Online Semi-Supervised Learning With Multiple Regularization Terms
Open Access
- 4 February 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 68479-68494
Abstract
Online semi-supervised learning (OS2L) has received much attention recently because of its well practical usefulness. Most of existing studies of online semi-supervised learning related to manifold regularization. In this study, we propose a novel online semi-supervised learning framework with multiple regularization terms based on the notion of ascending the dual function in constrained optimization. Using Fenchel conjugate, different semi-supervised regularization terms can be integrated in the dual function easily and directly. This approach is derived by updating limited dual coefficient variables on each learning round. To be practical, we also employ buffering strategies and sparse approximation approaches in this work. Experimental studies show that our methods achieve accuracy comparable to offline algorithms while consuming less time and memory. Specially, our online semi-supervised learning algorithms can handle the settings where the target hyperplane of classification continually drifts with the sequence of arriving instances. This paper paves a way to the design and analysis of online semi-supervised learning algorithms with multiple regularization terms.Keywords
Funding Information
- National Natural Science Foundation of China (71471174)
This publication has 31 references indexed in Scilit:
- A graph-based semi-supervised k nearest-neighbor method for nonlinear manifold distributed data classificationInformation Sciences, 2016
- Distributed semi-supervised support vector machinesNeural Networks, 2016
- A sparse logistic regression framework by difference of convex functions programmingApplied Intelligence, 2016
- A review of online learning in supervised neural networksNeural Computing and Applications, 2013
- Manifold proximal support vector machine for semi-supervised classificationApplied Intelligence, 2013
- Online Manifold Regularization by Dual Ascending ProcedureMathematical Problems in Engineering, 2013
- Online Coregularization for Multiview Semisupervised LearningThe Scientific World Journal, 2013
- Nonconvex Online Support Vector MachinesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- A primal-dual perspective of online learning algorithmsMachine Learning, 2007
- Synthesis of maximum margin and multiview learning using unlabeled dataNeurocomputing, 2007