mlsanityData to 7 Oct 2026

ProtoFL: Unsupervised Federated Learning via Prototypical Distillation

arXiv 2307.12450 ↗First posted 23 Jul 2023cs.CV cs.AI cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) is a promising approach for enhancing data privacy preservation, particularly for authentication systems. However, limited round communications, scarce representation, and scalability pose significant challenges to its deployment, hindering its full potential. In this paper, we propose 'ProtoFL', Prototypical Representation Distillation based unsupervised Federated Learning to enhance the representation power of a global model and reduce round communication costs. Additionally, we introduce a local one-class classifier based on normalizing flows to improve performance with limited data. Our study represents the first investigation of using FL to improve one-class classification performance. We conduct extensive experiments on five widely used benchmarks, namely MNIST, CIFAR-10, CIFAR-100, ImageNet-30, and Keystroke-Dynamics, to demonstrate the superior performance of our proposed framework over previous methods in the literature.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 31 of its 45 references that are in the map. First posted on arXiv 23 Jul 2023.

Builds on

31 of 45 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  4. 2016Density estimation using Real NVPcited by 2,029
  5. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  6. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  7. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 836
  8. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 763
  9. 2016MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognitioncited by 621
  10. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 537
  11. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
  12. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
19 more
  1. 2020Think Locally, Act Globally: Federated Learning with Local and Global Representationscited by 322
  2. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 320
  3. 2019Deep Semi-Supervised Anomaly Detectioncited by 290
  4. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  5. 2020Why Normalizing Flows Fail to Detect Out-of-Distribution Datacited by 220
  6. 2020Classification-Based Anomaly Detection for General Datacited by 210
  7. 2020Learning and Evaluating Representations for Deep One-class Classificationcited by 133
  8. 2020Explainable Deep One-Class Classificationcited by 126
  9. 2020Federated Learning with Only Positive Labelscited by 55
  10. 2022Orchestra: Unsupervised Federated Learning via Globally Consistent Clusteringcited by 45
  11. 2022FedX: Unsupervised Federated Learning with Cross Knowledge Distillationcited by 40
  12. 2022Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Imagescited by 35
  13. 2021FedFace: Collaborative Learning of Face Recognition Modelcited by 26
  14. 2020Unsupervised Video Anomaly Detection via Normalizing Flows with Implicit Latent Featurescited by 23
  15. 2022SphereFed: Hyperspherical Federated Learningcited by 19
  16. 2021FedFR: Joint Optimization Federated Framework for Generic and Personalized Face Recognitioncited by 16
  17. 2021Federated Learning of User Verification Models Without Sharing Embeddingscited by 11
  18. 2021Federated Learning-based Active Authentication on Mobile Devicescited by 7
  19. 2019NFAD: Fixing anomaly detection using normalizing flowscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 2; 2026: 1.

11 papers.

  1. 2024Federated Distillation: A Surveycited by 14
  2. 2024Rethinking the Representation in Federated Unsupervised Learning with Non-IID Datacited by 12
  3. 2024FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusioncited by 11
  4. 2024Navigating Distribution Shifts in Medical Image Analysis: A Surveycited by 5
  5. 2024Federated Source-free Domain Adaptation for Classification: Weighted Cluster Aggregation for Unlabeled Datacited by 4
  6. 2024Learning Unlabeled Clients Divergence for Federated Semi-Supervised Learning via Anchor Model Aggregationcited by 0
  7. 2024Federated Learning for Face Recognition via Intra-subject Self-supervised Learningcited by 0
  8. 2024FedHide: Federated Learning by Hiding in the Neighborscited by 0
  9. 2025FedDyMem: Efficient Federated Learning with Dynamic Memory and Memory-Reduce for Unsupervised Image Anomaly Detectioncited by 0
  10. 2025Cooperative Pseudo Labeling for Unsupervised Federated Classificationcited by 0
  11. 2026HiLoRA: Hierarchical Low-Rank Adaptation for Personalized Federated Learningcited by 0