Stony Brook University Computer Science

Dr. Kyuseok Shim from Seoul National University will be giving a talk on "Cardinality Estimation of Approximate String Queries Using Deep Learning in Database Management Systems".

Please find the seminar details below:
Title: Cardinality Estimation of Approximate String Queries Using Deep Learning in Database Management Systems
Date & Time: Friday, September 11, 2 PM
Venue: B206

Abstract
To process a query in a database management system, the query optimizer selects the most efficient execution plan from among the possible alternatives. Without query optimization, database systems would be highly inefficient. Because the cost of an execution plan is estimated based on the costs and output cardinalities of individual operators, accurate cost and cardinality estimation is essential for identifying an optimal plan. Accordingly, extensive research has been conducted on query optimization, cost estimation, and cardinality estimation.
Recently, deep learning models have been actively explored for cardinality estimation, as they can effectively capture underlying data patterns and correlations and have been shown to outperform traditional methods. This talk next presents an overview of both traditional and deep learning–based approaches for cardinality estimation of approximate string queries in database management systems.

Speaker Bio
Kyuseok Shim is a Professor at Department of Electrical and Computer Engineering in Seoul National University, Korea. Before that, he was an Assistant Professor at the Computer Science Department in KAIST (Korea), a member of technical staff at Bell Laboratories (Murray Hill) and a member of the Quest Data Mining project at IBM Almaden Research Center. He received a Ph.D. from the University of Maryland at College Park, Maryland in 1993. He is currently an Editor-In-Chief of the VLDB Journal, a director of ACM SIGKDD Executive Committee and the chair of DASFAA as well as PAKDD Steering Committee. He is a General Co-Chair for ACM SIGKDD 2026 and ACM SIGMOD 2028 conferences that are prestigious conferences in data mining and database systems. He became an ACM fellow and an IEEE fellow for his contributions to scalable data mining and query processing. He was previously a member of the VLDB Endowment Board of Trustees and a steering committee member of PAKDD as well as DASFAA conferences. He served as the President of the Korean Information Scientist and Engineers (KIISE) in 2022 and became a member of National Academy of Engineering of Korea in 2023. He served as a Program Co-Chair for PAKDD 2003, WWW 2014, ICDE 2015, APWeb 2016, BigComp 2019 and ICDM 2019 conferences. He has been serving on Program Committees of the leading database, data mining and AI conferences including SIGMOD, SIGKDD, ICDE, ICDM, EDBT, VLDB, WSDM, WWW, AAAI, SIGIR and CIKM. He has been working in the area of data mining, machine learning, privacy preservation, query processing, query optimization, data warehousing, semi-structured data (XML), stream data and histograms.