Skip navigation
Run Run Shaw Library City University of Hong KongRun Run Shaw Library

Please use this identifier to cite or link to this item: http://dspace.cityu.edu.hk/handle/2031/6803
Title: Trace Ratio Optimization based Semi-Supervised Multimodal Nonlinear Dimensionality Reduction for Marginal Manifold Visualization
Authors: Zhang, Zhao (張召)
Zhao, Mingbo (趙鳴博)
Prof. Chow, Tommy Wai Shing (周偉誠教授)
Department: Department of Electronic Engineering
Issue Date: Aug-2012
Award: Won the Second Runner-up in 2012 Postgraduate Paper Contest organized by the IEEE (HK) Computational Intelligence Chapter.
Supervisor: Prof. Chow, Tommy Wai-shing
Type: Article
Abstract: Visualizing similarity data of different objects by exhibiting more separate organizations with local and multimodal characteristics preserved is important in multivariate data analysis. Laplacian Eigenmaps (LAE) and Locally Linear Embedding (LLE) aim at preserving the projections of all similarity pairs in the close vicinity of the reduced output space, but they are unable to identify and separate inter-class neighbors. This paper considers the semi-supervised manifold learning problems. We apply the pairwise Cannot-Link and Must-Link constraints induced by the neighborhood graph to specify the types of neighboring pairs. More flexible regulation on supervised information is provided. Two novel multimodal nonlinear techniques, which we call trace ratio (TR) criterion based semi-supervised LAE (S2LAE) and LLE (S2LLE), are then proposed for marginal manifold visualization. Utilizing the TR optimization, the similarity based on the Euclidean distance is effectively preserved by the orthogonal projective matrix. We also present the kernelized S2LAE and S2LLE. We verify the feasibility of S2LAE and S2LLE through extensive simulations over benchmark real-world MIT CBCL, CMU PIE, MNIST and USPS datasets. Manifold visualizations show that S2LAE and S2LLE are able to deliver large margins between different clusters or classes with multimodal distributions preserved. Clustering evaluations show they can achieve comparable to or even better results than some widely used methods.
Appears in Collections:Student Works With External Awards 

Files in This Item:
File Description SizeFormat 
award_news.html169 BHTMLView/Open
award_winning_work.html163 BHTMLView/Open
Show full item record


Items in Digital CityU Collections are protected by copyright, with all rights reserved, unless otherwise indicated.

Send feedback to Library Systems
Privacy Policy | Copyright | Disclaimer