yakovdan/manifest

We propose a novel few-sample supervised feature selection (FS) method. It learns class-specific feature space manifolds using multi-feature association kernels. The composite kernel captures differences in learned associations, and a spectral-based FS score is derived using Riemannian geometry.

Few-Sample-Feature-Selection-via-Feature-Manifold-Learning

We propose a new method for few-sample supervised feature selection (FS). Our method first learns the manifold of the feature space of each class using kernels capturing multi-feature associations. Then, based on Riemannian geometry, a composite kernel is computed, extracting the differences between the learned feature associations. Finally, a FS score based on spectral analysis is computed.