PegasusN: A Scalable and Versatile Graph Mining System

How can we find patterns and anomalies in peta-scale graphs? Even recently proposed graph mining systems fail in processing peta-scale graphs. In this work, we propose PegasusN, a scalable and versatile graph mining system that runs on Hadoop and Spark. To handle enormous graphs, PegasusN provides and seamlessly integrates efficient algorithms for various graph mining operations: graph structure analyses, subgraph enumeration, graph generation, and graph visualization. PegasusN quickly processes extra-large graphs that other systems cannot handle.

Authors

• Ha-Myung Park
• Chiwan Park
• U Kang Seoul National University

Keywords

No keywords are indexed for this paper.