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

07/02/2019
by   Moming Duan, et al.
6

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. Compared with FedAvg, the state-of-the-art FL algorithm, Astraea shows +5.59 top-1 accuracy on the imbalanced EMNIST and imbalanced CINIC-10 datasets, respectively. Meanwhile, the communication traffic of Astraea can be 92 than that of FedAvg.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

page 6

page 7

page 9

research
08/22/2021

Flexible Clustered Federated Learning for Client-Level Data Distribution Shift

Federated Learning (FL) enables the multiple participating devices to co...
research
05/19/2021

Prototype Guided Federated Learning of Visual Feature Representations

Federated Learning (FL) is a framework which enables distributed model t...
research
10/14/2020

FedGroup: Ternary Cosine Similarity-based Clustered Federated Learning Framework toward High Accuracy in Heterogeneous Data

Federated Learning (FL) enables the multiple participating devices to co...
research
05/15/2023

FLARE: Detection and Mitigation of Concept Drift for Federated Learning based IoT Deployments

Intelligent, large-scale IoT ecosystems have become possible due to rece...
research
08/14/2023

FedEdge AI-TC: A Semi-supervised Traffic Classification Method based on Trusted Federated Deep Learning for Mobile Edge Computing

As a typical entity of MEC (Mobile Edge Computing), 5G CPE (Customer Pre...
research
07/17/2020

User-Oriented Multi-Task Federated Deep Learning for Mobile Edge Computing

Federated Learning (FL) is a recent approach for collaboratively trainin...
research
03/12/2021

SCEI: A Smart-Contract Driven Edge Intelligence Framework for IoT Systems

Federated learning (FL) utilizes edge computing devices to collaborative...

Please sign up or login with your details

Forgot password? Click here to reset