GRASP: Graph-Enhanced Retrieval for Accurate Schema Pruning in Text-to-SQL
ISPRS International Journal of Geo-Information · 02.06.2026 · 15 (6) · 248
DOI: 10.3390/ijgi15060248 ↗Kurz gefasst
Fachartikel in der Zeitschrift ISPRS International Journal of Geo-Information, online erschienen am 02.06.2026. Verfasst von Xiangjun Cheng und 3 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Recent advances in land system research depend heavily on efficient access to large-scale, multi-source remote sensing spatiotemporal databases. Although Text-to-SQL provides natural language interfaces, the scale and spatial complexity of remote sensing schemas generate significant noise for large language models, increasing inference costs and latency. This study presents graph-enhanced retrieval for accurate schema pruning (GRASP), a graph-based framework for schema pruning in remote sensing information systems. GRASP frames schema pruning as a semantic retrieval task and constructs a heterogeneous graph that represents both question semantics and database structure. By integrating a relation-aware transformer, a relational graph attention network, and pre-trained BERT representations, GRASP enhances schema understanding and supports joint table-column prediction through entity-level cross-attention. A dual-task objective combining contrastive learning with dynamic-threshold prediction mitigates class imbalance, while database value sampling and demonstration retrieval optimize inference performance. Experiments show that GRASP substantially improves schema pruning in spatiotemporal query scenarios: a 7B open-source LLM with GRASP surpasses an unaugmented 32B model on Spider; meanwhile, the framework also yields promising results on SpatialSQL, achieving a favorable balance among accuracy, cost, and deployment flexibility. GRASP provides a practical pathway for interdisciplinary researchers to query remote sensing databases in natural language, aiding spatiotemporal analysis.
Zitieren
APA
Cheng, X., Zhang, H., Li, C., & Xu, S. (2026). GRASP: Graph-Enhanced Retrieval for Accurate Schema Pruning in Text-to-SQL. ISPRS International Journal of Geo-Information, 15(6), 248. https://doi.org/10.3390/ijgi15060248
Vancouver
Cheng X, Zhang H, Li C, Xu S. GRASP: Graph-Enhanced Retrieval for Accurate Schema Pruning in Text-to-SQL. ISPRS International Journal of Geo-Information. 2026;15(6):248. doi:10.3390/ijgi15060248
BibTeX
@article{Cheng2026,
author = {Cheng, Xiangjun and Zhang, Hongmei and Li, Chao and Xu, Sining},
title = {GRASP: Graph-Enhanced Retrieval for Accurate Schema Pruning in Text-to-SQL},
journal = {ISPRS International Journal of Geo-Information},
year = {2026},
volume = {15},
number = {6},
pages = {248},
doi = {10.3390/ijgi15060248}
}
EUVIMED