Paper ID: 2411.07217

Feature Selection Based on Wasserstein Distance

Fuwei Li

In this paper, we present a novel feature selection method based on the Wasserstein distance. Feature selection plays a critical role in reducing the dimensionality of input data, thereby improving machine learning efficiency and generalization performance. Unlike traditional feature selection approaches that rely on criteria such as correlation or KL divergence, our method leverages the Wasserstein distance to measure the similarity between distributions of selected features and original features. This approach inherently accounts for similarities between classes, making it robust in scenarios involving noisy labels. Experimental results demonstrate that our method outperforms traditional approaches, particularly in challenging settings involving noisy labeled data.

Submitted: Nov 11, 2024