A Novel Higher-order Weisfeiler-Lehman Graph Convolution

07/01/2020
by   Clemens Damke, et al.
0

Current GNN architectures use a vertex neighborhood aggregation scheme, which limits their discriminative power to that of the 1-dimensional Weisfeiler-Lehman (WL) graph isomorphism test. Here, we propose a novel graph convolution operator that is based on the 2-dimensional WL test. We formally show that the resulting 2-WL-GNN architecture is more discriminative than existing GNN approaches. This theoretical result is complemented by experimental studies using synthetic and real data. On multiple common graph classification benchmarks, we demonstrate that the proposed model is competitive with state-of-the-art graph kernels and GNNs.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

11/22/2021

Graph Neural Networks with Parallel Neighborhood Aggregations for Graph Classification

We focus on graph classification using a graph neural network (GNN) mode...
01/03/2022

KerGNNs: Interpretable Graph Neural Networks with Graph Kernels

Graph kernels are historically the most widely-used technique for graph ...
06/10/2021

Graph Symbiosis Learning

We introduce a framework for learning from multiple generated graph view...
09/27/2021

Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks

In this paper, we study a novel meta aggregation scheme towards binarizi...
06/14/2020

Joint Adaptive Feature Smoothing and Topology Extraction via Generalized PageRank GNNs

In many important applications, the acquired graph-structured data inclu...
07/15/2021

Algorithmic Concept-based Explainable Reasoning

Recent research on graph neural network (GNN) models successfully applie...
04/24/2022

Subgroup Fairness in Graph-based Spam Detection

Fake reviews are prevalent on review websites such as Amazon and Yelp. G...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.