Awesome
LIO: Learning from Indirect Observations
A package for weakly supervised learning research based on PyTorch
<a href="https://github.com/YivanZhang/lio/blob/master/LICENSE"> <img alt="license" src="https://img.shields.io/github/license/YivanZhang/lio"> </a> <a href="https://pypi.org/project/lio/"> <img alt="pypi" src="https://badge.fury.io/py/lio.svg" alt="PyPI version"> </a>Installation
pip install lio
or
git clone https://github.com/YivanZhang/lio.git
pip install -e .
Most of the modules are designed as small (higher-order) functions.
Feel free to copy-paste only what you need for your existing workflow to reduce dependencies.
References
-
Approximating Instance-Dependent Noise via Instance-Confidence Embedding
Yivan Zhang and Masashi Sugiyama
[arXiv] [code] -
Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization
Yivan Zhang, Gang Niu, and Masashi Sugiyama
[arXiv] [ICML'21] [poster] [code] -
Learning from Aggregate Observations
Yivan Zhang, Nontawat Charoenphakdee, Zhenguo Wu, and Masashi Sugiyama
[arXiv] [NeurIPS'20] [poster] -
Learning from Indirect Observations
Yivan Zhang, Nontawat Charoenphakdee, and Masashi Sugiyama
[arXiv]