Joint structure feature exploration and regularization for multi-task graph classification

Shirui Pan, Jia Wu, Xingquan Zhuy, Chengqi Zhang, Philip S. Yuz

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contribution

3 Citations (Scopus)

Abstract

We formulate a new multi-task graph classification (MTG) problem, where multiple graph classification tasks are jointly regularized to find discriminative subgraphs shared by all tasks for learning. More details can be found in [1].

Original languageEnglish
Title of host publicationICDE 2016
Subtitle of host publicationProceedings of the 2016 IEEE 32nd International Conference on Data Engineering
Place of PublicationPiscataway, NJ
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages1474-1475
Number of pages2
ISBN (Electronic)9781509020201
DOIs
Publication statusPublished - 22 Jun 2016
Externally publishedYes
Event32nd IEEE International Conference on Data Engineering, ICDE 2016 - Helsinki, Finland
Duration: 16 May 201620 May 2016

Conference

Conference32nd IEEE International Conference on Data Engineering, ICDE 2016
CountryFinland
CityHelsinki
Period16/05/1620/05/16

Fingerprint Dive into the research topics of 'Joint structure feature exploration and regularization for multi-task graph classification'. Together they form a unique fingerprint.

  • Cite this

    Pan, S., Wu, J., Zhuy, X., Zhang, C., & Yuz, P. S. (2016). Joint structure feature exploration and regularization for multi-task graph classification. In ICDE 2016: Proceedings of the 2016 IEEE 32nd International Conference on Data Engineering (pp. 1474-1475). Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ICDE.2016.7498381