Using the previous posterior as the next prior in federated SGLD training cut iterations to 85% accuracy by about 50% over three days of radar data, with improved calibration.
On the impact of data heterogeneity in federated learning environments with application to healthcare networks,
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
-
Bayesian Federated Learning for Continual Training
Using the previous posterior as the next prior in federated SGLD training cut iterations to 85% accuracy by about 50% over three days of radar data, with improved calibration.