Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Efficient Node Selection in Private Personalized Decentralized Learning
RISE Research Institutes of Sweden, Digital Systems, Data Science. KTH Royal Institute of Technology, Sweden.ORCID iD: 0000-0001-7856-113X
AI Sweden, Sweden.
RISE Research Institutes of Sweden, Digital Systems, Data Science.ORCID iD: 0000-0002-9567-2218
AI Sweden, Sweden.
2024 (English)In: : Proceedings of Machine Learning Research, ML Research Press , 2024, Vol. 233Conference paper, Published paper (Refereed)
Abstract [en]

Personalized decentralized learning is a promising paradigm for distributed learning, enabling each node to train a local model on its own data and collaborate with other nodes to improve without sharing any data. However, this approach poses significant privacy risks, as nodes may inadvertently disclose sensitive information about their data or preferences through their collaboration choices. In this paper, we propose Private Personalized Decentralized Learning (PPDL), a novel approach that combines secure aggregation and correlated adversarial multi-armed bandit optimization to protect node privacy while facilitating efficient node selection. By leveraging dependencies between different arms, represented by potential collaborators, we demonstrate that PPDL can effectively identify suitable collaborators solely based on aggregated models. Additionally, we show that PPDL surpasses previous non-private methods in model performance on standard benchmarks under label and covariate shift scenarios. 

Place, publisher, year, edition, pages
ML Research Press , 2024. Vol. 233
Keywords [en]
Learning systems; Decentralized learning; Distributed learning; Local model; Multiarmed bandits (MABs); Node selection; Optimisations; Potential collaborators; Privacy risks; Secure aggregations; Sensitive informations; Benchmarking
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:ri:diva-72883Scopus ID: 2-s2.0-85189301070OAI: oai:DiVA.org:ri-72883DiVA, id: diva2:1854692
Conference
5th Northern Lights Deep Learning Conference, NLDL 2024. Tromso, Norway. 9 January 2024 through 11 January 2024
Available from: 2024-04-26 Created: 2024-04-26 Last updated: 2024-05-21Bibliographically approved

Open Access in DiVA

No full text in DiVA

Scopus

Authority records

Zec, Edvin ListoMogren, Olof

Search in DiVA

By author/editor
Zec, Edvin ListoMogren, Olof
By organisation
Data Science
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 101 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf