Document Type

Conference Paper

Department/Unit

Department of Computer Science

Title

Graph-based abstraction for privacy preserving manifold visualization

Language

English

Abstract

With the next-generation Web aiming to further facilitate data/information sharing and aggregation, providing data privacy protection support in an open networked environments becomes increasingly important. Learning-from abstraction is a recently proposed distributed data mining approach which first abstracts data at local sources using the agglomerative hierarchical clustering (AGH) algorithm and then aggregates the abstractions (instead of the data) for global analysis. In this paper, we explain the limitation of the use of AGH for local manifold preserving data abstraction and propose the use of the graph-based clustering approach (e.g., the minimum cut) for local data abstraction. The effectiveness of the proposed abstraction approach was evaluated using benchmarking datasets with promising results. The global analysis results obtained based on the minimum cut abstraction was found to outperform those based on the AGH abstraction, especially when the underlying manifold was complex.

Keywords

Data visualization, Next generation networking, Data privacy, Protection, Data mining, Abstracts, Clustering algorithms, Aggregates, Data analysis, Algorithm design and analysis

Publication Date

12-2006

Source Publication Title

Proceedings of the 2006 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology Workshops (WI-IAT 2006 Workshops)(WI-IATW'06)

Start Page

94

End Page

97

Conference Location

Hong Kong, China

Publisher

IEEE

Peer Reviewed

1

Copyright

Copyright © 2006 by The Institute of Electrical and Electronics Engineers, Inc.

Funder

This work is supported by HKBU FRG/05-06/I-6 and RGC HKBU/2102/06E.

DOI

10.1109/WI-IATW.2006.76

Link to Publisher's Edition

http://dx.doi.org/10.1109/WI-IATW.2006.76

ISBN (print)

9780769527499

This document is currently not available here.

Share

COinS