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

arXiv: https://arxiv.org/abs/1907.01132 · HTML: https://mlsanity.com/paper/1907.01132/

## Key facts

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

## Built on by (most cited first, 30 of 64)

- [Federated Learning on Non-IID Data: A Survey](https://mlsanity.com/paper/2106.06843/) (2021)
- [FedBABU: Towards Enhanced Representation for Federated Image Classification](https://mlsanity.com/paper/2106.06042/) (2021)
- [Heterogeneous Federated Learning: State-of-the-art and Research Challenges](https://mlsanity.com/paper/2307.10616/) (2023)
- [Flexible Clustered Federated Learning for Client-Level Data Distribution Shift](https://mlsanity.com/paper/2108.09749/) (2021)
- [FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reduction](https://mlsanity.com/paper/2205.13462/) (2022)
- [Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction](https://mlsanity.com/paper/2209.15245/) (2022)
- [Towards Federated Clustering: A Federated Fuzzy c-Means Algorithm (FFCM)](https://mlsanity.com/paper/2201.07316/) (2022)
- [Data Heterogeneity-Robust Federated Learning via Group Client Selection in Industrial IoT](https://mlsanity.com/paper/2202.01512/) (2022)
- [Federated Domain Generalization: A Survey](https://mlsanity.com/paper/2306.01334/) (2023)
- [The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learning](https://mlsanity.com/paper/2111.05326/) (2021)
- [Architectural Patterns for the Design of Federated Learning Systems](https://mlsanity.com/paper/2101.02373/) (2021)
- [Scalable federated machine learning with FEDn](https://mlsanity.com/paper/2103.00148/) (2021)
- [FedSAE: A Novel Self-Adaptive Federated Learning Framework in Heterogeneous Systems](https://mlsanity.com/paper/2104.07515/) (2021)
- [HFedMS: Heterogeneous Federated Learning with Memorable Data Semantics in Industrial Metaverse](https://mlsanity.com/paper/2211.03300/) (2022)
- [Re-thinking Federated Active Learning based on Inter-class Diversity](https://mlsanity.com/paper/2303.12317/) (2023)
- [PrivFairFL: Privacy-Preserving Group Fairness in Federated Learning](https://mlsanity.com/paper/2205.11584/) (2022)
- [A Survey on Class Imbalance in Federated Learning](https://mlsanity.com/paper/2303.11673/) (2023)
- [Failure Prediction in Production Line Based on Federated Learning: An Empirical Study](https://mlsanity.com/paper/2101.11715/) (2021)
- [Distributed Pruning Towards Tiny Neural Networks in Federated Learning](https://mlsanity.com/paper/2212.01977/) (2022)
- [Mobility Accelerates Learning: Convergence Analysis on Hierarchical Federated Learning in Vehicular Networks](https://mlsanity.com/paper/2401.09656/) (2024)
- [CSAFL: A Clustered Semi-Asynchronous Federated Learning Framework](https://mlsanity.com/paper/2104.08184/) (2021)
- [Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach](https://mlsanity.com/paper/2502.01145/) (2025)
- [FedDKD: Federated Learning with Decentralized Knowledge Distillation](https://mlsanity.com/paper/2205.00706/) (2022)
- [Study of the performance and scalability of federated learning for medical imaging with intermittent clients](https://mlsanity.com/paper/2207.08581/) (2022)
- [Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions](https://mlsanity.com/paper/2406.10861/) (2024)
- [Federated Learning Versus Classical Machine Learning: A Convergence Comparison](https://mlsanity.com/paper/2107.10976/) (2021)
- [Heterogeneous Federated Learning via Grouped Sequential-to-Parallel Training](https://mlsanity.com/paper/2201.12976/) (2022)
- [On the Design of Communication-Efficient Federated Learning for Health Monitoring](https://mlsanity.com/paper/2211.16952/) (2022)
- [FedILC: Weighted Geometric Mean and Invariant Gradient Covariance for Federated Learning on Non-IID Data](https://mlsanity.com/paper/2205.09305/) (2022)
- [FCA: Taming Long-tailed Federated Medical Image Classification by Classifier Anchoring](https://mlsanity.com/paper/2305.00738/) (2023)

## 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.