Federated Learning for All: A Reinforcement Learning-Based Approach for Ensuring Fairness in Client Selection

In federated learning, selecting participating devices (clients) is critical due to their inherent diversity. Clients typically hold non-IID data and possess varying computational and communication capabilities, which introduces heterogeneity that can impact overall system performance. Ignoring this...

Whakaahuatanga katoa

I tiakina i:

Ngā taipitopito rārangi puna kōrero
Ngā kaituhi matua:	Saeedeh Ghazi, Saeed Farzi, Amirhossein Nikoofard
Hōputu:	Artigo
Reo:	Inglês
I whakaputaina:	IEEE 2025-01-01
Rangatū:	IEEE Access
Ngā marau:	Client selection fairness federated learning reinforcement learning
Urunga tuihono:	https://ieeexplore.ieee.org/document/11072670/
Ngā Tūtohu:	Tāpirihia he Tūtohu Kāore He Tūtohu, Me noho koe te mea tuatahi ki te tūtohu i tēnei pūkete!

Federated Learning for All: A Reinforcement Learning-Based Approach for Ensuring Fairness in Client Selection

Ngā tūemi rite