ScholarGate
Assistent
Machine learningMachine learning

Robust Federated Learning

Robust Federated Learning utvider standard føderert læring med Byzantine-tolerante aggregeringsregler som beskytter den globale modellen mot ondsinnede, korrupte eller upålitelige klienter. I stedet for å naivt gjennomsnitte klientgradienter, filtrerer robuste aggregeringsmetoder som koordinatvis median eller Krum ut skadelige oppdateringer slik at et mindretall av adversarielle deltakere ikke kan spore av treningen.

Åpne i MethodMindSnartVideoSnartDownload slides

Les hele metoden

Kun for medlemmer

Logg inn med en gratis konto for å lese denne delen.

Logg inn

Method map

The neighbourhood of related methods — select a node to explore.

Kilder

  1. Blanchard, P., El Mhamdi, E. M., Guerraoui, R., & Stainer, J. (2017). Machine Learning with Adversaries: Byzantine Tolerant Gradient Descent. Advances in Neural Information Processing Systems, 30. link
  2. Yin, D., Chen, Y., Kannan, R., & Bartlett, P. (2018). Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates. Proceedings of the 35th International Conference on Machine Learning (ICML), PMLR 80:5650–5659. link

Slik siterer du denne siden

ScholarGate. (2026, June 3). Robust Federated Learning (Byzantine-Tolerant Distributed Training). ScholarGate. https://scholargate.app/no/machine-learning/robust-federated-learning

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side
ScholarGateRobust Federated Learning (Robust Federated Learning (Byzantine-Tolerant Distributed Training)). Hentet 2026-06-15 fra https://scholargate.app/no/machine-learning/robust-federated-learning · Datasett: https://doi.org/10.5281/zenodo.20539026