Privacy Preserving Text Recognition with Gradient-Boosting for Federated Learning

07/14/2020
by   Hanchi Ren, et al.
0

Typical machine learning approaches require centralized data for model training, which may not be possible where restrictions on data sharing are in place due to, for instance, privacy protection. The recently proposed Federated Learning (FL) frame-work allows learning a shared model collaboratively without data being centralized or data sharing among data owners. However, we show in this paper that the generalization ability of the joint model is poor on Non-Independent and Non-Identically Dis-tributed (Non-IID) data, particularly when the Federated Averaging (FedAvg) strategy is used in this collaborative learning framework thanks to the weight divergence phenomenon. We propose a novel boosting algorithm for FL to address this generalisation issue, as well as achieving much faster convergence in gradient based optimization. We demonstrate our Federated Boosting (FedBoost) method on privacy-preserved text recognition, which shows significant improvements in both performance and efficiency. The text images are based on publicly available datasets for fair comparison and we intend to make our implementation public to ensure reproducibility.

READ FULL TEXT

page 1

page 6

page 9

research
01/25/2019

SecureBoost: A Lossless Federated Learning Framework

The protection of user privacy is an important concern in machine learni...
research
07/24/2019

Boosting Privately: Privacy-Preserving Federated Extreme Boosting for Mobile Crowdsensing

The state-of-the-art federated learning brings a new direction for the d...
research
04/15/2023

Gradient-less Federated Gradient Boosting Trees with Learnable Learning Rates

The privacy-sensitive nature of decentralized datasets and the robustnes...
research
05/09/2020

Cloud-based Federated Boosting for Mobile Crowdsensing

The application of federated extreme gradient boosting to mobile crowdse...
research
08/21/2022

Fed-FSNet: Mitigating Non-I.I.D. Federated Learning via Fuzzy Synthesizing Network

Federated learning (FL) has emerged as a promising privacy-preserving di...
research
07/22/2020

FedOCR: Communication-Efficient Federated Learning for Scene Text Recognition

While scene text recognition techniques have been widely used in commerc...
research
01/27/2021

Accuracy and Privacy Evaluations of Collaborative Data Analysis

Distributed data analysis without revealing the individual data has rece...

Please sign up or login with your details

Forgot password? Click here to reset