TL;DR本文通过系统性实验评估关注网络的层数与性能之间的关系,发现残差连接可以解决 Oversquashing 现象,提高 GAT 模型的性能。因此,我们提出了 ADGAT 变体模型,可根据图的稀疏性自适应选择层数,从而显着提高了模型的性能。
Abstract
As one of the most popular GNN architectures, the graph attention networks
(gat) is considered the most advanced learning architecture for graph
representation and has been widely used in various graph mining tas