Autobahn：基于自同构的图神经网络
Autobahn: Automorphism-based Graph Neural Nets
摘要：
我们介绍了基于自同构的图神经网络（Autobahn），一个新的家庭的图神经网络。在一个高速公路，我们分解成一个子图的集合图，并应用局部卷积是等变的每个子图的自同构群。局部邻域和子图的特定选择恢复了现有的架构，例如消息传递神经网络。我们的形式主义还包括新颖的架构：作为一个例子，我们引入了一个图神经网络，它将图分解为路径和循环。由此产生的卷积反映了部分图可以变换的自然方式，保留了卷积的直观含义，而不会牺牲全局置换等方差。我们验证了我们的方法，应用Autobahn分子图，在那里它实现了竞争的结果与国家的最先进的消息传递算法。
英文摘要：
We introduce Automorphism-based graph neural networks (Autobahn), a new family of graph neural networks. In an Autobahn, we decompose the graph into a collection of subgraphs and apply local convolutions that are equivariant to each subgraph's automorphism group. Specific choices of local neighborhoods and subgraphs recover existing architectures such as message passing neural networks. Our formalism also encompasses novel architectures: as an example, we introduce a graph neural network that decomposes the graph into paths and cycles. The resulting convolutions reflect the natural way that parts of the graph can transform, preserving the intuitive meaning of convolution without sacrificing global permutation equivariance. We validate our approach by applying Autobahn to molecular graphs, where it achieves results competitive with state-of-the-art message passing algorithms.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
