mlsanityData to 7 Oct 2026

Multiresolution Equivariant Graph Variational Autoencoder

arXiv 2106.00967 ↗First posted 2 Jun 2021cs.LG cs.SI physics.chem-phcited by 20

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose Multiresolution Equivariant Graph Variational Autoencoders (MGVAE), the first hierarchical generative model to learn and generate graphs in a multiresolution and equivariant manner. At each resolution level, MGVAE employs higher order message passing to encode the graph while learning to partition it into mutually exclusive clusters and coarsening into a lower resolution that eventually creates a hierarchy of latent distributions. MGVAE then constructs a hierarchical generative model to variationally decode into a hierarchy of coarsened graphs. Importantly, our proposed framework is end-to-end permutation equivariant with respect to node ordering. MGVAE achieves competitive results with several generative tasks including general graph generation, molecular generation, unsupervised molecular representation learning to predict molecular properties, link prediction on citation graphs, and graph-based image generation.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 50 of its 98 references that are in the map. First posted on arXiv 2 Jun 2021.

Builds on

50 of 98 references.

References · 50

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  5. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  6. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  7. 2014DeepWalk: Online Learning of Social Representationscited by 1,543
  8. 2017Deep Setscited by 1,394
  9. 2016Variational Graph Auto-Encoderscited by 1,373
  10. 2016Group Equivariant Convolutional Networkscited by 1,154
  11. 2015Gated Graph Sequence Neural Networkscited by 792
  12. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
38 more
  1. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 762
  2. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 751
  3. 2020Benchmarking Graph Neural Networkscited by 672
  4. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
  5. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 635
  6. 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 503
  7. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  8. 2018GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Modelscited by 406
  9. 2018MolGAN: An implicit generative model for small molecular graphscited by 392
  10. 2019Provably Powerful Graph Networkscited by 385
  11. 2018GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoderscited by 375
  12. 2018Invariant and Equivariant Graph Networkscited by 339
  13. 2016Learning Convolutional Neural Networks for Graphscited by 314
  14. 2020GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generationcited by 301
  15. 2016Steerable CNNscited by 298
  16. 2016Molecular Graph Convolutions: Moving Beyond Fingerprintscited by 238
  17. 2019Efficient Graph Generation with Graph Recurrent Attention Networkscited by 231
  18. 2018Learning Deep Generative Models of Graphscited by 227
  19. 2017VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learningcited by 199
  20. 2018Constrained Graph Variational Autoencoders for Molecule Designcited by 182
  21. 2020Stochastic Normalizing Flowscited by 156
  22. 2019On the Universality of Invariant Networkscited by 151
  23. 2014A* Samplingcited by 150
  24. 2019Graph Wavelet Neural Networkcited by 131
  25. 2017PacGAN: The power of two samples in generative adversarial networkscited by 104
  26. 2019Graph Normalizing Flowscited by 103
  27. 2020On Learning Sets of Symmetric Elementscited by 97
  28. 2015Hierarchical Variational Modelscited by 89
  29. 2020Factorizable Graph Convolutional Networkscited by 79
  30. 2020Scalable Deep Generative Modeling for Sparse Graphscited by 63
  31. 2018Covariant Compositional Networks For Learning Graphscited by 54
  32. 2019Learning Hierarchical Priors in VAEscited by 53
  33. 2016On Valid Optimal Assignment Kernels and Applications to Graph Classificationcited by 49
  34. 2020The general theory of permutation equivarant neural networks and higher order graph variational encoderscited by 28
  35. 2019Prescribed Generative Adversarial Networkscited by 23
  36. 2020Set2Graph: Learning Graphs From Setscited by 16
  37. 2014Unsupervised Deep Haar Scattering on Graphscited by 6
  38. 2015Deep Haar Scattering Networkscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 6; 2024: 5; 2025: 2; 2026: 5.

20 papers.

Sort:

  1. 2022Temporal Multiresolution Graph Neural Networks For Epidemic Predictioncited by 11
  2. 2023Predicting COVID-19 pandemic by spatio-temporal graph neural networks: A New Zealand's studycited by 6
  3. 2023Geometry of Linear Neural Networks: Equivariance and Invariance under Permutation Groupscited by 5
  4. 2023Multiresolution Graph Transformers and Wavelet Positional Encoding for Learning Hierarchical Structurescited by 4
  5. 2024EvoMesh: Adaptive Physical Simulation with Hierarchical Graph Evolutionscited by 4
  6. 2024Interpreting Equivariant Representationscited by 2
  7. 2024Current Symmetry Group Equivariant Convolution Frameworks for Representation Learningcited by 2
  8. 2022ReGAE: Graph autoencoder based on recursive neural networkscited by 1
  9. 2023HDGL: A hierarchical dynamic graph representation learning model for brain disorder classificationcited by 1
  10. 2024Thermodynamics-informed graph neural networks for real-time simulation of digital human twinscited by 1
  11. 2023Target-aware Variational Auto-encoders for Ligand Generation with Multimodal Protein Representation Learningcited by 0
  12. 2023Symmetry-preserving graph attention network to solve routing problems at multiple resolutionscited by 0
8 more
  1. 2024Range-aware Positional Encoding via High-order Pretraining: Theory and Practicecited by 0
  2. 2025MOB-GCN: A Novel Multiscale Object-Based Graph Neural Network for Hyperspectral Image Classificationcited by 0
  3. 2025LGDC: Latent Graph Diffusion via Spectrum-Preserving Coarseningcited by 0
  4. 2026Binary Latent Protein Fitness Landscapes for Quantum Annealing Optimizationcited by 0
  5. 2026Q-BIOLAT: Binary Latent Protein Fitness Landscapes for QUBO-Based Optimizationcited by 0
  6. 2026PRIME: Protein Representation via Physics-Informed Multiscale Equivariant Hierarchiescited by 0
  7. 2026CARD: Coarse-to-fine Autoregressive Modeling with Radix-based Decomposition for Transferable Free Energy Estimationcited by 0
  8. 2026GeoGAE: Scalable Graph-Level Autoencoding via Hyperball Cloud Representationscited by 0