Federated Learning With Individualized Privacy Through Client Sampling

2025/01/29 by Lucas Lange, Lange, Lucas, Ole Borchardt +3
Computer Science · Social Sciences · #Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Internet Traffic Analysis and Secure E-voting #Machine Learning (cs.LG) #Privacy, Security, and Data Protection #Privacy-Preserving Technologies in Data

paper · pdf · doi:10.48550/arxiv.2501.17634

openalex publication_date 2025/01/29 · openalex created_date 2025/01/31 · openalex updated_date 2026/08/02

Abstract

Custom federated versions of SVHN and CIFAR-10 datasets used for the experiments in: Federated Learning With Individualized Privacy Through Client SamplingPlease cite this paper as reference. Further descriptions found in the paper(s).

Related

• Optimal Client Sampling in Federated Learning with Client-Level Heterogeneous Differential Privacy
• Federated Learning with Heterogeneous Differential Privacy
• Cross-silo Federated Learning with Record-level Personalized Differential Privacy
• A Game-Theoretic Framework for Privacy-Aware Client Sampling in Federated Learning
• Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation