Unsupervised and semi-supervised extraction of clusters from hypergraphs

Weiwei Du, Kohei Inoue, Kiichi Urahama

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

We extend a graph spectral method for extracting clusters from graphs representing pairwise similarity between data to hypergraph data with hyperedges denoting higher order similarity between data. Our method is robust to noisy outlier data and the number of clusters can be easily determined. The unsupervised method extracts clusters sequentially in the order of the majority of clusters. We derive from the unsupervised algorithm a semi-supervised one which can extract any cluster irrespective of its majority. The performance of those methods is exemplified with synthetic toy data and real image data.

Original languageEnglish
Pages (from-to)2315-2318
Number of pages4
JournalIEICE Transactions on Information and Systems
VolumeE89-D
Issue number7
DOIs
Publication statusPublished - Jan 1 2006

All Science Journal Classification (ASJC) codes

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering
  • Artificial Intelligence

Cite this

Unsupervised and semi-supervised extraction of clusters from hypergraphs. / Du, Weiwei; Inoue, Kohei; Urahama, Kiichi.

In: IEICE Transactions on Information and Systems, Vol. E89-D, No. 7, 01.01.2006, p. 2315-2318.

Research output: Contribution to journalArticle

@article{e7faea002c9a4427af968b109d58441c,
title = "Unsupervised and semi-supervised extraction of clusters from hypergraphs",
abstract = "We extend a graph spectral method for extracting clusters from graphs representing pairwise similarity between data to hypergraph data with hyperedges denoting higher order similarity between data. Our method is robust to noisy outlier data and the number of clusters can be easily determined. The unsupervised method extracts clusters sequentially in the order of the majority of clusters. We derive from the unsupervised algorithm a semi-supervised one which can extract any cluster irrespective of its majority. The performance of those methods is exemplified with synthetic toy data and real image data.",
author = "Weiwei Du and Kohei Inoue and Kiichi Urahama",
year = "2006",
month = "1",
day = "1",
doi = "10.1093/ietisy/e89-d.7.2315",
language = "English",
volume = "E89-D",
pages = "2315--2318",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "一般社団法人電子情報通信学会",
number = "7",

}

TY - JOUR

T1 - Unsupervised and semi-supervised extraction of clusters from hypergraphs

AU - Du, Weiwei

AU - Inoue, Kohei

AU - Urahama, Kiichi

PY - 2006/1/1

Y1 - 2006/1/1

N2 - We extend a graph spectral method for extracting clusters from graphs representing pairwise similarity between data to hypergraph data with hyperedges denoting higher order similarity between data. Our method is robust to noisy outlier data and the number of clusters can be easily determined. The unsupervised method extracts clusters sequentially in the order of the majority of clusters. We derive from the unsupervised algorithm a semi-supervised one which can extract any cluster irrespective of its majority. The performance of those methods is exemplified with synthetic toy data and real image data.

AB - We extend a graph spectral method for extracting clusters from graphs representing pairwise similarity between data to hypergraph data with hyperedges denoting higher order similarity between data. Our method is robust to noisy outlier data and the number of clusters can be easily determined. The unsupervised method extracts clusters sequentially in the order of the majority of clusters. We derive from the unsupervised algorithm a semi-supervised one which can extract any cluster irrespective of its majority. The performance of those methods is exemplified with synthetic toy data and real image data.

UR - http://www.scopus.com/inward/record.url?scp=33747881621&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33747881621&partnerID=8YFLogxK

U2 - 10.1093/ietisy/e89-d.7.2315

DO - 10.1093/ietisy/e89-d.7.2315

M3 - Article

AN - SCOPUS:33747881621

VL - E89-D

SP - 2315

EP - 2318

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 7

ER -