BEACON
Benchmark for Efficient and Accurate Counting of Subgraphs
BEACON is the first comprehensive benchmark for subgraph counting, enabling systematic comparisons of algorithmic (AL) and machine learning (ML) methods. It provides standardized datasets, reproducible evaluation protocols, and a public leaderboard to accelerate research in graph analytics.
Key Features
BEACON introduces several innovations to the field of subgraph counting
Our Oracle Dataset contains 26,435 graphs from TUDataset and OGB, covering bioinformatics, social networks, and more.
BEACON enables direct comparison between algorithmic methods (e.g., ESCAPE) and machine learning approaches (e.g., PPGN).
Our PyPI tool allows researchers to create custom graph datasets with specific properties for targeted evaluation.
Our leaderboard tracks performance across accuracy (Q-error, MAE), scalability, and robustness metrics.
Latest Updates
Stay informed about the latest developments in our benchmark
Version History
BEACON v1.2 Release
Added new network graphs
BEACON v1.1 Release
Improved evaluation server and documentation
Top Submissions
PPGN (ML)
Dataset: Set_1
Type: Machine Learning
DeSCo (ML)
Dataset: Set_3
Type: Machine Learning
ESCAPE (AL)
Dataset: Set_1
Type: Algorithmic