PRoBit+ combines one-bit stochastic quantization, ML-based aggregation, and an adaptive quantization range to achieve communication-efficient, differentially private, Byzantine-robust personalized federated learning.
Byzantine-robust and communication-efficient personalized federated learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
One-Bit Model Aggregation for Differentially Private and Byzantine-Robust Personalized Federated Learning
PRoBit+ combines one-bit stochastic quantization, ML-based aggregation, and an adaptive quantization range to achieve communication-efficient, differentially private, Byzantine-robust personalized federated learning.