CogDL: A Comprehensive Library for Graph Deep Learning

TL;DR

CogDL is a versatile library that streamlines graph deep learning research and applications by offering unified training, efficient sparse operators, and reproducible benchmarks for various graph tasks.

Contribution

It introduces a unified design for GNN training and evaluation, along with optimized sparse operators, enhancing efficiency and ease of use in graph deep learning.

Findings

Achieves state-of-the-art efficiency with optimized sparse operators.

Facilitates reproducible benchmarking for fundamental graph tasks.

Supports diverse graph learning applications with a unified framework.

Abstract

Graph neural networks (GNNs) have attracted tremendous attention from the graph learning community in recent years. It has been widely adopted in various real-world applications from diverse domains, such as social networks and biological graphs. The research and applications of graph deep learning present new challenges, including the sparse nature of graph data, complicated training of GNNs, and non-standard evaluation of graph tasks. To tackle the issues, we present CogDL, a comprehensive library for graph deep learning that allows researchers and practitioners to conduct experiments, compare methods, and build applications with ease and efficiency. In CogDL, we propose a unified design for the training and evaluation of GNN models for various graph tasks, making it unique among existing graph learning libraries. By utilizing this unified trainer, CogDL can optimize the GNN training loop with several training techniques, such as mixed precision training. Moreover, we develop efficient sparse operators for CogDL, enabling it to become the most competitive graph library for efficiency. Another important CogDL feature is its focus on ease of use with the aim of facilitating open and reproducible research of graph learning. We leverage CogDL to report and maintain benchmark results on fundamental graph tasks, which can be reproduced and directly used by the community.