paper-with-me

Papers

Avoid Overfitting User Specific Information in Federated Keyword Spotting

2022-06-17 · Xin-Chun Li, Jin-Lin Tang, Shaoming Song, Bingshuai Li, Yinchuan Li, Yunfeng Shao, Le Gan, De-Chuan Zhan

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.

📄 PDF Abstract BibTeX arXiv:2206.08864

Code (1)

lxcnju/FedKWS-UI 공식 구현 pytorch

Tasks

Keyword Spotting

Similar Papers 제목 키워드 기반

Federated Latent Class Regression for Hierarchical Data

2022-06-22 · Bin Yang, Thomas Carette, Masanobu Jimbo, Shinya Maruyama

Federated Learning (FL) allows a number of agents to participate in training a global machine learning model without disclosing locally stored data. Compared to traditional distributed learning, the heterogeneity (non-II…

Federated Learningregression

Multi-Source Collaborative Gradient Discrepancy Minimization for Federated Domain Generalization

2024-01-05 · Yikang Wei, Yahong Han

Federated Domain Generalization aims to learn a domain-invariant model from multiple decentralized source domains for deployment on unseen target domain. Due to privacy concerns, the data from different source domains ar…

Domain AdaptationDomain Generalization

Diverse Preference Augmentation with Multiple Domains for Cold-start Recommendations

2022-04-01 · Yan Zhang, Changyu Li, Ivor W. Tsang, Hui Xu 외

Cold-start issues have been more and more challenging for providing accurate recommendations with the fast increase of users and items. Most existing approaches attempt to solve the intractable problems via content-aware…

Domain AdaptationMeta-LearningTransfer Learning

User Modelling for Avoiding Overfitting in Interactive Knowledge Elicitation for Prediction

2017-10-13 · Pedram Daee, Tomi Peltola, Aki Vehtari, Samuel Kaski

In human-in-the-loop machine learning, the user provides information beyond that in the training data. Many algorithms and user interfaces have been designed to optimize and facilitate this human--machine interaction; ho…

BIG-bench Machine LearningSentiment Analysis

CATFL: Certificateless Authentication-based Trustworthy Federated Learning for 6G Semantic Communications

2023-02-01 · Gaolei Li, YuanYuan Zhao, Yi Li

Federated learning (FL) provides an emerging approach for collaboratively training semantic encoder/decoder models of semantic communication systems, without private user data leaving the devices. Most existing studies o…

Data PoisoningDecoderFederated LearningManagement+2