A Task-Driven Privacy-Preserving Data-Sharing Framework for the Industrial Internet

Simple item page
dc.contributor.authorShojaee, Parshinen
dc.contributor.authorZeng, Yingyanen
dc.contributor.authorWahed, Muntasiren
dc.contributor.authorSeth, Avien
dc.contributor.authorJin, Ranen
dc.contributor.authorLourentzou, Isminien
dc.date.accessioned2023-02-08T13:10:40Zen
dc.date.available2023-02-08T13:10:40Zen
dc.date.filed2022-04-07en
dc.date.issued2023-01en
dc.date.updated2023-02-07T20:37:41Zen
dc.description.abstractIndustrial Internet provides a collaborative computational platform for participating enterprises, allowing the collection of big data for machine learning tasks. Despite the promise of training and deployment acceleration, and the potential to optimize decision-making processes through data-sharing, the adoption of such technologies is impacted by the increasing concerns about information privacy. As enterprises prefer to keep data private, this limits interoperability. While prior work has largely explored privacy-preserving mechanisms, the proposed methods naively average or randomly sample data shared from all participants instead of selecting the most well-suited subsets for a particular downstream learning task. Motivated by the lack of effective data-sharing mechanisms for heterogeneous machine learning tasks in Industrial Internet, we propose PriED, a task-driven data-sharing framework that selectively fuses shared data and local data from participants to improve supervised learning performance. PriED utilizes privacy-preserving data distillation to facilitate data exchange, and dynamic data selection to optimize downstream machine learning tasks. We demonstrate performance improvements on a real semiconductor manufacturing case study.en
dc.format.mimetypeapplication/pdfen
dc.identifier.orcidJin, Ran [0000-0003-3847-4538]en
dc.identifier.urihttp://hdl.handle.net/10919/113725en
dc.language.isoenen
dc.rightsIn Copyrighten
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subjectAttentionen
dc.subjectData sharingen
dc.subjectData distillationen
dc.subjectIndustrial interneten
dc.subjectReinforcement learningen
dc.titleA Task-Driven Privacy-Preserving Data-Sharing Framework for the Industrial Interneten
dc.typeArticle - Refereeden
dc.type.dcmitypeTexten
pubs.organisational-group/Virginia Techen
pubs.organisational-group/Virginia Tech/Engineeringen
pubs.organisational-group/Virginia Tech/Engineering/Industrial and Systems Engineeringen
pubs.organisational-group/Virginia Tech/All T&R Facultyen
pubs.organisational-group/Virginia Tech/Engineering/COE T&R Facultyen

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
BigData_PriED.pdf
Size:
5.47 MB
Format:
Adobe Portable Document Format
Description:
Accepted version
Download

Collections

All Faculty Deposits
Scholarly Works, Computer Science
Scholarly Works, Industrial and Systems Engineering