Graph Neural Networks (GNN)


Graph neural networks (GNNs) are connectionist models that capture the dependence of graphs via message passing between the nodes of graphs. Unlike standard neural networks, graph neural networks retain a state that can represent information from its neighborhood with arbitrary depth.

Getting started

Deep Learning With Graph-Structured Representations
Novel approaches based on the theme of structuring the representations and computations of neural network-based models in the form of a graph.
graph-neural-networks graph-convolutional-networks graph-auto-encoders relational-graph-convolutional-networks

Tutorials

Deep Learning With Graph-Structured Representations
Novel approaches based on the theme of structuring the representations and computations of neural network-based models in the form of a graph.
graph-neural-networks graph-convolutional-networks graph-auto-encoders relational-graph-convolutional-networks
Implementing Graph Neural Networks with JAX
I’ll talk about my experience on how to build and train Graph Neural Networks (GNNs) with JAX.
graph-neural-networks jax graphs tutorial
ProteinGCN: Protein model quality assessment using GCNs
Source code for the paper: ProteinGCN: Protein model quality assessment using Graph Convolutional Networks.
protein-model-quality-estimation graph-convolutional-networks graph-neural-networks pytorch

Toolkits

DeepRobust
A pytorch adversarial library for attack and defense methods on images and graphs.
adversarial-learning adversarial-attacks adversarial-defense pytorch
GNNExplainer: Generating Explanations for Graph Neural Networks
General tool for explaining predictions made by graph neural networks (GNNs).
graph-neural-networks interpretability explainability graphs
DGL: Deep Graph Library
Python package built to ease deep learning on graph, on top of existing DL frameworks.
deep-graph-library dgl graph-convolutional-networks graph-neural-networks
StellarGraph - Machine Learning on Graphs
State-of-the-art algorithms for graph machine learning, making it easy to discover patterns and answer questions about graph-structured data.
graph-neural-networks graph-convolutional-networks stellargraph graphs

Research

Deep Learning With Graph-Structured Representations
Novel approaches based on the theme of structuring the representations and computations of neural network-based models in the form of a graph.
graph-neural-networks graph-convolutional-networks graph-auto-encoders relational-graph-convolutional-networks
ProteinGCN: Protein model quality assessment using GCNs
Source code for the paper: ProteinGCN: Protein model quality assessment using Graph Convolutional Networks.
protein-model-quality-estimation graph-convolutional-networks graph-neural-networks pytorch
ASAP: Pooling for Graph Neural Network (AAAI 2020)
ASAP is a sparse and differentiable pooling method that addresses the limitations of previous graph pooling layers.
graph-neural-networks graph-classification pool self-attention
Machine Learning on Graphs: A Model and Comprehensive Taxonomy
We propose a simple framework (GraphEDM) and a comprehensive Taxonomy to review and unify several graph representation learning methods.
graph-neural-networks graph-convolutional-networks autoencoders graph-regularization

Recent

DeepRobust
A pytorch adversarial library for attack and defense methods on images and graphs.
adversarial-learning adversarial-attacks adversarial-defense pytorch
ASAP: Pooling for Graph Neural Network (AAAI 2020)
ASAP is a sparse and differentiable pooling method that addresses the limitations of previous graph pooling layers.
graph-neural-networks graph-classification pool self-attention
Machine Learning on Graphs: A Model and Comprehensive Taxonomy
We propose a simple framework (GraphEDM) and a comprehensive Taxonomy to review and unify several graph representation learning methods.
graph-neural-networks graph-convolutional-networks autoencoders graph-regularization
Injecting Inductive Bias in Graph Neural Networks (MIT talk)
Equivariant Mesh Neural Networks and Neural Augmented (Factor) Graph Neural Networks.
graph-neural-networks video graphs tutorial
Table of Contents
Share a resource
Share a resource you found useful for this specific topic.
Topic experts
Share