Applied Artificial Intelligence Laboratory
Department of Industrial and Systems Engineering
KAIST, Daejeon, Republic of Korea
Contact: tmdwo0910 [at] kaist.ac.kr / tmdwo0910 [at] gmail.com
Homepage : https://sites.google.com/view/seungjae-shin
- Dataset Optimization (e.g. Dataset Selection, Dataset Condensation)
- Representation Learning, Generative Model
- Generalization (e.g. Debiasing, Fairness)
Korea Advanced Institute of Science and Technology (KAIST), Daejeon, the Republic of Korea (Mar. 2020 - present)
- Course of Doctor's Degree in AAILab, ISysE
- Academic Advisor: Professor Il-Chul Moon
Korea Advanced Institute of Science and Technology (KAIST), Daejeon, the Republic of Korea (Mar. 2018 ~ Feb. 2020)
- Master's Degree in AAILab, ISysE
- Academic Advisor: Professor Il-Chul Moon
Korea Advanced Institute of Science and Technology (KAIST), Daejeon, the Republic of Korea (Mar. 2013 ~ Feb. 2018)
- Bachelor of Science in Industrial and Systems Engineering (Minor. Science in Business and Technology Management)
PUBLICATIONS (* denotes the equal contribution.)
- Seungjae Shin*, HeeSun Bae*, DongHyeok Shin, Weonyoung Joo, Il-Chul Moon "Loss Curvature Matching for Dataset Selection and Condensation", International Conference on Artificial Intelligence and Statistics (AISTATS) 2023
- Seungjae Shin*, Heesun Bae*, Giwoon Kim, Youngsoon Cho, Dongwook Lee, Donggil Jeong, HyunJoon Kim, Hyunjung Lee, Hyungjun Moon, "Evaluation of Optimal Scene Time Interval for Out-of-hospital Cardiac Arrest using a Deep Neural Network", American Journal of Emergency Medicine
- Seungjae Shin, Byeonghu Na, HeeSun Bae, JoonHo Jang, Hyemi Kim, Kyungwoo Song, Youngjae Cho, Il-Chul Moon "Improving Group-based Robustness and Calibration via Ordered Risk and Confidence Regularization", Workshop on Spurious Correlations, Invariance, and Stability on International Conference on Machine Learning (ICML-SCIS) 2022
- HeeSun Bae*, Seungjae Shin*, Byeonghu Na, JoonHo Jang, Kyungwoo Song, Il-Chul Moon, "From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model", International Conference on Machine Learning (ICML 2022), Baltimore, Jul 17, 2022
- Dongjun Kim, Seungjae Shin, Kyungwoo Song, Wanmo Kang, Il-Chul Moon, "Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation", International Conference on Machine Learning (ICML 2022), Baltimore, Jul 17, 2022
- Hyuck Lee, Seungjae Shin, Heeyoung Kim "ABC : Auxiliary Balanced Classifier for Class-imbalanced Semi-supervised Learning" Conference on Neural Information Processing Systems (NeurIPS), 2021.
- Mingi Ji, Seungjae Shin, Seunghyun Hwang, Gibeom Park, Il-Chul Moon "Refine Myself by Teaching Myself : Feature Refinement via Self-Knowledge Distillation" IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
- Hyemi Kim, Seungjae Shin, JoonHo Jang, Kyungwoo Song, Weonyoung Joo, Wanmo Kang, Il-Chul Moon "Counterfactual Fairness with Disentangled Causal Effect Variational Autoencoder" AAAI Conference on Artificial Intelligence (AAAI) 2021.
- Seungjae Shin, Kyungwoo Song, Joonho Jang, Hyemi Kim, Weonyoung Joo, and Il-Chul Moon “Neutralizing Gender Bias in Word Embedding with Latent Disentanglement and Counterfactual Generation” Findings of Empirical Methods in Natural Language Processing (Findings of EMNLP) 2020.
- Kyungwoo Song, JoonHo Jang, Seungjae Shin, and Il-Chul Moon “Bivariate Beta-LSTM” AAAI Conference on Artificial Intelligence (AAAI) 2020.
- Joonho Jang, Seungjae Shin, Hyunjin Lee, Il-Chul Moon "Forecasting the Concentration of Particulate Matter in the Seoul Metropolitan Area Using a Gaussian Process Model" Sensors 2020
- Yongjin Shin, Gihun Lee, Seungjae Shin, Se-young Yun, Il-Chul Moon "FEWER : Federated Weight Recovery" DistributedML'20: Proceedings of the 1st Workshop on Distributed Machine Learning
- Dongjun Kim, Kyungwoo Song, Seungjae Shin, Il-Chul Moon "Posterior-Aided Regularization for Likelihood-Free Inference"
- Dongjun Kim, Weonyoung Joo, Seungjae Shin, Il-Chul Moon "Adversarial Likelihood-Free Inference on Black-Box Generator"
- Weonyoung Joo, Dongjun Kim, Seungjae Shin, Il-Chul Moon "Generalized Gumbel-Softmax Gradient Estimator for Various Discrete Random Variables"
AWARDS & SCHOLARSHIPS
- Dean's list, KAIST, 2014
- Honor student scholarship, KAIST, 2016
- 1st Prize (대상), KAIST Invention Award, 2017
- 최우수논문상, KSC2017 학부생 논문경진대회, 2017
- 송현상, KAIST ISysE, 2018
- Winner, Qualcomm Innovation Fellowship Korea, 2022
Seungjae Shin is a member of Applied Artificial Intelligence Laboratory. (2018.03 ~)