RGCVAE：用于分子设计的关系图条件化变分自编码器
RGCVAE: Relational Graph Conditioned Variational Autoencoder for Molecule Design
AI总结：
本文提出 RGCVAE，通过关系图同构编码器和新型概率解码器提升分子生成效果，在两个常用数据集上达到最先进性能并显著加快训练。
摘要：
识别表现出某些预先指定性质的分子是一个难以解决的问题。在过去几年中，深度生成模型已被用于分子生成。深度图变分自编码器属于最强大的机器学习工具之一，可用于解决这一问题。然而，现有方法在捕捉真实数据分布方面存在困难，并且往往计算成本高昂。在本工作中，我们提出 RGCVAE，这是一种高效且有效的图变分自编码器，其基础包括：（i）利用一种新型强大的关系图同构网络的编码网络；（ii）一个新颖的概率解码组件。在两个被广泛采用的数据集上与若干最先进的 VAE 方法相比，RGCVAE 展现出最先进的分子生成性能，同时训练速度显著更快。
英文摘要：
Identifying molecules that exhibit some pre-specified properties is a difficult problem to solve. In the last few years, deep generative models have been used for molecule generation. Deep Graph Variational Autoencoders are among the most powerful machine learning tools with which it is possible to address this problem. However, existing methods struggle in capturing the true data distribution and tend to be computationally expensive. In this work, we propose RGCVAE, an efficient and effective Graph Variational Autoencoder based on: (i) an encoding network exploiting a new powerful Relational Graph Isomorphism Network; (ii) a novel probabilistic decoding component. Compared to several state-of-the-art VAE methods on two widely adopted datasets, RGCVAE shows state-of-the-art molecule generation performance while being significantly faster to train.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
