1 Hit in 1.2 sec

SpeqNets: Sparsity-aware Permutation-equivariant Graph Networks [article]

Christopher Morris, Gaurav Rattan, Sandra Kiefer, Siamak Ravanbakhsh
2022 arXiv   pre-print
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