Search Results for author:
Found 7 papers, 5 papers with code
Communication-Efficient Federated Learning through Adaptive Weight Clustering and Server-Side Distillation
Federated Learning (FL) is a promising technique for the collaborative training of deep neural networks across multiple devices while preserving data privacy.
Federated Fine-Tuning of Foundation Models via Probabilistic Masking
Foundation Models (FMs) have revolutionized machine learning with their adaptability and high performance across tasks; yet, their integration into Federated Learning (FL) is challenging due to substantial communication overhead from their extensive parameterization.
FedCode: Communication-Efficient Federated Learning via Transferring Codebooks
To ensure a smooth learning curve and proper calibration of clusters between the server and the clients, FedCode periodically transfers model weights after multiple rounds of solely communicating codebooks.
Plug-and-Play Multilingual Few-shot Spoken Words Recognition
As technology advances and digital devices become prevalent, seamless human-machine communication is increasingly gaining significance.
Labeling Chaos to Learning Harmony: Federated Learning with Noisy Labels
Federated Learning (FL) is a distributed machine learning paradigm that enables learning models from decentralized private datasets, where the labeling effort is entrusted to the clients.
Privacy-preserving Speech Emotion Recognition through Semi-Supervised Federated Learning
To the best of our knowledge, this is the first federated SER approach, which utilizes self-training learning in conjunction with federated learning to exploit both labeled and unlabeled on-device data.
Federated Self-Training for Semi-Supervised Audio Recognition
Notably, we show that with as little as 3% labeled data available, FedSTAR on average can improve the recognition rate by 13. 28% compared to the fully supervised federated model.
