PyG (PyTorch Geometric) is a library built upon PyTorch to easily write and train Graph Neural Networks (GNNs) for a wide range of applications related to structured data. It consists of various methods for deep learning on graphs and other irregular structures, also known as geometric deep learning, from a variety of published papers.

Install PyG. Installation; Get Started. Introduction by Example; Colab Notebooks and Video Tutorials; Tutorials. Design of Graph Neural Networks. Creating Message Passing Networks; Heterogeneous Graph Learning; Working with Graph Datasets; Use-Cases & Applications; Distributed Training; Advanced Concepts. Advanced Mini-Batching; Memory ...

The PyG engine utilizes the powerful PyTorch deep learning framework, as well as additions of efficient CUDA libraries for operating on sparse data, e.g., pyg-lib, torch_scatter, torch_sparse and torch-cluster.

Graph Neural Network Library for PyTorch. Conda Files; Labels; Badges; License: MIT Home: https://github.com/pyg-team/pytorch_geometric 592340 total downloads ; Last ...

PyG 2.3 is fully compatible with the next generation release of PyTorch, bringing many new innovations and features such as torch.compile() and Python 3.11 support to PyG out-of-the-box. In particular, many PyG models and functions are speeded up significantly using torch.compile() in torch >= 2.0.0 .

Sep 12, 2021 · With this, we are releasing PyG 2.0, a new major release that brings sophisticated heterogeneous graph support, GraphGym and many other exciting features to PyG. We finally provide full heterogeneous graph support in PyG 2.0. See here for the accompanying tutorial.

PyG is a library built upon PyTorch to easily write and train Graph Neural Networks for a wide range of applications related to structured data. PyG is both friendly to machine learning researchers and first-time users of machine learning toolkits.

Apr 1, 2025 · PyG (PyTorch Geometric) is a library built upon PyTorch to easily write and train Graph Neural Networks (GNNs) for a wide range of applications related to structured data. It consists of various methods for deep learning on graphs and other irregular structures, also known as geometric deep learning, from a variety of published papers.

Dec 1, 2022 · PyG 2.2 includes numerous primitives to easily integrate with simple paradigms for scalable graph machine learning, enabling users to train GNNs on graphs far larger than the size of their machine's available memory.

Dec 22, 2022 · In this post, we will showcase how these features can be used to solve link prediction tasks on heterogenous graphs in PyG. Graphs capture both simple and complex interactions, and provide a...