A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is
While (message-passing) graph neural networks have clear limitations in approximating permutation-equivariant functions over graphs or general relational data, more expressive, higher-order graph neural ... By introducing new heuristics for the graph isomorphism problem, we devise a class of universal, permutation-equivariant graph networks, which, unlike previous architectures, offer a fine-grained control ... In Section 4, we will leverage these results to devise universal, permutation-equivariant graph networks. We start off with the following simple observation. ...arXiv:2203.13913v1 fatcat:m3mq4rppfjbhdarrieo6czrt7i