← ML Research Wiki / 2003.00982

Benchmarking Graph Neural Networks

Vijay Prakash Dwivedi Nanyang Technological University Singapore, Chaitanya K Joshi [email protected] University of Cambridge UK, Anh Tuan Luu Nanyang Technological University Singapore, Thomas Laurent [email protected] Loyola Marymount University USA, Yoshua Bengio [email protected] University of Montréal MilaCanada, Xavier Bresson [email protected] National University of Singapore (2023)

Paper Information
arXiv ID
Venue
Journal of machine learning research
Domain
Not specified
SOTA Claim
Yes
Reproducibility
7/10

Abstract

In the last few years, graph neural networks (GNNs) have become the standard toolkit for analyzing and learning from data on graphs. This emerging field has witnessed an extensive growth of promising techniques that have been applied with success to computer science, mathematics, biology, physics and chemistry. But for any successful field to become mainstream and reliable, benchmarks must be developed to quantify progress. This led us in March 2020 to release a benchmark framework that i) comprises of a diverse collection of mathematical and real-world graphs, ii) enables fair model comparison with the same parameter budget to identify key architectures, iii) has an open-source, easy-to-use and reproducible code infrastructure, and iv) is flexible for researchers to experiment with new theoretical ideas. As of December 2022, the GitHub repository 1 has reached 2,000 stars and 380 forks, which demonstrates the utility of the proposed open-source framework through the wide usage by the GNN community. In this paper, we present an updated version of our benchmark with a concise presentation of the aforementioned framework characteristics, an additional medium-sized molecular dataset AQSOL, similar to the popular ZINC, but with a real-world measured chemical target, and discuss how this framework can be leveraged to explore new GNN designs and insights. As a proof of value of our benchmark, we study the case of graph positional encoding (PE) in GNNs, which was introduced with this benchmark and has since spurred interest of exploring more powerful PE for Transformers and GNNs in a robust experimental setting.

Summary

The paper presents an open-source benchmarking framework for Graph Neural Networks (GNNs). It outlines the necessity for standardized benchmarks to assess progress in GNN research across various fields like computer science, biology, and physics. The updated framework now includes additional datasets, notably AQSOL, alongside a diverse collection of mathematical and real-world graphs allowing for fair model comparison. It highlights the effective use of positional encodings in enhancing the performance of GNNs, particularly through the use of Laplacian eigenvectors for graph positional encoding. The framework encourages exploration of GNN designs and aims to establish a modular and reproducible codebase for future research.

Methods

This paper employs the following methods:

  • Graph Neural Networks (GNNs)
  • Message Passing Graph Convolutional Networks (MP-GCNs)
  • Weisfeiler-Lehman (WL) GNNs

Models Used

  • GatedGCN
  • GraphSage
  • GAT
  • MoNet
  • vanilla GCN
  • 3WLGNN
  • RingGNN
  • GIN

Datasets

The following datasets were used in this research:

  • AQSOL
  • ZINC
  • OGBL-COLLAB
  • WikiCS
  • MNIST
  • CIFAR10
  • CSL
  • CYCLES
  • GraphTheoryProp
  • SBM (PATTERN/CLUSTER)
  • TSP

Evaluation Metrics

  • Mean Absolute Error (MAE)
  • Classification Accuracy
  • Hits@K
  • F1 Score

Results

  • Proposed benchmark framework facilitates better comparison and insights on GNNs
  • Laplacian Positional Encoding improves MP-GCNs performance
  • Anisotropic GNNs show enhanced results compared to isotropic models

Limitations

The authors identified the following limitations:

  • Challenges in universally defining datasets and their representative quality
  • Absence of consensus on experimental settings in the GNN literature

Technical Requirements

  • Number of GPUs: 4
  • GPU Type: None specified

Keywords

Graph Neural Networks Benchmarking Datasets Graph Representation Learning Positional Encoding

Papers Using Similar Methods

External Resources