FedCAR weights each client's generator by the inverse pairwise FID between its fake images and other clients' fake images, reporting modest FID improvements over FedAvg and centralized learning in non-i.i.d. chest X-ray generation.
Communications of the ACM63, 139 – 144 (2014),https://api.semanticscholar.org/CorpusID: 1033682
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
FedCAR: Cross-client Adaptive Re-weighting for Generative Models in Federated Learning
FedCAR weights each client's generator by the inverse pairwise FID between its fake images and other clients' fake images, reporting modest FID improvements over FedAvg and centralized learning in non-i.i.d. chest X-ray generation.