DeepAI AI Chat
Log In Sign Up

Federated User Representation Learning

by   Duc Bui, et al.

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 51 centralized training with only 0 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.


page 1

page 2

page 3

page 4


Privately Customizing Prefinetuning to Better Match User Data in Federated Learning

In Federated Learning (FL), accessing private client data incurs communi...

Over-the-Air Federated Learning with Enhanced Privacy

Federated learning (FL) has emerged as a promising learning paradigm in ...

Comparative assessment of federated and centralized machine learning

Federated Learning (FL) is a privacy preserving machine learning scheme,...

Federated Learning of User Verification Models Without Sharing Embeddings

We consider the problem of training User Verification (UV) models in fed...

Federated Learning of User Authentication Models

Machine learning-based User Authentication (UA) models have been widely ...

Domain-Invariant Representation Learning from EEG with Private Encoders

Deep learning based electroencephalography (EEG) signal processing metho...

eFedDNN: Ensemble based Federated Deep Neural Networks for Trajectory Mode Inference

As the most significant data source in smart mobility systems, GPS traje...