mlsanityData to 7 Oct 2026

An Unpooling Layer for Graph Generation

arXiv 2206.01874 ↗First posted 4 Jun 2022cs.LG stat.MLcited by 3

Not on the map. Why?

Abstract (arXiv)

We propose a novel and trainable graph unpooling layer for effective graph generation. Given a graph with features, the unpooling layer enlarges this graph and learns its desired new structure and features. Since this unpooling layer is trainable, it can be applied to graph generation either in the decoder of a variational autoencoder or in the generator of a generative adversarial network (GAN). We prove that the unpooled graph remains connected and any connected graph can be sequentially unpooled from a 3-nodes graph. We apply the unpooling layer within the GAN generator. Since the most studied instance of graph generation is molecular generation, we test our ideas in this context. Using the QM9 and ZINC datasets, we demonstrate the improvement obtained by using the unpooling layer instead of an adjacency-matrix-based approach.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 38 of its 63 references that are in the map. First posted on arXiv 4 Jun 2022.

Builds on

38 of 63 references.

References · 38

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2018How Powerful are Graph Neural Networks?cited by 4,355
  4. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  5. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  6. 2017Improved Training of Wasserstein GANscited by 2,223
  7. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  8. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  9. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  10. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
  11. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 762
  12. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 751
26 more
  1. 2019Graph Neural Networks for Social Recommendationcited by 711
  2. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
  3. 2019Graph U-Netscited by 489
  4. 2019Self-Attention Graph Poolingcited by 421
  5. 2018GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Modelscited by 406
  6. 2018MolGAN: An implicit generative model for small molecular graphscited by 392
  7. 2018GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoderscited by 375
  8. 2018Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generationcited by 363
  9. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 307
  10. 2020GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generationcited by 301
  11. 2017Grammar Variational Autoencodercited by 283
  12. 2022Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equationscited by 273
  13. 2018Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Modelscited by 270
  14. 2020MoFlow: An Invertible Flow Model for Generating Molecular Graphscited by 183
  15. 2021GraphDF: A Discrete Flow Model for Molecular Graph Generationcited by 177
  16. 2016Variational Autoencoder for Deep Learning of Images, Labels and Captionscited by 137
  17. 2017Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Modelscited by 116
  18. 2019GraphNVP: An Invertible Flow Model for Generating Molecular Graphscited by 115
  19. 2019Graph Convolutional Networks with EigenPoolingcited by 94
  20. 2018Learning Multimodal Graph-to-Graph Translation for Molecular Optimizationcited by 87
  21. 2013The Optimal Reward Baseline for Gradient-Based Reinforcement Learningcited by 84
  22. 2020Molecular graph generation with Graph Neural Networkscited by 79
  23. 2018NeVAE: A Deep Generative Model for Molecular Graphscited by 66
  24. 2019Deep learning for molecular design - a review of the state of the artcited by 38
  25. 2020Deep Graph Generators: A Surveycited by 36
  26. 2018Improving Chemical Autoencoder Latent Space and Molecular De novo Generation Diversity with Heteroencoderscited by 11

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 1.

3 papers.

  1. 2023Efficient and Scalable Graph Generation through Iterative Local Expansioncited by 35
  2. 2024HYGENE: A Diffusion-based Hypergraph Generation Methodcited by 8
  3. 2025LGDC: Latent Graph Diffusion via Spectrum-Preserving Coarseningcited by 0