151

MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning

Abstract

It is one typical and general topic of learning a good embedding model to efficiently learn the representation coefficients between two spaces/subspaces. To solve this task, L1L_{1} regularization is widely used for the pursuit of feature selection and avoiding overfitting, and yet the sparse estimation of features in L1L_{1} regularization may cause the underfitting of training data. L2L_{2} regularization is also frequently used, but it is a biased estimator. In this paper, we propose the idea that the features consist of three orthogonal parts, \emph{namely} sparse strong signals, dense weak signals and random noise, in which both strong and weak signals contribute to the fitting of data. To facilitate such novel decomposition, \emph{MSplit} LBI is for the first time proposed to realize feature selection and dense estimation simultaneously. We provide theoretical and simulational verification that our method exceeds L1L_{1} and L2L_{2} regularization, and extensive experimental results show that our method achieves state-of-the-art performance in the few-shot and zero-shot learning.

View on arXiv
Comments on this paper