Learning from Label and Feature Heterogeneity

Pei Yang, Jingrui He, Hongxia Yang, Haoda Fu

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

7 Scopus citations

Abstract

Multiple types of heterogeneity, such as label heterogeneity and feature heterogeneity, often co-exist in many real-world data mining applications, such as news article categorization, gene functionality prediction. To effectively leverage such heterogeneity, in this paper, we propose a novel graph-based framework for Learning with both Label and Feature heterogeneities, namely L2F. It models the label correlation by requiring that any two label-specific classifiers behave similarly on the same views if the associated labels are similar, and imposes the view consistency by requiring that view-based classifiers generate similar predictions on the same examples. To solve the resulting optimization problem, we propose an iterative algorithm, which is guaranteed to converge to the global optimum. Furthermore, we analyze its generalization performance based on Rademacher complexity, which sheds light on the benefits of jointly modeling the label and feature heterogeneity. Experimental results on various data sets show the effectiveness of the proposed approach.

Original languageEnglish (US)
Title of host publicationProceedings - 14th IEEE International Conference on Data Mining, ICDM 2014
EditorsRavi Kumar, Hannu Toivonen, Jian Pei, Joshua Zhexue Huang, Xindong Wu
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1079-1084
Number of pages6
EditionJanuary
ISBN (Electronic)9781479943029
DOIs
StatePublished - Jan 1 2014
Event14th IEEE International Conference on Data Mining, ICDM 2014 - Shenzhen, China
Duration: Dec 14 2014Dec 17 2014

Publication series

NameProceedings - IEEE International Conference on Data Mining, ICDM
NumberJanuary
Volume2015-January
ISSN (Print)1550-4786

Other

Other14th IEEE International Conference on Data Mining, ICDM 2014
CountryChina
CityShenzhen
Period12/14/1412/17/14

Keywords

  • Rademacher complexity
  • heterogeneity
  • multi-label learning
  • multi-view learning

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint Dive into the research topics of 'Learning from Label and Feature Heterogeneity'. Together they form a unique fingerprint.

  • Cite this

    Yang, P., He, J., Yang, H., & Fu, H. (2014). Learning from Label and Feature Heterogeneity. In R. Kumar, H. Toivonen, J. Pei, J. Zhexue Huang, & X. Wu (Eds.), Proceedings - 14th IEEE International Conference on Data Mining, ICDM 2014 (January ed., pp. 1079-1084). [7023450] (Proceedings - IEEE International Conference on Data Mining, ICDM; Vol. 2015-January, No. January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICDM.2014.42