Numerous research studies in the field of federated learning (FL) have
a...
Knowledge distillation(KD) is a widely-used technique to train compact m...
User-level differential privacy (DP) provides certifiable privacy guaran...
Training deep neural networks (DNNs) for meaningful differential privacy...
Many successful learning targets such as dice loss and cross-entropy los...
The newly proposed panoptic segmentation task, which aims to encompass t...