Challenges in large-graph processing: A vision

Abstract

As a representation of high connected objects, graphs receive a arising attention. By virtue of the interconnection of graph data, current general-purpose parallel data processing systems misfit effectively graph processing. Thus, a wide spectrum of dedicated graph processing system emerged. In this paper, we give a guidance of classical types of graph processing system. We discuss key features and the according challenges of graph processing from the aspect of graph data, graph algorithm as well as the computation implementation. Then we specify four strategies that should be taken into account when designing a graph processing systems. In the last part of our paper we make a comparison of present typical graph processing systems and specify their suitable application area.