https://github.com/modssc/modssc

ModSSC: A Modular Framework for Semi Supervised Classification
https://github.com/modssc/modssc

classification deep-learning gnn inductive-learning machine-learning semi-supervised semi-supervised-classification semi-supervised-learning torch transductive-learning

Last synced: 24 days ago
JSON representation

ModSSC: A Modular Framework for Semi Supervised Classification

• Host: GitHub
• URL: https://github.com/modssc/modssc
• Owner: ModSSC
• License: mit
• Created: 2025-12-28T19:18:13.000Z (4 months ago)
• Default Branch: main
• Last Pushed: 2026-03-17T20:44:18.000Z (about 1 month ago)
• Last Synced: 2026-03-18T09:58:37.792Z (about 1 month ago)
• Topics: classification, deep-learning, gnn, inductive-learning, machine-learning, semi-supervised, semi-supervised-classification, semi-supervised-learning, torch, transductive-learning
• Language: Python
• Homepage:
• Size: 4.41 MB
• Stars: 32
• Watchers: 0
• Forks: 7
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • Changelog: CHANGELOG.md
  • Contributing: .github/CONTRIBUTING.md
  • License: LICENSE
  • Code of conduct: .github/CODE_OF_CONDUCT.md
  • Citation: CITATION.bib
  • Codeowners: .github/CODEOWNERS
  • Security: .github/SECURITY.md
  • Governance: .github/GOVERNANCE.md

Awesome Lists containing this project

README

          
# ModSSC

[![Stars](https://img.shields.io/github/stars/ModSSC/ModSSC?style=for-the-badge&label=stars&color=0B3D91&labelColor=0B2D5E)](https://github.com/ModSSC/ModSSC/stargazers)

[![Downloads](https://img.shields.io/pepy/dt/modssc?style=for-the-badge&label=downloads&logo=python&labelColor=0B2D5E&color=0B3D91)](https://pepy.tech/projects/modssc)

[![PyPI](https://img.shields.io/pypi/v/modssc?style=for-the-badge&label=pypi&color=0B3D91&labelColor=0B2D5E)](https://pypi.org/project/modssc/)

[![codecov](https://img.shields.io/codecov/c/github/ModSSC/ModSSC?token=5S1R9H5L8G&style=for-the-badge&label=coverage&color=0B3D91&labelColor=0B2D5E)](https://codecov.io/gh/ModSSC/ModSSC)

[![CI](https://img.shields.io/github/actions/workflow/status/ModSSC/ModSSC/ci.yml?branch=main&style=for-the-badge&label=ci&color=0B3D91&labelColor=0B2D5E)](https://github.com/ModSSC/ModSSC/actions/workflows/ci.yml)

[![Docs](https://img.shields.io/github/actions/workflow/status/ModSSC/ModSSC/docs.yml?branch=main&style=for-the-badge&label=docs&color=0B3D91&labelColor=0B2D5E)](https://github.com/ModSSC/ModSSC/actions/workflows/docs.yml)

ModSSC is a modular framework for semi-supervised classification across heterogeneous

modalities (text, vision, tabular, graph, audio). It is designed for academic research with

reproducible pipelines and extensible method registries.

## Resources

Pick the path that fits your goal: learn the concepts, run examples, or dive into the research.

### Docs and reference

- **Documentation**: [overview and concepts](https://modssc.github.io/ModSSC).

- **Choose your path**: [pick the right entrypoint](https://modssc.github.io/ModSSC/getting-started/choose-your-path).

- **Getting started**: [install and first run](https://modssc.github.io/ModSSC/getting-started/installation).

- **Extras and platforms**: [choose optional dependencies](https://modssc.github.io/ModSSC/getting-started/extras-and-platforms).

- **CLI and API reference**: [full command and API list](https://modssc.github.io/ModSSC/reference/cli).

- **Troubleshooting**: [common failures and fixes](https://modssc.github.io/ModSSC/how-to/troubleshooting).

If you use benchmark configs with environment placeholders, set `MODSSC_OUTPUT_DIR`, `MODSSC_DATASET_CACHE_DIR`, and `MODSSC_PREPROCESS_CACHE_DIR` before running. See the [Configuration reference](https://modssc.github.io/ModSSC/reference/configuration) for examples.

### Examples

- **Examples**: small scripts in [examples/](examples/).

- **Notebooks**: interactive demos in [notebooks/](notebooks/).

- **Examples guide**: [script index and recommendations](https://modssc.github.io/ModSSC/examples/).

- **Notebook tour**: [interactive entrypoints by topic](https://modssc.github.io/ModSSC/notebooks/).

### Research and articles

- **Paper (arXiv)**: [research reference](https://arxiv.org/abs/2512.13228).

- **Articles (Medium)**: [deeper explanations](https://medium.com/@melvin.barbaux).

## Citation

If you use ModSSC in research, please cite:

```bibtex

@misc{barbaux2025modsscmodularframeworksemisupervised,

      title={ModSSC: A Modular Framework for Semi-Supervised Classification on Heterogeneous Data},

      author={Melvin Barbaux},

      year={2025},

      eprint={2512.13228},

      archivePrefix={arXiv},

      primaryClass={cs.LG},

      url={https://arxiv.org/abs/2512.13228},

}

```

## Contributing

If this work resonates with you, feel free to give the project a star on GitHub, fork it

to experiment on your own data, or jump in and contribute. Issues, discussions, and pull

requests are more than welcome.

You can also start a discussion on

[GitHub Discussions](https://github.com/ModSSC/ModSSC/discussions).

## License

```

MIT License

```