If you are interested in joining our lab, please send your transcript, CV, and a brief statement of your research interests to Prof. Yeon-Chang Lee.

For prospective graduate students: We have 0-1 available positions for master's or Ph.D. students for Spring 2026. Interested applicants are encouraged to contact us, but we strongly recommend completing an internship of at least two months in our lab before applying to the graduate program.

For undergraduate students: We welcome undergraduate interns, particularly 3rd-year students, who are aiming to pursue graduate studies in Spring 2027 (and more rarely, Fall 2026). If you're interested, please refer to this document for more information.

We are currently focusing on three key areas related to graph neural networks (GNN) and recommender systems (RecSys). 

• Trustworthy GNN: Advancing GNN architectures to dynamically adapt to evolving graph structures and changing node/edge features, while prioritizing fairness, robustness, and accuracy to ensure reliable, unbiased, and ethical outcomes;

• Responsible RecSys: Leveraging multimodal data, knowledge bases, and large language models to provide ethical, personalized recommendations that enhance user satisfaction and transparency; and

• Knowledge Graphs for GNN Applications: Strengthening GNN applications through the generation of domain-specific knowledge graph, driving advancements in fields such as traffic management, labor markets, healthcare, and social polarization.

• Graph Machine Learning

1) Graph Representation Learning: signed graphs (SIGIR'20, CIKM'20short, SIGIR'23short, TKDD'24) and directed graphs (WSDM'22) 

2) Dynamics in Graph Mining: temporal knowledge graph modeling (ICDM'22, Inf. Sci.'24), dynamic signed graph modeling (CIKM'23, CIKM'24), information pathway prediction (KDD'23), and visualization of trajectories on node embeddings

3) Robustness in Graph Mining: out-of-distribution generalization (WWW'23)

4) Fairness in Graph Mining: fair graph anomaly detection (CIKM'24) and fair graph neural networks (AAAI'25)

5) Graph-based Downstream Tasks: node ranking (SIGIR'21) and community detection (ICDM'21, TKDE'23)

• Recommender Systems

1) Graph-based Collaborative Filtering (AAAI'18, WSDM'22, SIGWEB Newsletter'23, CSUR'24, IJCAI'24)

2) Multi-modal Recommender Systems (CIKM'22)

3) Domain-specific Recommender Systems: TV shows (ICDE'19, ICDE'23), news articles (ICDE'22industry, CIKM'22short), and related searches (KDD'25industry)

• Graph + X: career trajectory prediction (KDD'25), anomaly detection (CIKM'24), polarization modeling (CIKM'24), etc