of using uniform transformations as in existing studies, GraphAug uses an automated augmentation model to avoid compromising critical label-related information of the graph, thereby producing label-invariant augmentations at most times. To ensure label-invariance, we develop a training method based on reinforcement learning to maximize an estimated label-invariance probability. Experiments show that GraphAug outperforms previous graph augmentation methods on various graph classification tasks.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 42 of its 66 references that are in the map. First posted on arXiv 26 Feb 2022.

Builds on

42 of 66 references.

References · 42

  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. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2018How Powerful are Graph Neural Networks?cited by 4,355
  6. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  7. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  8. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  9. 2020Graph Contrastive Learning with Augmentationscited by 1,203
  10. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
  11. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
  12. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
30 more
  1. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  2. 2019Graph U-Netscited by 489
  3. 2021Graph Contrastive Learning Automatedcited by 287
  4. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 280
  5. 2019Fast AutoAugmentcited by 243
  6. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
  7. 2019Graph Matching Networks for Learning the Similarity of Graph Structured Objectscited by 202
  8. 2020Data Augmentation for Graph Neural Networkscited by 200
  9. 2021Adversarial Graph Augmentation to Improve Graph Contrastive Learningcited by 200
  10. 2021Self-Supervised Learning of Graph Neural Networks: A Unified Reviewcited by 184
  11. 2019Understanding Attention and Generalization in Graph Neural Networkscited by 169
  12. 2021Spherical Message Passing for 3D Graph Networkscited by 166
  13. 2019Population Based Augmentation: Efficient Learning of Augmentation Policy Schedulescited by 153
  14. 2022G-Mixup: Graph Data Augmentation for Graph Classificationcited by 145
  15. 2022Data Augmentation for Deep Graph Learning: A Surveycited by 132
  16. 2021An Empirical Study of Graph Contrastive Learningcited by 113
  17. 2019Adversarial AutoAugmentcited by 111
  18. 2019Faster AutoAugment: Learning Augmentation Strategies using Backpropagationcited by 96
  19. 2017Learning to Compose Domain-Specific Transformations for Data Augmentationcited by 91
  20. 2021DIG: A Turnkey Library for Diving into Graph Deep Learning Researchcited by 76
  21. 2021AutoGCL: Automated Graph Contrastive Learning via Learnable View Generatorscited by 73
  22. 2022Graph Data Augmentation for Graph Machine Learning: A Surveycited by 61
  23. 2020Advanced Graph and Sequence Neural Networks for Molecular Property Prediction and Drug Discoverycited by 46
  24. 2020GraphCrop: Subgraph Cropping for Graph Classificationcited by 31
  25. 2021Graph Transplant: Node Saliency-Guided Graph Mixup with Local Structure Preservationcited by 30
  26. 2021Augmentations in Graph Contrastive Learning: Current Methodological Flaws & Towards Better Practicescited by 24
  27. 2015APAC: Augmented PAttern Classification with Neural Networkscited by 23
  28. 2020Data Augmentation for Graph Classificationcited by 22
  29. 2022Learning Graph Augmentations to Learn Graph Representationscited by 14
  30. 2020M-Evolve: Structural-Mapping-Based Data Augmentation for Graph Classificationcited by 11

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 5; 2024: 9; 2025: 3.

19 papers.

Sort:

By area:

  1. 2023Data-centric Graph Learning: A Surveycited by 22
  2. 2024SpeGCL: Self-supervised Graph Spectrum Contrastive Learning without Positive Samplescited by 20
  3. 2023Data-Centric Learning from Unlabeled Graphs with Diffusion Modelcited by 19
  4. 2022Reinforcement learning on graphs: A surveycited by 18
  5. 2023Graph Mixup with Soft Alignmentscited by 15
  6. 2022GraphTTA: Test Time Adaptation on Graph Neural Networkscited by 14
  7. 2024Cross-Domain Graph Data Scaling: A Showcase with Diffusion Modelscited by 8
  8. 2023Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learningcited by 6
  9. 2024Evolving to the Future: Unseen Event Adaptive Fake News Detection on Social Mediacited by 5
  10. 2024Node Duplication Improves Cold-start Link Predictioncited by 4
  11. 2023Equipping Federated Graph Neural Networks with Structure-aware Group Fairnesscited by 2
  12. 2024Unifying Graph Contrastive Learning via Graph Message Augmentationcited by 2
7 more
  1. 2025AugWard: Augmentation-Aware Representation Learning for Accurate Graph Classificationcited by 2
  2. 2024Learning Tree-Structured Composition of Data Augmentationcited by 1
  3. 2024CORE: Data Augmentation for Link Prediction via Information Bottleneckcited by 0
  4. 2024Dual-perspective Cross Contrastive Learning in Graph Transformerscited by 0
  5. 2024Reproducibility Study Of Learning Fair Graph Representations Via Automated Data Augmentationscited by 0
  6. 2025Towards Automated Self-Supervised Learning for Truly Unsupervised Graph Anomaly Detectioncited by 0
  7. 2025Enhancement of Quantum Semi-Supervised Learning via Improved Laplacian and Poisson Methodscited by 0