Vertical Federated Learning for Privacy-Preserving ML Model Development in Partially Disaggregated Networks
Nazila Hashemi, Pooyan Safari, Behnam Shariati, Johannes Fischer
Abstract
We present a novel framework that enables vendors and operators, with partial access to operational and monitoring features of a service, to collaboratively develop a ML-assisted solution without revealing any business-critical raw data to each other. We validate our proposal for a QoT estimation use-case.
Topics & Concepts
Computer scienceRaw dataService (business)Information privacyService providerData modelingDevelopment (topology)Computer securityDatabaseBusinessMathematicsMathematical analysisMarketingProgramming languagePrivacy-Preserving Technologies in DataCryptography and Data SecurityMobile Crowdsensing and Crowdsourcing