Taming Gradient Variance in Federated Learning with Networked Control Variates

Federated learning, a decentralized approach to machine learning, faces significant challenges such as extensive communication overheads, slow convergence, and unstable improvements. These challenges primarily stem from the gradient variance due to heterogeneous client data distributions. To address this, we introduce a novel Networked Control Variates (FedNCV) framework for Federated Learning. We adopt the REINFORCE Leave-One-Out (RLOO) as a fundamental control variate unit in the FedNCV framework, implemented at both client and server levels. At the client level, the RLOO control variate is employed to optimize local gradient updates, mitigating the variance introduced by data samples. Once relayed to the server, the RLOO-based estimator further provides an unbiased and low-variance aggregated gradient, leading to robust global updates. This dual-side application is formalized as a linear combination of composite control variates. We provide a mathematical expression capturing this integration of double control variates within FedNCV and present three theoretical results with corresponding proofs. This unique dual structure equips FedNCV to address data heterogeneity and scalability issues, thus potentially paving the way for large-scale applications. Moreover, we tested FedNCV on six diverse datasets under a Dirichlet distribution with {\alpha} = 0.1, and benchmarked its performance against six SOTA methods, demonstrating its superiority.

Noise Robust TTS for Low Resource Speakers using Pre-trained Model and Speech Enhancement

With the popularity of deep neural network, speech synthesis task has achieved significant improvements based on the end-to-end encoder-decoder framework in the recent days. More and more applications relying on speech synthesis technology have been widely used in our daily life. Robust speech synthesis model depends on high quality and customized data which needs lots of collecting efforts. It is worth investigating how to take advantage of low-quality and low resource voice data which can be easily obtained from the Internet for usage of synthesizing personalized voice. In this paper, the proposed end-to-end speech synthesis model uses both speaker embedding and noise representation as conditional inputs to model speaker and noise information respectively. 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. Experimental results show that the speech generated by the proposed approach has better subjective evaluation results than the method directly fine-tuning pre-trained multi-speaker speech synthesis model with denoised new speaker data.