论文标题
图形神经网络以学习不相交分子图的联合表示
Graph neural networks to learn joint representations of disjoint molecular graphs
论文作者
论文摘要
图形神经网络被广泛用于学习图的全局表示，然后将其用于回归或分类任务。通常，连接此类数据集中的图形，即每个训练样本由与全局标签关联的单个内部连接图组成。但是，有各种各样的尚未考虑的但相关的任务，其中标签被分配给了一组不相交图，这需要生成脱节图的全局表示形式。在本文中，我们提出了一个带有化学反应的新数据集，这说明了这项任务。每个样品都由一对分子图和一个与分子化学反应相关的标量度量的关节标签组成。我们显示了能够在数据集的组合子集中求解任务的图形神经网络的初始结果，但并不能很好地概括到完整的数据集和看不见的（sub）图。
Graph neural networks are widely used to learn global representations of graphs, which are then used for regression or classification tasks. Typically, the graphs in such data sets are connected, i.e. each training sample consists of a single internally connected graph associated with a global label. However, there is a wide variety of yet unconsidered but application-relevant tasks, where labels are assigned to sets of disjoint graphs, which requires the generation of global representations of disjoint graphs. In this paper, we present a new data set with chemical reactions, which is illustrating this task. Each sample consists of a pair of disjoint molecular graphs and a joint label representing a scalar measure associated with the chemical reaction of the molecules. We show the initial results of graph neural networks that are able to solve the task within a combinatorial subset of the dataset but do not generalize well to the full data set and unseen (sub)graphs.
