Graph Generation with K2-trees
Not on the map. Why?
Abstract (arXiv)
Generating graphs from a target distribution is a significant challenge across many domains, including drug discovery and social network analysis. In this work, we introduce a novel graph generation method leveraging K2-tree representation, originally designed for lossless graph compression. The K2-tree representation encompasses inherent hierarchy while enabling compact graph generation. In addition, we make contributions by (1) presenting a sequential K2-treerepresentation that incorporates pruning, flattening, and tokenization processes and (2) introducing a Transformer-based architecture designed to generate the sequence by incorporating a specialized tree positional encoding scheme. Finally, we extensively evaluate our algorithm on four general and two molecular graph datasets to confirm its superiority for graph generation.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 29 of its 50 references that are in the map. First posted on arXiv 30 May 2023.
Builds on
29 of 50 references.
References · 29
- 2017Attention Is All You Needcited by 60,361
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2018Self-Attention with Relative Position Representationscited by 1,120
- 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 787
- 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 652
- 2022DiGress: Discrete Denoising diffusion for graph generationcited by 520
- 2018GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Modelscited by 413
- 2018GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoderscited by 383
- 2020GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generationcited by 305
- 2022Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equationscited by 283
- 2020Permutation Invariant Graph Generation via Score-Based Generative Modelingcited by 270
- 2019Efficient Graph Generation with Graph Recurrent Attention Networkscited by 234
17 more
- 2018Learning Deep Generative Models of Graphscited by 229
- 2020Hierarchical Generation of Molecular Graphs using Structural Motifscited by 208
- 2020MoFlow: An Invertible Flow Model for Generating Molecular Graphscited by 185
- 2021GraphDF: A Discrete Flow Model for Molecular Graph Generationcited by 180
- 2019GraphNVP: An Invertible Flow Model for Generating Molecular Graphscited by 116
- 2018Graphite: Iterative Generative Modeling of Graphscited by 112
- 2019Graph Normalizing Flowscited by 104
- 2022SPECTRE: Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generatorscited by 99
- 2021GraphEBM: Molecular Graph Generation with Energy-Based Modelscited by 85
- 2023Efficient and Degree-Guided Graph Generation via Discrete Diffusion Modelingcited by 80
- 2021Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generationcited by 68
- 2019Mol-CycleGAN - a generative model for molecular optimizationcited by 66
- 2020GraphGen: A Scalable Approach to Domain-agnostic Labeled Graph Generationcited by 66
- 2019Self-Referencing Embedded Strings (SELFIES): A 100% robust molecular string representationcited by 23
- 2023Improving Graph Generation by Restricting Graph Bandwidthcited by 16
- 2018Survey and Taxonomy of Lossless Graph Compression and Space-Efficient Graph Representationscited by 12
- 2021Partition and Code: learning how to compress graphscited by 10
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 0; 2026: 2.
3 papers.