FedCFA replaces local latent factors with global average features to generate counterfactual samples, improving federated global model accuracy under heterogeneous data.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FedCFA: Alleviating Simpson's Paradox in Model Aggregation with Counterfactual Federated Learning
FedCFA replaces local latent factors with global average features to generate counterfactual samples, improving federated global model accuracy under heterogeneous data.