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.

cv_junghun_kim.pdf

Google scholar

LinkedIn

About

Carnegie Mellon University (Nov. 2026 - Present)

• Postdoctoral Fellow, School of Computer Science
• Advised by Prof. Christos Faloutsos

Seoul National University (Sep. 2020 - Aug. 2026)

• Ph.D. in Artificial Intelligence
• Advised by Prof. U Kang (Data Mining Lab)

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

• B.S in Department of Computer Science and Engineering & Mathematic Science

Publications

2026

• Robust Node Classification via Noise-robust Views and Prototype Relabeling Hoyoung Yoon, Junghun Kim, and U Kang CIKM 2026 [code | pdf | blog (Korean)]
• Sipu: Accurate Graph-based Positive-Unlabeled Learning under Heterophily Shihyung Park, Junghun Kim, and U Kang CIKM 2026 [code | pdf | blog (Korean)]
• Accurate Source-Free Speech Classification via Meta-Learned Target-Centric Model Merging Kahyun Park*, Junghun Kim*, and U Kang (*equal contribution) Interspeech 2026 [code | pdf | blog (Korean)]
• 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]