ILIKE Data Skipping

Data Skipping for Expensive Operators.

Project Leads: Mihail Stoian and Andi Zimmerer

Description

ILIKE Data Skipping is a research project by the Data Systems Lab at the University of Technology Nuremberg (UTN) that explores lightweight metadata and indexing techniques for accelerating expensive operators in analytical database systems.

The project studies data skipping for expensive database operations, among them joins and substring searches, at both the row and partition levels. By identifying data that cannot contribute to a query result, database systems can avoid unnecessary scans and expensive computation while preserving exact query results.

“A parrot is much like an approximate membership structure for substrings: give it sentences, and every so often it gives you a few pieces back.”

MLSkip: Data Skipping for ML Filters via Lightweight Metadata

Mihail Stoian, Mark Gerarts, Pascal Ginter, Andreas Zimmerer, Jan Van den Bussche, and Andreas Kipf

In 7th Workshop on Applied AI for Database Systems and Applications (AIDB), 2026

Bib PDF Code

@inproceedings{stoian2026mlskip,
  title = {{MLSkip}: Data Skipping for {ML} Filters via Lightweight Metadata},
  author = {Stoian, Mihail and Gerarts, Mark and Ginter, Pascal and Zimmerer, Andreas and Bussche, Jan Van {den} and Kipf, Andreas},
  year = {2026},
  maintitle = {Proceedings of the {VLDB} Endowment},
  booktitle = {7th Workshop on Applied {AI} for Database Systems and Applications ({AIDB})},
  publisher = {{VLDB} Endowment},
}

Instance-Optimized String Fingerprints

Mihail Stoian, Johannes Thürauf, Andreas Zimmerer, Alexander van Renen, and Andreas Kipf

VLDB 2025 Workshop: Applied AI for Database Systems and Applications (AIDB 2025), 2025

Bib PDF Code

@article{stoian2025stringfingerprints,
  author = {Stoian, Mihail and Thürauf, Johannes and Zimmerer, Andreas and van Renen, Alexander and Kipf, Andreas},
  title = {Instance-Optimized String Fingerprints},
  journal = {{VLDB} 2025 Workshop: Applied AI for Database Systems and Applications ({AIDB} 2025)},
  year = {2025},
}

Parachute: Single-Pass Bi-Directional Information Passing

Mihail Stoian, Andreas Zimmerer, Skander Krid, Amadou Latyr Ngom, Jialin Ding, Tim Kraska, and Andreas Kipf

Proceedings of the VLDB Endowment, 2025

Bib PDF Code

@article{stoian2025parachute,
  author = {Stoian, Mihail and Zimmerer, Andreas and Krid, Skander and Ngom, Amadou Latyr and Ding, Jialin and Kraska, Tim and Kipf, Andreas},
  title = {Parachute: Single-Pass Bi-Directional Information Passing},
  journal = {Proceedings of the {VLDB} Endowment},
  year = {2025},
}

Pruning in Snowflake: Working Smarter, Not Harder

Andreas Zimmerer, Damien Dam, Jan Kossmann, Juliane Waack, Ismail Oukid, and Andreas Kipf

In Companion of the 2025 International Conference on Management of Data (SIGMOD-Companion ’25), June 22–27, 2025, Berlin, Germany, 2025

Bib PDF Blog

@inproceedings{zimmerer2025pruning,
  title = {Pruning in Snowflake: Working Smarter, Not Harder},
  author = {Zimmerer, Andreas and Dam, Damien and Kossmann, Jan and Waack, Juliane and Oukid, Ismail and Kipf, Andreas},
  booktitle = {Companion of the 2025 International Conference on Management of Data ({SIGMOD}-Companion '25), June 22--27, 2025, Berlin, Germany},
  publisher = {{ACM}},
  year = {2025},
  isbn = {9798400715648},
}

Description

Publications