Skip to main navigation Skip to search Skip to main content

A peer learning method for building robust text classification models

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

Abstract

Classification is an essential task in many practical problems. A machine learning based classification model is built to minimize the error between actual labels and predicted labels generated by the model. When the model depends on only actual labels during the training, it can generate monotonous distributional predictions. In order to make a robust model, it needs to use other sources of information in addition to the original labels. To address this issue, we propose a peer learning method that enables the target model to reference multiple peer models and that can control the impact of peers on the target model during the training phase. The experiment results indicate that the proposed method is promising.

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE International Conference on Big Data and Smart Computing, BigComp 2021
EditorsHerwig Unger, Jinho Kim, U Kang, Chakchai So-In, Junping Du, Walid Saad, Young-guk Ha, Christian Wagner, Julien Bourgeois, Chanboon Sathitwiriyawong, Hyuk-Yoon Kwon, Carson Leung
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages321-324
Number of pages4
ISBN (Electronic)9781728189246
DOIs
StatePublished - Jan 2021
Event2021 IEEE International Conference on Big Data and Smart Computing, BigComp 2021 - Jeju Island, Korea, Republic of
Duration: 17 Jan 202120 Jan 2021

Publication series

NameProceedings - 2021 IEEE International Conference on Big Data and Smart Computing, BigComp 2021

Conference

Conference2021 IEEE International Conference on Big Data and Smart Computing, BigComp 2021
Country/TerritoryKorea, Republic of
CityJeju Island
Period17/01/2120/01/21

Keywords

  • Classification
  • Deep learning
  • Label refinery
  • Peer learning

Fingerprint

Dive into the research topics of 'A peer learning method for building robust text classification models'. Together they form a unique fingerprint.

Cite this