Fast Graph Representation Learning with PyTorch Geometric

TL;DR

PyTorch Geometric is a GPU-accelerated library for deep learning on graph-structured and irregular data, offering efficient processing, diverse methods, and comprehensive evaluation.

Contribution

The paper introduces PyTorch Geometric, a versatile library that integrates recent graph and 3D data processing methods with high efficiency and detailed comparative analysis.

Findings

High data throughput via sparse GPU acceleration

Support for diverse graph and 3D data processing methods

Comprehensive evaluation of implemented methods

Abstract

We introduce PyTorch Geometric, a library for deep learning on irregularly structured input data such as graphs, point clouds and manifolds, built upon PyTorch. In addition to general graph data structures and processing methods, it contains a variety of recently published methods from the domains of relational learning and 3D data processing. PyTorch Geometric achieves high data throughput by leveraging sparse GPU acceleration, by providing dedicated CUDA kernels and by introducing efficient mini-batch handling for input examples of different size. In this work, we present the library in detail and perform a comprehensive comparative study of the implemented methods in homogeneous evaluation scenarios.