Partitioning Graphs for the Cloud using Reinforcement Learning

In this paper, we propose Revolver, a parallel graph partitioning algorithm capable of partitioning large-scale graphs on a single shared-memory machine. Revolver employs an asynchronous processing framework, which leverages reinforcement learning and label propagation to adaptively partition a graph. In addition, it adopts a vertex-centric view of the graph where each vertex is assigned an autonomous agent responsible for selecting a suitable partition for it, distributing thereby the computation across all vertices. The intuition behind using a vertex-centric view is that it naturally fits the graph partitioning problem, which entails that a graph can be partitioned using local information provided by each vertex's neighborhood. We fully implemented and comprehensively tested Revolver using nine real-world graphs. Our results show that Revolver is scalable and can outperform three popular and state-of-the-art graph partitioners via producing comparable localized partitions, yet without sacrificing the load balance across partitions.