TACO assigns client-specific correction coefficients based on gradient magnitude and direction to reduce over-correction in non-IID federated learning, improving accuracy, rounds, and wall-clock time.
Communication-efficient learning of deep networks from decentralized data,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction
TACO assigns client-specific correction coefficients based on gradient magnitude and direction to reduce over-correction in non-IID federated learning, improving accuracy, rounds, and wall-clock time.