Options
Local distribution privacy in federated learning
Publikationstyp
Conference Paper
Date Issued
2024-07-01
Sprache
English
Volume
1138 SCI
Start Page
9
End Page
12
Citation
16th International Symposium on Intelligent Distributed Computing, IDC 2023
Contribution to Conference
Publisher DOI
Scopus ID
Publisher
Springer
ISSN
1860949X
ISBN
9783031600227
Privacy is a well-researched area in the context of Federated Learning. Typically, ensuring privacy means that individual data used for local training cannot be reconstructed by other local learners or a central server. Thus, it is the individual data points that should be private, but not the entire distribution of locally available data. In many cases, this makes sense because each data point comes from a different individual while all data points originate from a common global distribution. In this position paper, we address a more challenging task where the privacy of each local data distribution must be preserved. This is relevant for use cases where there is a one-to-one mapping from local learners to users, such as when each local learner is part of a personalized assistant on a smartphone. We provide a definition of this problem case, describe the challenges that need to be addressed, and formulate a possible approach to solve the problem.
Subjects
Federated Learning
Local Distribution Privacy
Mutual Information
DDC Class
004: Computer Sciences