HYGENE

KO | EN

gitlite — search

#hacktoberfest #llm #go #android #deep-learning #linux #docker #windows #cli #kubernetes #vue #awesome-list #openai #mcp

(★ 14)

Repository for the implementation of our work on hypergraph generation as part of the ANR project "SODA".

HYGENE Latest Version Download

Download Latest Version (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# HYGENE: A Diffusion-based Hypergraph Generation Method

This repository contains the reference implementation of the paper [HYGENE: A Diffusion-based Hypergraph Generation Method](https://arxiv.org/abs/2408.16457). Our work is based on [Efficient and Scalable Graph Generation through Iterative Local Expansion](https://openreview.net/forum?id=2XkTz7gdpc), many thanks for their great code!

## Setup

To get started, follow these steps:

+ Clone this repository

+ Create the specified [conda](https://docs.conda.io/en/latest/) environment named `hypergraph-generation` by running the following command:

```bash
    conda env create -f environment.yaml
    ```

Note that the `graph-tool` library is not available on Windows. This library is used for SBM hypergraph evaluation, which will consequently not work on Windows. Everything else should work regardless of the operating system.

## Usage

The main entry point is `main.py` with parameters managed by the [Hydra](https://hydra.cc/) framework.
To reproduce the results from the paper, run:

```bash
python main.py +experiment=XXX
```

where `XXX` is one of the following experiments:
`hypergraphErdosRenyi`, `hypergraphSBM`, `hypergraphEgo`, `hypergraphTree`, `meshBookshelf`, `meshPlant`, `meshPiano`

New experiments can be added by adding a pickle file in `data/` and creating a new config file in `config/experiment/` or passing the parameters directly through the command line. Please refer to the [Hydra documentation](https://hydra.cc/docs/intro/) for more information.

### Checkpoints

When `training.save_checkpoint` in the configuration is set to `True`, checkpoints are saved. To resume training from a checkpoint, set `training.resume` to the step number of the checkpoint, or to `True` to resume from the latest checkpoint.

### Wandb

To log the results to [Wandb](https://wandb.ai/), set `wandb.logging` to `True` in the configuration.

## Citation
When using this code, please cite our paper:
```
@inproceedings{gailhard2025hygene,
    title={HYGENE: A Diffusion-based Hypergraph Generation Method},
    author={Gailhard, Dorian and Tartaglione, Enzo and Naviner, Lirida and Giraldo, Jhony H.},
    booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
    year={2025},
}
```

## Acknowledgments
We acknowledge the [ANR – FRANCE](https://anr.fr/) (French National Research Agency) for its financial support of the [System On Chip Design leveraging Artificial Intelligence (SODA)](https://anr.fr/Project-ANR-23-IAS3-0004) project under grant ANR-23-IAS3-0004. This project has also been partially funded by the [Hi!PARIS Center on Data Analytics and Artificial Intelligence](https://www.hi-paris.fr/).

HYGENE

HYGENE Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

HYGENE

HYGENE Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

Download README