DECLARATIVE STACK FOR DISTRIBUTED GRAPH PROCESSING

摘要

Recently, people, devices, processes and other entities have been more connected than at any other point in history. In general, graphs have been used to represent data sets in various application domains including computational biology, social science, telecommunications, astronomy, semantic web and protein networks among many others. In practice, systemsstacks of large scale graph processing platforms are suffering from the lack of declarative processing interface. They are mainly relying on low level programming abstractions which can be only used by sophisticated software developers and are not adequate for many users. In order to tackle this challenge and improve the performance and user acceptance of large scale graph processing frameworks, we present a declarative querying framework that can seamlessly integrate with various big graph processing system platforms. Our experimental evaluation shows the effectiveness and efficiency of our proposed framework.