P2U sends a low-precision model followed by a residual update, reporting better accuracy and lower bandwidth than direct quantization in image classification benchmarks.
Stochastic binary-ternary quantization for communication efficient federated computation,
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
P$^2$U: Progressive Precision Update For Efficient Model Distribution
P2U sends a low-precision model followed by a residual update, reporting better accuracy and lower bandwidth than direct quantization in image classification benchmarks.