FedWSQ applies weight standardization in federated learning and uses Gaussian-optimal non-uniform quantization with a shared global scaling vector, improving accuracy at very low bit rates.
Qsparse-Local-SGD: Distributed SGD with quantiza- tion, sparsification, and local computations.IEEE Journal on Selected Areas in Information Theory , 1(1):217–226, 2020
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FedWSQ: Efficient Federated Learning with Weight Standardization and Distribution-Aware Non-Uniform Quantization
FedWSQ applies weight standardization in federated learning and uses Gaussian-optimal non-uniform quantization with a shared global scaling vector, improving accuracy at very low bit rates.