Acceleration Algorithms in GNNs: A Survey

TL;DR

This survey reviews various algorithms designed to accelerate training, inference, and execution of Graph Neural Networks, highlighting recent advances, existing libraries, and future research directions for scalable GNN applications.

Contribution

It systematically categorizes and characterizes existing acceleration algorithms in GNNs and discusses related libraries and future research directions.

Findings

Summarizes and categorizes GNN acceleration approaches

Reviews libraries including the SGL library

Proposes future research directions in GNN acceleration

Abstract

Graph Neural Networks (GNNs) have demonstrated effectiveness in various graph-based tasks. However, their inefficiency in training and inference presents challenges for scaling up to real-world and large-scale graph applications. To address the critical challenges, a range of algorithms have been proposed to accelerate training and inference of GNNs, attracting increasing attention from the research community. In this paper, we present a systematic review of acceleration algorithms in GNNs, which can be categorized into three main topics based on their purpose: training acceleration, inference acceleration, and execution acceleration. Specifically, we summarize and categorize the existing approaches for each main topic, and provide detailed characterizations of the approaches within each category. Additionally, we review several libraries related to acceleration algorithms in GNNs and discuss our Scalable Graph Learning (SGL) library. Finally, we propose promising directions for future research. A complete summary is presented in our GitHub repository: https://github.com/PKU-DAIR/SGL/blob/main/Awsome-GNN-Acceleration.md.