Mafunzo yaliyoimarishwa kwa njia ya shirikishi
Mafunzo yaliyoimarishwa kwa njia ya shirikishi huongeza mfumo wa mafunzo ya shirikishi kwa kuongeza vipengee vya adhabu kwenye lengo la kila mteja, na kuunganisha masasisho ya ndani karibu na modeli ya kimataifa. Muundo wa kawaida — FedProx — huongeza kipengee cha karibu ambacho hudhibiti ni mbali gani mteja mmoja anaweza kuepuka, kuboresha utangamano na utulivu wakati usambazaji wa data wa wateja unatofautiana sana.
Soma mbinu kamili
Ingia kwa akaunti ya bure ili kusoma sehemu hii.
Method map
The neighbourhood of related methods — select a node to explore.
Vyanzo
- 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 ↗
- 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 ↗
Jinsi ya kunukuu ukurasa huu
ScholarGate. (2026, June 3). Regularized Federated Learning (Proximal and Penalty-Based Approaches). ScholarGate. https://scholargate.app/sw/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.
- Federated LearningFaragha↔ compare
- Jifunze MtandaoniUjifunzaji wa Mashine↔ compare
- Uboreshaji wa Gradient UlioimarishwaUjifunzaji wa Mashine↔ compare
- Usajili wa Usawazishaji wa UsawazishajiUjifunzaji wa Mashine↔ compare
- Ujifunzaji Nusu-SimamiwaUjifunzaji wa Mashine↔ compare
- Kujifunza kwa uhamishajiUjifunzaji wa Mashine↔ compare
Umeona tatizo kwenye ukurasa huu? Ripoti au pendekeza marekebisho →