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
Decentralized adaptive clustering of deep nets is beneficial for client collaboration
RISE Research Institutes of Sweden, Digital Systems, Data Science. KTH Royal Institute of Technology, Sweden.ORCID iD: 0000-0001-7856-113X
RISE Research Institutes of Sweden, Digital Systems, Data Science.
RISE Research Institutes of Sweden, Digital Systems, Data Science.ORCID iD: 0009-0004-1803-4193
RISE Research Institutes of Sweden, Digital Systems, Data Science.ORCID iD: 0000-0002-9567-2218
Show others and affiliations
2022 (English)Conference paper, Published paper (Refereed)
Abstract [en]

We study the problem of training personalized deep learning models in a decentralized peer-to-peer setting, focusing on the setting where data distributions differ between the clients and where different clients have different local learning tasks. We study both covariate and label shift, and our contribution is an algorithm which for each client finds beneficial collaborations based on a similarity estimate for the local task. Our method does not rely on hyperparameters which are hard to estimate, such as the number of client clusters, but rather continuously adapts to the network topology using soft cluster assignment based on a novel adaptive gossip algorithm. We test the proposed method in various settings where data is not independent and identically distributed among the clients. The experimental evaluation shows that the proposed method performs better than previous state-of-the-art algorithms for this problem setting, and handles situations well where previous methods fail

Place, publisher, year, edition, pages
2022.
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:ri:diva-62529OAI: oai:DiVA.org:ri-62529DiVA, id: diva2:1726686
Conference
International Workshop on Trustworthy Federated Learning 2022
Available from: 2023-01-13 Created: 2023-01-13 Last updated: 2024-07-28Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Full teext

Authority records

Zec, Edvin ListoWillbo, MartinMogren, OlofGirdzijauskas, Sarunas

Search in DiVA

By author/editor
Zec, Edvin ListoWillbo, MartinMogren, OlofGirdzijauskas, Sarunas
By organisation
Data Science
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 205 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