Robust Federated Learning
Robust Federated Learning udvider standard federated learning med Byzantine-tolerante aggregeringsregler, der beskytter den globale model mod ondsindede, korrupte eller upålidelige klienter. I stedet for naivt at gennemsnitliggøre klientgradienter filtrerer robuste aggregeringsmetoder som koordinatvis median eller Krum skadelige opdateringer fra, så et mindretal af adversarielle deltagere ikke kan afspore træningen.
Læs hele metoden
Log ind med en gratis konto for at læse dette afsnit.
Method map
The neighbourhood of related methods — select a node to explore.
Kilder
- 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 ↗
- 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 ↗
Sådan citerer du denne side
ScholarGate. (2026, June 3). Robust Federated Learning (Byzantine-Tolerant Distributed Training). ScholarGate. https://scholargate.app/da/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.
- Bayesiansk fødereret læringMaskinlæring↔ compare
- Fødereret læringPrivatlivsbeskyttelse↔ compare
- Online Federated LearningMaskinlæring↔ compare
- Robust Gradient BoostingMaskinlæring↔ compare
- Semi-supervised Federated LearningMaskinlæring↔ compare
- OverførselslæringMaskinlæring↔ compare
Har du fundet en fejl på denne side? Indberet den eller foreslå en rettelse →