Conditioning a global FL model on local PCA statistics of client data matches oracle cluster performance across heterogeneous settings and is robust to sparse data with zero added communication.
Learning multiple layers of features from tiny images
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Client-Conditional Federated Learning via Local Training Data Statistics
Conditioning a global FL model on local PCA statistics of client data matches oracle cluster performance across heterogeneous settings and is robust to sparse data with zero added communication.