Information-theoretic privacy in federated submodel learning
We consider information-theoretic privacy in federated submodel learning, where a global server has multiple submodels. Compared to the privacy considered in the conventional federated submodel learning where secure aggregation is adopted for ensuring privacy, information-theoretic privacy provides...
Main Authors: | Minchul Kim, Jungwoo Lee |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-06-01
|
Series: | ICT Express |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2405959522000297 |
Similar Items
-
An Information-Theoretic Analysis of the Cost of Decentralization for Learning and Inference under Privacy Constraints
by: Sharu Theresa Jose, et al.
Published: (2022-03-01) -
Privatized graph federated learning
by: Elsa Rizk, et al.
Published: (2023-08-01) -
Reliability Assessment of Thermocompressed Epoxy Molding Compound through Glass via Interposer Architecture by the Submodeling Simulation Approach
by: Shih-Hung Wang, et al.
Published: (2022-10-01) -
Improving Texture Prediction by Increasing Mesh Resolution in Submodel: A Crystal Plasticity FE Study and Experiment Verification
by: Yu Liu, et al.
Published: (2023-05-01) -
Improved Information-Theoretic Generalization Bounds for Distributed, Federated, and Iterative Learning
by: Leighton Pate Barnes, et al.
Published: (2022-08-01)