Random Manifold Sampling and Joint Sparse Regularization for Multi-label Feature Selection

2022/04/13 by Li, Haibao, Zhai, Hongzhi
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.2204.06445

Abstract

Multi-label learning is usually used to mine the correlation between features and labels, and feature selection can retain as much information as possible through a small number of features. ℓ_2,1 regularization method can get sparse coefficient matrix, but it can not solve multicollinearity problem effectively. The model proposed in this paper can obtain the most relevant few features by solving the joint constrained optimization problems of ℓ_2,1 and ℓ_F regularization.In manifold regularization, we implement random walk strategy based on joint information matrix, and get a highly robust neighborhood graph.In addition, we given the algorithm for solving the model and proved its convergence.Comparative experiments on real-world data sets show that the proposed method outperforms other methods.

Related

• Joint Adaptive Graph and Structured Sparsity Regularization for Unsupervised Feature Selection
• Implicit Regularization for Multi-label Feature Selection
• Manifold Regularization Classification Model Based On Improved Diffusion Map
• ManiFeSt: Manifold-based Feature Selection for Small Data Sets
• Semi-Supervised Multi-Label Feature Selection with Consistent Sparse Graph Learning