Research map / Graph learning / Graph algorithms and clustering
D-VAE: A Variational Autoencoder for Directed Acyclic Graphs
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 asynchronous message passing that follows DAG dependencies to encode computations | D-VAE · Neural architectures | RMSE: 0.478$\pm$0.002 -> 0.384$\pm$0.002 | Helped |
| Use asynchronous message passing that follows DAG dependencies to encode computations | D-VAE · Bayesian networks | RMSE: 0.369$\pm$0.003 -> 0.300$\pm$0.004 | Helped |
| Use D-VAE latent space instead of S-VAE for Bayesian optimization | Neural architecture search on CIFAR-10 · CIFAR-10 | Test accuracy: 92.79\% -> 94.80\% | Helped |
| Search with D-VAE latent space rather than the training set | Bayesian network structure learning · Asia dataset | BIC: -11141.89 -> -11125.75 | Helped |
| Add global layer IDs to the aggregation function to preserve concatenation order (ablation) | D-VAE neural architecture encoder · Neural architectures | performance | Helped |
| Add reverse-direction encoding and concatenate forward and reverse states (ablation) | D-VAE neural architecture encoder · Neural architectures | performance | Helped |
| Use reverse-direction encoding (ablation) | D-VAE neural architecture encoder · Neural architectures | convergence speed | Helped |
Closest papers by meaning
- DAG-GNN: DAG Structure Learning with Graph Neural Networks (ICML 2019 · similarity 0.91)
- Dirichlet Graph Variational Autoencoder (NeurIPS 2020 · similarity 0.91)
- Semi-Implicit Graph Variational Auto-Encoders (NeurIPS 2019 · similarity 0.90)
- Directed Graph Grammars for Sequence-based Learning (ICML 2025 · similarity 0.88)
- ProDAG: Projected Variational Inference for Directed Acyclic Graphs (NeurIPS 2025 · similarity 0.86)
- DAG-Aware Variational Autoencoder for Social Propagation Graph Generation (AAAI 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.