Semisupervised Manifold Regularization via a Subnetwork-Based Representation Learning Model

• Published in: IEEE transactions on cybernetics Vol. 53; no. 11; pp. 6923 - 6936
• Main Authors: Zhang, Wandong, Wu, Q. M. Jonathan, Yang, Yimin
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.11.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Classification; Coding; Data mining; Data representation; Kernel; Machine learning; manifold regularization (MR); Manifolds; Multilayers; Neural networks; Nonhomogeneous media; Regularization; Representations; Semi-supervised learning; semisupervised classification; Semisupervised learning; subnet neural network; Support vector machines; Task analysis; Training
• ISSN: 2168-2267; 2168-2275; 2168-2275
• DOI: 10.1109/TCYB.2022.3177573

Semisupervised classification with a few labeled training samples is a challenging task in the area of data mining. Moore-Penrose inverse (MPI)-based manifold regularization (MR) is a widely used technique in tackling semisupervised classification. However, most of the existing MPI-based MR algorithms can only generate loosely connected feature encoding, which is generally less effective in data representation and feature learning. To alleviate this deficiency, we introduce a new semisupervised multilayer subnet neural network called SS-MSNN. The key contributions of this article are as follows: 1) a novel MPI-based MR model using the subnetwork structure is introduced. The subnet model is utilized to enrich the latent space representations iteratively; 2) a one-step training process to learn the discriminative encoding is proposed. The proposed SS-MSNN learns parameters by directly optimizing the entire network, accepting input from one end, and producing output at the other end; and 3) a new semisupervised dataset called HFSWR-RDE is built for this research. Experimental results on multiple domains show that the SS-MSNN achieves promising performance over the other semisupervised learning algorithms, demonstrating fast inference speed and better generalization ability.