GraphflowDB: A DBMS for large scale graph data management

GraphflowDB is an in-memory DBMS targeting primarily read-heavy subgraph query workloads equivalent to select-project-join (SPJ) queries over graph data. The system supports the openCypher language. Our research focuses on rethinking each core database component including query processing and optimization, storage layout and compression, and materialized views.


Pinterest Labs Tech Talk: "GraphflowDB and Modern Query Processing Techniques for Graph Database Systems" (March 2021)



Current Contributors Previous Contributors