Machine learningMachine learning

Federated Active Learning (Federated Active Learning)

Federated Active Learning apvieno aktīvās mācīšanās anotāciju efektivitāti ar federatīvās mācīšanās privātumu aizsargājošo decentralizāciju. Kopīgs globālais modelis tiek apmācīts izplatītiem klientiem, no kuriem katrs neatkarīgi sarindo savus neiezīmētos lokālos datus un pieprasa anotācijas tikai visinformatīvākajiem piemēriem, visu laiku paturot izejas datus ierīcē.

Atvērt MethodMindDrīzumāVideoDrīzumāDownload slides

Lasīt pilno metodes aprakstu

Tikai dalībniekiem

Piesakieties ar bezmaksas kontu, lai lasītu šo sadaļu.

Pieteikties

Method map

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

Avoti

  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

Kā citēt šo lapu

ScholarGate. (2026, June 3). Federated Active Learning (Active Learning within Federated Learning). ScholarGate. https://scholargate.app/lv/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
ScholarGateActive Learning Federated Learning (Federated Active Learning (Active Learning within Federated Learning)). Izgūts 2026-06-15 no https://scholargate.app/lv/machine-learning/active-learning-federated-learning · Datu kopa: https://doi.org/10.5281/zenodo.20539026