Federated learning (FL) enables collaborative training of medical image segmentation models without sharing raw patient data, yet existing approaches assume a homogeneous compute budget across institutions, limiting participation of low-resource sites. We propose Fed-ADApt, a depth-adaptive federated framework for UNet...
Abhijeet Parida, Zhi-Fan Jiang, Pooneh Roshanitabrizi et al.· 0 citations
TRAP, a one-sided penalty on tokenwise TRA that acts only where the target model pulls ahead of its reference, brings memorization near the level of an untrained model at little utility cost, where generic regularizers barely move and differential privacy gives up most of what fine-tuning bought.
Muhammed Ustaomeroglu, Zi-Yue Xu, Han-Shen Xiao et al.· 0 citations
Two distinct effects are reported: paired-example FedAvg partially recovers the missing-ECG gap, while validation-selected completion is a task-specific classifier-logit correction rather than literal ECG recovery.
Holger R. Roth, Zi-Yue Xu, P. Cnudde· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.