Saerom Park

Dr. Saerom Park

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 November 2019 in Neural Networks
Verified
Journal Article
Closed access
SPSaerom Park
Saerom Park
JLJaewook Lee
Jaewook Lee
KKKyoungok Kim
Kyoungok Kim

24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
YCYujin Choi
Yujin Choi
JPJinseong Park
Jinseong Park
HKHoki Kim
Hoki Kim
JLJaewook Lee
Jaewook Lee
SPSaerom Park
Saerom Park
Diffusion models have shown their effectiveness in generation tasks by well-approximating the underlying probability distribution. However, diffusion models are known to suffer from an amplified inherent bias from the training data in terms of fairness. While the sampling process of diffusion models can be controlled by conditional guidance, previous works have attempted to find empirical guidance to achieve quantitative fairness. To address this limitation, we propose a fairness-aware sampling method called \textit{attribute switching} mechanism for diffusion models. Without additional training, the proposed sampling can obfuscate sensitive attributes in generated data without relying on classifiers. We mathematically prove and experimentally demonstrate the effectiveness of the proposed method on two key aspects: (i) the generation of fair data and (ii) the preservation of the utility of the generated data.

17 October 2018 in Computational Intelligence and Neuroscience
Verified
Journal Article
Open access
JHJunghoon Hah
Junghoon Hah
WLWoo Jin Lee
Woo Jin Lee
JLJaewook Lee
Jaewook Lee
SPSaerom Park
Saerom Park
This paper describes a new image generation algorithm based on generative adversarial network. With an information-theoretic extension to the autoencoder-based discriminator, this new algorithm is able to learn interpretable representations from the input images. Our model not only adversarially minimizes the Wasserstein distance-based losses of the discriminator and generator but also maximizes the mutual information between small subset of the latent variables and the observation. We also train our model with proportional control theory to keep the equilibrium between the discriminator and the generator balanced, and as a result, our generative adversarial network can mitigate the convergence problem. Through the experiments on real images, we validate our proposed method, which can manipulate the generated images as desired by controlling the latent codes of input variables. In addition, the visual qualities of produced images are effectively maintained, and the model can stably converge to the equilibrium. However, our model has a difficulty in learning disentangling factors because our model does not regularize the independence between the interpretable factors. Therefore, in the future, we will develop a generative model that can learn disentangling factors.

15 August 2022 in Applied Intelligence
Verified
Journal Article
Closed access
PDF file
JBJunyoung Byun
Junyoung Byun
SPSaerom Park
Saerom Park
YCYujin Choi
Yujin Choi
JLJaewook Lee
Jaewook Lee

25 June 2019 in Sustainability
Verified
Journal Article
Open access
PDF file
HKHyungjin Ko
Hyungjin Ko
JLJaewook Lee
Jaewook Lee
JBJunyoung Byun
Junyoung Byun
BSBumho Son
Bumho Son
SPSaerom Park
Saerom Park
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.

31 December 2020 in Electronics Letters
Verified
Journal Article
Open access
PDF file
JBJ. Byun
J. Byun
JLJ. Lee
J. Lee
SPSaerom Park
Saerom Park
The authors proposed a privacy‐preserving evaluation algorithm for support vector clustering with a fully homomorphic encryption. The proposed method assigns clustering labels to encrypted test data with an encrypted support function. This method inherits the advantageous properties of support vector clustering, which is naturally inductive to cluster new test data from complex distributions. The authors efficiently implemented the proposed method with elaborate packing of the plaintexts and avoiding non‐polynomial operations that are not friendly to homomorphic encryption. These experimental results showed that the proposed model is effective in terms of clustering performance and has robustness against the error that occurs from homomorphic evaluation and approximate operations.