mlsanityData to 14 Oct 2026

Cooperative Pseudo Labeling for Unsupervised Federated Classification

arXiv 2510.10100 ↗First posted 11 Oct 2025cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Unsupervised Federated Learning (UFL) aims to collaboratively train a global model across distributed clients without sharing data or accessing label information. Previous UFL works have predominantly focused on representation learning and clustering tasks. Recently, vision language models (e.g., CLIP) have gained significant attention for their powerful zero-shot prediction capabilities. Leveraging this advancement, classification problems that were previously infeasible under the UFL paradigm now present promising new opportunities, yet remain largely unexplored. In this paper, we extend UFL to the classification problem with CLIP for the first time and propose a novel method, underlineFederated underlineCooperative underlinePseudo underlineLabeling (FedCoPL). Specifically, clients estimate and upload their pseudo label distribution, and the server adjusts and redistributes them to avoid global imbalance among classes. Moreover, we introduce a partial prompt aggregation protocol for effective collaboration and personalization. In particular, visual prompts containing general image features are aggregated at the server, while text prompts encoding personalized knowledge are retained locally. Extensive experiments demonstrate the superior performance of our FedCoPL compared to baseline methods. Our code is available at hrefhttps://github.com/krumpguo/FedCoPLhttps://github.com/krumpguo/FedCoPL.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 53 of its 62 references that are in the map. First posted on arXiv 11 Oct 2025.

Builds on

53 of 62 references.

References · 53

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  5. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  6. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  7. 2021Learning to Prompt for Vision-Language Modelscited by 2,281
  8. 2013Describing Textures in the Wildcited by 2,125
  9. 2022Visual Prompt Tuningcited by 1,681
  10. 2019VisualBERT: A Simple and Performant Baseline for Vision and Languagecited by 1,296
  11. 2017Remote Sensing Image Scene Classification: Benchmark and State of the Artcited by 797
  12. 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 568
38 more
  1. 2022Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Modelscited by 382
  2. 2021Federated Learning on Non-IID Data: A Surveycited by 346
  3. 2021No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Datacited by 241
  4. 2022Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learningcited by 172
  5. 2023LingoQA: Visual Question Answering for Autonomous Drivingcited by 145
  6. 2022PromptFL: Let Federated Participants Cooperatively Learn Prompts Instead of Models -- Federated Learning in Age of Foundation Modelcited by 134
  7. 2022Unsupervised Prompt Learning for Vision-Language Modelscited by 127
  8. 2020Federated Unsupervised Representation Learningcited by 93
  9. 2022Divergence-aware Federated Self-Supervised Learningcited by 73
  10. 2023FedCLIP: Fast Generalization and Personalization for CLIP in Federated Learningcited by 70
  11. 2021Collaborative Unsupervised Visual Representation Learning from Decentralized Datacited by 69
  12. 2023FedDisco: Federated Learning with Discrepancy-Aware Collaborationcited by 67
  13. 2023Efficient Model Personalization in Federated Learning via Client-Specific Prompt Generationcited by 54
  14. 2022Dual Modality Prompt Tuning for Vision-Language Pre-Trained Modelcited by 52
  15. 2022Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learningcited by 46
  16. 2024Global and Local Prompts Cooperation via Optimal Transport for Federated Learningcited by 46
  17. 2022Orchestra: Unsupervised Federated Learning via Globally Consistent Clusteringcited by 45
  18. 2022FedX: Unsupervised Federated Learning with Cross Knowledge Distillationcited by 40
  19. 2023Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuningcited by 30
  20. 2023L-DAWA: Layer-wise Divergence Aware Weight Aggregation in Federated Self-Supervised Visual Representation Learningcited by 30
  21. 2022Federated Adaptive Prompt Tuning for Multi-Domain Collaborative Learningcited by 29
  22. 2023POUF: Prompt-oriented unsupervised fine-tuning for large pre-trained modelscited by 29
  23. 2024Harmonizing Generalization and Personalization in Federated Prompt Learningcited by 27
  24. 2023Improving Compositional Text-to-image Generation with Large Vision-Language Modelscited by 24
  25. 2022Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clientscited by 20
  26. 2024Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Datacited by 20
  27. 2023Text-driven Prompt Generation for Vision-Language Models in Federated Learningcited by 17
  28. 2024Mixture of Experts Made Personalized: Federated Prompt Learning for Vision-Language Modelscited by 17
  29. 2023PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guaranteescited by 15
  30. 2023Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimizationcited by 13
  31. 2024Rethinking the Representation in Federated Unsupervised Learning with Non-IID Datacited by 13
  32. 2023ProtoFL: Unsupervised Federated Learning via Prototypical Distillationcited by 12
  33. 2024Exploring Vacant Classes in Label-Skewed Federated Learningcited by 10
  34. 2022Federated Semi-Supervised Learning with Prototypical Networkscited by 8
  35. 2024Beyond Local Sharpness: Communication-Efficient Global Sharpness-aware Minimization for Federated Learningcited by 8
  36. 2023Towards the Theory of Unsupervised Federated Learning: Non-asymptotic Analysis of Federated EM Algorithmscited by 7
  37. 2023Dynamic Heterogeneous Federated Learning with Multi-Level Prototypescited by 7
  38. 2024Federated Unsupervised Domain Generalization using Global and Local Alignment of Gradientscited by 7

50 most cited of 53 All 53 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023CLIP-guided Federated Learning on Heterogeneous and Long-Tailed Data
  2. 2025FedDEAP: Adaptive Dual-Prompt Tuning for Multi-Domain Federated Learning
  3. 2025Zero-Shot Decentralized Federated Learning
  4. 2026FedSIR: Spectral Client Identification and Relabeling for Federated Learning with Noisy Labels
  5. 2025FedRSClip: Federated Learning for Remote Sensing Scene Classification Using Vision-Language Models
  6. 2026FedSSMCoOp: SSM Encoders for light-weight Federated Prompt Learning for Few-shot Classification
  7. 2025CAPT: Class-Aware Prompt Tuning for Federated Long-Tailed Learning with Vision-Language Model
  8. 2026FedMPT: Federated Multi-label Prompt Tuning of Vision-Language Models