Provable Mutual Benefits from Federated Learning in Privacy-Sensitive Domains

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Tsoy, Nikita, Mihalkova, Anna, Todorova, Teodora, Konstantinov, Nikola
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910687360450560
author Tsoy, Nikita
Mihalkova, Anna
Todorova, Teodora
Konstantinov, Nikola
author_facet Tsoy, Nikita
Mihalkova, Anna
Todorova, Teodora
Konstantinov, Nikola
contents Cross-silo federated learning (FL) allows data owners to train accurate machine learning models by benefiting from each others private datasets. Unfortunately, the model accuracy benefits of collaboration are often undermined by privacy defenses. Therefore, to incentivize client participation in privacy-sensitive domains, a FL protocol should strike a delicate balance between privacy guarantees and end-model accuracy. In this paper, we study the question of when and how a server could design a FL protocol provably beneficial for all participants. First, we provide necessary and sufficient conditions for the existence of mutually beneficial protocols in the context of mean estimation and convex stochastic optimization. We also derive protocols that maximize the total clients' utility, given symmetric privacy preferences. Finally, we design protocols maximizing end-model accuracy and demonstrate their benefits in synthetic experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2403_06672
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Provable Mutual Benefits from Federated Learning in Privacy-Sensitive Domains
Tsoy, Nikita
Mihalkova, Anna
Todorova, Teodora
Konstantinov, Nikola
Machine Learning
Cryptography and Security
Computer Science and Game Theory
Cross-silo federated learning (FL) allows data owners to train accurate machine learning models by benefiting from each others private datasets. Unfortunately, the model accuracy benefits of collaboration are often undermined by privacy defenses. Therefore, to incentivize client participation in privacy-sensitive domains, a FL protocol should strike a delicate balance between privacy guarantees and end-model accuracy. In this paper, we study the question of when and how a server could design a FL protocol provably beneficial for all participants. First, we provide necessary and sufficient conditions for the existence of mutually beneficial protocols in the context of mean estimation and convex stochastic optimization. We also derive protocols that maximize the total clients' utility, given symmetric privacy preferences. Finally, we design protocols maximizing end-model accuracy and demonstrate their benefits in synthetic experiments.
title Provable Mutual Benefits from Federated Learning in Privacy-Sensitive Domains
topic Machine Learning
Cryptography and Security
Computer Science and Game Theory
url https://arxiv.org/abs/2403.06672