skip to main content
Idioma:
Primo Search
Clear Search Box
Search in: Busca Geral
Busca Avançada
Busca por Índices
Tipo de recurso Mostra resultados com: Mostra resultados com: Índice

Towards More Efficient Data Valuation in Healthcare Federated Learning Using Ensembling

Kumar, Sourav ; Lakshminarayanan, A. ; Chang, Ken ; Guretno, Feri ; Mien, Ivan Ho ; Kalpathy-Cramer, Jayashree ; Krishnaswamy, Pavitra ; Singh, Praveer Xu, Daguang ; Albarqouni, Shadi ; Bano, Sophia ; Bakas, Spyridon ; Cardoso, M. Jorge ; Landman, Bennett ; Qin, Chen ; Khanal, Bishesh ; Rekik, Islem ; Rieke, Nicola ; Li, Xiaoxiao ; Roth, Holger ; Sheet, Debdoot

Distributed, Collaborative, and Federated Learning, and Affordable AI and Healthcare for Resource Diverse Global Health, 2022-09, Vol.13573, p.119-129 [Periódico revisado por pares]

Cham: Springer Nature Switzerland

Sem texto completo

Citações Citado por
  • Título:
    Towards More Efficient Data Valuation in Healthcare Federated Learning Using Ensembling
  • Autor: Kumar, Sourav ; Lakshminarayanan, A. ; Chang, Ken ; Guretno, Feri ; Mien, Ivan Ho ; Kalpathy-Cramer, Jayashree ; Krishnaswamy, Pavitra ; Singh, Praveer
  • Xu, Daguang ; Albarqouni, Shadi ; Bano, Sophia ; Bakas, Spyridon ; Cardoso, M. Jorge ; Landman, Bennett ; Qin, Chen ; Khanal, Bishesh ; Rekik, Islem ; Rieke, Nicola ; Li, Xiaoxiao ; Roth, Holger ; Sheet, Debdoot
  • Assuntos: Data valuation ; Federated Learning ; Healthcare AI
  • É parte de: Distributed, Collaborative, and Federated Learning, and Affordable AI and Healthcare for Resource Diverse Global Health, 2022-09, Vol.13573, p.119-129
  • Notas: S. Kumar and A. Lakshminarayanan—Equally contributing first authors.P. Krishnaswamy and P. Singh—Equal senior authors.
  • Descrição: Federated Learning (FL) wherein multiple institutions collaboratively train a machine learning model without sharing data is becoming popular. Participating institutions might not contribute equally - some contribute more data, some better quality data or some more diverse data. To fairly rank the contribution of different institutions, Shapley value (SV) has emerged as the method of choice. Exact SV computation is impossibly expensive, especially when there are hundreds of contributors. Existing SV computation techniques use approximations. However, in healthcare where the number of contributing institutions are likely not of a colossal scale, computing exact SVs is still exorbitantly expensive, but not impossible. For such settings, we propose an efficient SV computation technique called SaFE (Shapley Value for Federated Learning using Ensembling). We empirically show that SaFE computes values that are close to exact SVs, and that it performs better than current SV approximations. This is particularly relevant in medical imaging setting where widespread heterogeneity across institutions is rampant and fast accurate data valuation is required to determine the contribution of each participant in multi-institutional collaborative learning.
  • Editor: Cham: Springer Nature Switzerland
  • Idioma: Inglês
Links
Voltar para lista de resultados
Ir para página anteriorAnterior Resultado  9 AvançarIr para próxima página

  • Realização: ABCD-USP USP   Logos de Redes Sociais: Freepik

Buscando em bases de dados remotas. Favor aguardar.