edGNN: a Simple and Powerful GNN for Directed Labeled Graphs

04/18/2019
by   Guillaume Jaume, et al.
0

The ability of a graph neural network (GNN) to leverage both the graph topology and graph labels is fundamental to building discriminative node and graph embeddings. Building on previous work, we theoretically show that edGNN, our model for directed labeled graphs, is as powerful as the Weisfeiler--Lehman algorithm for graph isomorphism. Our experiments support our theoretical findings, confirming that graph neural networks can be used effectively for inference problems on directed graphs with both node and edge labels. Code available at https://github.com/guillaumejaume/edGNN.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/21/2021

Boost then Convolve: Gradient Boosting Meets Graph Neural Networks

Graph neural networks (GNNs) are powerful models that have been successf...
research
09/20/2023

Improving Article Classification with Edge-Heterogeneous Graph Neural Networks

Classifying research output into context-specific label taxonomies is a ...
research
04/22/2019

DAG-GNN: DAG Structure Learning with Graph Neural Networks

Learning a faithful directed acyclic graph (DAG) from samples of a joint...
research
04/10/2017

Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs

A number of problems can be formulated as prediction on graph-structured...
research
10/22/2020

Graph Neural Network for Large-Scale Network Localization

Graph neural networks (GNNs) are popular to use for classifying structur...
research
10/05/2020

CopulaGNN: Towards Integrating Representational and Correlational Roles of Graphs in Graph Neural Networks

Graph-structured data are ubiquitous. However, graphs encode diverse typ...
research
06/10/2022

We Cannot Guarantee Safety: The Undecidability of Graph Neural Network Verification

Graph Neural Networks (GNN) are commonly used for two tasks: (whole) gra...

Please sign up or login with your details

Forgot password? Click here to reset