External Resources¶
Matthias Fey and Jan E. Lenssen: Fast Graph Representation Learning with PyTorch Geometric [Paper, Slides (3.3MB), Poster (2.3MB), Notebook]
Soumith Chintala: Automatic Differentiation, PyTorch and Graph Neural Networks [Talk (starting from 26:15)]
Stanford University: Graph Neural Networks using PyTorch Geometric [Talk (starting from 33:33)]
Antonio Longa, Gabriele Santin and Giovanni Pellegrini: PyTorch Geometric Tutorial [Website, GitHub]
Nicolas Chaulet et al.: PyTorch Points 3D - A framework for running common deep learning models for point cloud analysis tasks that heavily relies on Pytorch Geometric [Github, Documentation]
Weihua Hu et al.: Open Graph Benchmark - A collection of large-scale benchmark datasets, data loaders, and evaluators for graph machine learning, including PyG support and examples [Website, GitHub]
DeepSNAP - A PyTorch library that bridges between graph libraries such as NetworkX and PyG [GitHub, Documentation]
Quiver - A distrbuted graph learning library for PyTorch Geometric [GitHub]
Benedek Rozemberczki: PyTorch Geometric Temporal - A temporal GNN library built upon PyG [GitHub, Documentation]
Steeve Huang: Hands-on Graph Neural Networks with PyTorch & PyTorch Geometric [Tutorial, Code]
Francesco Landolfi: PyTorch Geometric Tutorial [PDF (0.4MB)]
Sachin Sharma: How to Deploy (almost) any PyTorch Geometric Model on Nvidia’s Triton Inference Server with an Application to Amazon Product Recommendation and ArangoDB [Blog]
Amitoz Azad: torch_pdegraph - Solving PDEs on Graphs with PyTorch Geometric [Devpost, GitHub]
Amitoz Azad: Primal-Dual Algorithm for Total Variation Processing on Graphs [Jupyter]