Federated Self-Supervised Few-Shot Face Recognition

Makhanov N. Amirgaliyev B. Islamgozhayev T. Yedilkhan D.
October 2025 Multidisciplinary Digital Publishing Institute (MDPI)

Journal of Imaging
2025 #11 Issue 10

This paper presents a systematic framework that combines federated learning, self-supervised learning, and few-shot learning paradigms for privacy-preserving face recognition. We use the large-scale CASIA-WebFace dataset for self-supervised pre-training using SimCLR in a federated setting, followed by federated few-shot fine-tuning on the LFW dataset using prototypical networks. Through comprehensive evaluation across six state-of-the-art architectures (ResNet, DenseNet, MobileViT, ViT-Small, CvT, and CoAtNet), we demonstrate that while our federated approach successfully preserves data privacy, it comes with significant performance trade-offs. Our results show 12–30% accuracy degradation compared to centralized methods, representing the substantial cost of privacy preservation. We find that traditional CNNs show superior robustness to federated constraints compared to transformer-based architectures, and that five-shot configurations provide an optimal balance between data efficiency and performance. This work provides important empirical insights and establishes benchmarks for federated few-shot face recognition, quantifying the privacy–utility trade-offs that practitioners must consider when deploying such systems in real-world applications.

face recognition , federated learning , few-shot learning , privacy-preserving machine learning , self-supervised learning

Text of the article Перейти на текст статьи

Smart City Research Center, Astana IT University, Astana, 010000, Kazakhstan

Smart City Research Center

10 лет помогаем публиковать статьи Международный издатель

Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026