# DEFactor: Differentiable Edge Factorization-based Probabilistic Graph Generation

arXiv: https://arxiv.org/abs/1811.09766 · HTML: https://mlsanity.com/paper/1811.09766/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2018.

## Built on by (most cited first, 24 of 24)

- [Equivariant Energy-Guided SDE for Inverse Molecular Design](https://mlsanity.com/paper/2209.15408/) (2022)
- [Learning to Extend Molecular Scaffolds with Structural Motifs](https://mlsanity.com/paper/2103.03864/) (2021)
- [A Survey on Deep Graph Generation: Methods and Applications](https://mlsanity.com/paper/2203.06714/) (2022)
- [MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Design](https://mlsanity.com/paper/2203.14500/) (2022)
- [Conditional Diffusion Based on Discrete Graph Structures for Molecular Graph Generation](https://mlsanity.com/paper/2301.00427/) (2023)
- [JANUS: Parallel Tempered Genetic Algorithm Guided by Deep Neural Networks for Inverse Molecular Design](https://mlsanity.com/paper/2106.04011/) (2021)
- [Learning Joint 2D & 3D Diffusion Models for Complete Molecule Generation](https://mlsanity.com/paper/2305.12347/) (2023)
- [MAGNet: Motif-Agnostic Generation of Molecules from Shapes](https://mlsanity.com/paper/2305.19303/) (2023)
- [Fragment-based Sequential Translation for Molecular Optimization](https://mlsanity.com/paper/2111.01009/) (2021)
- [The power of motifs as inductive bias for learning molecular distributions](https://mlsanity.com/paper/2306.17246/) (2023)
- [Text-guided Diffusion Model for 3D Molecule Generation](https://mlsanity.com/paper/2410.03803/) (2024)
- [CCGG: A Deep Autoregressive Model for Class-Conditional Graph Generation](https://mlsanity.com/paper/2110.03800/) (2021)
- [Overcoming Order in Autoregressive Graph Generation](https://mlsanity.com/paper/2402.03387/) (2024)
- [Recent Developments in GNNs for Drug Discovery](https://mlsanity.com/paper/2506.01302/) (2025)
- [Geometric learning of the conformational dynamics of molecules using dynamic graph neural networks](https://mlsanity.com/paper/2106.13277/) (2021)
- [Operator Autoencoders: Learning Physical Operations on Encoded Molecular Graphs](https://mlsanity.com/paper/2105.12295/) (2021)
- [GraphTune: A Learning-based Graph Generative Model with Tunable Structural Features](https://mlsanity.com/paper/2201.11494/) (2022)
- [Genetic Algorithm for Constrained Molecular Inverse Design](https://mlsanity.com/paper/2112.03518/) (2021)
- [Gransformer: Transformer-based Graph Generation](https://mlsanity.com/paper/2203.13655/) (2022)
- [Bayesian Sequential Stacking Algorithm for Concurrently Designing Molecules and Synthetic Reaction Networks](https://mlsanity.com/paper/2204.01847/) (2022)
- [Unsupervised Learning of Graph from Recipes](https://mlsanity.com/paper/2401.12088/) (2024)
- [Heterogeneous Graph Generation: A Hierarchical Approach using Node Feature Pooling](https://mlsanity.com/paper/2410.11972/) (2024)
- [Generative Model for Synthesizing Ionizable Lipids: A Monte Carlo Tree Search Approach](https://mlsanity.com/paper/2412.00807/) (2024)
- [JTreeformer: Graph-Transformer via Latent-Diffusion Model for Molecular Generation](https://mlsanity.com/paper/2504.20770/) (2025)

## Abstract (arXiv)

Generating novel molecules with optimal properties is a crucial step in many industries such as drug discovery. Recently, deep generative models have shown a promising way of performing de-novo molecular design. Although graph generative models are currently available they either have a graph size dependency in their number of parameters, limiting their use to only very small graphs or are formulated as a sequence of discrete actions needed to construct a graph, making the output graph non-differentiable w.r.t the model parameters, therefore preventing them to be used in scenarios such as conditional graph generation. In this work we propose a model for conditional graph generation that is computationally efficient and enables direct optimisation of the graph. We demonstrate favourable performance of our model on prototype-based molecular graph conditional generation tasks.