direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Inhalt des Dokuments

DIMA Researchers @SIGMOD 2017

Prof. Dr. Tilmann Rabl, Dr. Sebastian Schelter, and Christoph Boden from TU Berlin’s Database Systems and Information Management (DIMA) Group recently presented their research at SIGMOD 2017 (the 2017 International Conference on Management of Data), which was held in Chicago, Illinois (USA), on May 14th - 19th, 2017. DIMA contributions included presenting a full paper, a workshop paper, and organizing a workshop.

I. Full Paper


Prof. Dr. Tilmann Rabl presented the full research paper “Query Centric Partitioning and Allocation for Partially Replicated Database Systems,” which describes a novel partitioning and allocation algorithm for shared-nothing cluster databases. This research was jointly conducted with Prof. Dr. Hans-Arno Jacobsen from the Technische Universität Munich (TUM) Middleware Systems Research Group. A video of the presentation is available at


II. Workshop Paper


Doctoral student Christoph Boden presented his paper on “Benchmarking Data Flow Systems for Scalable Machine Learning” at the BeyondMR: Algorithms and Systems for MapReduce and Beyond Workshop (co-located at SIGMOD 2017). In his talk, he presented a novel benchmark consisting of workloads, experiments, metrics, and datasets. In addition, he shared the insights he gained via implementing and running benchmarks on distributed dataflow systems, such as Apache Flink and Apache Spark for scalable machine learning workloads for data up to four billion data points and 100 million dimensions. A video of the presentation is available at


III. The 1st International DEEM Workshop


Postdoctoral Researcher, Dr. Sebastian Schelter organized the first international workshop on “Data Management for End-To-End Machine Learning” (DEEM). The Chair of the DIMA Group, Prof. Dr. Volker Markl served on the Steering Committee and Prof. Dr. Tilmann Rabl was a member of the Program Committee. The workshop was well attended with around fifty participants and featured four invited talks and six paper presentations. Among the highlights were contributions on ”End to End Model Training for MSR Machine Translation” by Microsoft and ”Machine Learning for Recommender Systems at Twitter” by Twitter. Details about the workshop may be found at


Zusatzinformationen / Extras

Quick Access:

Schnellnavigation zur Seite über Nummerneingabe

Auxiliary Functions