Graph Deconvolutional Generation
Not on the map. Why?
Abstract (arXiv)
Graph generation is an extremely important task, as graphs are found throughout different areas of science and engineering. In this work, we focus on the modern equivalent of the Erdos-Renyi random graph model: the graph variational autoencoder (GVAE). This model assumes edges and nodes are independent in order to generate entire graphs at a time using a multi-layer perceptron decoder. As a result of these assumptions, GVAE has difficulty matching the training distribution and relies on an expensive graph matching procedure. We improve this class of models by building a message passing neural network into GVAE's encoder and decoder. We demonstrate our model on the specific task of generating small organic molecules
Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Feb 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 4; 2022: 4; 2023: 4; 2024: 2; 2025: 2.
16 papers.
Sort:
- 2022A Survey on Deep Graph Generation: Methods and Applicationscited by 69
- 2021Keeping it Simple: Language Models can learn Complex Molecular Distributionscited by 68
- 2022Molecule Generation for Drug Design: a Graph Learning Perspectivecited by 13
- 2023Node-Aligned Graph-to-Graph (NAG2G): Elevating Template-Free Deep Learning Approaches in Single-Step Retrosynthesiscited by 9
- 2021Brain Multigraph Prediction using Topology-Aware Adversarial Graph Neural Networkcited by 7
- 2023MAGNet: Motif-Agnostic Generation of Molecules from Shapescited by 7
- 2023The power of motifs as inductive bias for learning molecular distributionscited by 6
- 2022Evaluating Graph Generative Models with Contrastively Learned Featurescited by 5
- 2023MHG-GNN: Combination of Molecular Hypergraph Grammar with Graph Neural Networkcited by 4
- 2024Overcoming Order in Autoregressive Graph Generationcited by 3
- 2021Operator Autoencoders: Learning Physical Operations on Encoded Molecular Graphscited by 1
- 2021Permutation Equivariant Generative Adversarial Networks for Graphscited by 0
4 more
- 2022Gransformer: Transformer-based Graph Generationcited by 0
- 2024Heterogeneous Graph Generation: A Hierarchical Approach using Node Feature Poolingcited by 0
- 2025Auto-encoding Molecules: Graph-Matching Capabilities Mattercited by 0
- 2025GIN-Graph: A Generative Interpretation Network for Model-Level Explanation of Graph Neural Networkscited by 0
- 2025GIN-Graph: A Generative Interpretation Network for Model-Level Explanation of Graph Neural Networks8 Mar 2025
- 2025Auto-encoding Molecules: Graph-Matching Capabilities Matter1 Mar 2025
- 2024Heterogeneous Graph Generation: A Hierarchical Approach using Node Feature Pooling15 Oct 2024
- 2024Overcoming Order in Autoregressive Graph Generation4 Feb 2024
- 2023MHG-GNN: Combination of Molecular Hypergraph Grammar with Graph Neural Network28 Sep 2023
- 2023Node-Aligned Graph-to-Graph (NAG2G): Elevating Template-Free Deep Learning Approaches in Single-Step Retrosynthesis27 Sep 2023
- 2023MAGNet: Motif-Agnostic Generation of Molecules from Shapes30 May 2023
- 2023The power of motifs as inductive bias for learning molecular distributions4 Apr 2023
- 2022Evaluating Graph Generative Models with Contrastively Learned Features13 Jun 2022
- 2022Gransformer: Transformer-based Graph Generation25 Mar 2022
- 2022A Survey on Deep Graph Generation: Methods and Applications13 Mar 2022
- 2022Molecule Generation for Drug Design: a Graph Learning Perspective18 Feb 2022
4 more
- 2021Permutation Equivariant Generative Adversarial Networks for Graphs7 Dec 2021
- 2021Keeping it Simple: Language Models can learn Complex Molecular Distributions6 Dec 2021
- 2021Operator Autoencoders: Learning Physical Operations on Encoded Molecular Graphs26 May 2021
- 2021Brain Multigraph Prediction using Topology-Aware Adversarial Graph Neural Network6 May 2021
- 2022A Survey on Deep Graph Generation: Methods and Applicationscited by 69
- 2021Keeping it Simple: Language Models can learn Complex Molecular Distributionscited by 68
- 2022Molecule Generation for Drug Design: a Graph Learning Perspectivecited by 13
- 2023Node-Aligned Graph-to-Graph (NAG2G): Elevating Template-Free Deep Learning Approaches in Single-Step Retrosynthesiscited by 9
- 2021Brain Multigraph Prediction using Topology-Aware Adversarial Graph Neural Networkcited by 7
- 2023MAGNet: Motif-Agnostic Generation of Molecules from Shapescited by 7
- 2023The power of motifs as inductive bias for learning molecular distributionscited by 6
- 2022Evaluating Graph Generative Models with Contrastively Learned Featurescited by 5
- 2023MHG-GNN: Combination of Molecular Hypergraph Grammar with Graph Neural Networkcited by 4
- 2024Overcoming Order in Autoregressive Graph Generationcited by 3
- 2021Operator Autoencoders: Learning Physical Operations on Encoded Molecular Graphscited by 1
- 2021Permutation Equivariant Generative Adversarial Networks for Graphscited by 0
12 most cited of 16 All 16 (JSON)
- 2025GIN-Graph: A Generative Interpretation Network for Model-Level Explanation of Graph Neural Networks8 Mar 2025
- 2025Auto-encoding Molecules: Graph-Matching Capabilities Matter1 Mar 2025
- 2024Heterogeneous Graph Generation: A Hierarchical Approach using Node Feature Pooling15 Oct 2024
- 2024Overcoming Order in Autoregressive Graph Generation4 Feb 2024
- 2023MHG-GNN: Combination of Molecular Hypergraph Grammar with Graph Neural Network28 Sep 2023
- 2023Node-Aligned Graph-to-Graph (NAG2G): Elevating Template-Free Deep Learning Approaches in Single-Step Retrosynthesis27 Sep 2023
- 2023MAGNet: Motif-Agnostic Generation of Molecules from Shapes30 May 2023
- 2023The power of motifs as inductive bias for learning molecular distributions4 Apr 2023
- 2022Evaluating Graph Generative Models with Contrastively Learned Features13 Jun 2022
- 2022Gransformer: Transformer-based Graph Generation25 Mar 2022
- 2022A Survey on Deep Graph Generation: Methods and Applications13 Mar 2022
- 2022Molecule Generation for Drug Design: a Graph Learning Perspective18 Feb 2022
12 newest of 16 All 16 (JSON)