JoonHo Jang

I am a Ph.D. student at Applied Artificial Intelligence Lab, advised by Professor Il-Chul Moon at Korea Advanced Institute of Science and Technology (KAIST). I received my B.S. in Industrial and Systems Engineering from KAIST in February 2017 and my M.S. in Industrial and Systems Engineering from KAIST in February 2019, respectively.

Contact: adkto8093 [at] kaist [dot] ac [dot] kr // adkto193812 [at] gmail [dot] com

[Google Scholar] [LinkedIn] [CV]

My research interests include general machine learning theory and applications with

Domain Adaptation (e.g. Open-Set Domain Adaptation, Test-Time Adaptation) : [C6, P2]
- Main research topic for my doctoral dissertation.
Active Learning, Learning with Noisy Label, Multi-label Classification : [C4, C7, C5, C8]
Debiasing, Fairness : [P1, C2, C3, W1]

Education

Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea (Mar. 2019 ~ Feb. 2024, Expected)

Ph.D. candidate, Dept. of Industrial and Systems Engineering (IsysE), Advisor: Prof. Il-Chul Moon

Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea (Mar. 2017 ~ Feb. 2019)

M.S., Dept. of Industrial and Systems Engineering (IsysE), Advisor: Prof. Il-Chul Moon

Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea (Feb. 2012 ~ Feb. 2017)

B.S., Dept. of Industrial and Systems Engineering (IsysE).

Selected Publication

Unknown-Aware Domain Adversarial Learning for Open-Set Domain Adaptation [Paper]

JoonHo Jang, Byeonghu Na, Dong Hyeok Shin, Mingi Ji, Kyungwoo Song, Il-Chul Moon
Neural Information Processing Systems (NeruIPS) 2022

Towards Pareto-Optimality for Test-Time Adaptation

JoonHo Jang, Donghyeok Shin, Byeonghu Na, HeeSun Bae, Il-Chul Moon
Preprint, Under Review

Publications

(C: Conference, W: Workshop, J: Journal, P: Preprint, *: Equal contribution)

[P2] Towards Pareto-Optimality for Test-Time Adaptation

JoonHo Jang, Donghyeok Shin, Byeonghu Na, HeeSun Bae, Il-Chul Moon
Preprint, Under Review

[P1] Training Unbiased Diffusion Models From Biased Dataset

Yeongmin Kim, Byeonghu Na, JoonHo Jang, Minsang Part, Dongjun Kim, Wanmo Kang, Il-Chul Moon
Preprint, Under Review

[C8] Hierarchical Multi-Label Classification with Partial Labels and Unknown Hierarchy [Paper]

Suhyeon Jo, Donghyeok Shin, Byeonghu Na, JoonHo Jang, and Il-Chul Moon
International Conference on Information and Knowledge Management (CIKM) 2023

[C7] SAAL: Sharpness-Aware Active Learning [Paper]

Yoon-Yeong Kim*, Youngjae Cho*, JoonHo Jang, Byeonghu Na, Yeongmin Kim, Kyungwoo Song, Wanmo Kang, Il-Chul Moon
International Conference on Machine Learning (ICML) 2023

[C6] Unknown-Aware Domain Adversarial Learning for Open-Set Domain Adaptation [Paper]

JoonHo Jang, Byeonghu Na, Dong Hyeok Shin, Mingi Ji, Kyungwoo Song, Il-Chul Moon
Neural Information Processing Systems (NeruIPS) 2022

[C5] From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model [Paper]

HeeSun Bae*, Seungjae Shin*, Byeonghu Na, JoonHo Jang, Kyungwoo Song, and Il-Chul Moon
International Conference on Machine Learning (ICML) 2022

[W1] Improving Group-based Robustness and Calibration via Ordered Risk and Confidence Regularization [Paper]

Seungjae Shin, Byeonghu Na, HeeSun Bae, JoonHo Jang, Hyemi Kim, Kyungwoo Song, Youngjae Cho, and Il-Chul Moon
International Conference on Machine Learning (ICML) 2022 Workshop on Spurious Correlations, Invariance, and Stability (SCIS)

[C4] LADA: Look-Ahead Data Acquisition via Augmentation for Deep Active Learning [Paper]

Yoon-Yeong Kim, Kyungwoo Song, JoonHo Jang, and Il-Chul Moon
Neural Information Processing Systems (NeruIPS) 2021

[C3] Counterfactual Fairness with Disentangled Causal Effect Variational Autoencoder [Paper]

Hyemi Kim, Seungjae Shin, JoonHo Jang, Kyungwoo Song, Weonyoung Joo, Wanmo Kang, Il-Chul Moon
AAAI Conference on Artificial Intelligence (AAAI) 2021

[C2] Neutralizing Gender Bias in Word Embedding with Latent Disentanglement and Counterfactual Generation [Paper]

Seungjae Shin, Kyungwoo Song, Joonho Jang, Hyemi Kim, Weonyoung Joo, and Il-Chul Moon
Findings of Empirical Methods in Natural Language Processing (Findings of EMNLP) 2020

[C1] Bivariate Beta-LSTM [Paper]

Kyungwoo Song, JoonHo Jang, Seungjae Shin, and Il-Chul Moon
AAAI Conference on Artificial Intelligence (AAAI) 2020

[J1] Forecasting the Concentration of Particulate Matter in the Seoul Metropolitan Area Using a Gaussian Process Model [Paper]

Joonho Jang, Seungjae Shin, Hyunjin Lee, Il-Chul Moon
Sensors 2020

Project Experience

Development of Prediction Models for Measurements in Semiconductor Manufacturing based on Estimation of External Factors (2023)

funded by semiconductor company in Korea

Transfer Learning on Classification Model for Wafer Defect Patterns (2022)

funded by semiconductor company in Korea

Development of Classification Model for Wafer Defect Patterns (2021)

funded by semiconductor company in Korea

Development of a Child Abuse Prediction Model based on Social Security Information System (2021)

funded by Government Agency

Traffic Data-based Analysis and Prediction Model Development for the Concentration of Particulate Matter (2020)

funded by Government Agency

Forecasting the Concentration of Particulate Matter in the Seoul Metropolitan Area Using a Gaussian Process Model (2018-2019)

funded by Government-funded Research Institute

Awards

Qualcomm Innovation Fellowship South Korea 2023 Finalist
Paper Award @ Korea Artificial Intelligence Association (KAIA) 2021 Summer Conference
- Subject of "Unknown-Aware Domain Adversarial Learning for Open-Set Domain Adaptation"

Activities

Teaching Assistant

Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea

Data Structure and Analysis (2017 Fall, 2018 Spring, 2018 Fall, 2019 Spring, 2019 Fall, 2023 Spring)

Applications of AI and DM Technology (2021 Fall, 2022 Fall)

Academic Service

Conference Reviewer

Neural Information Processing Systems (NeurIPS): 2022, 2023
International Conference on Computer Vision (ICCV): 2023

Page updated

Google Sites

Report abuse