Enhancing Privacy and Communication Efficiency in Federated Learning Through Selective Low-Rank Adaptation and Differential Privacy

Federated learning (FL) enables collaborative model training without centralizing raw data, but its application to large-scale vision models remains constrained by high communication cost, data heterogeneity, and privacy risks. Furthermore, in real-world applications such as autonomous driving and h...

Whakaahuatanga katoa

I tiakina i:

Ngā taipitopito rārangi puna kōrero
Ngā kaituhi matua:	Takuto Miyata, Liuyi Yang, Zhiyi Zhu, Patrick Finnerty, Chikara Ohta
Hōputu:	Artigo
Reo:	Inglês
I whakaputaina:	MDPI AG 2025-12-01
Rangatū:	Applied Sciences
Ngā marau:	BiT communication efficiency differential privacy federated learning low-rank adaptation LoRA
Urunga tuihono:	https://www.mdpi.com/2076-3417/15/24/13102
Ngā Tūtohu:	Tāpirihia he Tūtohu Kāore He Tūtohu, Me noho koe te mea tuatahi ki te tūtohu i tēnei pūkete!

Enhancing Privacy and Communication Efficiency in Federated Learning Through Selective Low-Rank Adaptation and Differential Privacy

Ngā tūemi rite