Skip to main content

GECo method to explain GNNs.

Project description

GECo Logo

GECo Explainer

A community-based explainer for Graph Neural Networks.


📦 PyPI Status

PyPI version Downloads License


📥 Installation

Install GECo Explainer from PyPI:

pip install geco-explainer

🐍 Conda Status

Anaconda-Server Badge Anaconda-Server Badge Anaconda-Server Badge Anaconda-Server Badge Anaconda-Server Badge Anaconda-Server Badge

🐍 Conda Installation

Install via conda:

conda install salvatorecalderaro::geco-explainer

🐍 Conda (via environment)

You can also set up a Conda environment and install via pip:

conda create -n geco python=3.10
conda activate geco
pip install geco-explainer

📘 Example Usage (Jupyter Notebook)

You can try out GECo Explainer using our interactive Jupyter example:

👉 View GECo_example.ipynb


Citation

If you use GECo in your research, please cite the following paper:

@article{calderaro2024geco,
  title={The GECo algorithm for Graph Neural Networks Explanation},
  author={Calderaro, Salvatore and Amato, Domenico and Lo Bosco, Giosu{\`e} and Rizzo, Riccardo and Vella, Filippo},
  journal={arXiv preprint arXiv:2411.11391},
  year={2024}
}

DOI link


Contact

For questions or collaborations, contact: salvatore.calderaro01@unipa.it

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

geco_explainer-0.2.2.tar.gz (3.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

geco_explainer-0.2.2-py3-none-any.whl (4.1 kB view details)

Uploaded Python 3

File details

Details for the file geco_explainer-0.2.2.tar.gz.

File metadata

  • Download URL: geco_explainer-0.2.2.tar.gz
  • Upload date:
  • Size: 3.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.11

File hashes

Hashes for geco_explainer-0.2.2.tar.gz
Algorithm Hash digest
SHA256 16db48c30cd925c5f7e0600b71a0798d56f39f1309893ff179b8ff002a4afaf2
MD5 52c9ee173e8f1cefefd5aaf25e4f768e
BLAKE2b-256 303316bb96e9c55a6d75d55b6767855067b41c3d4640a218ae8ee454f0ed8583

See more details on using hashes here.

File details

Details for the file geco_explainer-0.2.2-py3-none-any.whl.

File metadata

  • Download URL: geco_explainer-0.2.2-py3-none-any.whl
  • Upload date:
  • Size: 4.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.11

File hashes

Hashes for geco_explainer-0.2.2-py3-none-any.whl
Algorithm Hash digest
SHA256 5ecf6964801e36a0551ecfe96fa1c4b9bf70038f770164d5d60afd53c5b821c6
MD5 0f4307debe51db8c200941d0676bf55f
BLAKE2b-256 2cb0dee3a09006fd38b33916ff11749adaf5c747d429b09666f839d6451136d6

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page