SCIENCE@home

LSM-Community: A Graph Storage System Exploiting Community Structure in Social Networks

Songyao Wang,Chaokun Wang,Fang Niu,Cheng Wu

Published 2025 in IEEE International Conference on Data Engineering

ABSTRACT

Recently, several social network analysis algorithms have been optimized by leveraging the community structure commonly found in graphs. Since community structure is fun-damental to these algorithms, storing graphs based on their community structure can significantly enhance the performance of graph algorithms that rely on it for optimization. However, existing graph storage systems do not natively store graphs according to the community structure, which limits their per-formance in retrieving communities. To fill this gap, we pro-pose LSM-Community, a graph storage system inspired by the LSM - Tree design that stores graphs on disk based on their community structure. To dynamically maintain the community structure during graph updates, we present the community-centric dynamic community detection algorithm $(C^{3}D)$. Experimental results demonstrate that LSM-Community outperforms other storage systems in classical community discovery tasks (e.g., performing CD on UK-2007 dataset with LSM-Community is $86.12\times$ faster than Neo4j) while maintaining high performance on classical graph analytic algorithms. This indicates that LSM-Community efficiently supports community discovery and query processing while preserving the performance of classical analytic algorithms,

PUBLICATION RECORD

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

REFERENCES

Showing 1-42 of 42 references · Page 1 of 1

CITED BY

  • No citing papers are available for this paper.

Showing 0-0 of 0 citing papers · Page 1 of 1