Data Management
The Data Management Lab was founded in 2017 by Prof. Carsten Binnig and is part of the Department of Computer Science at TU Darmstadt in Darmstadt, Germany.
TU Darmstadt is one of the leading technical universities in Germany. Its Computer Science department consistently ranks among the top 5 in Germany. TU Darmstadt offers a unique environment for research in data management due to strong cooperations with other groups like the Machine Learning Lab or Distributed Systems Programming Lab, as well as ample interdisciplinary interaction.
Our lab page lists all team members. Please see our job listings if you are interested in working with us.
Research
We conduct research in several areas of databases and data management in conjunction with artificial intelligence (AI). The groups main focus areas are Systems for AI and AI for Systems.
Teaching
Our lab regularly offers courses, seminars and labs on various data management topics. Furthermore, we offer term projects and Bachelors and Masters thesis projects with different focus areas.
News
-
2020/02/20
Our paper “DeepDB: Learn from Data, not from Queries!” was accepted to VLDB2020 Tokyo
The typical approach for learned DBMS components is to capture the behavior by running a representative set of queries and use the observations to train a machine learning model. We propose to learn a pure data-driven model.
-
2020/01/07
36th Chaos Communication Congress: How sustainable is Deep Learning?
Our lab members Nadja Geisler and Benjamin Hättasch talked about about the Deep Learning Hype and its consequences and impacts at the 36C3 in Leipzig
-
2019/11/27
In the first submission cycle 3 out of 3 papers are accepted to SIGMOD 2020
IDEBench: A new Benchmark for Interactive Data Exploration / DB4ML: An In-Memory Database Kernel with Machine Learning Support / DBPal: A Fully Pluggable NL2SQL Training Pipeline
-
2019/11/08
FG DB Symposium 2020 on ML for Systems and Systems for ML
Get your seat now: http://www.fgdb-symposium.de/ for more info!
-
2019/10/15
Our paper “DBMS Fitting: Why should we learn what we already know?” was accepted to CIDR 2020
In this paper, we propose an alternative approach to learn DBMS components.