Survey on Characterizing and Understanding GNNs from a Computer Architecture Perspective

TL;DR

This survey comprehensively reviews how graph neural networks are characterized from a computer architecture perspective, focusing on their performance bottlenecks and implications for parallel and distributed systems.

Contribution

It introduces a triple-level classification method to categorize and compare existing GNN characterization efforts, highlighting future directions for hardware and software optimization.

Findings

Identifies key performance bottlenecks in GNNs for parallel architectures.

Provides a systematic classification framework for GNN characterization efforts.

Suggests promising future research directions in GNN hardware and software optimization.

Abstract

Characterizing and understanding graph neural networks (GNNs) is essential for identifying performance bottlenecks and facilitating their deployment in parallel and distributed systems. Despite substantial work in this area, a comprehensive survey on characterizing and understanding GNNs from a computer architecture perspective is lacking. This work presents a comprehensive survey, proposing a triple-level classification method to categorize, summarize, and compare existing efforts, particularly focusing on their implications for parallel architectures and distributed systems. We identify promising future directions for GNN characterization that align with the challenges of optimizing hardware and software in parallel and distributed systems. Our survey aims to help scholars systematically understand GNN performance bottlenecks and execution patterns from a computer architecture perspective, thereby contributing to the development of more efficient GNN implementations across diverse parallel architectures and distributed systems.