Knowledge Network Node
Journal of Software. 2021, (03) Core

Cross-Silo Federated Learning-to-RankChinese Full Text

SHI Ding-Yuan;WANG Yan-Sheng;ZHENG Peng-Fei;TONG Yong-Xin;State Key Laboratory of Software Development Enviroment (Beihang University);Beijing Advanced Innovation Center for Big Data and Brain Computing (Beihang University);School of Computer Science and Engineering, Beihang University;

Abstract: Learning-to-rank（LTR） model has made a remarkable achievement. However, traditional training scheme for LTR model requires large amount of text data. Considering the increasing concerns about privacy protection, it is becoming infeasible to collect text data from multiple data owners as before, and thus data is forced to save separately. The separation turns data owners into data silos, among which the data can hardly exchange, causing LTR training severely compromised. Inspired by the recent pr... More
Keywords：

learning-to-rank; data silo; federated learning; sketch; differential privacy;

  • DOI：

    10.13328/j.cnki.jos.006174

  • Series：

    (I) Electronic Technology ＆ Information Science; (J) Economics ＆ Management

  • Subject：

    Computer Software and Application of Computer; Automation Technology; Enterprise Economy

  • Classification Code：

    TP181;F270.7

Download the mobile appuse the app to scan this coderead the article.

Tips: Please download CAJViewer to view CAJ format full text.

Download: 1062 Page: 669-688 Pagecount: 20 Size: 969K

Related Literature
  • Similar Article
  • Reader Recommendation
  • Associated Author