Complex data analytics that involve data mining often comprise not only a single algorithm but also further data processing steps, for example, to restrict the search space or to filter the result. We demonstrate graph mining with Gradoop, the first scalable system supporting declarative analytical programs composed from multiple graph operations. We use a business intelligence example including frequent subgraph mining to highlight the analytical capabilities enabled by such programs. The results can be visualized and, to show its ease of use, the program can be modified on visitors request. Gradoop is built on top of state-of-the-art big data technology and out-of-the-box horizontally scalable. Its source code is publicly available and designed for easy extensibility. We offer to the graph mining community, to apply Gradoop in large scale use cases and to contribute further algorithms.
%0 Conference Paper
%1 7836824
%A Petermann, André
%A Junghanns, Martin
%A Kemper, Stephan
%A Gómez, Kevin
%A Teichmann, Niklas
%A Rahm, Erhard
%B 2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW)
%D 2016
%K Data Intelligence Mining;Business algorithms;Conferences;Graph analysis;Data and design mining;Business;Algorithm models;Libraries;Partitioning
%P 1316--1319
%R 10.1109/ICDMW.2016.0193
%T Graph Mining for Complex Data Analytics
%X Complex data analytics that involve data mining often comprise not only a single algorithm but also further data processing steps, for example, to restrict the search space or to filter the result. We demonstrate graph mining with Gradoop, the first scalable system supporting declarative analytical programs composed from multiple graph operations. We use a business intelligence example including frequent subgraph mining to highlight the analytical capabilities enabled by such programs. The results can be visualized and, to show its ease of use, the program can be modified on visitors request. Gradoop is built on top of state-of-the-art big data technology and out-of-the-box horizontally scalable. Its source code is publicly available and designed for easy extensibility. We offer to the graph mining community, to apply Gradoop in large scale use cases and to contribute further algorithms.
@inproceedings{7836824,
abstract = {Complex data analytics that involve data mining often comprise not only a single algorithm but also further data processing steps, for example, to restrict the search space or to filter the result. We demonstrate graph mining with Gradoop, the first scalable system supporting declarative analytical programs composed from multiple graph operations. We use a business intelligence example including frequent subgraph mining to highlight the analytical capabilities enabled by such programs. The results can be visualized and, to show its ease of use, the program can be modified on visitors request. Gradoop is built on top of state-of-the-art big data technology and out-of-the-box horizontally scalable. Its source code is publicly available and designed for easy extensibility. We offer to the graph mining community, to apply Gradoop in large scale use cases and to contribute further algorithms.},
added-at = {2024-10-02T10:38:17.000+0200},
author = {Petermann, André and Junghanns, Martin and Kemper, Stephan and Gómez, Kevin and Teichmann, Niklas and Rahm, Erhard},
biburl = {https://puma.scadsai.uni-leipzig.de/bibtex/28d2732121c743631704910594ce3c273/scadsfct},
booktitle = {2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW)},
doi = {10.1109/ICDMW.2016.0193},
interhash = {b5ce12f2dbdab0309e94c5ebb7e367c3},
intrahash = {8d2732121c743631704910594ce3c273},
issn = {2375-9259},
keywords = {Data Intelligence Mining;Business algorithms;Conferences;Graph analysis;Data and design mining;Business;Algorithm models;Libraries;Partitioning},
month = Dec,
pages = {1316--1319},
timestamp = {2024-10-02T10:38:17.000+0200},
title = {Graph Mining for Complex Data Analytics},
year = 2016
}