ScholarGate
Asistent
Machine learningMachine learning

Federated Active Learning

Federated Active Learning kombinuje efikasnost anotiranja aktivnog učenja sa decentralizacijom federativnog učenja koja čuva privatnost. Zajednički globalni model se trenira na distribuiranim klijentima, od kojih svaki nezavisno rangira svoje lokalne podatke bez oznaka i zahteva oznake samo za najinformativnije primere, zadržavajući sirove podatke na uređaju tokom celog procesa.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte celu metodu

Samo za članove

Prijavite se besplatnim nalogom da biste pročitali ovaj odeljak.

Prijavite se

Method map

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

Federated Active Learning
Aktivno učenjeFederated Learning[CYRILLIC SCRIPT DETECTE…Samostalno učenjeSemi-supervised LearningTransferno učenje

Izvori

  1. Ro, J. Y., Ali, A., Lin, Z., & Suresh, A. T. (2021). Scaling Federated Learning for Fine-tuning of Large Language Models. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP). link ↗
  2. Federated learning. Wikipedia. link ↗

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). Federated Active Learning (Active Learning within Federated Learning). ScholarGate. https://scholargate.app/sr/machine-learning/active-learning-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 →

Uočili ste grešku na ovoj stranici? Prijavite je ili predložite ispravku →

ScholarGate — Active Learning Federated Learning (Federated Active Learning (Active Learning within Federated Learning)). Preuzeto 2026-06-15 sa https://scholargate.app/sr/machine-learning/active-learning-federated-learning · Skup podataka: https://doi.org/10.5281/zenodo.20539026