Avoid Overfitting User Specific Information in Federated Keyword Spotting

06/17/2022
by   Xin-Chun Li, et al.
0

Keyword spotting (KWS) aims to discriminate a specific wake-up word from other signals precisely and efficiently for different users. Recent works utilize various deep networks to train KWS models with all users' speech data centralized without considering data privacy. Federated KWS (FedKWS) could serve as a solution without directly sharing users' data. However, the small amount of data, different user habits, and various accents could lead to fatal problems, e.g., overfitting or weight divergence. Hence, we propose several strategies to encourage the model not to overfit user-specific information in FedKWS. Specifically, we first propose an adversarial learning strategy, which updates the downloaded global model against an overfitted local model and explicitly encourages the global model to capture user-invariant information. Furthermore, we propose an adaptive local training strategy, letting clients with more training data and more uniform class distributions undertake more local update steps. Equivalently, this strategy could weaken the negative impacts of those users whose data is less qualified. Our proposed FedKWS-UI could explicitly and implicitly learn user-invariant information in FedKWS. Abundant experimental results on federated Google Speech Commands verify the effectiveness of FedKWS-UI.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/11/2022

Production federated keyword spotting via distillation, filtering, and joint federated-centralized training

We trained a keyword spotting model using federated learning on real use...
research
12/03/2020

Robust Federated Learning with Noisy Labels

Federated learning is a paradigm that enables local devices to jointly t...
research
04/08/2022

Global Update Guided Federated Learning

Federated learning protects data privacy and security by exchanging mode...
research
04/23/2023

Personalized Federated Learning via Gradient Modulation for Heterogeneous Text Summarization

Text summarization is essential for information aggregation and demands ...
research
07/15/2022

Communication-Efficient Diffusion Strategy for Performance Improvement of Federated Learning with Non-IID Data

Federated learning (FL) is a novel learning paradigm that addresses the ...
research
04/09/2022

Divergence-aware Federated Self-Supervised Learning

Self-supervised learning (SSL) is capable of learning remarkable represe...
research
07/28/2021

Secure Bayesian Federated Analytics for Privacy-Preserving Trend Detection

Federated analytics has many applications in edge computing, its use can...

Please sign up or login with your details

Forgot password? Click here to reset