Data Mining & Machine Learning Lab

We investigate cutting-edge algorithms to solve real-world complexities. Our core research spans across fundamental machine learning methodologies and innovative data science applications.

RESEARCH TOPIC 01

Announcement

Join Our Lab! We are recruiting students interested in data mining, recommender systems, personalized machine learning, and information retrieval. If you are interested, please contact jinhong@ssu.ac.kr.

Latest News

Paper

Our work on recommendation free from users, IDs, and GNNs has been accepted at WWW 2026

Jan 13, 2026

Paper

Our work on SSL for signed graphs has been accepted at ICDM 2025

Aug 28, 2025

Award

Our survey on multi-behavior RecSys received PAKDD Best Survey Paper Award

Jun 12, 2025

Paper

Our work on lightweight signed bipartite GNNs has been accepted at Neural Networks

Jun 3, 2025

Paper

Our work on lightweight tensor compression has been accepted at KAIS

May 24, 2025

More News

Click to view past news

Recent Publications

RECENT 1 PUBLICATION

Personalized Ranking on Cascading Behavior Graphs for Accurate Multi-Behavior Recommendation

ACM Transactions on Intelligent Systems and Technolog

2026-05-04

RECENT 2 PUBLICATION

AlphaFree: Recommendation Free from Users, IDs, and GNNs

The Web Conference

2026-04-01

RECENT 3 PUBLICATION

A Comprehensive Survey on Multi-Behavior Recommender Systems: Extended Taxonomy and Recent Advances

International Journal of Data Science and Analytics

2026-01-24

RECENT 4 PUBLICATION

Learning Recommender Systems with User Preference Based Soft Label Negative Sampling

Korea Database Conference

2025-11-07

RECENT 5 PUBLICATION

Sequential Recommendation with LLM Reranking by Integrating Collaborative Filtering and Textual Semantics

Korea Database Conference

2025-11-07

Contact Us

Lab Location

Room 225, Information Science Building, 50, Sadang-ro, Dongjak-gu, Seoul

Email Contact

jinhong@ssu.ac.kr

Office Phone

+82–02–820–0909

Data Mining & Machine Learning Lab

Personalized Machine Learning and Recommender Systems

Graph Machine Learning

Lightweight and Scalable Data Mining

Announcement

Latest News

Our work on recommendation free from users, IDs, and GNNs has been accepted at WWW 2026

Our work on SSL for signed graphs has been accepted at ICDM 2025

Our survey on multi-behavior RecSys received PAKDD Best Survey Paper Award

Our work on lightweight signed bipartite GNNs has been accepted at Neural Networks

Our work on lightweight tensor compression has been accepted at KAIS

More News

Recent Publications

Personalized Ranking on Cascading Behavior Graphs for Accurate Multi-Behavior Recommendation

AlphaFree: Recommendation Free from Users, IDs, and GNNs

A Comprehensive Survey on Multi-Behavior Recommender Systems: Extended Taxonomy and Recent Advances

Learning Recommender Systems with User Preference Based Soft Label Negative Sampling

Sequential Recommendation with LLM Reranking by Integrating Collaborative Filtering and Textual Semantics

Contact Us