mlsanityData to 7 Oct 2026

Dirichlet Graph Variational Autoencoder

arXiv 2010.04408 ↗First posted 9 Oct 2020cs.LGcited by 40

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) and Variational Autoencoders (VAEs) have been widely used in modeling and generating graphs with latent factors. However, there is no clear explanation of what these latent factors are and why they perform well. In this work, we present Dirichlet Graph Variational Autoencoder (DGVAE) with graph cluster memberships as latent factors. Our study connects VAEs based graph generation and balanced graph cut, and provides a new way to understand and improve the internal mechanism of VAEs based graph generation. Specifically, we first interpret the reconstruction term of DGVAE as balanced graph cut in a principled way. Furthermore, motivated by the low pass characteristics in balanced graph cut, we propose a new variant of GNN named Heatts to encode the input graph into cluster memberships. Heatts utilizes the Taylor series for fast computation of heat kernels and has better low pass characteristics than Graph Convolutional Networks (GCN). Through experiments on graph generation and graph clustering, we demonstrate the effectiveness of our proposed framework.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 12; 2023: 9; 2024: 5; 2025: 5; 2026: 3.

40 papers.

Sort:

By area:

  1. 2021Self-Supervised Learning of Graph Neural Networks: A Unified Reviewcited by 184
  2. 2021Graph-based Semi-supervised Learning: A Comprehensive Reviewcited by 79
  3. 2023Efficient and Degree-Guided Graph Generation via Discrete Diffusion Modelingcited by 75
  4. 2022A Survey on Deep Graph Generation: Methods and Applicationscited by 69
  5. 2022A Survey of Deep Graph Clustering: Taxonomy, Challenge, Application, and Open Resourcecited by 26
  6. 2022Modularity-Aware Graph Autoencoders for Joint Community Detection and Link Predictioncited by 22
  7. 2022NVDiff: Graph Generation through the Diffusion of Node Vectorscited by 18
  8. 2021Deconvolutional Networks on Graph Datacited by 16
  9. 2023Contrastive Graph Clustering in Curvature Spacescited by 15
  10. 2022Wiener Graph Deconvolutional Network Improves Graph Self-Supervised Learningcited by 13
  11. 2023A Convergent Single-Loop Algorithm for Relaxation of Gromov-Wasserstein in Graph Datacited by 10
  12. 2021Mask-GVAE: Blind Denoising Graphs via Partitioncited by 9
28 more
  1. 2023Node-Aligned Graph-to-Graph (NAG2G): Elevating Template-Free Deep Learning Approaches in Single-Step Retrosynthesiscited by 9
  2. 2024A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspectivecited by 9
  3. 2023Continual Learning with Dirichlet Generative-based Rehearsalcited by 7
  4. 2022Hyperspectral Pixel Unmixing with Latent Dirichlet Variational Autoencodercited by 5
  5. 2024Neural Graph Generator: Feature-Conditioned Graph Generation using Latent Diffusion Modelscited by 5
  6. 2023A Contrastive Variational Graph Auto-Encoder for Node Clusteringcited by 4
  7. 2024Signed Graph Autoencoder for Explainable and Polarization-Aware Network Embeddingscited by 4
  8. 2022Interpretable Node Representation with Attribute Decodingcited by 3
  9. 2023EDGE++: Improved Training and Sampling of EDGEcited by 3
  10. 2024Uncertainty Quantification on Graph Learning: A Surveycited by 3
  11. 2025Gen-C: Populating Virtual Worlds with Generative Crowdscited by 3
  12. 2022Deep Graph Clustering via Mutual Information Maximization and Mixture Modelcited by 2
  13. 2022SCGG: A Deep Structure-Conditioned Graph Generative Modelcited by 2
  14. 2023Modeling and design of heterogeneous hierarchical bioinspired spider web structures using generative deep learning and additive manufacturingcited by 2
  15. 2025BN-Pool: Bayesian Nonparametric Pooling for Graphscited by 2
  16. 2021Operator Autoencoders: Learning Physical Operations on Encoded Molecular Graphscited by 1
  17. 2021Graph2Graph Learning with Conditional Autoregressive Modelscited by 1
  18. 2022New Frontiers in Graph Autoencoders: Joint Community Detection and Link Predictioncited by 1
  19. 2023Variational Autoencoders for Feature Exploration and Malignancy Prediction of Lung Lesionscited by 1
  20. 2026Principled Latent Diffusion for Graphs via Laplacian Autoencoderscited by 1
  21. 2022Stratified Graph Spectracited by 0
  22. 2022Gransformer: Transformer-based Graph Generationcited by 0
  23. 2024A Review of Graph-Powered Data Quality Applications for IoT Monitoring Sensor Networkscited by 0
  24. 2025To Share or Not to Share: Investigating Weight Sharing in Variational Graph Autoencoderscited by 0
  25. 2025NGTM: Substructure-based Neural Graph Topic Model for Interpretable Graph Generationcited by 0
  26. 2025BikeVAE-GNN: A Variational Autoencoder-Augmented Hybrid Graph Neural Network for Sparse Bicycle Volume Estimationcited by 0
  27. 2026Beyond the Academic Monoculture: A Unified Framework and Industrial Perspective for Attributed Graph Clusteringcited by 0
  28. 2026Rethinking Generalization in Graph Neural Networks: A Structural Complexity Perspectivecited by 0