mlsanityData to 14 Oct 2026

Collaborative Unsupervised Visual Representation Learning from Decentralized Data

arXiv 2108.06492 ↗First posted 14 Aug 2021cs.DC cs.AI cs.CVcited by 69

Not on the map. Why?

Abstract (arXiv)

Unsupervised representation learning has achieved outstanding performances using centralized data available on the Internet. However, the increasing awareness of privacy protection limits sharing of decentralized unlabeled image data that grows explosively in multiple parties (e.g., mobile phones and cameras). As such, a natural problem is how to leverage these data to learn visual representations for downstream tasks while preserving data privacy. To address this problem, we propose a novel federated unsupervised learning framework, FedU. In this framework, each party trains models from unlabeled data independently using contrastive learning with an online network and a target network. Then, a central server aggregates trained models and updates clients' models with the aggregated model. It preserves data privacy as each party only has access to its raw data. Decentralized data among multiple parties are normally non-independent and identically distributed (non-IID), leading to performance degradation. To tackle this challenge, we propose two simple but effective methods: 1) We design the communication protocol to upload only the encoders of online networks for server aggregation and update them with the aggregated encoder; 2) We introduce a new module to dynamically decide how to update predictors based on the divergence caused by non-IID. The predictor is the other component of the online network. Extensive experiments and ablations demonstrate the effectiveness and significance of FedU. It outperforms training with only one party by over 5% and other methods by over 14% in linear and semi-supervised evaluation on non-IID data.

Key facts. Cited by 69 papers in the map (data through 14 Oct 2026). Builds on 31 of its 44 references that are in the map. First posted on arXiv 14 Aug 2021.

Builds on

31 of 44 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  5. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  7. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  8. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  9. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  10. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  11. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  12. 2016Matching Networks for One Shot Learningcited by 2,255
19 more
  1. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  2. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,845
  3. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
  4. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  5. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
  6. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,382
  7. 2016Colorful Image Colorizationcited by 1,114
  8. 2018Federated Learning with Non-IID Datacited by 1,108
  9. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,066
  10. 2019S4L: Self-Supervised Semi-Supervised Learningcited by 335
  11. 2019Revisiting Self-Supervised Visual Representation Learningcited by 251
  12. 2019Privacy-preserving Federated Brain Tumour Segmentationcited by 169
  13. 2018Multi-Institutional Deep Learning Modeling Without Sharing Patient Data: A Feasibility Study on Brain Tumor Segmentationcited by 149
  14. 2020Federated Unsupervised Representation Learningcited by 93
  15. 2020Performance Optimization for Federated Person Re-identification via Benchmark Analysiscited by 50
  16. 2019Real-World Image Datasets for Federated Learningcited by 30
  17. 2020Towards Utilizing Unlabeled Data in Federated Learning: A Survey and Prospectivecited by 27
  18. 2021EasyFL: A Low-code Federated Learning Platform For Dummiescited by 20
  19. 2021Towards Unsupervised Domain Adaptation for Deep Face Recognition under Privacy Constraints via Federated Learningcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 21; 2023: 15; 2024: 16; 2025: 10; 2026: 6.

69 papers.

Sort:

By area:

  1. 2023When Foundation Model Meets Federated Learning: Motivations, Challenges, and Future Directionscited by 84
  2. 2022Divergence-aware Federated Self-Supervised Learningcited by 73
  3. 2022FedAvg with Fine Tuning: Local Updates Lead to Representation Learningcited by 56
  4. 2023FedMultimodal: A Benchmark For Multimodal Federated Learningcited by 51
  5. 2022Orchestra: Unsupervised Federated Learning via Globally Consistent Clusteringcited by 45
  6. 2022FedX: Unsupervised Federated Learning with Cross Knowledge Distillationcited by 40
  7. 2022Label-Efficient Self-Supervised Federated Learning for Tackling Data Heterogeneity in Medical Imagingcited by 39
  8. 2022CD2-pFed: Cyclic Distillation-guided Channel Decoupling for Model Personalization in Federated Learningcited by 34
  9. 2023L-DAWA: Layer-wise Divergence Aware Weight Aggregation in Federated Self-Supervised Visual Representation Learningcited by 30
  10. 2023Multi-metrics adaptively identifies backdoors in Federated learningcited by 23
  11. 2022Federated Cycling (FedCy): Semi-supervised Federated Learning of Surgical Phasescited by 18
  12. 2022A Hybrid Self-Supervised Learning Framework for Vertical Federated Learningcited by 17
38 more
  1. 2022Federated Self-supervised Learning for Heterogeneous Clientscited by 16
  2. 2022Distributed Contrastive Learning for Medical Image Segmentationcited by 16
  3. 2023Re-thinking Federated Active Learning based on Inter-class Diversitycited by 14
  4. 2024FedMef: Towards Memory-efficient Federated Dynamic Pruningcited by 14
  5. 2022Federated Self-supervised Learning for Video Understandingcited by 13
  6. 2023Federated Learning without Full Labels: A Surveycited by 13
  7. 2024Rethinking the Representation in Federated Unsupervised Learning with Non-IID Datacited by 13
  8. 2022Does Learning from Decentralized Non-IID Unlabeled Data Benefit from Self Supervision?cited by 12
  9. 2023FedWon: Triumphing Multi-domain Federated Learning Without Normalizationcited by 11
  10. 2022Optimizing Performance of Federated Person Re-identification: Benchmarking and Analysiscited by 9
  11. 2023Combating Data Imbalances in Federated Semi-supervised Learning with Dual Regulatorscited by 9
  12. 2024A Comprehensive Survey of Federated Transfer Learning: Challenges, Methods and Applicationscited by 8
  13. 2022Federated Momentum Contrastive Clusteringcited by 7
  14. 2024Federated Unsupervised Domain Generalization using Global and Local Alignment of Gradientscited by 7
  15. 2024COALA: A Practical and Vision-Centric Federated Learning Platformcited by 7
  16. 2022Self-supervised On-device Federated Learning from Unlabeled Streamscited by 6
  17. 2023Contrastive encoder pre-training-based clustered federated learning for heterogeneous datacited by 5
  18. 2024FedSC: Provable Federated Self-supervised Learning with Spectral Contrastive Objective over Non-i.i.d. Datacited by 5
  19. 2024Simple Unsupervised Knowledge Distillation With Space Similaritycited by 5
  20. 2023Tackling the Non-IID Issue in Heterogeneous Federated Learning by Gradient Harmonizationcited by 4
  21. 2024CCFC: Bridging Federated Clustering and Contrastive Learningcited by 4
  22. 2021Towards Communication-Efficient and Privacy-Preserving Federated Representation Learningcited by 3
  23. 2023FedIL: Federated Incremental Learning from Decentralized Unlabeled Data with Convergence Analysiscited by 3
  24. 2023FedMAE: Federated Self-Supervised Learning with One-Block Masked Auto-Encodercited by 3
  25. 2023Language-Guided Transformer for Federated Multi-Label Classificationcited by 3
  26. 2022Federated Training of Dual Encoding Models on Small Non-IID Client Datasetscited by 2
  27. 2024Exploring Federated Self-Supervised Learning for General Purpose Audio Understandingcited by 2
  28. 2024Personalized Federated Learning with Adaptive Feature Aggregation and Knowledge Transfercited by 2
  29. 2024Calibre: Towards Fair and Accurate Personalized Federated Learning with Self-Supervised Learningcited by 2
  30. 2022Smart Multi-tenant Federated Learningcited by 1
  31. 2022Feature Correlation-guided Knowledge Transfer for Federated Self-supervised Learningcited by 1
  32. 2023UFed-GAN: A Secure Federated Learning Framework with Constrained Computation and Unlabeled Datacited by 1
  33. 2024Distributionally Robust Alignment for Medical Federated Vision-Language Pre-training Under Data Heterogeneitycited by 1
  34. 2025FedDyMem: Efficient Federated Learning with Dynamic Memory and Memory-Reduce for Unsupervised Image Anomaly Detectioncited by 1
  35. 2025Federated Self-Supervised Learning for One-Shot Cross-Modal and Cross-Imaging Technique Segmentationcited by 1
  36. 2025SAFE: Self-Adjustment Federated Learning Framework for Remote Sensing Collaborative Perceptioncited by 1
  37. 2025FSSUAVL: A Discriminative Framework using Vision Models for Federated Self-Supervised Audio and Image Understandingcited by 1
  38. 2025BackFed: An Efficient & Standardized Benchmark Suite for Backdoor Attacks in Federated Learningcited by 1

50 most cited of 69 All 69 (JSON)