Learning quantization-aware linear paths in weight space yields a midpoint whose direct quantization matches quantization-aware training performance without using straight-through estimators.
arXiv preprint arXiv:2412.15846 (2024)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
This survey introduces a taxonomy for quantization in federated learning organized around client heterogeneity, aggregation consistency, non-IID robustness, privacy integration, and hardware co-optimization, while analyzing interactions with core FL behaviors.
citing papers explorer
-
Neural Network Quantization by Learning Low-Loss Subspaces
Learning quantization-aware linear paths in weight space yields a midpoint whose direct quantization matches quantization-aware training performance without using straight-through estimators.
-
Quantization in Federated Learning: Methods, Challenges and Future Directions
This survey introduces a taxonomy for quantization in federated learning organized around client heterogeneity, aggregation consistency, non-IID robustness, privacy integration, and hardware co-optimization, while analyzing interactions with core FL behaviors.