2017/10/21 by Sang Woo Jun, Andy Wright, Jun, Sang-Woo +7
Computer Science · #Advanced Graph Neural Networks #Cloud Computing and Resource Management #Databases (cs.DB) #FOS: Computer and information sciences #Graph Theory and Algorithms
paper · pdf · doi:10.48550/arxiv.1710.07736
openalex publication_date 2017/10/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We present BigSparse, a fully external graph analytics system that picks up where semi-external systems like FlashGraph and X-Stream, which only store vertex data in memory, left off. BigSparse stores both edge and vertex data in an array of SSDs and avoids random updates to the vertex data, by first logging the vertex updates and then sorting the log to sequentialize accesses to the SSDs. This newly introduced sorting overhead is reduced significantly by interleaving sorting with vertex reduction operations. In our experiments on a server with 32GB to 64GB of DRAM, BigSparse outperforms other in-memory and semi-external graph analytics systems for algorithms such as PageRank, BreadthFirst Search, and Betweenness-Centrality for terabyte-size graphs with billions of vertices. BigSparse is capable of highspeed analytics of much larger graphs, on the same machine configuration.