Dongmin Park


Ph.D. Candidate in Data Mining Lab, KAIST

Email: dongminparkxkxkxk@kaist.ac.kr

Phone: +82 o1o-8q37-8424

Google Scholar / Linked in / CV

I am a Ph.D. Candidate in Data Mining Lab @ KAIST, advised by Prof. Jae-Gil Lee. During Ph.D., I worked as research scientist intern on various industry labs, including Meta AI, Naver AI, and Krafton AI. My research interest lies in improving AI technologies under real-world scenarios, especially in the areas of data-centric AI, multi-modal language models, and ML applications. News

Dec 2023: Passed my Ph.D. Defense :)

Dec 2023: A Paper on 'Adaptive Shorcut Debiasing for Online Continual Learning' Accepted to AAAI 2024.

Dec 2023: A Paper on 'Data Pruning under Label Noise' published at NeurIPS 2023.

Jul 2023: A Paper on 'Time-series Semi-supervised Learning' published at ICML 2023.

Jun 2023: Started 'AI Research Internship' at Meta AI.

May 2023: Passed my Ph.D. Proposal.
Work Experience

Publications Google scholar profile

2023
D. Kim, D. Park, Y. Shin, J. Bang, H. Song, JG. Lee. Adaptive Shorcut Debiasing for Online Continual Learning. The AAAI Conference on Artificial Intelligence (AAAI) 2024.
D. Park, S. Choi, D. Kim, H. Song, JG. Lee. Robust Data Pruning under Label Noise via Maximizing Re-labeling Accuracy. Annual Conference on Neural Information Processing Systems (NeurIPS) 2023. [pdf] [code]
Y. Shin, S. Yoon, H. Song, D. Park, B. Kim, JG. Lee, BS. Lee. Context Consistency Regularization for Label Sparsity in Time Series. International Conference on Machine Learning (ICML) 2023. [pdf]

2022
D. Park, Y. Shin, J. Bang, Y. Lee, H. Song, JG. Lee. Meta-Query-Net: Resolving Purity-Informativeness Dilemma in Open-set Active Learning. Annual Conference on Neural Information Processing Systems (NeurIPS) 2022. [pdf] [code]
D. Park, D. Papailiopoulos, K. Lee. Active Learning is a Strong Baseline for Data Subset Selection. Has it Trained Yet? Workshop on Annual Conference on Neural Information Processing Systems (NeurIPS, Workshop) 2022. [pdf] [code]
D. Park, J. Kang, H. Song, S. Yoon, JG Lee. Multi-view POI-level Cellular Trajectory Reconstruction for Digital Contact Tracing of Infectious Diseases. International Conference on Data Minig (ICDM) 2022. [pdf]
H. Song, M. Kim, D. Park, Y. Shin, JG. Lee. Learning from Noisy Labels with Deep Neural Networks: A Survey. IEEE Transactions on Neural Networks and Learning Systems (TNNLS) 2022. The most cited survey paper on handling noisy labels with DNNs. [pdf] [code]
M. Kim, H. Song, Y. Shin, D. Park, K. Shin, JG. Lee. Meta-Learning for Online Update of Recommender Systems. The AAAI Conference on Artificial Intelligence (AAAI) 2022. [pdf]

2021
D. Park, H. Song, M. Kim, JG. Lee. Task-Agnostic Undesirable Feature Deactivation Using Out-of-Distribution Data. Annual Conference on Neural Information Processing Systems (NeurIPS) 2021. [pdf] [code]
H. Song, M. Kim, D. Park, Y. Shin, JG. Lee. Robust Learning by Self-Transition for Handling Noisy Labels. International Conference on Knowledge Discovery and Data Mining (KDD) 2021. Oral Presentation. [pdf]

2020
M. Kim, J. Kang, Dim, H. Song, H. Min, Y. Nam, D. Park, JG. Lee. Hi-COVIDNet: Deep Learning Approach to Predict Inbound COVID-19 Patients and Case Study in South Korea . International Conference on Knowledge Discovery and Data Mining (KDD) 2020. Oral Presentation. [pdf] [code]
H. Song, M. Kim, D. Park, JG. Lee. How Does Early Stopping Help Generalization against Label Noise? . International Conference on Machine Learning (ICML, Workshop) 2020. [pdf] [code]
D. Park, H. Song, M. Kim, JG. Lee. TRAP: Two-level Regularized Autoencoder-based Embedding for Power-law Distributed Data. TheWebConf (WWW) 2020. Oral Presentation. [pdf] [code]

2019
D. Park, S. Yoon, H. Song, JG. Lee. MLAT: Metric Learning for kNN in Streaming Time Series. International Conference on Knowledge Discovery and Data Mining (KDD, Workshop) 2019. [pdf]

 

Services

Reviewer for ICML, NeurIPS, ICLR, CVPR, ICCV, KDD, AAAI, TNNLS since 2021

Awards

© 2022 Dongmin Park. Thanks Dr. Hwanjun Song and Dr. Deqing Sun for the template.