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

## TL;DR

Astraea is a novel federated learning framework that improves classification accuracy on mobile devices by addressing data imbalance through data augmentation and client rescheduling, reducing communication costs.

## Contribution

Astraea introduces a self-balancing federated learning framework combining global data augmentation and mediator-based client rescheduling to mitigate data imbalance effects.

## Key findings

- Achieves +5.59% and +5.89% accuracy improvements on imbalanced datasets.
- Reduces communication traffic by 82% compared to FedAvg.
- Effectively alleviates data imbalance in federated learning environments.

## Abstract

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.