The work gives conditions favoring complete-case over IPW estimators in federated settings with missing data and introduces a multi-model calibrated weighting estimator that is consistent when at least one candidate model is correct at each site.
Journal of Biomedical Informatics , volume=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ME 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Federated Learning with Incomplete Data: When to Use Complete Cases and When to Weight
The work gives conditions favoring complete-case over IPW estimators in federated settings with missing data and introduces a multi-model calibrated weighting estimator that is consistent when at least one candidate model is correct at each site.