A pre-trained teacher-guided distillation framework, PM-AFL++, improves clean and adversarial accuracy of federated models while reducing communication rounds and parameters.
Evaluating text-to-visual generation with image-to-text generation,
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.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Towards Communication-Efficient Adversarial Federated Learning for Robust Edge Intelligence
A pre-trained teacher-guided distillation framework, PM-AFL++, improves clean and adversarial accuracy of federated models while reducing communication rounds and parameters.