White Papers

Parallel Spectral Clustering Algorithm for Large-Scale Community Data Mining

Overview The spectral clustering algorithm has been shown to be very effective in finding clusters of non-linear boundaries. Unfortunately, spectral clustering suffers from the scalability problem in both memory use and computational time. In this work, the author parallelizes the algorithm by dividing both memory use and computation on distributed machines. Empirical study on some small datasets shows the accuracy of the parallelization scheme. Empirical study on a large community dataset obtained from Orkut demonstrates the scalability of the parallel spectral clustering algorithm.

Download White Paper

By downloading you agree to our Terms and Conditions. These include information regarding use of your personal data.

Publisher
University of California
File Format
PDF
Date Published
Oct 1, 2008
Format
White Papers
Topics
Parallel Processing, Data Mining - Analysis

Similiar White Papers

Exploiting Functional Decomposition for Efficient Parallel Processing of Multiple Data Analysis Queries

Exploiting Functional Decomposition for Efficient Parallel Processing of Multiple Data Analysis Queries

Reuse is a powerful method for improving system performance. This paper examines functional decomposition for improving

Publisher: Ohio State University  |  Tags: applications, data

Get more from BI by understanding your analysis needs

Get more from BI by understanding your analysis needs

Across your organization, different types of users - casual users, power users and executives - access data in order to

Publisher: IBM  |  Tags: bi, business intelligence, data

A DOM Tree Alignment Model for Mining Parallel Data From the Web

A DOM Tree Alignment Model for Mining Parallel Data From the Web

This paper presents a new web mining scheme for parallel data acquisition. Based on the Document Object Model (DOM), a w

Publisher: Microsoft  |  Tags: data

University of California White Papers

Escape From the Computer Lab: Education in Mobile Wireless Networks

Escape From the Computer Lab: Education in Mobile Wireless Networks

As mobile wireless network technology becomes widespread, the importance of education about this new form of communicati

Publisher: University of California  |  Tags: computing, mobile wireless, mobility, network, portable devices, university of california

Stateless Load Balancing Over Multiple MPLS Paths

Stateless Load Balancing Over Multiple MPLS Paths

The paper proposes a flow-independent approach to balance the load coming from several multimedia applications (i.e., IP

Publisher: University of California  |  Tags: applications, ip, mpls, network

Enhancing TCP Over HSDPA by Cross-Layer Signalling

Enhancing TCP Over HSDPA by Cross-Layer Signalling

A comprehensive performance evaluation of a cross-layer solution to increase users' downlink data rates over HSDPA is pr

Publisher: University of California  |  Tags: base station, data, hsdpa, ip, server

Mesh Topology Construction for Interconnected Wireless LANs

Mesh Topology Construction for Interconnected Wireless LANs

The 802.11s working group has been formed recently to recommend an Extended Service Set (ESS) that enables wider area co

Publisher: University of California  |  Tags: network

Directed Diffusion for Wireless Sensor Networking

Directed Diffusion for Wireless Sensor Networking

Advances in processor, memory and radio technology will enable small and cheap nodes capable of sensing, communication a

Publisher: University of California  |  Tags: data, network