Online heterogeneous transfer by hedge ensemble of offline and online decisions

Yuguang Yan, Qingyao Wu*, Mingkui Tan, Kwok Po NG, Huaqing Min, Ivor W. Tsang

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

46 Citations (Scopus)

Abstract

In this paper, we study the online heterogeneous transfer (OHT) learning problem, where the target data of interest arrive in an online manner, while the source data and auxiliary co-occurrence data are from offline sources and can be easily annotated. OHT is very challenging, since the feature spaces of the source and target domains are different. To address this, we propose a novel technique called OHT by hedge ensemble by exploiting both offline knowledge and online knowledge of different domains. To this end, we build an offline decision function based on a heterogeneous similarity that is constructed using labeled source data and unlabeled auxiliary co-occurrence data. After that, an online decision function is learned from the target data. Last, we employ a hedge weighting strategy to combine the offline and online decision functions to exploit knowledge from the source and target domains of different feature spaces. We also provide a theoretical analysis regarding the mistake bounds of the proposed approach. Comprehensive experiments on three real-world data sets demonstrate the effectiveness of the proposed technique.

Original languageEnglish
Pages (from-to)3252-3263
Number of pages12
JournalIEEE Transactions on Neural Networks and Learning Systems
Volume29
Issue number7
DOIs
Publication statusPublished - Jul 2018

Scopus Subject Areas

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence

User-Defined Keywords

  • Co-occurrence data
  • hedge weighting
  • heterogeneous transfer learning (HTL)
  • online learning

Fingerprint

Dive into the research topics of 'Online heterogeneous transfer by hedge ensemble of offline and online decisions'. Together they form a unique fingerprint.

Cite this