Mahdi Esmailoghli

Research associate at the Data Integration and Data Preparation (D2IP) group of Techinal University of Berlin.

I am a Ph.D. student at the Data Integration and Data Preparation group under the supervision of Prof. Dr. Ziawasch Abedjan. I received my M.Sc. degree from Amirkabir University of Technology (Tehran Polytechnic). I worked on distributed and unsupervised anomaly detection and explanation systems in the healthcare domain as my master thesis.

My current research interest lies in data discovery in data lakes. In particular, I develop systems to efficiently explore large data lakes to enhance the data at hand to train more effective machine learning (ML) models. To this end, I have developed indexes and algorithms to efficiently discover relevant tables from data lake corpora with hundreds of millions of tables.



Mahdi Esmailoghli

Address

Technische Universität Berlin, TEL Building, Office 1110
Ernst-Reuter-Platz 7
10587 Berlin, Germany

Contact

esmailoghli (at) tu-berlin.de
Twitter
GitHub
LinkedIn
Google Scholar
YouTube
dblp

Publications & Talks

Publications

arXiv
 PDF
"Blend: A Unified Data Discovery System": Mahdi Esmailoghli, Christoph Schnell, Renée J. Miller, Ziawasch Abedjan. 2023.

SIGMOD 2023
 PDF
"Demonstrating MATE and COCOA for Data Discovery": Jannis Becktepe, Mahdi Esmailoghli, Maximilian Koch, Ziawasch Abedjan. International Conference on Management of Data. 2023.

BTW 2023
 PDF
"Duplicate Table Discovery with Xash": Maximilian Koch, Mahdi Esmailoghli, , Sören Auer, Ziawasch Abedjan. Conference on Database Systems for Business, Technology and Web. 2023.

VLDB 2022
 PDF
 Video
 Slides
 Poster
 Code
"MATE: multi-attribute table extraction": Mahdi Esmailoghli, Jorge-Arnulfo Quiané-Ruiz, Ziawasch Abedjan. In Proceedings of the International Conference on Very Large Data Bases. 2022.

EDBT 2021
 PDF
 Video
 Slides
 Code
"COCOA: COrrelation COefficient-Aware Data Augmentation.": Mahdi Esmailoghli, Jorge-Arnulfo Quiané-Ruiz, Ziawasch Abedjan. International Conference on Extending Database Technology (EDBT). 2021.

BTW 2021
 PDF
"Combining Programming-by-Example with Transformation Discovery from large Databases": Aslihan Özmen, Mahdi Esmailoghli, Ziawasch Abedjan. Conference on Database Systems for Business, Technology and Web. 2021.

Informatik Spektrum 2020
 PDF
"Data Science für alle: Grundlagen der Datenprogrammierung": Ziawasch Abedjan, Hagen Anuth, Mahdi Esmailoghli, Mohammad Mahdavi, Felix Neutatz, Binger Chen. Informatik Spektrum. 2020.

CIDR 2020
 PDF
"CAFE: Constraint-Aware Feature Extraction from Large Databases": Mahdi Esmailoghli, Ziawasch Abedjan. The Conference on Innovative Data Systems Research (CIDR). 2020.

Datenbank-Spektrum 2019
 PDF
 Slides
"Particulate matter matters—the data science challenge@ BTW 2019": Holger J. Meyer, Hannes Grunert, Tim Waizenegger, Lucas Woltmann, Claudio Hartmann, Wolfgang Lehner, Mahdi Esmailoghli, Sergey Redyuk, Ricardo Martinez, Ziawasch Abedjan, Ariane Ziehn, Tilmann Rabl, Volker Markl, Christian Schmitz, Dhiren Devinder Serai, Tatiane Escobar Gava. Datenbank-Spektrum. 2019.

BTW 2019
 PDF
"Explanation of Air Pollution Using External Data Sources": Mahdi Esmailoghli, Sergey Redyuk, Ricardo Martinez, Ziawasch Abedjan, Tilmann Rabl, Volker Markl. Conference on Database Systems for Business, Technology and Web. 2019.

JTE 2016
 PDF
"Design of a Driver Assistant System Based on Vehicular Communications Using Fuzzy Logic": Mahdi Esmailoghli, Saleh Yousefi. Quarterly Journal of Transportation Engineering. 2016.

Talks

Guest Talk
"A Unified Data Discovery System": Mahdi Esmailoghli. Information Systems Group at Hasso Plattner Institute (HPI). May 2024.

TaDA@VLDB 2023
"MATE: Multi-Attribute Table Extraction". Tabular Data Analysis (TaDA) workshop at VLDB. 2023.

Guest Talk
"Scalable Data Discovery For Machine Learning": Mahdi Esmailoghli. Khoury College of Computer Sciences at Northeastern University . 2023.

Academic Service

  • CIKM 2023 - 32nd ACM International Conference on Information and Knowledge Management - PC Member/Reviewer Research Track

Awards

  • National university entrance exam exemption award (for M.Sc. degree)
  • Top 1 student based on GPA, in B.Sc degree
  • Ranked #4 in 19th national Computer Olympiad Of Iran September 2014
  • Ranked #1 in 19th national Computer Olympiad Of Iran semi final June 2014
  • Ranked #10 in 18th national Computer Olympiad Of Iran August 2013
  • Ranked #2 in 18th national Computer Olympiad Of Iran semi final June 2013

Education

  • Technische Universität Berlin - Research associate in the Data Integration and Data Preparation group (D2IP) under the supervision of Prof. Dr. Ziawasch Abedjan (2024 - Present)
  • Leibniz Universität Hannover - Research associate in DataBase Systems group (DBS) under the supervision of Prof. Dr. Ziawasch Abedjan (2020 - 2024)
  • Technische Universität Berlin - Research associate in Big Data Management (BigDaMa) group under the supervision of Prof. Dr. Ziawasch Abedjan (2018 - 2020)
  • Amirkabir University of Technology (Tehran Polytechnic) - Master's Degree, Computer Software Engineering (2015 - 2017)
  • Urmia UniversityBachelor’s Degree, Computer Software Engineering (2010 - 2014)

Teaching

TU Berlin

  • Programmierpraktikum: Datensysteme SS 2024

Leibniz Universität Hannover

  • Big-Data Technologies WS 2023
  • Data Science Foundation SS 2023
  • Big-Data Technologies WS 2022
  • Data Science Foundation SS 2022
  • Advanced Topics in Database Systems WS 2021
  • Advanced Topics in Database Systems SS 2021

TU Berlin

  • Data Science Application SS 2020
  • Data Science 1: Essentials of Data Programming WS 2019
  • Data Science 1: Essentials of Data Programming SS 2019
  • Data Science Application SS 2019
  • Data Science Application WS 2018

Amirkabir University of Technology (Tehran Polytechnic)

  • Data Intensive Computing, TA for Dr. Amir Payberah associate professor at KTH Royal Institute of Technology, Stockholm, Sweden

© Mahdi Esmailoghli   |   Last Update: 14 May 2024 |   Imprint and Data Privacy