Implicit Regularization for Multi-label Feature Selection
This work addresses feature selection for multi-label learning tasks, offering an incremental improvement over existing sparse methods.
The paper tackles feature selection in multi-label learning by introducing a new estimator using implicit regularization and label embedding, which reduces extra bias and can lead to benign overfitting, as shown in experiments on benchmark datasets.
In this paper, we address the problem of feature selection in the context of multi-label learning, by using a new estimator based on implicit regularization and label embedding. Unlike the sparse feature selection methods that use a penalized estimator with explicit regularization terms such as $l_{2,1}$-norm, MCP or SCAD, we propose a simple alternative method via Hadamard product parameterization. In order to guide the feature selection process, a latent semantic of multi-label information method is adopted, as a label embedding. Experimental results on some known benchmark datasets suggest that the proposed estimator suffers much less from extra bias, and may lead to benign overfitting.