ProFe reduces decentralized federated learning communication by 40-50% through teacher-student distillation, prototype sharing, and 16-bit quantization, with slight accuracy gains in non-IID settings and about 20% more training time.
Communication-efficient learning of deep networks from decentralized data,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
ProFe: Communication-Efficient Decentralized Federated Learning via Distillation and Prototypes
ProFe reduces decentralized federated learning communication by 40-50% through teacher-student distillation, prototype sharing, and 16-bit quantization, with slight accuracy gains in non-IID settings and about 20% more training time.