Where Did the Gap Go? Reassessing the Long-Range Graph Benchmark

Jan Tönshoff, Martin Ritzert, Eran Rosenbluth, Martin Grohe

Keywords: Graph Neural Networks, Message Passing, Graph Transformers, Long-Range Graph Benchmark

TL;DR: MPGNNs are much better than reported on LRGB

Abstract:

The recent Long-Range Graph Benchmark (LRGB, Dwivedi et al. 2022) introduced a set of graph learning tasks strongly dependent on long-range interaction between vertices.
Empirical evidence suggests that on these tasks Graph Transformers significantly outperform Message Passing GNNs (MPGNNs).
In this paper, we carefully reevaluate multiple MPGNN baselines as well as the Graph Transformer GPS (Rampášek et al. 2022) on LRGB.
Through a rigorous empirical analysis, we demonstrate that the reported performance gap is overestimated due to suboptimal hyperparameter choices.
It is noteworthy that across multiple datasets the performance gap completely vanishes after basic hyperparameter optimization.
In addition, we discuss the impact of lacking feature normalization for LRGB's vision datasets and highlight a spurious implementation of LRGB's link prediction metric.
The principal aim of our paper is to establish a higher standard of empirical rigor within the graph machine learning community.

Submission Type: Extended abstract (max 4 main pages).

Agreement: Check this if you are okay with being contacted to participate in an anonymous survey.

Software: https://github.com/toenshoff/LRGB

Submission Number: 109