Graph neural network


Topic | v1 | created by jjones |
Description

A graph neural network (GNN) is a class of neural networks for processing data represented by graph data structures. They were popularized by their use in supervised learning on properties of various molecules. Since their inception, several variants of the simple message passing neural network (MPNN) framework have been proposed. These models optimize GNNs for use on larger graphs and apply them to domains such as social networks, citation networks, and online communities. It has been mathematically proven that GNNs are a weak form of the Weisfeiler–Lehman graph isomorphism test, so any GNN model is at least as powerful as this test. There is now growing interest in uniting GNNs with other so-called "geometric deep learning models" to better understand how and why these models work.


Relations

e.g. Graph convolutional networks (GCN)

Generalization of neural networks to arbitrary graphs.

subtopic of Deep learning

Deep learning (also known as deep structured learning) is part of a broader family of machine learnin...

used by PyTorch geometric

PyTorch Geometric (PyG) is a geometric deep learning extension library for PyTorch. It consists of...

used by Spektral

Spektral is a Python library for graph deep learning, based on the Keras API and TensorFlow 2. The ma...


Edit details Edit relations Attach new author Attach new topic Attach new resource
Resources

treated in An Attempt at Demystifying Graph Deep Learning - Essays on Data Science

8.0 rating 1.0 level 10.0 clarity 3.0 background – 1 rating

There are a ton of great explainers of what graph neural networks are. However, I find that a lot of...

treated in A Comprehensive Survey on Graph Neural Networks

8.0 rating 7.0 level 7.0 clarity 5.0 background – 1 rating

We propose a new taxonomy to divide the state-of-the-art graph neural networks into four categories,...