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.

2020-03-30 · A breakdown of the inner workings of GNNs.

graph-neural-networks graph-deep-learning graphs illustrated

2019-12-04 · A Comprehensive Survey on Graph Neural Networks.

graph-neural-networks graph-convolutional-networks graph-autoencoders spatial-temporal-gnns

2020-04-23 · 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

2020-06-14 · Introduce a series of effective graph-structured networks, including non-local neural networks, spatial generalized propagation networks, etc.

graph-neural-networks graph-structured-networks non-local-neural-networks spatial-generalized-propagation-networks

2020-07-20 · Does depth in graph neural network architectures bring any advantage?

graph-neural-networks depth graphs tutorial

2020-07-27 · In this post, we describe Temporal Graph Network, a generic framework for deep learning on dynamic graphs.

graph-neural-networks temporal-graph-networks graphs article

Geometric deep learning extension library for PyTorch.

graph-neural-networks graph-convolutional-networks pytorch geometric

A pytorch adversarial library for attack and defense methods on images and graphs.

adversarial-learning adversarial-attacks adversarial-defense pytorch

2019-11-13 · General tool for explaining predictions made by graph neural networks (GNNs).

graph-neural-networks interpretability explainability graphs

2020-05-14 · Little Ball of Fur is a graph sampling extension library for NetworkX.

node-classification graph-classification network-science network-sampling

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

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

Graph Neural Networks with Keras and Tensorflow 2.

graph-neural-networks graph-convolutional-networks tensorflow keras

2020-03-03 · A general purpose community detection and network embedding library for research built on NetworkX.

community-detection graph-classification graph-clustering node-classification