Skip to content

Latest commit

 

History

History
7 lines (5 loc) · 451 Bytes

README.md

File metadata and controls

7 lines (5 loc) · 451 Bytes

Implementation of Contrastive Feature Selection (CFS)

This repository contains a public implementation of Contrastive Feature Selection (CFS), originally described in "Feature Selection in the Contrastive Analysis Setting" (NeurIPS 2023). The method was originally developed using Python 3.9.13 with Pytorch 1.13.0 and Pytorch-Lightning 1.9.3.

See Grassy_MNIST_example.ipynb for an example of how to use CFS.