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–Rnyi random graph model: the graph variational autoencoder (GVAE) (Simonovsky and Komodakis 2018 Int. Conf. on Artificial Neural Networks pp 412–22). 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.

图生成是一项极其重要的任务，因为在科学和工程的不同领域都可以找到图。在这项工作中，我们专注于 Erdos-Rnyi 随机图模型的现代等价物：图变分自编码器 (GVAE)（Simonovsky 和 ​​Komodakis 2018 Int. Conf. on人工神经网络第 412-22 页）。该模型假设边和节点是独立的，以便使用多层感知器解码器一次生成整个图。由于这些假设，GVAE 难以匹配训练分布并依赖于昂贵的图匹配程序。我们通过在 GVAE 的编码器和解码器中构建消息传递神经网络来改进此类模型。我们在生成有机小分子的特定任务上展示了我们的模型。