Building LEGO Using Deep Generative Models of Graphs
arXiv:2012.11543
Abstract
Generative models are now used to create a variety of high-quality digital artifacts. Yet their use in designing physical objects has received far less attention. In this paper, we advocate for the construction toy, LEGO, as a platform for developing generative models of sequential assembly. We develop a generative model based on graph-structured neural networks that can learn from human-built structures and produce visually compelling designs. Our code is released at: https://github.com/uoguelph-mlrg/GenerativeLEGO.
NeurIPS 2020 ML4eng workshop paper
References in corpus (11)
- Language Models are Few-Shot Learners
- Junction Tree Variational Autoencoder for Molecular Graph Generation
- Kronecker Graphs: An Approach to Modeling Networks
- MolGAN: An implicit generative model for small molecular graphs
- Learning Deep Generative Models of Graphs
- A note on the evaluation of generative models
- Improved Precision and Recall Metric for Assessing Generative Models
- Syntax-Directed Variational Autoencoder for Structured Data
- Reliable Fidelity and Diversity Metrics for Generative Models
- Combinatorial 3D Shape Generation via Sequential Assembly
- A neural network approach to ordinal regression