mlsanityData to 13 Oct 2026

Learning Graph Augmentations to Learn Graph Representations

arXiv 2201.09830 ↗First posted 24 Jan 2022cs.LG cs.NEcited by 14

Not on the map. Why?

Abstract (arXiv)

Devising augmentations for graph contrastive learning is challenging due to their irregular structure, drastic distribution shifts, and nonequivalent feature spaces across datasets. We introduce LG2AR, Learning Graph Augmentations to Learn Graph Representations, which is an end-to-end automatic graph augmentation framework that helps encoders learn generalizable representations on both node and graph levels. LG2AR consists of a probabilistic policy that learns a distribution over augmentations and a set of probabilistic augmentation heads that learn distributions over augmentation parameters. We show that LG2AR achieves state-of-the-art results on 18 out of 20 graph-level and node-level benchmarks compared to previous unsupervised models under both linear and semi-supervised evaluation protocols. The source code will be released here: https://github.com/kavehhassani/lg2ar

Key facts. Cited by 14 papers in the map (data through 13 Oct 2026). Builds on 53 of its 74 references that are in the map. First posted on arXiv 24 Jan 2022.

Builds on

53 of 74 references.

References · 53

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,009
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,318
  3. 2017Graph Attention Networkscited by 8,888
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,712
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,492
  6. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,730
  7. 2018How Powerful are Graph Neural Networks?cited by 4,373
  8. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,024
  9. 2017Neural Message Passing for Quantum Chemistrycited by 3,471
  10. 2020Exploring Simple Siamese Representation Learningcited by 2,860
  11. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,726
  12. 2016node2vec: Scalable Feature Learning for Networkscited by 1,915
38 more
  1. 2017Deep Setscited by 1,404
  2. 2016Variational Graph Auto-Encoderscited by 1,379
  3. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,269
  4. 2020Graph Contrastive Learning with Augmentationscited by 1,207
  5. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,142
  6. 2018Deep Graph Infomaxcited by 1,104
  7. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,003
  8. 2019Strategies for Pre-training Graph Neural Networkscited by 965
  9. 2020Learning to Simulate Complex Physics with Graph Networkscited by 873
  10. 2015Gated Graph Sequence Neural Networkscited by 794
  11. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 753
  12. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 723
  13. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 680
  14. 2020Contrastive Multi-View Representation Learning on Graphscited by 652
  15. 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 545
  16. 2020Deep Graph Contrastive Representation Learningcited by 537
  17. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  18. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 505
  19. 2020GCC: Graph Contrastive Coding for Graph Neural Network Pre-Trainingcited by 462
  20. 2021A Survey of Data Augmentation Approaches for NLPcited by 408
  21. 2021Graph Self-Supervised Learning: A Surveycited by 289
  22. 2021Graph Contrastive Learning Automatedcited by 287
  23. 2020Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networkscited by 257
  24. 2019Fast AutoAugmentcited by 243
  25. 2017graph2vec: Learning Distributed Representations of Graphscited by 229
  26. 2020Graph Representation Learning via Graphical Mutual Information Maximizationcited by 217
  27. 2019Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacementcited by 208
  28. 2020Data Augmentation for Graph Neural Networkscited by 203
  29. 2021Adversarial Graph Augmentation to Improve Graph Contrastive Learningcited by 200
  30. 2021Self-Supervised Learning of Graph Neural Networks: A Unified Reviewcited by 184
  31. 2020Interpreting Graph Neural Networks for NLP With Differentiable Edge Maskingcited by 153
  32. 2019Faster AutoAugment: Learning Augmentation Strategies using Backpropagationcited by 96
  33. 2019Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learningcited by 94
  34. 2018Bayesian graph convolutional neural networks for semi-supervised classificationcited by 89
  35. 2019Unsupervised Multi-Task Feature Learning on Point Cloudscited by 89
  36. 2018Adversarially Regularized Graph Autoencoder for Graph Embeddingcited by 84
  37. 2020Memory-Based Graph Networkscited by 56
  38. 2017Learning Graph Representations with Embedding Propagationcited by 38

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2022: 5; 2023: 3; 2024: 2; 2025: 3; 2026: 1.

14 papers.

Sort:

  1. 2022Data Augmentation for Deep Graph Learning: A Surveycited by 133
  2. 2022Graph Data Augmentation for Graph Machine Learning: A Surveycited by 62
  3. 2023Data-centric Graph Learning: A Surveycited by 22
  4. 2022Automated Data Augmentations for Graph Classificationcited by 20
  5. 2022Data Augmentation on Graphs: A Technical Surveycited by 10
  6. 2023Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learningcited by 7
  7. 2022Evaluating Graph Generative Models with Contrastively Learned Featurescited by 5
  8. 2023ENGAGE: Explanation Guided Data Augmentation for Graph Representation Learningcited by 5
  9. 2024From Overfitting to Robustness: Quantity, Quality, and Variety Oriented Negative Sample Selection in Graph Contrastive Learningcited by 4
  10. 2024Structure-Aware Consensus Network on Graphs with Few Labeled Nodescited by 2
  11. 2025SOLA-GCL: Subgraph-Oriented Learnable Augmentation Method for Graph Contrastive Learningcited by 2
  12. 2025A Binary Classification Social Network Dataset for Graph Machine Learningcited by 1
2 more
  1. 2025Towards Automated Self-Supervised Learning for Truly Unsupervised Graph Anomaly Detectioncited by 0
  2. 2026AdNGCL: Adaptive Negative Scheduling for Graph Contrastive Learningcited by 0