Email: [email protected]

I am a PhD student at the Data Mining Lab in Seoul National University, advised by Professor U Kang.

My research focuses on learning under uncertainty, with an emphasis on graph-structured data. I develop algorithms that remain robust when labels, structures, or domains are incomplete, noisy, or shifting, and I aim to make them practically useful for large-scale, real-world systems.

Google scholar

Education

Seoul National University (Sep. 2020 - Current)

Ph.D. Candidate in the Graduate School of Artificial Intelligence
Expected Graduation: 2026.08

Sung Kyun Kwan University (Mar. 2015 - Aug. 2020)

B.S in Department of Computer Science and Engineering & Mathematic Science
GPA: 4.14 / 4.50; C.S.: 4.26 / 4.50

Publications

2026

Dual-level Reweighting for Positive-Unlabeled Graph Classification Junghun Kim, Shihyung Park, and U Kang WWW 2026 [code | pdf | blog (Korean)]
Fast and Accurate Domain Adaptation for Irregular and Regular Tensor Decomposition Junghun Kim, Kahyun Park, Jun-Gi Jang, and U Kang IEEE Transactions on Knowledge and Data Engineering [code | pdf | blog (Korean)]

2025

PiGLeT: Probabilistic Message Passing for Semi-supervised Link Sign Prediction Kahyun Park, Junghun Kim, Jinhong Jung, and U Kang ICDM 2025 [code | pdf | blog (Korean)]
Accurate Graph-based Multi-Positive Unlabeled Learning via Disentangled Multi-view Feature Propagation Junghun Kim, Ka Hyun Park, Hoyoung Yoon, and U Kang KDD 2025 [code | pdf | blog (Korean)]
Accurate Link Prediction for Edge-Incomplete Graphs via PU Learning Junghun Kim, Ka Hyun Park, Hoyoung Yoon, and U Kang AAAI 2025 [code | pdf | blog (Korean)] Accepted as oral presentation
Accurate Semi-supervised Automatic Speech Recognition for Ordinary and Characterized Speeches via Multi-hypotheses-based Curriculum Learning Ka Hyun Park*, Junghun Kim******,* and U Kang (*equal contribution) PLOS ONE [code | pdf | blog (Korean)]