论文标题
物理受限的预测分子潜在空间发现，图形散射变异自动编码器
Physics-Constrained Predictive Molecular Latent Space Discovery with Graph Scattering Variational Autoencoder
论文作者
论文摘要
人工智能的最新进展推动了创新的计算材料建模和设计技术的发展。生成深度学习模型已用于分子表示，发现和设计。在这项工作中，我们评估了基于小数据制度中的变异推理和图理论开发的分子生成模型的预测能力。提出了鼓励能量稳定分子的物理约束。编码网络基于具有自适应光谱过滤器的散射变换，以便对模型进行更好的概括。解码网络是一个单发图生成模型，该模型在分子拓扑结构的原子类型。贝叶斯形式主义被认为是在分子特性的预测估计中捕获不确定性的。通过生成具有所需目标特性的分子来评估模型的性能。
Recent advances in artificial intelligence have propelled the development of innovative computational materials modeling and design techniques. Generative deep learning models have been used for molecular representation, discovery, and design. In this work, we assess the predictive capabilities of a molecular generative model developed based on variational inference and graph theory in the small data regime. Physical constraints that encourage energetically stable molecules are proposed. The encoding network is based on the scattering transform with adaptive spectral filters to allow for better generalization of the model. The decoding network is a one-shot graph generative model that conditions atom types on molecular topology. A Bayesian formalism is considered to capture uncertainties in the predictive estimates of molecular properties. The model's performance is evaluated by generating molecules with desired target properties.
