Tsukada Lab. Computer Network Group

A Comprehensive Survey on Privacy-Preserving Techniques in Federated Recommendation Systems

Muhammad Asad, Saima Shaukat, Ehsan Javanmardi, Jin Nakazato, Manabu Tsukada

Applied Sciences, May 18, 2023

Summary in three lines

  • The survey examines federated learning for recommender systems that rely on sensitive user information.
  • Participants train shared models using intermediate parameters while retaining raw data locally.
  • It reviews privacy protection methods, remaining research issues, and potential directions.

Figures from the paper

Figure 1: Training a federated recommender system
Figure 1. Training a federated recommender systemSource: Figure 1 from Asad et al., Applied Sciences, 2023 (© 2023 The Authors, CC BY 4.0, publisher version)Client devices update local models and share intermediate updates with a cloud aggregator.

Abstract

Big data is a rapidly growing field, and new developments are constantly emerging to address various challenges. One such development is the use of federated learning for recommendation systems (FRSs). An FRS provides a way to protect user privacy by training recommendation models using intermediate parameters instead of real user data. This approach allows for cooperation between data platforms while still complying with privacy regulations. In this paper, we explored the current state of research on FRSs, highlighting existing research issues and possible solutions. Specifically, we looked at how FRSs can be used to protect user privacy while still allowing organizations to benefit from the data they share. Additionally, we examined potential applications of FRSs in the context of big data, exploring how these systems can be used to facilitate secure data sharing and collaboration. Finally, we discuss the challenges associated with developing and deploying FRSs in the real world and how these challenges can be addressed.

How to cite

M. Asad, S. Shaukat, E. Javanmardi, J. Nakazato, and M. Tsukada, “A Comprehensive Survey on Privacy-Preserving Techniques in Federated Recommendation Systems,” Applied Sciences, 2023, doi: 10.3390/app13106201.

BibTeX

@article{Asad2023,
  title         = {A Comprehensive Survey on Privacy-Preserving Techniques in Federated  Recommendation Systems},
  author        = {Muhammad Asad and Saima Shaukat and Ehsan Javanmardi and Jin Nakazato and Manabu Tsukada},
  doi           = {10.3390/app13106201},
  issn          = {2076-3417},
  year          = {2023},
  date          = {2023-05-18},
  urldate       = {2023-05-18},
  journal       = {Applied Sciences},
  abstract      = {Big data is a rapidly growing field, and new developments are constantly emerging to address various challenges. One such development is the use of federated learning for recommendation systems (FRSs). An FRS provides a way to protect user privacy by training recommendation models using intermediate parameters instead of real user data. This approach allows for cooperation between data platforms while still complying with privacy regulations. In this paper, we explored the current state of research on FRSs, highlighting existing research issues and possible solutions. Specifically, we looked at how FRSs can be used to protect user privacy while still allowing organizations to benefit from the data they share. Additionally, we examined potential applications of FRSs in the context of big data, exploring how these systems can be used to facilitate secure data sharing and collaboration. Finally, we discuss the challenges associated with developing and deploying FRSs in the real world and how these challenges can be addressed.},
  keywords      = {},
  pubstate      = {published},
  tppubtype     = {article}
}