DeepAI AI Chat
Log In Sign Up

A Novel Higher-order Weisfeiler-Lehman Graph Convolution

by   Clemens Damke, et al.

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.


page 1

page 2

page 3

page 4


Graph Neural Networks with Parallel Neighborhood Aggregations for Graph Classification

We focus on graph classification using a graph neural network (GNN) mode...

KerGNNs: Interpretable Graph Neural Networks with Graph Kernels

Graph kernels are historically the most widely-used technique for graph ...

Graph Symbiosis Learning

We introduce a framework for learning from multiple generated graph view...

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

In this paper, we study a novel meta aggregation scheme towards binarizi...

Joint Adaptive Feature Smoothing and Topology Extraction via Generalized PageRank GNNs

In many important applications, the acquired graph-structured data inclu...

Subgroup Fairness in Graph-based Spam Detection

Fake reviews are prevalent on review websites such as Amazon and Yelp. G...

Algorithmic Concept-based Explainable Reasoning

Recent research on graph neural network (GNN) models successfully applie...