Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks

10/04/2018
by   Christopher Morris, et al.
0

In recent years, graph neural networks (GNNs) have emerged as a powerful neural architecture to learn vector representations of nodes and graphs in a supervised, end-to-end fashion. Up to now, GNNs have only been evaluated empirically---showing promising results. The following work investigates GNNs from a theoretical point of view and relates them to the 1-dimensional Weisfeiler-Leman graph isomorphism heuristic (1-WL). We show that GNNs have the same expressiveness as the 1-WL in terms of distinguishing non-isomorphic (sub-)graphs. Hence, both algorithms also have the same shortcomings. Based on this, we propose a generalization of GNNs, so-called k-dimensional GNNs (k-GNNs), which can take higher-order graph structures at multiple scales into account. These higher-order structures play an essential role in the characterization of social networks and molecule graphs. Our experimental evaluation confirms our theoretical findings as well as confirms that higher-order information is useful in the task of graph classification and regression.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/29/2021

The Logic of Graph Neural Networks

Graph neural networks (GNNs) are deep learning architectures for machine...
research
06/12/2021

Graph Neural Networks with Local Graph Parameters

Various recent proposals increase the distinguishing power of Graph Neur...
research
01/27/2022

A Higher-Order Semantic Dependency Parser

Higher-order features bring significant accuracy gains in semantic depen...
research
02/21/2023

Higher-order Sparse Convolutions in Graph Neural Networks

Graph Neural Networks (GNNs) have been applied to many problems in compu...
research
05/27/2022

Deep Ensembles for Graphs with Higher-order Dependencies

Graph neural networks (GNNs) continue to achieve state-of-the-art perfor...
research
03/18/2022

Towards Training Billion Parameter Graph Neural Networks for Atomic Simulations

Recent progress in Graph Neural Networks (GNNs) for modeling atomic simu...
research
06/08/2023

Hybrid Graph: A Unified Graph Representation with Datasets and Benchmarks for Complex Graphs

Graphs are widely used to encapsulate a variety of data formats, but rea...

Please sign up or login with your details

Forgot password? Click here to reset