mlsanityData to 7 Oct 2026

D-VAE: A Variational Autoencoder for Directed Acyclic Graphs

arXiv 1904.11088 ↗First posted 24 Apr 2019cs.LG stat.MLcited by 98

Not on the map. Why?

Abstract (arXiv)

Graph structured data are abundant in the real world. Among different graph types, directed acyclic graphs (DAGs) are of particular interest to machine learning researchers, as many machine learning models are realized as computations on DAGs, including neural networks and Bayesian networks. In this paper, we study deep generative models for DAGs, and propose a novel DAG variational autoencoder (D-VAE). To encode DAGs into the latent space, we leverage graph neural networks. We propose an asynchronous message passing scheme that allows encoding the computations on DAGs, rather than using existing simultaneous message passing schemes to encode local graph structures. We demonstrate the effectiveness of our proposed DVAE through two tasks: neural architecture search and Bayesian network structure learning. Experiments show that our model not only generates novel and valid DAGs, but also produces a smooth latent space that facilitates searching for DAGs with better performance through Bayesian optimization.

Key facts. Cited by 98 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 15; 2023: 15; 2024: 25; 2025: 18; 2026: 11.

98 papers.

Sort:

By area:

  1. 2023Neural Architecture Search: Insights from 1000 Paperscited by 136
  2. 2021DiBS: Differentiable Bayesian Structure Learningcited by 105
  3. 2021Directed Acyclic Graph Network for Conversational Emotion Recognitioncited by 97
  4. 2022MVP: Multimodality-guided Visual Pre-trainingcited by 92
  5. 2022Local Latent Space Bayesian Optimization over Structured Inputscited by 78
  6. 2021Directed Acyclic Graph Neural Networkscited by 70
  7. 2022A Survey on Deep Graph Generation: Methods and Applicationscited by 69
  8. 2023CktGNN: Circuit Graph Neural Network for Electronic Design Automationcited by 55
  9. 2023Graph Metanetworks for Processing Diverse Neural Architecturescited by 55
  10. 2022Causal Structure Learning: a Combinatorial Perspectivecited by 46
  11. 2021DeepGate: Learning Neural Representations of Logic Gatescited by 37
  12. 2021Rapid Neural Architecture Search by Learning to Generate Graphs from Datasetscited by 33
38 more
  1. 2022Transformers over Directed Acyclic Graphscited by 23
  2. 2024Scale Equivariant Graph Metanetworkscited by 23
  3. 2021CATE: Computation-aware Neural Architecture Encoding with Transformerscited by 21
  4. 2024ArtFormer: Controllable Generation of Diverse 3D Articulated Objectscited by 21
  5. 2022PACE: A Parallelizable Computation Encoder for Directed Acyclic Graphscited by 20
  6. 2024Beyond Euclid: An Illustrated Guide to Modern Machine Learning with Geometric, Topological, and Algebraic Structurescited by 20
  7. 2021VACA: Design of Variational Graph Autoencoders for Interventional and Counterfactual Queriescited by 18
  8. 2024Generative Modelling of Structurally Constrained Graphscited by 17
  9. 2022Learning Where To Look -- Generative NAS is Surprisingly Efficientcited by 15
  10. 2023DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Modelscited by 15
  11. 2024Multi-conditioned Graph Diffusion for Neural Architecture Searchcited by 13
  12. 2022Neural Topological Ordering for Computation Graphscited by 12
  13. 2024Efficient Data Subset Selection to Generalize Training Across Models: Transductive and Inductive Networkscited by 12
  14. 2022DeepTPI: Test Point Insertion with Deep Reinforcement Learningcited by 10
  15. 2025AUTOCIRCUIT-RL: Reinforcement Learning-Driven LLM for Automated Circuit Topology Generationcited by 10
  16. 2023Causality-based CTR Prediction using Graph Neural Networkscited by 9
  17. 2023PG-LBO: Enhancing High-Dimensional Bayesian Optimization with Pseudo-Label and Gaussian Process Guidancecited by 9
  18. 2021Task-Adaptive Neural Network Search with Meta-Contrastive Learningcited by 8
  19. 2023Molecule Design by Latent Prompt Transformercited by 8
  20. 2024LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph Generationcited by 8
  21. 2025The quest for the GRAph Level autoEncoder (GRALE)cited by 8
  22. 2021Towards Efficient Local Causal Structure Learningcited by 7
  23. 2021Materials Representation and Transfer Learning for Multi-Property Predictioncited by 7
  24. 2022Methods for Recovering Conditional Independence Graphs: A Surveycited by 7
  25. 2023DeepSeq: Deep Sequential Circuit Learningcited by 7
  26. 2024What Are Good Positional Encodings for Directed Graphs?cited by 7
  27. 2022Graph Neural Networks Intersect Probabilistic Graphical Models: A Surveycited by 6
  28. 2023An algorithmic framework for the optimization of deep neural networks architectures and hyperparameterscited by 6
  29. 2024Convolutional Learning on Directed Acyclic Graphscited by 6
  30. 2024Preventing Representational Rank Collapse in MPNNs by Splitting the Computational Graphcited by 6
  31. 2021Graph-based Neural Architecture Search with Operation Embeddingscited by 5
  32. 2022CODEBench: A Neural Architecture and Hardware Accelerator Co-Design Frameworkcited by 5
  33. 2024Automated Multi-Task Learning for Joint Disease Prediction on Electronic Health Recordscited by 5
  34. 2024DeepSeq2: Enhanced Sequential Circuit Learning with Disentangled Representationscited by 5
  35. 2025Unveiling Discrete Clues: Superior Healthcare Predictions for Rare Diseasescited by 5
  36. 2024Quantum Architecture Search with Unsupervised Representation Learningcited by 4
  37. 2024Signed Graph Autoencoder for Explainable and Polarization-Aware Network Embeddingscited by 4
  38. 2025The Robustness of Differentiable Causal Discovery in Misspecified Scenarioscited by 4

50 most cited of 98 All 98 (JSON)