Research map / Graph learning / Graph self-supervised learning
Dirichlet Graph Variational Autoencoder
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use Dirichlet cluster-membership latents and Heatts instead of GCN-based Abl-VAE | DGVAE · Graph generation, six graph families | NLL and RMSE | Helped |
| Replace Heatts with GCN in the encoder (ablation) | DGVAE · Graph generation | NLL and RMSE | Hurt |
| Replace Heatts with GCN in the encoder (ablation) | DGVAE · Pubmed, Citeseer, and Wiki | ACC, NMI, and F1 | Hurt |
| Use reconstruction-focused inner-loop updates during training (ablation) | DGVAE · Erdos-Renyi graphs | posterior collapse | Helped |
| Use the third-order Taylor heat-kernel filter rather than the first-order GCN filter | Heatts · Spectral low-pass filtering | distance to ideal low-pass filter | Helped |
Closest papers by meaning
- D-VAE: A Variational Autoencoder for Directed Acyclic Graphs (NeurIPS 2019 · similarity 0.91)
- HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder for Graph Representation Learning (NeurIPS 2024 · similarity 0.86)
- Rethinking Graph Masked Autoencoders through Alignment and Uniformity (AAAI 2024 · similarity 0.86)
- Generative Graph Pattern Machine (NeurIPS 2025 · similarity 0.86)
- Deep Multi-modal Graph Clustering via Graph Transformer Network (AAAI 2025 · similarity 0.86)
- Graph Geometry-Preserving Autoencoders (ICML 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.