PegasusN: A Scalable and Versatile Graph Mining System

Authors

  • Ha-Myung Park Korea Advanced Institute of Science and Technology
  • Chiwan Park Seoul National University
  • U Kang Seoul National University

Keywords:

graph mining, distributed system, hadoop, spark

Abstract

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.

Downloads

Published

2018-04-29

How to Cite

Park, H.-M., Park, C., & Kang, U. (2018). PegasusN: A Scalable and Versatile Graph Mining System. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/11372