185 409

Cited 21 times in

Implementing Vertical Federated Learning Using Autoencoders: Practical Application, Generalizability, and Utility Study

 Dongchul Cha  ;  MinDong Sung  ;  Yu-Rang Park 
 JMIR MEDICAL INFORMATICS, Vol.9(6) : e26598, 2021-06 
Journal Title
Issue Date
coding ; data ; data sharing ; dataset ; federated learning ; machine learning ; model ; performance ; privacy ; protection ; security ; training ; unsupervised learning ; vertically incomplete data
Background: Machine learning (ML) is now widely deployed in our everyday lives. Building robust ML models requires a massive amount of data for training. Traditional ML algorithms require training data centralization, which raises privacy and data governance issues. Federated learning (FL) is an approach to overcome this issue. We focused on applying FL on vertically partitioned data, in which an individual's record is scattered among different sites.

Objective: The aim of this study was to perform FL on vertically partitioned data to achieve performance comparable to that of centralized models without exposing the raw data.

Methods: We used three different datasets (Adult income, Schwannoma, and eICU datasets) and vertically divided each dataset into different pieces. Following the vertical division of data, overcomplete autoencoder-based model training was performed for each site. Following training, each site's data were transformed into latent data, which were aggregated for training. A tabular neural network model with categorical embedding was used for training. A centrally based model was used as a baseline model, which was compared to that of FL in terms of accuracy and area under the receiver operating characteristic curve (AUROC).

Results: The autoencoder-based network successfully transformed the original data into latent representations with no domain knowledge applied. These altered data were different from the original data in terms of the feature space and data distributions, indicating appropriate data security. The loss of performance was minimal when using an overcomplete autoencoder; accuracy loss was 1.2%, 8.89%, and 1.23%, and AUROC loss was 1.1%, 0%, and 1.12% in the Adult income, Schwannoma, and eICU dataset, respectively.

Conclusions: We proposed an autoencoder-based ML model for vertically incomplete data. Since our model is based on unsupervised learning, no domain-specific knowledge is required in individual sites. Under the circumstances where direct data sharing is not available, our approach may be a practical solution enabling both data protection and building a robust model.
Files in This Item:
T202103022.pdf Download
Appears in Collections:
1. College of Medicine (의과대학) > Dept. of Biomedical Systems Informatics (의생명시스템정보학교실) > 1. Journal Papers
1. College of Medicine (의과대학) > Dept. of Internal Medicine (내과학교실) > 1. Journal Papers
1. College of Medicine (의과대학) > Dept. of Otorhinolaryngology (이비인후과학교실) > 1. Journal Papers
Yonsei Authors
Park, Yu Rang(박유랑) ORCID logo https://orcid.org/0000-0002-4210-2094
Sung, MinDong(성민동) ORCID logo https://orcid.org/0000-0002-5217-8877
Cha, Dongchul(차동철) ORCID logo https://orcid.org/0000-0002-0043-5026
사서에게 알리기


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.