Federated User Representation Learning

Abstract

Collaborative personalization, such as through learned user representations (embeddings), can improve the prediction accuracy of neural-network-based models significantly. We propose Federated User Representation Learning (FURL), a simple, scalable, privacy-preserving and resource-efficient way to utilize existing neural personalization techniques in the Federated Learning (FL) setting. FURL divides model parameters into federated and private parameters. Private parameters, such as private user embeddings, are trained locally, but unlike federated parameters, they are not transferred to or averaged on the server. We show theoretically that this parameter split does not affect training for most model personalization approaches. Storing user embeddings locally not only preserves user privacy, but also improves memory locality of personalization compared to on-server training. We evaluate FURL on two datasets, demonstrating a significant improvement in model quality with 8% and 51% performance increases, and approximately the same level of performance as centralized training with only 0% and 4% reductions. Furthermore, we show that user embeddings learned in FL and the centralized setting have a very similar structure, indicating that FURL can learn collaboratively through the shared parameters while preserving user privacy.

References in corpus (9)

• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Federated Learning: Strategies for Improving Communication Efficiency
• Federated Learning with Non-IID Data
• Federated Optimization: Distributed Machine Learning for On-Device Intelligence
• How To Backdoor Federated Learning
• Secure Federated Transfer Learning
• Federated Optimization in Heterogeneous Networks
• Federated Collaborative Filtering for Privacy-Preserving Personalized Recommendation System
• Expanding the Reach of Federated Learning by Reducing Client Resource Requirements

Cited by in corpus (12)

• Three Approaches for Personalization with Applications to Federated Learning
• FedBEVT: Federated Learning Bird's Eye View Perception Transformer in Road Traffic Systems
• No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data
• A Systematic Literature Review on Federated Learning: From A Model Quality Perspective
• UNIDEAL: Curriculum Knowledge Distillation Federated Learning
• Aggregate or Not? Exploring Where to Privatize in DNN Based Federated Learning Under Different Non-IID Scenes
• Customized Video QoE Estimation with Algorithm-Agnostic Transfer Learning
• Federated Natural Language Generation for Personalized Dialogue System
• Preliminary Steps Towards Federated Sentiment Classification
• SEEC: Semantic Vector Federation across Edge Computing Environments
• Machine Learning Systems for Intelligent Services in the IoT: A Survey
• Federated Marginal Personalization for ASR Rescoring