Logo des Repositoriums

Auflistung nach Autor:in "Junghanns, Martin"

1 - 3 von 3
  • Konferenzbeitrag
    The Big Picture: Understanding large-scale graphs using Graph Grouping with GRADOOP
    (Datenbanksysteme für Business, Technologie und Web (BTW 2017), 2017) Junghanns, Martin; Petermann, André; Teichmann, Niklas; Rahm, Erhard
    Graph grouping supports data analysts in decision making based on the characteristics of large-scale, heterogeneous networks containing millions or even billions of vertices and edges. We demonstrate graph grouping with G , a scalable system supporting declarative programs composed from multiple graph operations. Using social network data, we highlight the analytical capabilities enabled by graph grouping in combination with other graph operators. The resulting graphs are visualized and visitors are invited to either modify existing or write new analytical programs. G is implemented on top of Apache Flink, a state-of-the-art distributed dataflow framework, and thus allows us to scale graph analytical programs across multiple machines. In the demonstration, programs can either be executed locally or remotely on our research cluster.
  • Konferenzbeitrag
    Distributed FoodBroker: Skalierbare Generierung graphbasierter Geschäftsprozessdaten
    (Datenbanksysteme für Business, Technologie und Web (BTW 2017) - Workshopband, 2017) Kemper, Stephan; Petermann, André; Junghanns, Martin
    Graphen eignen sich zur Modellierung und Analyse komplexer Zusammenha ̈nge zwischen beliebi- gen Objekten. Eine mo ̈gliche Anwendung ist die graphbasierte Analyse von Gescha ̈ftsprozessen. Fu ̈r die Entwicklung und Evaluierung entsprechener Analysetools werden Datensa ̈tze beno ̈tigt. Food- Broker ist ein Datengenerator, welcher vordefinierte Gescha ̈ftsprozesse simuliert und die Daten in Form von Graphen lokal auf einem Rechner erzeugt. Um Graphen beliebiger Gro ̈ßer erstellen zu ko ̈nnen, zeigen wir in diesem Beitrag wie FoodBroker mit Hilfe der Open-Source-Frameworks GRADOOP und Apache Flink auf verteilten Systemen implementiert werden kann.
  • Konferenzbeitrag
    Distributed Grouping of Property Graphs with GRADOOP
    (Datenbanksysteme für Business, Technologie und Web (BTW 2017), 2017) Junghanns, Martin; Petermann, André; Rahm, Erhard
    Property graphs are an intuitive way to model, analyze and visualize complex relationships among heterogeneous data objects, for example, as they occur in social, biological and information networks. These graphs typically contain thousands or millions of vertices and edges and their entire representation can easily overwhelm an analyst. One way to reduce complexity is the grouping of vertices and edges to summary graphs. In this paper, we present an algorithm for graph grouping with support for attribute aggregation and structural summarization by user-defined vertex and edge properties. The algorithm is part of G , an open-source system for graph analytics. G is implemented on top of Apache Flink, a state-of-the-art distributed dataflow framework, and thus allows us to scale graph analytical programs across multiple machines. Our evaluation demonstrates the scalability of the algorithm on real-world and synthetic social network data.