ENABLING ON-DEVICE TRAINING OF SPEECH RECOGNITION MODELS WITH FEDERATED DROPOUT
Dhruv Guliani, Lillian Zhou, Changwan Ryu, Tien-Ju Yang, Harry Zhang, Yonghui Xiao, Francoise Beaufays, Giovanni Motta
-
SPS
IEEE Members: $11.00
Non-members: $15.00Length: 00:11:17
Federated learning can be used to train machine learning models on the edge on local data that never leave devices, providing privacy by default. This presents a challenge pertaining to the communication and computation costs associated with clients' devices. These costs are strongly correlated with the size of the model being trained, and are significant for state-of-the-art automatic speech recognition models. We propose using federated dropout to reduce the size of client models while training a full-size model server-side. We provide empirical evidence of the effectiveness of federated dropout, and propose a novel approach to vary the dropout rate applied at each layer. Furthermore, we find that federated dropout enables a set of smaller sub-models within the larger model to independently have low word error rates, making it easier to dynamically adjust the size of the model deployed for inference.