Machine learningMachine learning

Federizirano samoučenje

Federated samoučenje kombinuje federativno treniranje — gde podaci nikada ne napuštaju lokalne uređaje — sa samoučenim zadacima kao što su kontrastivno učenje ili maskirano predviđanje. Klijenti uče opšte reprezentacije iz sopstvenih neoznačenih podataka i dele samo ažuriranja modela, a ne sirove podatke, sa centralnim serverom koji ih agregira u globalni enkoder.

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.

Izvori

  1. Zhuang, W., Wen, Y., & Zhang, S. (2021). Divergence-aware Federated Self-Supervised Learning. In International Conference on Learning Representations (ICLR 2022). link
  2. Federated learning. Wikipedia. link

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). Self-supervised Learning in Federated Settings. ScholarGate. https://scholargate.app/sr/machine-learning/self-supervised-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
ScholarGateSelf-supervised Federated learning (Self-supervised Learning in Federated Settings). Preuzeto 2026-06-15 sa https://scholargate.app/sr/machine-learning/self-supervised-federated-learning · Skup podataka: https://doi.org/10.5281/zenodo.20539026