Home

Welcome to the Machine Intelligence and Data Science (MIDaS) Laboratory @ Yonsei University

Introduction

The MIDaS lab has been established in the School of Mathematics and Computing (Computational Science and Engineering) at Yonsei since March 2019 and is led by Professor Won-Yong Shin. Our lab has been funded by the BK21 Four program. Our research focuses basically on data mining and machine learning in broad fields of basic science, social media, healthcare, bioinformatics, and wireless networking.

Recruiting!

Ph.D., M.S., and Undergraduate Research positions available (scholarship and competitive subsidies offered). If any of you are interested in our lab, please feel free to contact Prof. Shin at wy.shin_at_yonsei.ac.kr. 

For international applicants: Please customize your research statement along with the research directions above in the MIDaS Lab. Dr. Shin will not respond to email broadcasting. 

For undergraduate applicants: Please refer to the link.

(학부 인턴십 프로그램에 관심이 있는 학생들은 위 링크를 참고하기 바랍니다. 타대학 학생도 지원가능 합니다.)

대학원 석/박사과정 및 학부 연구 학생 모집 (장학금 및 연구비 지급)합니다. 우리 연구실에서 수행하는 연구에 관심이 있는 학생들은 e-mail 을 보내주시기 바랍니다. 혹시 학부 인턴을 하지 않았는데 대학원 진학을 고려하는 학생이라면 아래 영상을 필히 시청해보기 바랍니다.

[석사 진학하려는 사람들이 꼭 봐야할 영상]

Latest News

• The two papers, entitled "When labels are far away: Progressive trust propagation for urban region classification under spatial label scarcity" and "CGU: Controllable graph unlearning via forgetting flow", have been accepted for presentation at the ACM SIGKDD Conference on Knowledge Discovery & Data Mining (KDD 2027). 

• Dr. Shin has won the 2026 KICS Distinguished Service Award. 

• The paper, entitled "Metapath-based hyperbolic contrastive learning for heterogeneous graph embedding", has been accepted for publication at the IEEE Transactions on Network Science and Engineering. 

• The paper, entitled "TRACE: Tourism recommendation with accountable citation evidence", has been accepted for presentation at the the Annual Conference on Neural Information Processing Systems (NeurIPS 2026) (Evaluations and Datasets Track).

• Dr. Shin received the Best Teaching Award for the Spring 2026 semester from the Yonsei University Graduate School of Engineering.

• The paper, entitled "Effective heterophilous heterogeneous graph Learning via decoupled spectral filtering and curriculum learning", has been accepted for presentation at the International ACM Conference on Knowledge and Information Management (CIKM 2026).

• The paper, entitled "Memory is no longer a bottleneck: Memory-efficient graph filtering for scalable collaborative filtering", has been accepted for publication at the IEEE Transactions on Knowledge and Data Engineering.

• The paper, entitled "Accurate reconstruction of the standard 12-lead ECG from a single lead based on inherent principles of ECG", has been accepted for presentation at the International Conference on Medical Imaging Computing and Computer Assisted Intervention (MICCAI 2026).

• The paper, entitled "Seven security challenges in cross-domain multi-agent LLM systems", has been accepted for publication at the npj Artificial Intelligence.

• The two papers, entitled "Semi-supervised neural super-resolution for mesh-based simulations" and "Teaching molecular dynamics to a non-autoregressive ionic transport predictor", have been accepted for presentation at the International Conference on Machine Learning (ICML 2026). 

• The paper, entitled "Training-free adjustable polynomial graph filtering for ultra-fast multimodal recommendation", has been accepted for publication at the Engineering Applications of Artificial Intelligence.

• The paper, entitled "SCOUT: Structure-aware aspect and anchor-count selection for node attribute augmentation via positional information", has been accepted for presentation at the ACM Web Conference (WWW 2026).  

• The paper, entitled "Real-time prediction of breast cancer sites using deformation-aware graph neural network", has been accepted for publication at the Engineering Applications of Artificial Intelligence.

• The paper, entitled "Tokenize once, recommend anywhere: Unified item tokenization for multi-domain LLM-based recommendation“, has been accepted for presentation at the Annual AAAI Conference on Artificial Intelligence (AAAI-26).

• The paper, entitled "Leveraging retrieval-augmented language models for accurate item/feature selection in conversational recommender systems", has been accepted for presentation at the ACM International Conference on Web Search and Data Mining (WSDM 2026).