DFS-BiHyper: Discrete Feature Selection via Bi-Level Optimization for Hyperparameter Tuning

This repository provides a python implementation of LLSRFS as described in the paper "Discrete Feature Selection via Bi-Level Optimization for Hyperparameter Tuning".

Datasets

All data sets can be obtained from the UCI machine learning repository (https://archive.ics.uci.edu/ml/datasets.php) or scikit-feature selection repository (https://jundongl.github.io/scikit-feature/datasets.html).

Environment Settings

• numpy
• matplotlib
• scikit-learn
• scipy
• pandas

Running the code

Implementation of DFS-BiHyper with $p = 1$ in

DFS_BiHyper_L21.py

Implementation of DFS-BiHyper with $p = 0$ in

DFS_BiHyper_L20.py

You can run the following demo function directly

main.py

Citation

Contact

If you have any questions, please feel free to contact me with [email protected]