ScholarGate
Asistent
Machine learningMachine learning

Robusno federalno učenje

Robusno federalno učenje proširuje standardno federalno učenje pravilima agregacije tolerantnim na bizantske napade koja štite globalni model od zlonamjernih, oštećenih ili nepouzdanih klijenata. Umjesto naivnog prosjekovanja gradijenata klijenata, robusne metode agregacije poput medijana po koordinatama ili Kruma filtriraju štetne ažuriranja tako da manjina sudionika koji djeluju kao neprijatelji ne može poremetiti obuku.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte cijelu metodu

Samo za članove

Prijavite se besplatnim računom kako biste pročitali ovaj odjeljak.

Prijavite se

Method map

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

Izvori

  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

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). Robust Federated Learning (Byzantine-Tolerant Distributed Training). ScholarGate. https://scholargate.app/hr/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)). Preuzeto 2026-06-15 s https://scholargate.app/hr/machine-learning/robust-federated-learning · Skup podataka: https://doi.org/10.5281/zenodo.20539026