Multi-graph-view learning for complicated object classification

Jia Wu, Shirui Pan, Xingquan Zhu, Zhihua Cai, Chengqi Zhang

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

In this paper, we propose to represent and classify complicated objects. In order to represent the objects, we propose a multi-graph-view model which uses graphs constructed from multiple graph-views to represent an object. In addition, a bag based multi-graph model is further used to relax labeling by only requiring one label for a bag of graphs, which represent one object. In order to learn classification models, we propose a multi-graph-view bag learning algorithm (MGVBL), which aims to explore subgraph features from multiple graphviews for learning. By enabling a joint regularization across multiple graph-views, and enforcing labeling constraints at the bag and graph levels, MGVBL is able to discover most effective subgraph features across all graph-views for learning. Experiments on real-world learning tasks demonstrate the performance of MGVBL for complicated object classification.

Original languageEnglish
Title of host publicationProceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence
EditorsQiang Yang, Michael Wooldridge
Place of PublicationPalo Alto CA USA
PublisherInternational Joint Conferences on Artificial Intelligence
Pages3953-3959
Number of pages7
ISBN (Electronic)9781577357384
Publication statusPublished - 2015
Externally publishedYes
EventInternational Joint Conference on Artificial Intelligence 2015 - Buenos Aires, Argentina
Duration: 25 Jul 20151 Aug 2015
Conference number: 24th
https://www.ijcai-15.org/index.php?option=com_content&view=article&id=71:call-for-papers&catid=9:uncategorised&Itemid=477

Conference

ConferenceInternational Joint Conference on Artificial Intelligence 2015
Abbreviated titleIJCAI 2015
CountryArgentina
CityBuenos Aires
Period25/07/151/08/15
Internet address

Cite this

Wu, J., Pan, S., Zhu, X., Cai, Z., & Zhang, C. (2015). Multi-graph-view learning for complicated object classification. In Q. Yang, & M. Wooldridge (Eds.), Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence (pp. 3953-3959). Palo Alto CA USA: International Joint Conferences on Artificial Intelligence.
Wu, Jia ; Pan, Shirui ; Zhu, Xingquan ; Cai, Zhihua ; Zhang, Chengqi. / Multi-graph-view learning for complicated object classification. Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence . editor / Qiang Yang ; Michael Wooldridge. Palo Alto CA USA : International Joint Conferences on Artificial Intelligence, 2015. pp. 3953-3959
@inproceedings{6225f0dcc5ef4c8e82c28e8e2c5716d3,
title = "Multi-graph-view learning for complicated object classification",
abstract = "In this paper, we propose to represent and classify complicated objects. In order to represent the objects, we propose a multi-graph-view model which uses graphs constructed from multiple graph-views to represent an object. In addition, a bag based multi-graph model is further used to relax labeling by only requiring one label for a bag of graphs, which represent one object. In order to learn classification models, we propose a multi-graph-view bag learning algorithm (MGVBL), which aims to explore subgraph features from multiple graphviews for learning. By enabling a joint regularization across multiple graph-views, and enforcing labeling constraints at the bag and graph levels, MGVBL is able to discover most effective subgraph features across all graph-views for learning. Experiments on real-world learning tasks demonstrate the performance of MGVBL for complicated object classification.",
author = "Jia Wu and Shirui Pan and Xingquan Zhu and Zhihua Cai and Chengqi Zhang",
year = "2015",
language = "English",
pages = "3953--3959",
editor = "Qiang Yang and Michael Wooldridge",
booktitle = "Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence",
publisher = "International Joint Conferences on Artificial Intelligence",

}

Wu, J, Pan, S, Zhu, X, Cai, Z & Zhang, C 2015, Multi-graph-view learning for complicated object classification. in Q Yang & M Wooldridge (eds), Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence . International Joint Conferences on Artificial Intelligence, Palo Alto CA USA, pp. 3953-3959, International Joint Conference on Artificial Intelligence 2015, Buenos Aires, Argentina, 25/07/15.

Multi-graph-view learning for complicated object classification. / Wu, Jia; Pan, Shirui; Zhu, Xingquan; Cai, Zhihua; Zhang, Chengqi.

Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence . ed. / Qiang Yang; Michael Wooldridge. Palo Alto CA USA : International Joint Conferences on Artificial Intelligence, 2015. p. 3953-3959.

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

TY - GEN

T1 - Multi-graph-view learning for complicated object classification

AU - Wu, Jia

AU - Pan, Shirui

AU - Zhu, Xingquan

AU - Cai, Zhihua

AU - Zhang, Chengqi

PY - 2015

Y1 - 2015

N2 - In this paper, we propose to represent and classify complicated objects. In order to represent the objects, we propose a multi-graph-view model which uses graphs constructed from multiple graph-views to represent an object. In addition, a bag based multi-graph model is further used to relax labeling by only requiring one label for a bag of graphs, which represent one object. In order to learn classification models, we propose a multi-graph-view bag learning algorithm (MGVBL), which aims to explore subgraph features from multiple graphviews for learning. By enabling a joint regularization across multiple graph-views, and enforcing labeling constraints at the bag and graph levels, MGVBL is able to discover most effective subgraph features across all graph-views for learning. Experiments on real-world learning tasks demonstrate the performance of MGVBL for complicated object classification.

AB - In this paper, we propose to represent and classify complicated objects. In order to represent the objects, we propose a multi-graph-view model which uses graphs constructed from multiple graph-views to represent an object. In addition, a bag based multi-graph model is further used to relax labeling by only requiring one label for a bag of graphs, which represent one object. In order to learn classification models, we propose a multi-graph-view bag learning algorithm (MGVBL), which aims to explore subgraph features from multiple graphviews for learning. By enabling a joint regularization across multiple graph-views, and enforcing labeling constraints at the bag and graph levels, MGVBL is able to discover most effective subgraph features across all graph-views for learning. Experiments on real-world learning tasks demonstrate the performance of MGVBL for complicated object classification.

UR - http://www.scopus.com/inward/record.url?scp=84949758172&partnerID=8YFLogxK

M3 - Conference Paper

SP - 3953

EP - 3959

BT - Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence

A2 - Yang, Qiang

A2 - Wooldridge, Michael

PB - International Joint Conferences on Artificial Intelligence

CY - Palo Alto CA USA

ER -

Wu J, Pan S, Zhu X, Cai Z, Zhang C. Multi-graph-view learning for complicated object classification. In Yang Q, Wooldridge M, editors, Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence . Palo Alto CA USA: International Joint Conferences on Artificial Intelligence. 2015. p. 3953-3959