Junyoung Byun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Junyoung Byun has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Jaewook Lee
Seoul National University
6 shared publications - Hyungjin Ko
Department of Consumer Science, Sungkyunkwan University, Seoul, South Korea
4 shared publications - Yujin Choi
Seoul National University
4 shared publications Jaewook Lee
3 shared publications- Saerom Park
Ulsan National Institute of Science and Technology, Ulsan, Republic of Korea
3 shared publications - Bumho Son
Department of Business Administration, Chung-Ang University, Seoul, Republic of Korea
1 shared publication
Latest Publications
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (10) , 1-12
Communication-Efficient Federated Traffic Prediction via Hierarchical Split Learning
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (10) , 1-12
Communication-Efficient Federated Traffic Prediction via Hierarchical Split Learning
- 15 November 2025
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 163
Differentially private upsampling for enhanced anomaly detection in imbalanced data
- 15 November 2025
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 163
Differentially private upsampling for enhanced anomaly detection in imbalanced data
- 9 June 2025
- Published by Elsevier in Future Generation Computer Systems
- Vol. 174
Advancing financial privacy: A novel integrative approach for privacy-preserving optimal portfolio
- 9 June 2025
- Published by Elsevier in Future Generation Computer Systems
- Vol. 174
Advancing financial privacy: A novel integrative approach for privacy-preserving optimal portfolio
- 20 August 2024
- Published by Elsevier in Pattern Recognition
- Vol. 157
Improving the utility of differentially private clustering through dynamical processing
- 20 August 2024
- Published by Elsevier in Pattern Recognition
- Vol. 157
Improving the utility of differentially private clustering through dynamical processing
- 26 July 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 256
Privacy-preserving inference resistant to model extraction attacks
- 26 July 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 256
Privacy-preserving inference resistant to model extraction attacks
- 13 March 2023
- Published by Elsevier in Finance Research Letters
- Vol. 54
A Privacy-preserving mean–variance optimal portfolio
- 13 March 2023
- Published by Elsevier in Finance Research Letters
- Vol. 54
A Privacy-preserving mean–variance optimal portfolio
- 15 August 2022
- Published by Springer Nature in Applied Intelligence
- Vol. 53 (9) , 10114-10129
Efficient homomorphic encryption framework for privacy-preserving regression
- 15 August 2022
- Published by Springer Nature in Applied Intelligence
- Vol. 53 (9) , 10114-10129
Efficient homomorphic encryption framework for privacy-preserving regression
- 20 April 2022
- Published by Elsevier in Pattern Recognition
- Vol. 129
Variational cycle-consistent imputation adversarial networks for general missing patterns
- 20 April 2022
- Published by Elsevier in Pattern Recognition
- Vol. 129
Variational cycle-consistent imputation adversarial networks for general missing patterns
- Open Access
- 25 June 2019
- Published by MDPI AG in Sustainability
- Vol. 11 (12) , 3489
Loss-Driven Adversarial Ensemble Deep Learning for On-Line Time Series Analysis
Developing a robust and sustainable system is an important problem in which deep learning models are used in real-world applications. Ensemble methods combine diverse models to improve performance and achieve robustness. The analysis of time series data requires dealing with continuously incoming instances; however, most ensemble models suffer when adapting to a change in data distribution. Therefore, we propose an on-line ensemble deep learning algorithm that aggregates deep learning models and adjusts the ensemble weight based on loss value in this study. We theoretically demonstrate that the ensemble weight converges to the limiting distribution, and, thus, minimizes the average total loss from a new regret measure based on adversarial assumption. We also present an overall framework that can be applied to analyze time series. In the experiments, we focused on the on-line phase, in which the ensemble models predict the binary class for the simulated data and the financial and non-financial real data. The proposed method outperformed other ensemble approaches. Moreover, our method was not only robust to the intentional attacks but also sustainable in data distribution changes. In the future, our algorithm can be extended to regression and multiclass classification problems.
- 25 June 2019
- Published by MDPI AG in Sustainability
- Vol. 11 (12) , 3489
Open AccessLoss-Driven Adversarial Ensemble Deep Learning for On-Line Time Series Analysis
Developing a robust and sustainable system is an important problem in which deep learning models are used in real-world applications. Ensemble methods combine diverse models to improve performance and achieve robustness. The analysis of time series data requires dealing with continuously incoming instances; however, most ensemble models suffer when adapting to a change in data distribution. Therefore, we propose an on-line ensemble deep learning algorithm that aggregates deep learning models and adjusts the ensemble weight based on loss value in this study. We theoretically demonstrate that the ensemble weight converges to the limiting distribution, and, thus, minimizes the average total loss from a new regret measure based on adversarial assumption. We also present an overall framework that can be applied to analyze time series. In the experiments, we focused on the on-line phase, in which the ensemble models predict the binary class for the simulated data and the financial and non-financial real data. The proposed method outperformed other ensemble approaches. Moreover, our method was not only robust to the intentional attacks but also sustainable in data distribution changes. In the future, our algorithm can be extended to regression and multiclass classification problems.