Fast Graph Representation Learning with PyTorch Geometric
Matthias Fey、Jan E. Lenssen Department of Computer Graphics TU Dortmund University 44227 Dortmund, Germany
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.
中文速览
图神经网络（Graph Neural Network, GNN）近年来在图、点云和流形数据上取得了突出进展，但将这些方法高效落地的工程难度极高——稀疏、不规则、变长的数据结构很难在GPU上跑出理想速度。PyTorch Geometric（PyG）正是为此而生：它基于PyTorch构建，通过自定义CUDA核函数、gather/scatter加速以及块对角稀疏批处理，将几十种主流GNN算法（GCN、GAT、GraphSAGE、GIN、PointNet++等）统一到一套简洁的消息传递接口之下。实验结果表明，PyG在多项节点分类、图分类和点云分类基准上均能复现原论文精度，训练速度比Deep Graph Library的同期版本快最高40倍。这一工具极大地降低了几何深度学习的研究门槛，为图结构数据上的方法开发和公平比较提供了统一的基础平台。
原文 arXiv:1903.02428;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1903.02428v3