Federated Learning of User Verification Models Without Sharing Embeddings

Hossein Hosseini, Hyunsin Park, Sungrack Yun, Christos Louizos, Joseph Soriaga, Max Welling
Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4328-4336, 2021.

Abstract

We consider the problem of training User Verification (UV) models in federated setup, 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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v139-hosseini21a, title = {Federated Learning of User Verification Models Without Sharing Embeddings}, author = {Hosseini, Hossein and Park, Hyunsin and Yun, Sungrack and Louizos, Christos and Soriaga, Joseph and Welling, Max}, booktitle = {Proceedings of the 38th International Conference on Machine Learning}, pages = {4328--4336}, year = {2021}, editor = {Meila, Marina and Zhang, Tong}, volume = {139}, series = {Proceedings of Machine Learning Research}, month = {18--24 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v139/hosseini21a/hosseini21a.pdf}, url = {https://proceedings.mlr.press/v139/hosseini21a.html}, abstract = {We consider the problem of training User Verification (UV) models in federated setup, 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.} }
Endnote
%0 Conference Paper %T Federated Learning of User Verification Models Without Sharing Embeddings %A Hossein Hosseini %A Hyunsin Park %A Sungrack Yun %A Christos Louizos %A Joseph Soriaga %A Max Welling %B Proceedings of the 38th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Marina Meila %E Tong Zhang %F pmlr-v139-hosseini21a %I PMLR %P 4328--4336 %U https://proceedings.mlr.press/v139/hosseini21a.html %V 139 %X We consider the problem of training User Verification (UV) models in federated setup, 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.
APA
Hosseini, H., Park, H., Yun, S., Louizos, C., Soriaga, J. & Welling, M.. (2021). Federated Learning of User Verification Models Without Sharing Embeddings. Proceedings of the 38th International Conference on Machine Learning, in Proceedings of Machine Learning Research 139:4328-4336 Available from https://proceedings.mlr.press/v139/hosseini21a.html.

Related Material