A Fair Comparison of Graph Neural Networks for Graph Classification

by   Federico Errica, et al.

Experimental reproducibility and replicability is a critical topic in machine learning. Authors have often raised concerns about such scholarship issues, which are aimed at improving the quality of the field. Recently, the graph representation learning field has attracted the attention of a wide research community, which resulted in a large stream of works. As such, several Graph Neural Network models have been developed to effectively tackle graph classification. However, experimental procedures often lack rigorousness and are hardly reproducible. Motivated by this, we provide an overview of common practices that should be avoided to fairly compare with the state of the art. To counter this troubling trend, we ran more than 47000 experiments in a controlled and uniform framework to re-evaluate five popular models across nine common benchmarks. Moreover, by comparing GNNs with structure-agnostic baselines we provide convincing evidence that, on some datasets, structural information has not been exploited yet. We believe that this work can contribute to the development of the graph learning field, by providing a much needed grounding for rigorous evaluations of graph classification models.


page 1

page 2

page 3

page 4


Application of Graph Neural Networks and graph descriptors for graph classification

Graph classification is an important area in both modern research and in...

Graph Neural Networks for Small Graph and Giant Network Representation Learning: An Overview

Graph neural networks denote a group of neural network models introduced...

Graph Warp Module: an Auxiliary Module for Boosting the Power of Graph Neural Networks

Recently, Graph Neural Networks (GNNs) are trending in the machine learn...

Large-scale graph representation learning with very deep GNNs and self-supervision

Effectively and efficiently deploying graph neural networks (GNNs) at sc...

Strengthening structural baselines for graph classification using Local Topological Profile

We present the analysis of the topological graph descriptor Local Degree...

Benchmarking Graph Neural Networks for FMRI analysis

Graph Neural Networks (GNNs) have emerged as a powerful tool to learn fr...

Flurry: a Fast Framework for Reproducible Multi-layered Provenance Graph Representation Learning

Complex heterogeneous dynamic networks like knowledge graphs are powerfu...

Please sign up or login with your details

Forgot password? Click here to reset