Empowering GNNs via Edge-Aware Weisfeiler-Leman Algorithm

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Meng, Yu, Haiyang, Ji, Shuiwang
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910305040203776
author Liu, Meng
Yu, Haiyang
Ji, Shuiwang
author_facet Liu, Meng
Yu, Haiyang
Ji, Shuiwang
contents Message passing graph neural networks (GNNs) are known to have their expressiveness upper-bounded by 1-dimensional Weisfeiler-Leman (1-WL) algorithm. To achieve more powerful GNNs, existing attempts either require ad hoc features, or involve operations that incur high time and space complexities. In this work, we propose a general and provably powerful GNN framework that preserves the scalability of the message passing scheme. In particular, we first propose to empower 1-WL for graph isomorphism test by considering edges among neighbors, giving rise to NC-1-WL. The expressiveness of NC-1-WL is shown to be strictly above 1-WL and below 3-WL theoretically. Further, we propose the NC-GNN framework as a differentiable neural version of NC-1-WL. Our simple implementation of NC-GNN is provably as powerful as NC-1-WL. Experiments demonstrate that our NC-GNN performs effectively and efficiently on various benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2206_02059
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Empowering GNNs via Edge-Aware Weisfeiler-Leman Algorithm
Liu, Meng
Yu, Haiyang
Ji, Shuiwang
Machine Learning
Artificial Intelligence
Message passing graph neural networks (GNNs) are known to have their expressiveness upper-bounded by 1-dimensional Weisfeiler-Leman (1-WL) algorithm. To achieve more powerful GNNs, existing attempts either require ad hoc features, or involve operations that incur high time and space complexities. In this work, we propose a general and provably powerful GNN framework that preserves the scalability of the message passing scheme. In particular, we first propose to empower 1-WL for graph isomorphism test by considering edges among neighbors, giving rise to NC-1-WL. The expressiveness of NC-1-WL is shown to be strictly above 1-WL and below 3-WL theoretically. Further, we propose the NC-GNN framework as a differentiable neural version of NC-1-WL. Our simple implementation of NC-GNN is provably as powerful as NC-1-WL. Experiments demonstrate that our NC-GNN performs effectively and efficiently on various benchmarks.
title Empowering GNNs via Edge-Aware Weisfeiler-Leman Algorithm
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2206.02059