Search Results for author:
Found 4 papers, 1 papers with code
Towards Optimal Customized Architecture for Heterogeneous Federated Learning with Contrastive Cloud-Edge Model Decoupling
To address these issues, we propose a novel federated learning framework called FedCMD, a model decoupling tailored to the Cloud-edge supported federated learning that separates deep neural networks into a body for capturing shared representations in Cloud and a personalized head for migrating data heterogeneity.
Taming Gradient Variance in Federated Learning with Networked Control Variates
To address this, we introduce a novel Networked Control Variates (FedNCV) framework for Federated Learning.
Protected Long-Distance Guiding of Hypersound Underneath a Nano-Corrugated Surface
Within a new paradigm for communications on the nanoscale, high-frequency surface acoustic waves are becoming effective data carrier and encoder.
Mesoscale and Nanoscale Physics
Noise Robust TTS for Low Resource Speakers using Pre-trained Model and Speech Enhancement
Firstly, the speech synthesis model is pre-trained with both multi-speaker clean data and noisy augmented data; then the pre-trained model is adapted on noisy low-resource new speaker data; finally, by setting the clean speech condition, the model can synthesize the new speaker's clean voice.
