mlsanityData to 14 Oct 2026

Astraea: Self-balancing Federated Learning for Improving Classification Accuracy of Mobile Deep Learning Applications

arXiv 1907.01132 ↗First posted 2 Jul 2019cs.LG cs.DC stat.MLcited by 64

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) is a distributed deep learning method which enables multiple participants, such as mobile phones and IoT devices, to contribute a neural network model while their private training data remains in local devices. This distributed approach is promising in the edge computing system where have a large corpus of decentralized data and require high privacy. However, unlike the common training dataset, the data distribution of the edge computing system is imbalanced which will introduce biases in the model training and cause a decrease in accuracy of federated learning applications. In this paper, we demonstrate that the imbalanced distributed training data will cause accuracy degradation in FL. To counter this problem, we build a self-balancing federated learning framework call Astraea, which alleviates the imbalances by 1) Global data distribution based data augmentation, and 2) Mediator based multi-client rescheduling. The proposed framework relieves global imbalance by runtime data augmentation, and for averaging the local imbalance, it creates the mediator to reschedule the training of clients based on Kullback-Leibler divergence (KLD) of their data distribution. Compared with FedAvg, the state-of-the-art FL algorithm, Astraea shows +5.59% and +5.89% improvement of top-1 accuracy on the imbalanced EMNIST and imbalanced CINIC-10 datasets, respectively. Meanwhile, the communication traffic of Astraea can be 82% lower than that of FedAvg.

Key facts. Cited by 64 papers in the map (data through 14 Oct 2026). First posted on arXiv 2 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 13; 2022: 18; 2023: 13; 2024: 10; 2025: 8; 2026: 2.

64 papers.

Sort:

By area:

  1. 2021Federated Learning on Non-IID Data: A Surveycited by 346
  2. 2021FedBABU: Towards Enhanced Representation for Federated Image Classificationcited by 182
  3. 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 161
  4. 2021Flexible Clustered Federated Learning for Client-Level Data Distribution Shiftcited by 47
  5. 2022FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reductioncited by 35
  6. 2022Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reductioncited by 32
  7. 2022Towards Federated Clustering: A Federated Fuzzy c-Means Algorithm (FFCM)cited by 30
  8. 2022Data Heterogeneity-Robust Federated Learning via Group Client Selection in Industrial IoTcited by 25
  9. 2023Federated Domain Generalization: A Surveycited by 25
  10. 2021The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learningcited by 23
  11. 2021Architectural Patterns for the Design of Federated Learning Systemscited by 17
  12. 2021Scalable federated machine learning with FEDncited by 16
38 more
  1. 2021FedSAE: A Novel Self-Adaptive Federated Learning Framework in Heterogeneous Systemscited by 16
  2. 2022HFedMS: Heterogeneous Federated Learning with Memorable Data Semantics in Industrial Metaversecited by 14
  3. 2023Re-thinking Federated Active Learning based on Inter-class Diversitycited by 14
  4. 2022PrivFairFL: Privacy-Preserving Group Fairness in Federated Learningcited by 13
  5. 2023A Survey on Class Imbalance in Federated Learningcited by 13
  6. 2021Failure Prediction in Production Line Based on Federated Learning: An Empirical Studycited by 11
  7. 2022Distributed Pruning Towards Tiny Neural Networks in Federated Learningcited by 11
  8. 2024Mobility Accelerates Learning: Convergence Analysis on Hierarchical Federated Learning in Vehicular Networkscited by 11
  9. 2021CSAFL: A Clustered Semi-Asynchronous Federated Learning Frameworkcited by 10
  10. 2025Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approachcited by 10
  11. 2022FedDKD: Federated Learning with Decentralized Knowledge Distillationcited by 9
  12. 2022Study of the performance and scalability of federated learning for medical imaging with intermittent clientscited by 9
  13. 2024Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutionscited by 9
  14. 2021Federated Learning Versus Classical Machine Learning: A Convergence Comparisoncited by 7
  15. 2022Heterogeneous Federated Learning via Grouped Sequential-to-Parallel Trainingcited by 7
  16. 2022On the Design of Communication-Efficient Federated Learning for Health Monitoringcited by 6
  17. 2022FedILC: Weighted Geometric Mean and Invariant Gradient Covariance for Federated Learning on Non-IID Datacited by 4
  18. 2023FCA: Taming Long-tailed Federated Medical Image Classification by Classifier Anchoringcited by 4
  19. 2022TinyMLOps: Operational Challenges for Widespread Edge AI Adoptioncited by 3
  20. 2023DPP-based Client Selection for Federated Learning with Non-IID Datacited by 3
  21. 2023Towards Open Federated Learning Platforms: Survey and Vision from Technical and Legal Perspectivescited by 3
  22. 2023Tram-FL: Routing-based Model Training for Decentralized Federated Learningcited by 3
  23. 2025pMixFed: Efficient Personalized Federated Learning through Adaptive Layer-Wise Mixupcited by 3
  24. 2021Management of Resource at the Network Edge for Federated Learningcited by 2
  25. 2022FedRN: Exploiting k-Reliable Neighbors Towards Robust Federated Learningcited by 2
  26. 2022Combining Stochastic Defenses to Resist Gradient Inversion: An Ablation Studycited by 2
  27. 2023FLASH-RL: Federated Learning Addressing System and Static Heterogeneity using Reinforcement Learningcited by 2
  28. 2024Federated Learning for Blind Image Super-Resolutioncited by 2
  29. 2025Efficient Federated Learning with Heterogeneous Data and Adaptive Dropoutcited by 2
  30. 2025FedGA: A Fair Federated Learning Framework Based on the Gini Coefficientcited by 2
  31. 2021ARFED: Attack-Resistant Federated averaging based on outlier eliminationcited by 1
  32. 2022TOFU: Towards Obfuscated Federated Updates by Encoding Weight Updates into Gradients from Proxy Datacited by 1
  33. 2022Improving the Robustness of Federated Learning for Severely Imbalanced Datasetscited by 1
  34. 2022Suppressing Noise from Built Environment Datasets to Reduce Communication Rounds for Convergence of Federated Learningcited by 1
  35. 2023A Secure Aggregation for Federated Learning on Long-Tailed Datacited by 1
  36. 2023Federated Learning on Edge Sensing Devices: A Reviewcited by 1
  37. 2023LEFL: Low Entropy Client Sampling in Federated Learningcited by 1
  38. 2024A Multi-Level Approach for Class Imbalance Problem in Federated Learning for Remote Industry 4.0 Applicationscited by 1

50 most cited of 64 All 64 (JSON)