微信服务号

微信订阅号

2025-4-24- 8
Home > Archive>Volume 32, Issue 3, 2021 >669-688. DOI:10.13328/j.cnki.jos.006174
PDF HTML XML Export Cite reminder
Cross-Silo Federated Learning-to-Rank
Author:
Affiliation:

Fund Project:

National Key Research and Development Program of China (2018AAA0101100); National Natural Science Foundation of China (61822201, U1811463); State Key Laboratory of Software Development Environment (Beihang University) Open Program (SKLSDE-2020ZX-15)

  • Article
    • | |
  • Metrics
    • |
  • Reference
    • |
  • Related
    • |
  • Cited by
    • | |
  • Comments
    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 progress in federated learning, a novel framework is proposed named cross-silo federated learning-to-rank (CS-F-LTR), which addresses two unique challenges faced by LTR when applied it to federated scenario. In order to deal with the cross-party feature generation problem, CS-F-LTR utilizes a sketch and differential privacy based method, which is much more efficient than encryption-based protocols meanwhile the accuracy loss is still guaranteed. To tackle with the missing label problem, CS-F-LTR relies on a semi-supervised learning mechanism that facilitates fast labeling with mutual labelers. Extensive experiments conducted on public datasets verify the effectiveness of the proposed framework.

    Reference
    Related
    Cited by
Get Citation

史鼎元,王晏晟,郑鹏飞,童咏昕.面向企业数据孤岛的联邦排序学习.软件学报,2021,32(3):669-688

Copy
Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:July 19,2020
  • Revised:September 03,2020
  • Online: January 21,2021
  • Published: March 06,2021
Links:Institute of Software, CASChina Computer FederationCASNSFC
You are the first2037977Visitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-4
Address：4# South Fourth Street, Zhong Guan Cun, Beijing 100190,Postal Code：100190
Phone：010-62562563 Fax：010-62562533 Email：jos@iscas.ac.cn
Technical Support：Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063