ScholarGate
Pembantu
Machine learningMachine learning

Pembelajaran Bersekutu Terregulasi

Pembelajaran bersekutu terregulasi melanjutkan rangka kerja pembelajaran bersekutu dengan menambahkan sebutan penalti pada objektif tempatan setiap klien, menambat kemas kini tempatan lebih dekat kepada model global. Formulasi kanonik — FedProx — menambahkan sebutan proksimal yang mengawal sejauh mana klien individu boleh terpesong, meningkatkan penumpuan dan kestabilan apabila taburan data klien berbeza secara ketara.

Buka dalam MethodMindTidak lama lagiVideoTidak lama lagiDownload slides

Baca kaedah sepenuhnya

Ahli sahaja

Log masuk dengan akaun percuma untuk membaca bahagian ini.

Log masuk

Method map

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

Sumber

  1. Li, T., Sahu, A. K., Zaheer, M., Sanjabi, M., Talwalkar, A., & Smith, V. (2020). Federated Optimization in Heterogeneous Networks. Proceedings of Machine Learning and Systems (MLSys), 2, 429–450. link
  2. McMahan, B., Moore, E., Ramage, D., Hampson, S., & y Arcas, B. A. (2017). Communication-Efficient Learning of Deep Networks from Decentralized Data. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR 54, 1273–1282. link

Cara memetik halaman ini

ScholarGate. (2026, June 3). Regularized Federated Learning (Proximal and Penalty-Based Approaches). ScholarGate. https://scholargate.app/ms/machine-learning/regularized-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
ScholarGateRegularized Federated Learning (Regularized Federated Learning (Proximal and Penalty-Based Approaches)). Dicapai 2026-06-15 daripada https://scholargate.app/ms/machine-learning/regularized-federated-learning · Set data: https://doi.org/10.5281/zenodo.20539026