Log In Sign Up

Going Deeper into Permutation-Sensitive Graph Neural Networks

by   Zhongyu Huang, et al.

The invariance to permutations of the adjacency matrix, i.e., graph isomorphism, is an overarching requirement for Graph Neural Networks (GNNs). Conventionally, this prerequisite can be satisfied by the invariant operations over node permutations when aggregating messages. However, such an invariant manner may ignore the relationships among neighboring nodes, thereby hindering the expressivity of GNNs. In this work, we devise an efficient permutation-sensitive aggregation mechanism via permutation groups, capturing pairwise correlations between neighboring nodes. We prove that our approach is strictly more powerful than the 2-dimensional Weisfeiler-Lehman (2-WL) graph isomorphism test and not less powerful than the 3-WL test. Moreover, we prove that our approach achieves the linear sampling complexity. Comprehensive experiments on multiple synthetic and real-world datasets demonstrate the superiority of our model.


page 1

page 2

page 3

page 4


On the Universality of Graph Neural Networks on Large Random Graphs

We study the approximation power of Graph Neural Networks (GNNs) on late...

Curvature Graph Neural Network

Graph neural networks (GNNs) have achieved great success in many graph-b...

Towards Deeper Graph Neural Networks with Differentiable Group Normalization

Graph neural networks (GNNs), which learn the representation of a node b...

Scaling Up Graph Neural Networks Via Graph Coarsening

Scalability of graph neural networks remains one of the major challenges...

LSP : Acceleration and Regularization of Graph Neural Networks via Locality Sensitive Pruning of Graphs

Graph Neural Networks (GNNs) have emerged as highly successful tools for...

Graph Neural Network Bandits

We consider the bandit optimization problem with the reward function def...

Discriminative structural graph classification

This paper focuses on the discrimination capacity of aggregation functio...

Code Repositories


Official implementation of the ICML 2022 paper "Going Deeper into Permutation-Sensitive Graph Neural Networks"

view repo