Federated Learning of User Verification Models Without Sharing Embeddings

04/18/2021
by   Hossein Hosseini, et al.
0

We consider the problem of training User Verification (UV) models in federated setting, where each user has access to the data of only one class and user embeddings cannot be shared with the server or other users. To address this problem, we propose Federated User Verification (FedUV), a framework in which users jointly learn a set of vectors and maximize the correlation of their instance embeddings with a secret linear combination of those vectors. We show that choosing the linear combinations from the codewords of an error-correcting code allows users to collaboratively train the model without revealing their embedding vectors. We present the experimental results for user verification with voice, face, and handwriting data and show that FedUV is on par with existing approaches, while not sharing the embeddings with other users or the server.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 9

07/09/2020

Federated Learning of User Authentication Models

Machine learning-based User Authentication (UA) models have been widely ...
04/21/2020

Federated Learning with Only Positive Labels

We consider learning a multi-class classification model in the federated...
11/26/2019

Federated Learning for Ranking Browser History Suggestions

Federated Learning is a new subfield of machine learning that allows fit...
09/27/2019

Federated User Representation Learning

Collaborative personalization, such as through learned user representati...
06/15/2021

Canonical Face Embeddings

We present evidence that many common convolutional neural networks (CNNs...
06/12/2020

Backdoor Attacks on Federated Meta-Learning

Federated learning allows multiple users to collaboratively train a shar...
12/10/2018

Aggregation and Embedding for Group Membership Verification

This paper proposes a group membership verification protocol preventing ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.