Data Mining Lab.

Welcome to Data Mining Laboratory in the Department of Computer Science and Engineering at Seoul National University. Our research interests lie in big data mining which aims to find models, algorithms, and systems for scalable data analysis with applications on knowledge discovery, learning, and anomaly detection. Specifically, we focus on the following research topics: deep learning & scalable machine learning, recommendation system, big graph mining, big tensor mining, online stream mining, and anomaly/fraud detection.

What's New

  • [Aug 2018] A paper accepted to CIKM 2018, a top tier data mining conference.

    A paper is accepted to CIKM 2018, a top tier data mining conference. The paper "Zoom-SVD: Fast and Memory Efficient Method for Extracting Key Patterns in an Arbitrary Time Range" proposed an algorithm which extracts key patterns of multiple time series data in an arbitrary time range.

  • [Jun 2018] Jinhong Jung won BK21 Plus Excellent Research Award.

    Ph.D. student Jinhong Jung won the BK21 Plus Excellent Research Award. BK21 Plus Excellent Research Award is given to excellent graduate students in the Engineering area. Congratulations!

  • [Jan 2018] 2 students in DM Lab. won HumanTech Award.

    B.S. student Sejoon Oh won the HumanTech award (gold, 1st in Computer Science) from Samsung, from his paper "Scalable Tucker Factorization for Sparse Tensors - Algorithms and Discoveries". M.S/Ph.D. student Jun-gi Jang also won the Humantech award (honorable mention, 4th in Computer Science), from his paper "Fast and Memory-Efficient Method for Time Ranged Singular Value Decomposition". HumanTech award is given to best papers in the engineering area, and it is the most prestigious award among such kind in Korea. Congratulations!

  • [Dec 2017] 2 papers accepted to ICDE 2018, a top tier database conference.

    2 papers are accepted to ICDE 2018, a top tier database conference. The paper "TPA: Fast, Scalable, and Accurate Method for Approximate Random Walk with Restart on Billion Scale Graphs" proposed an algorithm which computes RWR scores approximately exploiting PageRank and block-wise structure of real-world graphs. The paper "Scalable Tucker Factorization for Sparse Tensors - Algorithms and Discoveries" proposed a scalable Tucker factorization method for sparse tensors, which updates factor matrices in a row-wise manner.

  • [Dec 2017] 2 papers accepted to The Web Conference 2018, a top tier data mining conference.

    2 research track papers are accepted to The Web Conference 2018, a top tier data mining conference. The paper "SIDE: Representation Learning in Signed Directed Networks" proposed a network embedding algorithm for signed directed networks. The paper "Fast and Accurate Random Walk with Restart on Dynamic Graphs with Guarantees" proposed an algorithm computing Random Walk with Restart efficiently on dynamic graphs.

<< Older news