Training deep neural networks on imbalanced data sets

Shoujin Wang, Wei Liu, Jia Wu, Longbing Cao, Qinxue Meng, Paul J. Kennedy

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

119 Citations (Scopus)

Abstract

Deep learning has become increasingly popular in both academic and industrial areas in the past years. Various domains including pattern recognition, computer vision, and natural language processing have witnessed the great power of deep networks. However, current studies on deep learning mainly focus on data sets with balanced class labels, while its performance on imbalanced data is not well examined. Imbalanced data sets exist widely in real world and they have been providing great challenges for classification tasks. In this paper, we focus on the problem of classification using deep network on imbalanced data sets. Specifically, a novel loss function called mean false error together with its improved version mean squared false error are proposed for the training of deep networks on imbalanced data sets. The proposed method can effectively capture classification errors from both majority class and minority class equally. Experiments and comparisons demonstrate the superiority of the proposed approach compared with conventional methods in classifying imbalanced data sets on deep neural networks.

Original languageEnglish
Title of host publicationIJCNN 2016
Subtitle of host publicationProceedings of the 2016 International Joint Conference on Neural Networks
Place of PublicationPiscataway, NJ
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages4368-4374
Number of pages7
ISBN (Electronic)9781509006205, 9781509006199
ISBN (Print)9781509006212
DOIs
Publication statusPublished - 31 Oct 2016
Externally publishedYes
Event2016 International Joint Conference on Neural Networks, IJCNN 2016 - Vancouver, Canada
Duration: 24 Jul 201629 Jul 2016

Conference

Conference2016 International Joint Conference on Neural Networks, IJCNN 2016
CountryCanada
CityVancouver
Period24/07/1629/07/16

Keywords

  • Data imbalance
  • Deep neural network
  • Loss function

Fingerprint Dive into the research topics of 'Training deep neural networks on imbalanced data sets'. Together they form a unique fingerprint.

Cite this