Distributed Power-law Graph Computing Distributed Power-law Graph Computing: Theoretical and Empirical Analysis∗

Typically, a large-scale natural graph follows a skewed power law. In distributed graphstructured computations, the skewness usually makes a bad partitioning, which leads to high communication cost and workload imbalance. Therefore, graph partitioning (GP) is a challenging issue. To tackle this challenge, we introduce degree-based techniques into GP via vertex-cut. Accordingly, we develop a novel GP approach called PowerLore. PowerLore is attractive because it naturally exploits the skewed degree distribution. In addition, we conduct the theoretical analysis. And experiments on several large skewed graphs further show that our PowerLore outperforms the state-of-the-art baselines in both decreasing communication costs and guaranteeing good balance.