PathDB: A system for evaluating regular path queries

TL;DR

PathDB is an in-memory Java graph database optimized for regular path queries, demonstrating competitive performance and flexibility compared to existing systems through benchmark evaluations.

Contribution

Introduces PathDB, a modular, optimized system for evaluating regular path queries with demonstrated efficiency and versatility in benchmark tests.

Findings

PathDB achieves competitive execution times with commercial graph systems.

Modular design allows targeted optimizations for path query processing.

Benchmark results show PathDB's flexibility in handling complex and dynamic path queries.

Abstract

PathDB is a Java-based graph database designed for in-memory data loading and querying. By utilizing Regular Path Queries (RPQ) and a closed path algebra, PathDB processes paths through its three main components: the parser, the logical plan, and the physical plan. This modular design allows for targeted optimizations and modifications without impacting overall functionality. Benchmark experiments illustrate PathDB's execution times and flexibility in handling dynamic and complex path queries, compared to baseline methods like Depth-First Search (DFS) and Breadth-First Search (BFS) guided by an automaton, highlighting PathDB optimizations that contribute to its performance. PathDB was also evaluated against leading commercial graph systems, including Neo4j, Memgraph, and K\`uzu. Benchmark experiments demonstrated PathDB competitive execution times and its ability to support a wide range of path query types.