OpenGSL: A Comprehensive Benchmark for Graph Structure Learning

by   Zhiyao Zhou, et al.

Graph Neural Networks (GNNs) have emerged as the de facto standard for representation learning on graphs, owing to their ability to effectively integrate graph topology and node attributes. However, the inherent suboptimal nature of node connections, resulting from the complex and contingent formation process of graphs, presents significant challenges in modeling them effectively. To tackle this issue, Graph Structure Learning (GSL), a family of data-centric learning approaches, has garnered substantial attention in recent years. The core concept behind GSL is to jointly optimize the graph structure and the corresponding GNN models. Despite the proposal of numerous GSL methods, the progress in this field remains unclear due to inconsistent experimental protocols, including variations in datasets, data processing techniques, and splitting strategies. In this paper, we introduce OpenGSL, the first comprehensive benchmark for GSL, aimed at addressing this gap. OpenGSL enables a fair comparison among state-of-the-art GSL methods by evaluating them across various popular datasets using uniform data processing and splitting strategies. Through extensive experiments, we observe that existing GSL methods do not consistently outperform vanilla GNN counterparts. However, we do observe that the learned graph structure demonstrates a strong generalization ability across different GNN backbones, despite its high computational and space requirements. We hope that our open-sourced library will facilitate rapid and equitable evaluation and inspire further innovative research in the field of GSL. The code of the benchmark can be found in


page 7

page 17


Boost then Convolve: Gradient Boosting Meets Graph Neural Networks

Graph neural networks (GNNs) are powerful models that have been successf...

Deep Graph Structure Learning for Robust Representations: A Survey

Graph Neural Networks (GNNs) are widely used for analyzing graph-structu...

Towards Unsupervised Deep Graph Structure Learning

In recent years, graph neural networks (GNNs) have emerged as a successf...

Homophily-enhanced Structure Learning for Graph Clustering

Graph clustering is a fundamental task in graph analysis, and recent adv...

pyGSL: A Graph Structure Learning Toolkit

We introduce pyGSL, a Python library that provides efficient implementat...

Examining the Effects of Degree Distribution and Homophily in Graph Learning Models

Despite a surge in interest in GNN development, homogeneity in benchmark...

Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Data

Graph condensation, which reduces the size of a large-scale graph by syn...

Please sign up or login with your details

Forgot password? Click here to reset