# Federated Learning of User Verification Models Without Sharing Embeddings

arXiv: https://arxiv.org/abs/2104.08776 · HTML: https://mlsanity.com/paper/2104.08776/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 29 references that are in the map.
- First posted on arXiv 18 Apr 2021.

## Builds on (most cited first, 12 of 12)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [LEAF: A Benchmark for Federated Settings](https://mlsanity.com/paper/1812.01097/) (2018)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [Exploiting Unintended Feature Leakage in Collaborative Learning](https://mlsanity.com/paper/1805.04049/) (2018)
- [The Non-IID Data Quagmire of Decentralized Machine Learning](https://mlsanity.com/paper/1910.00189/) (2019)
- [Additive Margin Softmax for Face Verification](https://mlsanity.com/paper/1801.05599/) (2018)
- [Unsupervised Learning by Predicting Noise](https://mlsanity.com/paper/1704.05310/) (2017)
- [Federated Learning with Only Positive Labels](https://mlsanity.com/paper/2004.10342/) (2020)
- [Improving on-device speaker verification using federated learning with privacy](https://mlsanity.com/paper/2008.02651/) (2020)
- [Automated Latent Fingerprint Recognition](https://mlsanity.com/paper/1704.01925/) (2017)
- [An End-to-End Text-independent Speaker Verification Framework with a Keyword Adversarial Network](https://mlsanity.com/paper/1908.02612/) (2019)

## Built on by (most cited first, 11 of 11)

- [ProtoFL: Unsupervised Federated Learning via Prototypical Distillation](https://mlsanity.com/paper/2307.12450/) (2023)
- [Making Batch Normalization Great in Federated Deep Learning](https://mlsanity.com/paper/2303.06530/) (2023)
- [A Mutual Information Perspective on Federated Contrastive Learning](https://mlsanity.com/paper/2405.02081/) (2024)
- [FedABC: Targeting Fair Competition in Personalized Federated Learning](https://mlsanity.com/paper/2302.07450/) (2023)
- [Feature Diversification and Adaptation for Federated Domain Generalization](https://mlsanity.com/paper/2407.08245/) (2024)
- [FedBug: A Bottom-Up Gradual Unfreezing Framework for Federated Learning](https://mlsanity.com/paper/2307.10317/) (2023)
- [Project Florida: Federated Learning Made Easy](https://mlsanity.com/paper/2307.11899/) (2023)
- [CRSFL: Cluster-based Resource-aware Split Federated Learning for Continuous Authentication](https://mlsanity.com/paper/2405.07174/) (2024)
- [Towards Zero-trust Security for the Metaverse](https://mlsanity.com/paper/2302.08885/) (2023)
- [IPFed: Identity protected federated learning for user authentication](https://mlsanity.com/paper/2405.03955/) (2024)
- [FedHide: Federated Learning by Hiding in the Neighbors](https://mlsanity.com/paper/2409.07808/) (2024)

## Abstract (arXiv)

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.