An Active Learning Approach with Uncertainty, Representativeness, and Diversity

Authors:

Abstract
Big data from the Internet of Things may create big challenge for data classification. Most active learning approaches select either uncertain or representative unlabeled instances to query their labels. Although several active learning algorithms have been proposed to combine the two criteria for query selection, they are usually ad hoc in finding unlabeled instances that are both informative and representative and fail to take the diversity of instances into account. We address this challenge by presenting a new active learning framework which considers uncertainty, representativeness, and diversity creation. The proposed approach provides a systematic way for measuring and combining the uncertainty, representativeness, and diversity of an instance. Firstly, use instances’ uncertainty and representativeness to constitute the most informative set. Then, use the kernelk-means clustering algorithm to filter the redundant samples and the resulting samples are queried for labels. Extensive experimental results show that the proposed approach outperforms several state-of-the-art active learning approaches.
Funding Information
  • Natural Science Foundation of Jiangsu Province (BK2011376, SG201257, BE2012075, SKLCC2013XX, SXZ201302, KJS1329, SX201205, CXLX12 0810, 61070169, 61003054, 61170020, 13KJB520021)
  • Science and Technology Support Program of Suzhou (BK2011376, SG201257, BE2012075, SKLCC2013XX, SXZ201302, KJS1329, SX201205, CXLX12 0810, 61070169, 61003054, 61170020, 13KJB520021)
  • Science and Technology Support Program of Jiangsu Province (BK2011376, SG201257, BE2012075, SKLCC2013XX, SXZ201302, KJS1329, SX201205, CXLX12 0810, 61070169, 61003054, 61170020, 13KJB520021)
  • Suzhou Key Laboratory of Converged Communication (BK2011376, SG201257, BE2012075, SKLCC2013XX, SXZ201302, KJS1329, SX201205, CXLX12 0810, 61070169, 61003054, 61170020, 13KJB520021)
  • The Opening Project of Suzhou High-Tech Key Laboratory of Cloud Computing & Intelligent Information Processing (BK2011376, SG201257, BE2012075, SKLCC2013XX, SXZ201302, KJS1329, SX201205, CXLX12 0810, 61070169, 61003054, 61170020, 13KJB520021)
  • Provincial Key Laboratory for Computer Information Processing Technology (BK2011376, SG201257, BE2012075, SKLCC2013XX, SXZ201302, KJS1329, SX201205, CXLX12 0810, 61070169, 61003054, 61170020, 13KJB520021)
  • Open Fund of Jiangsu Province Software Engineering R&D Center (BK2011376, SG201257, BE2012075, SKLCC2013XX, SXZ201302, KJS1329, SX201205, CXLX12 0810, 61070169, 61003054, 61170020, 13KJB520021)
  • Jiangsu College Graduate Research and Innovation Plan (BK2011376, SG201257, BE2012075, SKLCC2013XX, SXZ201302, KJS1329, SX201205, CXLX12 0810, 61070169, 61003054, 61170020, 13KJB520021)
  • National Natural Science Foundation of China (BK2011376, SG201257, BE2012075, SKLCC2013XX, SXZ201302, KJS1329, SX201205, CXLX12 0810, 61070169, 61003054, 61170020, 13KJB520021)
  • National Natural Science Foundation of China (BK2011376, SG201257, BE2012075, SKLCC2013XX, SXZ201302, KJS1329, SX201205, CXLX12 0810, 61070169, 61003054, 61170020, 13KJB520021)
  • National Natural Science Foundation of China (BK2011376, SG201257, BE2012075, SKLCC2013XX, SXZ201302, KJS1329, SX201205, CXLX12 0810, 61070169, 61003054, 61170020, 13KJB520021)
  • Jiangsu Province Colleges and Universities Natural Science Research Project (BK2011376, SG201257, BE2012075, SKLCC2013XX, SXZ201302, KJS1329, SX201205, CXLX12 0810, 61070169, 61003054, 61170020, 13KJB520021)

This publication has 5 references indexed in Scilit: