Best first over-sampling for multilabel classification

Xusheng Ai, Jian Wu, Victor S. Sheng, Yufeng Yao, Pengpeng Zhao, Zhiming Cui

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

2 Scopus citations

Abstract

Learning from imbalanced multilabel data is a challenging task. It has attracted considerable attention recently. In this paper we propose a MultiLabel Best First Over-sampling (ML-BFO) to improve the performance of multilabel classification algorithms, based on imbalance minimization and Wilson's ENN rule. Our experimental results show that ML-BFO not only duplicates fewer samples but also reduces the imbalance level much more than two state-of-the-art multilabel sampling methods, i.e., an over-sampling method LP-ROS and an under-sampling method MLeNN. Besides, ML-BFO significantly improves the performance of multilabel classification algorithms, and performs much better than LP-ROS and MLeNN.

Original languageEnglish
Title of host publicationCIKM 2015 - Proceedings of the 24th ACM International Conference on Information and Knowledge Management
PublisherAssociation for Computing Machinery
Pages1803-1806
Number of pages4
ISBN (Electronic)9781450337946
DOIs
StatePublished - Oct 17 2015
Event24th ACM International Conference on Information and Knowledge Management, CIKM 2015 - Melbourne, Australia
Duration: Oct 19 2015Oct 23 2015

Publication series

NameInternational Conference on Information and Knowledge Management, Proceedings
Volume19-23-Oct-2015

Conference

Conference24th ACM International Conference on Information and Knowledge Management, CIKM 2015
Country/TerritoryAustralia
CityMelbourne
Period10/19/1510/23/15

Keywords

  • Heuristic
  • Multilabel learning
  • Resampling

Fingerprint

Dive into the research topics of 'Best first over-sampling for multilabel classification'. Together they form a unique fingerprint.

Cite this