FedPSD improves personalized federated learning by using previous-epoch model outputs as teachers and a locally prior-weighted softmax loss, reporting higher client and server accuracy on three benchmarks.
Rethinking personalized federated learning from knowledge perspective,
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.AI 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Federated Progressive Self-Distillation with Logits Calibration for Personalized IIoT Edge Intelligence
FedPSD improves personalized federated learning by using previous-epoch model outputs as teachers and a locally prior-weighted softmax loss, reporting higher client and server accuracy on three benchmarks.