Roshni Chakraborty

When Features Become Instances: Inverted Contrastive Learning for Unsupervised Feature Selection

The proposed Inverted Contrastive Learning for Unsupervised Feature Selection (ICLFS), a feature-wise contrastive framework that reformulates UFS as a representation learning problem over features rather than samples, shows that feature-wise contrastive representation consistency provides a strong and effective alterna...