@article{Dong2026, 
author = {Bowen Dong and Wenjun Wang and Xueli Liu and Yuejun Wang and Dan Yin},
title = {GraphCon: A Parallel Graph Construction from Relational Data},
year = {2026},
journal = {Big Data Mining and Analytics},
volume = {9},
number = {2},
pages = {448-464},
keywords = {relational data transformation, data integration, graph construction, parallel scalability},
url = {https://www.sciopen.com/article/10.26599/BDMA.2025.9020062},
doi = {10.26599/BDMA.2025.9020062},
abstract = {Converting relational data into a property graph is advantageous for relational data analysis using graph algorithms. However, existing methods for constructing property graphs from relational data often require complex join operations when predefined entities and relationships are given. Additionally, constructing graphs from large-scale relational data is time-consuming due to the need to aggregate instances from multiple tables. To address this issue, this paper proposes a schema-based graph construction method called GraphCon. GraphCon employs a schema-based mapping mechanism to achieve equivalent mapping between the graph schema and the relational schema. Additionally, we optimize a complex join strategy, InstanceJoin, in the graph construction process. To improve efficiency in handling large-scale data, we introduce a parallel algorithm that includes a data partition strategy based on the graph schema and a load-balancing strategy to enhance scalability. Experiments using the TPC-H benchmark and real-life datasets validate the efficiency and scalability of our proposed methods.}
}