hypertorch 0.1.1

HyperTorch is a library for hypergraph learning and benchmarking.

HyperTorch

Repo
Package
Testing
Contact

About the project

HyperTorch 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). HyperTorch 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 HyperTorch 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.

Table of contents

• Main features
• Getting started
  • Run examples
• Contributing
• Documentation
• License
• Discussion

Main features

Feature	What you can do	Highlights	Location
Dataset management	Load, process, and validate hypergraph datasets	HIF loader/processor, built-in datasets such as Algebra, Cora, Pubmed, DBLP, Amazon, and IMDB	hypertorch.data
Splitting, sampling, and batching	Prepare train/validation/test data and mini-batches	Dataset splitters, node and hyperedge samplers, negative samplers, data loaders	hypertorch.data
Feature enrichment	Enrich node and hyperedge features before training	Laplacian positional encodings, Node2Vec features, hyperedge weights and attributes	hypertorch.data
Models	Access hypergraph models	HGNN, HGNNP, HNHN, HyperGCN, GCN, MLP/SLP, NHP, Node2Vec, VilLain, CommonNeighbors	hypertorch.models
Neural components	Build models and pipelines	Layers, aggregators, losses, and activation/normalization helpers	hypertorch.nn
HLP pipelines	Use ready-to-train hyperlink prediction modules	HLP modules with encoders, configs, losses, and stage metrics for multiple models	hypertorch.hlp
Training and benchmarking	Train, compare, checkpoint, and report model runs	Multi-model trainer, schedulers, TensorBoard support, CSV/Markdown/LaTeX result tables	hypertorch.train

Getting started

For users working with the pip package manager, HyperTorch can be installed from PyPI.

pip install hypertorch

# if you want to install optional dependencies for tensorboard support:
pip install "hypertorch[tensorboard]"

or alternatively, using uv:

uv add hypertorch # or uv pip install hypertorch

# for optional dependencies for tensorboard support:
uv add "hypertorch[tensorboard]"

If you want to build the project from source, see the documentation for more details.

Run examples

You can download the examples directory and run the example scripts to get started.

With Python:

python3 examples/hyperlink_prediction/nhp.py

Or with uv:

uv run examples/hyperlink_prediction/nhp.py

Contributing

See CONTRIBUTING.md for details on contributing to the project.

Documentation

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 127.0.0.1:8000

and open the browser at http://localhost:8000 to access the documentation.

License

See LICENSE.

Discussion

Most development discussions take place on GitHub in this repo, via the GitHub issue tracker.