Age Aware Scheduling for Differentially-Private Federated Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Lin, Kuan-Yu, Lin, Hsuan-Yin, Hsu, Yu-Pin, Huang, Yu-Chih
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911945219637248
author Lin, Kuan-Yu
Lin, Hsuan-Yin
Hsu, Yu-Pin
Huang, Yu-Chih
author_facet Lin, Kuan-Yu
Lin, Hsuan-Yin
Hsu, Yu-Pin
Huang, Yu-Chih
contents This paper explores differentially-private federated learning (FL) across time-varying databases, delving into a nuanced three-way tradeoff involving age, accuracy, and differential privacy (DP). Emphasizing the potential advantages of scheduling, we propose an optimization problem aimed at meeting DP requirements while minimizing the loss difference between the aggregated model and the model obtained without DP constraints. To harness the benefits of scheduling, we introduce an age-dependent upper bound on the loss, leading to the development of an age-aware scheduling design. Simulation results underscore the superior performance of our proposed scheme compared to FL with classic DP, which does not consider scheduling as a design factor. This research contributes insights into the interplay of age, accuracy, and DP in federated learning, with practical implications for scheduling strategies.
format Preprint
id arxiv_https___arxiv_org_abs_2405_05962
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Age Aware Scheduling for Differentially-Private Federated Learning
Lin, Kuan-Yu
Lin, Hsuan-Yin
Hsu, Yu-Pin
Huang, Yu-Chih
Machine Learning
Cryptography and Security
Distributed, Parallel, and Cluster Computing
This paper explores differentially-private federated learning (FL) across time-varying databases, delving into a nuanced three-way tradeoff involving age, accuracy, and differential privacy (DP). Emphasizing the potential advantages of scheduling, we propose an optimization problem aimed at meeting DP requirements while minimizing the loss difference between the aggregated model and the model obtained without DP constraints. To harness the benefits of scheduling, we introduce an age-dependent upper bound on the loss, leading to the development of an age-aware scheduling design. Simulation results underscore the superior performance of our proposed scheme compared to FL with classic DP, which does not consider scheduling as a design factor. This research contributes insights into the interplay of age, accuracy, and DP in federated learning, with practical implications for scheduling strategies.
title Age Aware Scheduling for Differentially-Private Federated Learning
topic Machine Learning
Cryptography and Security
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2405.05962