# Improving Federated Learning Face Recognition via Privacy-Agnostic Clusters

arXiv: https://arxiv.org/abs/2201.12467 · HTML: https://mlsanity.com/paper/2201.12467/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 45 references that are in the map.
- First posted on arXiv 29 Jan 2022.

## Builds on (most cited first, 23 of 23)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://mlsanity.com/paper/1607.08221/) (2016)
- [Differentially Private Federated Learning: A Client Level Perspective](https://mlsanity.com/paper/1712.07557/) (2017)
- [Learning Face Representation from Scratch](https://mlsanity.com/paper/1411.7923/) (2014)
- [MagFace: A Universal Representation for Face Recognition and Quality Assessment](https://mlsanity.com/paper/2103.06627/) (2021)
- [A Hybrid Approach to Privacy-Preserving Federated Learning](https://mlsanity.com/paper/1812.03224/) (2018)
- [Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learning](https://mlsanity.com/paper/1911.10692/) (2019)
- [L2-constrained Softmax Loss for Discriminative Face Verification](https://mlsanity.com/paper/1703.09507/) (2017)
- [A Study of Face Obfuscation in ImageNet](https://mlsanity.com/paper/2103.06191/) (2021)
- [Towards Backward-Compatible Representation Learning](https://mlsanity.com/paper/2003.11942/) (2020)
- [Learning Compatible Embeddings](https://mlsanity.com/paper/2108.01958/) (2021)
- [Secure Face Matching Using Fully Homomorphic Encryption](https://mlsanity.com/paper/1805.00577/) (2018)
- [FedFace: Collaborative Learning of Face Recognition Model](https://mlsanity.com/paper/2104.03008/) (2021)
- [Differentially Private k-Means with Constant Multiplicative Error](https://mlsanity.com/paper/1804.08001/) (2018)
- [Locating a Small Cluster Privately](https://mlsanity.com/paper/1604.05590/) (2016)
- [Searching for Alignment in Face Recognition](https://mlsanity.com/paper/2102.05447/) (2021)
- [Federated Face Recognition](https://mlsanity.com/paper/2105.02501/) (2021)
- [PoseFace: Pose-Invariant Features and Pose-Adaptive Loss for Face Recognition](https://mlsanity.com/paper/2107.11721/) (2021)

## Built on by (most cited first, 18 of 18)

- [Accelerated Federated Learning with Decoupled Adaptive Optimization](https://mlsanity.com/paper/2207.07223/) (2022)
- [Learning to Generate Image Embeddings with User-level Differential Privacy](https://mlsanity.com/paper/2211.10844/) (2022)
- [FaceMAE: Privacy-Preserving Face Recognition via Masked Autoencoders](https://mlsanity.com/paper/2205.11090/) (2022)
- [COALA: A Practical and Vision-Centric Federated Learning Platform](https://mlsanity.com/paper/2407.16560/) (2024)
- [Privacy-Enhancing Paradigms within Federated Multi-Agent Systems](https://mlsanity.com/paper/2503.08175/) (2025)
- [Clip Body and Tail Separately: High Probability Guarantees for DPSGD with Heavy Tails](https://mlsanity.com/paper/2405.17529/) (2024)
- [Towards Privacy-Preserving, Real-Time and Lossless Feature Matching](https://mlsanity.com/paper/2208.00214/) (2022)
- [PCDP-SGD: Improving the Convergence of Differentially Private SGD via Projection in Advance](https://mlsanity.com/paper/2312.03792/) (2023)
- [SVDefense: Effective Defense against Gradient Inversion Attacks via Singular Value Decomposition](https://mlsanity.com/paper/2510.03319/) (2025)
- [A Survey of Face Recognition](https://mlsanity.com/paper/2212.13038/) (2022)
- [PAFedFV: Personalized and Asynchronous Federated Learning for Finger Vein Recognition](https://mlsanity.com/paper/2404.13237/) (2024)
- [Federated Active Learning for Target Domain Generalisation](https://mlsanity.com/paper/2312.02247/) (2023)
- [Federated Learning Method for Preserving Privacy in Face Recognition System](https://mlsanity.com/paper/2403.05344/) (2024)
- [Adaptive Hybrid Masking Strategy for Privacy-Preserving Face Recognition Against Model Inversion Attack](https://mlsanity.com/paper/2403.10558/) (2024)
- [AdaFedFR: Federated Face Recognition with Adaptive Inter-Class Representation Learning](https://mlsanity.com/paper/2405.13467/) (2024)
- [RDP: Ranked Differential Privacy for Facial Feature Protection in Multiscale Sparsified Subspace](https://mlsanity.com/paper/2408.00294/) (2024)
- [Privacy Preserved Federated Learning with Attention-Based Aggregation for Biometric Recognition](https://mlsanity.com/paper/2510.01113/) (2025)
- [Private Face Recognition Training Dataset Publication via Identity-Decoupled and Geometry-Preserving Face Distillation](https://mlsanity.com/paper/2607.27764/) (2026)

## Abstract (arXiv)

The growing public concerns on data privacy in face recognition can be greatly addressed by the federated learning (FL) paradigm. However, conventional FL methods perform poorly due to the uniqueness of the task: broadcasting class centers among clients is crucial for recognition performances but leads to privacy leakage. To resolve the privacy-utility paradox, this work proposes PrivacyFace, a framework largely improves the federated learning face recognition via communicating auxiliary and privacy-agnostic information among clients. PrivacyFace mainly consists of two components: First, a practical Differentially Private Local Clustering (DPLC) mechanism is proposed to distill sanitized clusters from local class centers. Second, a consensus-aware recognition loss subsequently encourages global consensuses among clients, which ergo results in more discriminative features. The proposed framework is mathematically proved to be differentially private, introducing a lightweight overhead as well as yielding prominent performance boosts (textite.g., +9.63% and +10.26% for TAR@FAR=1e-4 on IJB-B and IJB-C respectively). Extensive experiments and ablation studies on a large-scale dataset have demonstrated the efficacy and practicability of our method.