GraphLake: A Purpose-Built Graph Compute Engine for Lakehouse
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917312367427584 |
|---|---|
| author | Liu, Shige Chen, Songting Qin, Chengjie Wu, Mingxi Wang, Jianguo |
| author_facet | Liu, Shige Chen, Songting Qin, Chengjie Wu, Mingxi Wang, Jianguo |
| contents | In this paper, we introduce GraphLake, a purpose-built graph compute engine for Lakehouse. GraphLake is built on top of the commercial graph database TigerGraph. It maps Lakehouse tables to vertex and edge types in a labeled property graph and supports graph analytics over Lakehouse tables using GSQL. To minimize startup time, it loads only the graph topology. Furthermore, it introduces a series of techniques to ensure query efficiency over Lakehouse tables, including a graph-aware caching mechanism and two Lakehouse-optimized parallel primitives. Extensive experiments demonstrate that GraphLake significantly outperforms PuppyGraph, the current state-of-the-art graph compute engine for Lakehouse, by achieving both lower startup and query time. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_03705 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GraphLake: A Purpose-Built Graph Compute Engine for Lakehouse Liu, Shige Chen, Songting Qin, Chengjie Wu, Mingxi Wang, Jianguo Databases H.2.4 In this paper, we introduce GraphLake, a purpose-built graph compute engine for Lakehouse. GraphLake is built on top of the commercial graph database TigerGraph. It maps Lakehouse tables to vertex and edge types in a labeled property graph and supports graph analytics over Lakehouse tables using GSQL. To minimize startup time, it loads only the graph topology. Furthermore, it introduces a series of techniques to ensure query efficiency over Lakehouse tables, including a graph-aware caching mechanism and two Lakehouse-optimized parallel primitives. Extensive experiments demonstrate that GraphLake significantly outperforms PuppyGraph, the current state-of-the-art graph compute engine for Lakehouse, by achieving both lower startup and query time. |
| title | GraphLake: A Purpose-Built Graph Compute Engine for Lakehouse |
| topic | Databases H.2.4 |
| url | https://arxiv.org/abs/2603.03705 |