| Repo |     |
| Package |  |
| Testing |  |
| Contact |
HyperBench is a library for hypergraph learning and benchmarking. It provides a standardized workflow for loading hypergraph datasets, training models, evaluating them under comparable settings, and reporting results. The current release focuses on Hyperlink Prediction, with ready-to-run pipelines for established hypergraph baselines.
The library is built around extensibility: datasets are represented in HIF format and converted into typed tensor objects, models can be implemented as standard Lightning modules, and benchmarking is handled through reusable trainers, samplers, metrics, loggers, and result exporters (Markdown/LaTeX). HyperBench includes preloaded datasets, mini-batch and full-hypergraph data loading, negative sampling utilities, structural feature enrichers, neural components, and built-in models such as HGNN, HNHN, HyperGCN, GCN, MLP/SLP, NHP, Node2Vec, VilLain, and more.
Use HyperBench to:
- Benchmark existing models across a shared collection of hypergraph datasets.
- Develop custom PyTorch or PyTorch Lightning models and train and compare them against the built-in baselines.
- Integrate new datasets through the HIF format and run the same training, evaluation, and reporting pipeline on them.
| Feature | What you can do | Highlights | Package |
|---|---|---|---|
| Dataset management | Load, preprocess, and manage hypergraph datasets | HIF loader/processor, built-in datasets such as Algebra, Cora, Pubmed, DBLP, Amazon, and IMDB | hyperbench.data |
| Sampling and batching | Sample sub-hypergraphs and prepare training batches | DataLoader, node and hyperedge samplers, and full-hypergraph evaluation batches | hyperbench.data |
| Training and benchmarking | Train and benchmark models out of the box | Multi-model trainer, negative sampling, schedulers, Markdown/LaTeX result tables | hyperbench.train |
| Models | Access a wide range of hypergraph models | HGNN, HGNNP, HNHN, HyperGCN, GCN, MLP/SLP, NHP, Node2Vec, VilLain, CommonNeighbors | hyperbench.models |
| Neural network components | Build custom architectures and pipelines | Convolutions, aggregators, losses, scorers, enrichers, positional encodings | hyperbench.nn |
| HLP pipelines | Use ready-to-run training and evaluation pipelines | HLP modules with encoders, configs, and loss definitions for multiple models | hyperbench.hlp |
For users working with the pip package manager, hyperbench can be installed from PyPI.
pip install hyperbench
# if you want to install optional dependencies for tensorboard support:
pip install "hyperbench[tensorboard]"or alternatively, using uv:
uv add hyperbench # or uv pip install hyperbench
# for optional dependencies:
uv add "hyperbench[tensorboard]"If you want to build the project from source, see the documentation for more details.
You can download examples directory and run the example scripts to get started.
With Python:
python3 examples/early_stopping.pyOr with uv:
uv run examples/early_stopping.pySee CONTRIBUTING.md for details on contributing to the project.
You can find the extensive documentation here.
Alternatively, you can build the documentation locally with the following commands:
make docs
# With explicit commands
uv run zensical build --clean -f zensical.toml
uv run zensical serve -f zensical.toml -a 127.0.0.1:8000and open the browser at http://localhost:8000 to access the documentation.
See LICENSE.
Most development discussions take place on GitHub in this repo, via the GitHub issue tracker.
