SecCoGC combines cooperative gradient coding with real-field zero-sum privacy noise, giving exact global model reconstruction in federated learning under unreliable communication without a privacy-utility trade-off.
Locally differen- tially private online federated learning with correlated noise,
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.IT 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Coding-Enforced Robust Secure Aggregation for Federated Learning Under Unreliable Communication
SecCoGC combines cooperative gradient coding with real-field zero-sum privacy noise, giving exact global model reconstruction in federated learning under unreliable communication without a privacy-utility trade-off.