mlsanityData to 7 Oct 2026

Active Federated Learning

arXiv 1909.12641 ↗First posted 27 Sep 2019cs.LG stat.MLcited by 63

Not on the map. Why?

Abstract (arXiv)

Federated Learning allows for population level models to be trained without centralizing client data by transmitting the global model to clients, calculating gradients locally, then averaging the gradients. Downloading models and uploading gradients uses the client's bandwidth, so minimizing these transmission costs is important. The data on each client is highly variable, so the benefit of training on different clients may differ dramatically. To exploit this we propose Active Federated Learning, where in each round clients are selected not uniformly at random, but with a probability conditioned on the current model and the data on the client to maximize efficiency. We propose a cheap, simple and intuitive sampling scheme which reduces the number of required training iterations by 20-70% while maintaining the same model accuracy, and which mimics well known resampling techniques under certain conditions.

Key facts. Cited by 63 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 8; 2023: 14; 2024: 15; 2025: 11; 2026: 6.

63 papers.

Sort:

By area:

  1. 2023Towards Building the Federated GPT: Federated Instruction Tuningcited by 184
  2. 2021On Large-Cohort Training for Federated Learningcited by 73
  3. 2021Towards Fairness-Aware Federated Learningcited by 57
  4. 2021FedCor: Correlation-Based Active Client Selection Strategy for Heterogeneous Federated Learningcited by 43
  5. 2022Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reductioncited by 32
  6. 2023On the Convergence of Federated Averaging with Cyclic Client Participationcited by 31
  7. 2022Communication-Efficient Device Scheduling for Federated Learning Using Stochastic Optimizationcited by 28
  8. 2021FedSAE: A Novel Self-Adaptive Federated Learning Framework in Heterogeneous Systemscited by 16
  9. 2023On the Role of Server Momentum in Federated Learningcited by 16
  10. 2022Knowledge-Aware Federated Active Learning with Non-IID Datacited by 15
  11. 2024FedImpro: Measuring and Improving Client Update in Federated Learningcited by 15
  12. 2022Fed-FSNet: Mitigating Non-I.I.D. Federated Learning via Fuzzy Synthesizing Networkcited by 14
38 more
  1. 2023Exploiting Label Skews in Federated Learning with Model Concatenationcited by 14
  2. 2023A Survey on Class Imbalance in Federated Learningcited by 12
  3. 2025From Points to Coalitions: Hierarchical Contrastive Shapley Values for Prioritizing Data Samplescited by 12
  4. 2023Towards Interpretable Federated Learningcited by 11
  5. 2022A Snapshot of the Frontiers of Client Selection in Federated Learningcited by 9
  6. 2024FedGCS: A Generative Framework for Efficient Client Selection in Federated Learning via Gradient-based Optimizationcited by 9
  7. 2021Is Shapley Value fair? Improving Client Selection for Mavericks in Federated Learningcited by 7
  8. 2021Dubhe: Towards Data Unbiasedness with Homomorphic Encryption in Federated Learning Client Selectioncited by 7
  9. 2023FedDebug: Systematic Debugging for Federated Learning Applicationscited by 6
  10. 2023A Comprehensive Survey On Client Selections in Federated Learningcited by 6
  11. 2021Sustainable Federated Learningcited by 5
  12. 2024FedFair^3: Unlocking Threefold Fairness in Federated Learningcited by 5
  13. 2022FedMint: Intelligent Bilateral Client Selection in Federated Learning with Newcomer IoT Devicescited by 4
  14. 2023Privacy-preserving and Uncertainty-aware Federated Trajectory Prediction for Connected Autonomous Vehiclescited by 4
  15. 2024FedReMa: Improving Personalized Federated Learning via Leveraging the Most Relevant Clientscited by 3
  16. 2022Online Meta-Learning for Model Update Aggregation in Federated Learning for Click-Through Rate Predictioncited by 2
  17. 2023Heterogeneity-Guided Client Sampling: Towards Fast and Efficient Non-IID Federated Learningcited by 2
  18. 2024Ranking-based Client Selection with Imitation Learning for Efficient Federated Learningcited by 2
  19. 2024SFedCA: Credit Assignment-Based Active Client Selection Strategy for Spiking Federated Learningcited by 2
  20. 2025Widening the Network Mitigates the Impact of Data Heterogeneity on FedAvgcited by 2
  21. 2022Over-the-Air Federated Multi-Task Learning via Model Sparsification and Turbo Compressed Sensingcited by 1
  22. 2023Welfare and Fairness Dynamics in Federated Learning: A Client Selection Perspectivecited by 1
  23. 2023LEFL: Low Entropy Client Sampling in Federated Learningcited by 1
  24. 2024Emulating Full Participation: An Effective and Fair Client Selection Strategy for Federated Learningcited by 1
  25. 2024Load Balancing in Federated Learningcited by 1
  26. 2024TIFeD: a Tiny Integer-based Federated learning algorithm with Direct feedback alignmentcited by 1
  27. 2025VFL-RPS: Relevant Participant Selection in Vertical Federated Learningcited by 1
  28. 2025Communication-Efficient Device Scheduling for Federated Learning Using Lyapunov Optimizationcited by 1
  29. 2025Fairness in Federated Learning: Fairness for Whom?cited by 1
  30. 2025FedABC: Attention-Based Client Selection for Federated Learning with Long-Term Viewcited by 1
  31. 2021FedProf: Selective Federated Learning with Representation Profilingcited by 0
  32. 2021Over-the-Air Federated Multi-Task Learningcited by 0
  33. 2023FedCliP: Federated Learning with Client Pruningcited by 0
  34. 2023Distributed sequential federated learningcited by 0
  35. 2024FLASH: Federated Learning Across Simultaneous Heterogeneitiescited by 0
  36. 2024Active ML for 6G: Towards Efficient Data Generation, Acquisition, and Annotationcited by 0
  37. 2024Differentially Private Active Learning: Balancing Effective Data Selection and Privacycited by 0
  38. 2024Age-of-Gradient Updates for Federated Learning over Random Access Channelscited by 0

50 most cited of 63 All 63 (JSON)