论文标题
Weisfeiler-Lehman嵌入分子图神经网络
Weisfeiler-Lehman Embedding for Molecular Graph Neural Networks
论文作者
论文摘要
图神经网络（GNN）是预测分子化学特性的好选择。但是，与其他深层网络相比，由于“深度诅咒”，GNN的当前性能受到限制。受到化学领域的长期特征工程的启发，我们使用weisfeiler-lehman（WL）嵌入扩展了原子表示，该嵌入旨在捕获主导分子化学特性的局部原子模式。在表示性方面，我们显示WL嵌入可以替换具有较小重量标准的Relu GNN的前两层 - 正常的嵌入和隐藏的GNN层。然后，我们证明WL嵌入始终如一地改善了多个GNN架构和几个分子图数据集的经验性能。
A graph neural network (GNN) is a good choice for predicting the chemical properties of molecules. Compared with other deep networks, however, the current performance of a GNN is limited owing to the "curse of depth." Inspired by long-established feature engineering in the field of chemistry, we expanded an atom representation using Weisfeiler-Lehman (WL) embedding, which is designed to capture local atomic patterns dominating the chemical properties of a molecule. In terms of representability, we show WL embedding can replace the first two layers of ReLU GNN -- a normal embedding and a hidden GNN layer -- with a smaller weight norm. We then demonstrate that WL embedding consistently improves the empirical performance over multiple GNN architectures and several molecular graph datasets.
