Welcome to the LearnData Lab

Machine Learning and Data Mining Research lab at SKKU

LearnData Lab develops machine learning systems that enable AI to reason over complex relational data.

We are a research group in the Department of Software at Sungkyunkwan University (SKKU), led by Prof. Hogun Park. Our work focuses on machine learning, data mining, and trustworthy AI for graph-structured data.

We study how intelligent systems can learn from and reason over structured information such as social networks, knowledge graphs, and multi-modal relational data. Our research spans graph representation learning, explainable AI, and knowledge-enhanced machine learning.

Our goal is to build reliable and interpretable AI systems that bridge theoretical advances in machine learning with real-world applications.

Research Areas

1. Machine Learning and Data Mining for Graph-Structured Data

We study algorithms capable of modeling complex relational information that arises in social and interaction networks, knowledge graphs and ontologies, educational and behavioral logs, multi-modal graphs, and multi-sensor data. By developing scalable graph representation learning techniques, we aim to enable AI systems that can understand and reason over large-scale relational structures. These methods support emerging applications such as GraphRAG, knowledge-grounded reasoning, multi-agent learning, and agent orchestration over structured data.

2. Explainable, Robust, and Trustworthy AI

Our work seeks to improve the transparency and reliability of modern deep learning models by developing methods for interpretability and model understanding. This includes research on post-hoc explainability for graph neural networks, mechanistic interpretability of large language models, knowledge-enhanced LLMs, and knowledge editing techniques. We also study neural watermarking, model provenance, and approaches that integrate logical and symbolic reasoning with modern machine learning to ensure AI systems remain reliable and accountable in real-world environments.

We are looking for passionate new PhD students (or MS/PhD integrated program students) and Postdocs to join the team. (more info) !

Open positions are available for PhD students and Postdoctoral researchers. No opening for MS students for now.

We are grateful for funding from the National Research Foundation of Korea (NRF), BK21, Information & Communications Technology Planning & Evaluation (IITP), National IT Industry Promotion Agency (NIPA), Korea Creative Content Agency (KOCCA), LG Electronics, Samsung Research, NCSOFT, Samsung Display, and NAVER.

News

Feb. 2026

One paper have been accepted to the ESWA Journal. Congratulations, Jaehyun and Heesoo!

Jan. 2026

Two papers have been accepted to the ICLR 2026. Congratulations, Wooseok, Hyunju, and Woohyun!

Aug. 2025

A paper has been accepted to the CIKM 2025. Congratulations, Minku!

July 2025

I gave a talk titled Providing Explanations for Unsupervised Graph Learning Models at the University of British Columbia.

May. 2025

A paper has been accepted to the ACL 2025. Congratulations, Hongjun, Minji,and Heesoo!

May. 2025

A paper has been accepted to the KDD 2025. Congratulations, Heesoo, Chanyong, and Geonhee!

May. 2025

A paper has been accepted to the ICML 2025. Congratulations, Woohyun!

Feb. 2025

A paper has been accepted to the PAKDD 2025. Congratulations, Hongjun, Heesoo, Gayeong, and Juann!

Jan. 2025

A paper has been accepted to the NAACL 2025. Congratulations, Jiwon!

... see all News