Robust multiview feature selection via view weighted
- PDF / 1,597,214 Bytes
- 25 Pages / 439.642 x 666.49 pts Page_size
- 74 Downloads / 231 Views
Robust multiview feature selection via view weighted Jing Zhong1 · Ping Zhong2 · Yimin Xu1 · Liran Yang1 Received: 2 October 2019 / Revised: 29 July 2020 / Accepted: 12 August 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract In recent years, combining the multiple views of data to perform feature selection has been popular. As the different views are the descriptions from different angles of the same data, the abundant information coming from multiple views instead of the single view can be used to improve the performance of identification. In this paper, through the view weighted strategy, we propose a novel robust supervised multiview feature selection method, in which the robust feature selection is performed under the effect of l2,1 -norm. The proposed model has the following advantages. Firstly, different from the commonly used view concatenation that is liable to ignore the physical meaning of features and cause over-fitting, the proposed method divides the original space into several subspaces and performs feature selection in the subspaces, which can reduce the computational complexity. Secondly, the proposed method assigns different weights to views adaptively according to their importance, which shows the complementarity and the specificity of views. Then, the iterative algorithm is given to solve the proposed model, and in each iteration, the original large-scale problem is split into the small-scale subproblems due to the divided original space. The performance of the proposed method is compared with several related state-of-the-art methods on the widely used multiview datasets, and the experimental results demonstrate the effectiveness of the proposed method. Keywords Supervised multiview feature selection · View weighted strategy · Specificity of views · Robustness
1 Introduction With the extensive development of information technology, the data collected from practical applications are usually high dimensional. How to learn such high dimensional data effectively is an important issue in machine learning [1, 5]. As well known, high dimensionality brings great difficulties in the procedure of data processing, such as the high computational Ping Zhong
[email protected] 1
College of Information and Electrical Engineering, China Agricultural University, Beijing, 100083, China
2
College of Science, China Agricultural University, Beijing, 100083, China
Multimedia Tools and Applications
complexity and the increased probability of over-fitting. To strengthen the discrimination of these models built on the high dimensional data, it is necessary to eliminate the redundant and irrelevant features. Therefore, the dimensionality reduction technology is proposed to find the optimal feature set of low dimension to represent the original data. Feature extraction [6, 42] and feature selection [9, 31] are the two major methods used for dimensionality reduction. Feature extraction reduces the dimensionality of data by reconstructing new features. Tan et al. [23] proposed a n
Data Loading...
