论文标题
用图形神经网络以外的分子学习
Learning with Molecules beyond Graph Neural Networks
论文作者
论文摘要
我们演示了一个深度学习框架，该框架固有地基于关系逻辑的高度表达性语言，从而捕获了任意复杂的图形结构。我们通过指定关系逻辑中的基本传播规则来展示如何在框架中轻松介绍图形神经网络和类似模型。然后，使用的语言的声明性质允许轻松地修改并将传播方案扩展到复杂的结构中，例如我们在本文中为简短演示选择的分子环。
We demonstrate a deep learning framework which is inherently based in the highly expressive language of relational logic, enabling to, among other things, capture arbitrarily complex graph structures. We show how Graph Neural Networks and similar models can be easily covered in the framework by specifying the underlying propagation rules in the relational logic. The declarative nature of the used language then allows to easily modify and extend the propagation schemes into complex structures, such as the molecular rings which we choose for a short demonstration in this paper.
