mlsanityData to 14 Oct 2026

Federated Visual Classification with Real-World Data Distribution

arXiv 2003.08082 ↗First posted 18 Mar 2020cs.LG cs.CV stat.MLcited by 128

Not on the map. Why?

Abstract (arXiv)

Federated Learning enables visual models to be trained on-device, bringing advantages for user privacy (data need never leave the device), but challenges in terms of data diversity and quality. Whilst typical models in the datacenter are trained using data that are independent and identically distributed (IID), data at source are typically far from IID. Furthermore, differing quantities of data are typically available at each device (imbalance). In this work, we characterize the effect these real-world data distributions have on distributed learning, using as a benchmark the standard Federated Averaging (FedAvg) algorithm. To do so, we introduce two new large-scale datasets for species and landmark classification, with realistic per-user data splits that simulate real-world edge learning scenarios. We also develop two new algorithms (FedVC, FedIR) that intelligently resample and reweight over the client pool, bringing large improvements in accuracy and stability in training. The datasets are made available online.

Key facts. Cited by 128 papers in the map (data through 14 Oct 2026). First posted on arXiv 18 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 24; 2022: 35; 2023: 22; 2024: 24; 2025: 14; 2026: 9.

128 papers.

Sort:

By area:

  1. 2021Model-Contrastive Federated Learningcited by 766
  2. 2021Towards Personalized Federated Learningcited by 464
  3. 2021Federated Learning on Non-IID Data: A Surveycited by 346
  4. 2021A Field Guide to Federated Optimizationcited by 315
  5. 2021FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Spacecited by 287
  6. 2021No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Datacited by 241
  7. 2022FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settingscited by 125
  8. 2022Federated Learning with Partial Model Personalizationcited by 114
  9. 2022Improving Generalization in Federated Learning by Seeking Flat Minimacited by 98
  10. 2023Personalized Federated Learning with Feature Alignment and Classifier Collaborationcited by 97
  11. 2023Deep Model Fusion: A Surveycited by 91
  12. 2022On the Importance and Applicability of Pre-Training for Federated Learningcited by 71
38 more
  1. 2022Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learningcited by 71
  2. 2023FedFed: Feature Distillation against Data Heterogeneity in Federated Learningcited by 54
  3. 2022Virtual Homogeneity Learning: Defending against Data Heterogeneity in Federated Learningcited by 52
  4. 2022Preserving Privacy in Federated Learning with Ensemble Cross-Domain Knowledge Distillationcited by 45
  5. 2021Cluster-driven Graph Federated Learning over Multiple Domainscited by 44
  6. 2021Federated Multi-Target Domain Adaptationcited by 44
  7. 2021FedCor: Correlation-Based Active Client Selection Strategy for Heterogeneous Federated Learningcited by 43
  8. 2022FedDrive: Generalizing Federated Learning to Semantic Segmentation in Autonomous Drivingcited by 41
  9. 2021FedCV: A Federated Learning Framework for Diverse Computer Vision Taskscited by 32
  10. 2024Relaxed Contrastive Learning for Federated Learningcited by 32
  11. 2022Motley: Benchmarking Heterogeneity and Personalization in Federated Learningcited by 31
  12. 2022Acceleration of Federated Learning with Alleviated Forgetting in Local Trainingcited by 29
  13. 2022Federated Adaptive Prompt Tuning for Multi-Domain Collaborative Learningcited by 29
  14. 2022FedFM: Anchor-based Feature Matching for Data Heterogeneity in Federated Learningcited by 27
  15. 2023Federated Generalized Category Discoverycited by 27
  16. 2024FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-Tuningcited by 27
  17. 2021Resource-Efficient Federated Learningcited by 26
  18. 2022Towards Federated Learning against Noisy Labels via Local Self-Regularizationcited by 26
  19. 2022Learning to Generate Image Embeddings with User-level Differential Privacycited by 23
  20. 2021Prototype Guided Federated Learning of Visual Feature Representationscited by 22
  21. 2022FLAIR: Federated Learning Annotated Image Repositorycited by 22
  22. 2021FedDis: Disentangled Federated Learning for Unsupervised Brain Pathology Segmentationcited by 19
  23. 2022SphereFed: Hyperspherical Federated Learningcited by 19
  24. 2023GPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated Learningcited by 18
  25. 2022DReS-FL: Dropout-Resilient Secure Federated Learning for Non-IID Clients via Secret Data Sharingcited by 17
  26. 2023Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancercited by 17
  27. 2022Semi-Decentralized Federated Learning with Collaborative Relayingcited by 16
  28. 2022Knowledge-Aware Federated Active Learning with Non-IID Datacited by 16
  29. 2022FedSkip: Combatting Statistical Heterogeneity with Federated Skip Aggregationcited by 16
  30. 2021On Bridging Generic and Personalized Federated Learning for Image Classificationcited by 15
  31. 2021Decentralized Unsupervised Learning of Visual Representationscited by 15
  32. 2023AEDFL: Efficient Asynchronous Decentralized Federated Learning with Heterogeneous Devicescited by 15
  33. 2024FedImpro: Measuring and Improving Client Update in Federated Learningcited by 15
  34. 2024Personalized Federated Learning via Feature Distribution Adaptationcited by 13
  35. 2024Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directionscited by 13
  36. 2021A Quantitative Metric for Privacy Leakage in Federated Learningcited by 12
  37. 2022FedNorm: Modality-Based Normalization in Federated Learning for Multi-Modal Liver Segmentationcited by 12
  38. 2023Federated Learning over Coupled Graphscited by 12

50 most cited of 128 All 128 (JSON)