A feature-enhanced ranking-based classifier for multimodal data and heterogeneous information networks

Scott Deeann Chen, Ying Yu Chen, Jiawei Han, Pierre Moulin

Research output: Contribution to journalConference article

Abstract

We propose a heterogeneous information network mining algorithm: feature-enhanced Rank Class (F-Rank Class). F-Rank Class extends Rank Class to a unified classification framework that can be applied to binary or multiclass classification of unimodal or multimodal data. We experimented on a multimodal document dataset, 2008/9 Wikipedia Selection for Schools. For unimodal classification, F-Rank Class is compared to support vector machines (SVMs). F-Rank Class provides improvements up to 27.3% on the Wikipedia dataset. For multimodal document classification, F-Rank Class shows improvements up to 19.7% in accuracy when compared to SVM-based meta-classifiers. We also study 1) how the structure of the network and 2) how the choice of parameters affect the classification results.

Original languageEnglish (US)
Article number6729588
Pages (from-to)997-1002
Number of pages6
JournalProceedings - IEEE International Conference on Data Mining, ICDM
DOIs
StatePublished - Dec 1 2013
Event13th IEEE International Conference on Data Mining, ICDM 2013 - Dallas, TX, United States
Duration: Dec 7 2013Dec 10 2013

Fingerprint

Classifiers
Support vector machines

Keywords

  • classification
  • heterogeneous information network
  • multimodal
  • ranking

ASJC Scopus subject areas

  • Engineering(all)

Cite this

A feature-enhanced ranking-based classifier for multimodal data and heterogeneous information networks. / Chen, Scott Deeann; Chen, Ying Yu; Han, Jiawei; Moulin, Pierre.

In: Proceedings - IEEE International Conference on Data Mining, ICDM, 01.12.2013, p. 997-1002.

Research output: Contribution to journalConference article

@article{60fa7e3f413b4b6f9b014576ae5f0f71,
title = "A feature-enhanced ranking-based classifier for multimodal data and heterogeneous information networks",
abstract = "We propose a heterogeneous information network mining algorithm: feature-enhanced Rank Class (F-Rank Class). F-Rank Class extends Rank Class to a unified classification framework that can be applied to binary or multiclass classification of unimodal or multimodal data. We experimented on a multimodal document dataset, 2008/9 Wikipedia Selection for Schools. For unimodal classification, F-Rank Class is compared to support vector machines (SVMs). F-Rank Class provides improvements up to 27.3{\%} on the Wikipedia dataset. For multimodal document classification, F-Rank Class shows improvements up to 19.7{\%} in accuracy when compared to SVM-based meta-classifiers. We also study 1) how the structure of the network and 2) how the choice of parameters affect the classification results.",
keywords = "classification, heterogeneous information network, multimodal, ranking",
author = "Chen, {Scott Deeann} and Chen, {Ying Yu} and Jiawei Han and Pierre Moulin",
year = "2013",
month = "12",
day = "1",
doi = "10.1109/ICDM.2013.71",
language = "English (US)",
pages = "997--1002",
journal = "Proceedings - IEEE International Conference on Data Mining, ICDM",
issn = "1550-4786",

}

TY - JOUR

T1 - A feature-enhanced ranking-based classifier for multimodal data and heterogeneous information networks

AU - Chen, Scott Deeann

AU - Chen, Ying Yu

AU - Han, Jiawei

AU - Moulin, Pierre

PY - 2013/12/1

Y1 - 2013/12/1

N2 - We propose a heterogeneous information network mining algorithm: feature-enhanced Rank Class (F-Rank Class). F-Rank Class extends Rank Class to a unified classification framework that can be applied to binary or multiclass classification of unimodal or multimodal data. We experimented on a multimodal document dataset, 2008/9 Wikipedia Selection for Schools. For unimodal classification, F-Rank Class is compared to support vector machines (SVMs). F-Rank Class provides improvements up to 27.3% on the Wikipedia dataset. For multimodal document classification, F-Rank Class shows improvements up to 19.7% in accuracy when compared to SVM-based meta-classifiers. We also study 1) how the structure of the network and 2) how the choice of parameters affect the classification results.

AB - We propose a heterogeneous information network mining algorithm: feature-enhanced Rank Class (F-Rank Class). F-Rank Class extends Rank Class to a unified classification framework that can be applied to binary or multiclass classification of unimodal or multimodal data. We experimented on a multimodal document dataset, 2008/9 Wikipedia Selection for Schools. For unimodal classification, F-Rank Class is compared to support vector machines (SVMs). F-Rank Class provides improvements up to 27.3% on the Wikipedia dataset. For multimodal document classification, F-Rank Class shows improvements up to 19.7% in accuracy when compared to SVM-based meta-classifiers. We also study 1) how the structure of the network and 2) how the choice of parameters affect the classification results.

KW - classification

KW - heterogeneous information network

KW - multimodal

KW - ranking

UR - http://www.scopus.com/inward/record.url?scp=84894679778&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84894679778&partnerID=8YFLogxK

U2 - 10.1109/ICDM.2013.71

DO - 10.1109/ICDM.2013.71

M3 - Conference article

AN - SCOPUS:84894679778

SP - 997

EP - 1002

JO - Proceedings - IEEE International Conference on Data Mining, ICDM

JF - Proceedings - IEEE International Conference on Data Mining, ICDM

SN - 1550-4786

M1 - 6729588

ER -