Explore a technical talk that introduces C3 (Compressing Correlated Columns), an innovative compression framework designed to exploit correlations between columns for more effective data compression. Learn how this framework builds upon typical lightweight compression infrastructure by incorporating six new multi-column compression schemes, developed based on patterns observed in real-world datasets. Discover how C3's sampling-based algorithm selects optimal compression schemes for each column, resulting in approximately 20% higher compression ratios compared to traditional single-column compression methods when tested on the Public BI benchmark. Presented by Thomas Glas, a computer science master's student at the Technical University of Munich and researcher at CWI's Database Architectures Group, this 25-minute presentation from the Dutch Seminar on Data Systems Design offers valuable insights into advancing columnar data compression techniques.
C3: Compressing Correlated Columns - A Framework for Multi-Column Data Compression
DSDSD - Dutch Seminar on Data Systems Design via YouTube
Overview
Syllabus
We hold bi-weekly talks on Fridays from PM to 5 PM CET for and by researchers and practitioners designing and implementing data systems. The objective is to establish a new forum for the Dutch Data Systems community to unite, foster collaborations between its members, and bring in high-quality international speakers. We would like to invite all researchers, especially PhD students, who are working on related topics to join the events. It is an excellent opportunity to receive feedback early on from researchers in your field.
Taught by
DSDSD - Dutch Seminar on Data Systems Design
Related Courses
-
Efficient CSV Parsing - On the Complexity of Simple Things
-
LingoDB: An Open Compilation and Optimization Framework for Sustainable Data Processing
-
Shredding Deeply Nested JSON for Efficient Analytics in DuckDB
-
Lambda Functions and List Operations in DuckDB SQL
-
Efficient Detection of Multivariate Correlations in Static and Streaming Data
-
Towards LLM-augmented Database Systems
