mlsanityData to 14 Oct 2026

Evaluating Graph Generative Models with Contrastively Learned Features

arXiv 2206.06234 ↗First posted 13 Jun 2022stat.ML cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

A wide range of models have been proposed for Graph Generative Models, necessitating effective methods to evaluate their quality. So far, most techniques use either traditional metrics based on subgraph counting, or the representations of randomly initialized Graph Neural Networks (GNNs). We propose using representations from contrastively trained GNNs, rather than random GNNs, and show this gives more reliable evaluation metrics. Neither traditional approaches nor GNN-based approaches dominate the other, however: we give examples of graphs that each approach is unable to distinguish. We demonstrate that Graph Substructure Networks (GSNs), which in a way combine both approaches, are better at distinguishing the distances between graph datasets.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 46 of its 58 references that are in the map. First posted on arXiv 13 Jun 2022.

Builds on

46 of 58 references.

References · 46

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  6. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  7. 2018How Powerful are Graph Neural Networks?cited by 4,393
  8. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  9. 2016Improved Techniques for Training GANscited by 2,970
  10. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  11. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,405
  12. 2018Demystifying MMD GANscited by 1,293
34 more
  1. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,273
  2. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  3. 2018Deep Graph Infomaxcited by 1,106
  4. 2018Which Training Methods for GANs do actually Converge?cited by 679
  5. 2020Contrastive Multi-View Representation Learning on Graphscited by 652
  6. 2017Wasserstein GANcited by 639
  7. 2020Deep Graph Contrastive Representation Learningcited by 539
  8. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  9. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 464
  10. 2020GCC: Graph Contrastive Coding for Graph Neural Network Pre-Trainingcited by 463
  11. 2019InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximizationcited by 441
  12. 2020Reliable Fidelity and Diversity Metrics for Generative Modelscited by 434
  13. 2018GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Modelscited by 413
  14. 2018Assessing Generative Models via Precision and Recallcited by 406
  15. 2018MolGAN: An implicit generative model for small molecular graphscited by 393
  16. 2020Improving Graph Neural Network Expressivity via Subgraph Isomorphism Countingcited by 313
  17. 2015A note on the evaluation of generative modelscited by 292
  18. 2021Graph Contrastive Learning Automatedcited by 287
  19. 2020Can Graph Neural Networks Count Substructures?cited by 236
  20. 2019Efficient Graph Generation with Graph Recurrent Attention Networkscited by 234
  21. 2018Learning Deep Generative Models of Graphscited by 229
  22. 2018Pros and Cons of GAN Evaluation Measurescited by 224
  23. 2020Learning Deep Kernels for Non-Parametric Two-Sample Testscited by 130
  24. 2017Stabilizing Training of Generative Adversarial Networks through Regularizationcited by 118
  25. 2019GraphNVP: An Invertible Flow Model for Generating Molecular Graphscited by 116
  26. 2022Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlapcited by 105
  27. 2020A Systematic Survey on Deep Generative Models for Graph Generationcited by 94
  28. 2020Scalable Deep Generative Modeling for Sparse Graphscited by 65
  29. 2022On Evaluation Metrics for Graph Generative Modelscited by 46
  30. 2021Evaluation Metrics for Graph Generative Models: Problems, Pitfalls, and Practical Solutionscited by 39
  31. 2018On gradient regularizers for MMD GANscited by 28
  32. 2022Cross-Domain Few-Shot Graph Classificationcited by 19
  33. 2020Graph Deconvolutional Generationcited by 16
  34. 2022Learning Graph Augmentations to Learn Graph Representationscited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 0; 2025: 2; 2026: 1.

5 papers.

  1. 2022A Framework for Large Scale Synthetic Graph Dataset Generationcited by 6
  2. 2025PolyGraph Discrepancy: a classifier-based metric for graph generationcited by 3
  3. 2023Topology Only Pre-Training: Towards Generalised Multi-Domain Graph Modelscited by 1
  4. 2025Graph Generative Models Evaluation with Masked Autoencodercited by 0
  5. 2026Diversity Curves for Graph Representation Learningcited by 0