View in EDS

TBSI: a Transformer-based spatial learned index for efficient construction and query.

Saved in:
Bibliographic Details
Title: TBSI: a Transformer-based spatial learned index for efficient construction and query.
Authors: Hu, Yusen1,2 (AUTHOR), Tang, Peng1,2 (AUTHOR), Meng, Yuhang1,2 (AUTHOR), Hu, Linshu1,2,3 (AUTHOR), Zhang, Feng1,2,3 (AUTHOR) zfcarnation@zju.edu.cn, Liu, Renyi1,2,3 (AUTHOR)
Source: International Journal of Geographical Information Science. Jul2026, Vol. 40 Issue 7, p1943-1971. 29p.
Subjects: Quadtrees, Indexing, Data management, Machine learning, Geospatial data, Transformer models, Search algorithms
Abstract: The exponential growth of geographic data reveals limitations in traditional spatial indices. Spatial learned indices that incorporate machine learning models have been proposed to enhance index performance. However, due to the considerable overhead of fine-grained data partitioning and the complexity of hierarchical model structures, existing spatial learned indices still exhibit bottlenecks in index construction and query processing. To address the aforementioned issues, we propose TBSI, an in-memory Transformer-based spatial learned index with an end-to-end structure. TBSI employs an enhanced quadtree to optimize data partitioning and utilizes a Transformer-based position prediction model to manage each data partition, preserving a simple yet effective index structure. TBSI exhibits superior performance in both index construction and query processing. We also design spatial query algorithms based on a filtering-refinement mechanism and data update algorithms based on buffers and flag arrays to support efficient query processing and index maintenance. Extensive experiments on real-world and synthetic datasets demonstrated that, compared to baselines, TBSI achieved up to 23.4 times speedup in build time, up to 24.3 times reduction in index size, up to 5.9 times improvement in range queries, and up to 4.5 times improvement in kNN queries. Also, TBSI exhibited robust adaptability to dynamic data updates. [ABSTRACT FROM AUTHOR]
Copyright of International Journal of Geographical Information Science is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 194641328
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: TBSI: a Transformer-based spatial learned index for efficient construction and query.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Hu%2C+Yusen%22">Hu, Yusen</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Tang%2C+Peng%22">Tang, Peng</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Meng%2C+Yuhang%22">Meng, Yuhang</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Hu%2C+Linshu%22">Hu, Linshu</searchLink><relatesTo>1,2,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhang%2C+Feng%22">Zhang, Feng</searchLink><relatesTo>1,2,3</relatesTo> (AUTHOR)<i> zfcarnation@zju.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Liu%2C+Renyi%22">Liu, Renyi</searchLink><relatesTo>1,2,3</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22International+Journal+of+Geographical+Information+Science%22">International Journal of Geographical Information Science</searchLink>. Jul2026, Vol. 40 Issue 7, p1943-1971. 29p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Quadtrees%22">Quadtrees</searchLink><br /><searchLink fieldCode="DE" term="%22Indexing%22">Indexing</searchLink><br /><searchLink fieldCode="DE" term="%22Data+management%22">Data management</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Geospatial+data%22">Geospatial data</searchLink><br /><searchLink fieldCode="DE" term="%22Transformer+models%22">Transformer models</searchLink><br /><searchLink fieldCode="DE" term="%22Search+algorithms%22">Search algorithms</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: The exponential growth of geographic data reveals limitations in traditional spatial indices. Spatial learned indices that incorporate machine learning models have been proposed to enhance index performance. However, due to the considerable overhead of fine-grained data partitioning and the complexity of hierarchical model structures, existing spatial learned indices still exhibit bottlenecks in index construction and query processing. To address the aforementioned issues, we propose TBSI, an in-memory Transformer-based spatial learned index with an end-to-end structure. TBSI employs an enhanced quadtree to optimize data partitioning and utilizes a Transformer-based position prediction model to manage each data partition, preserving a simple yet effective index structure. TBSI exhibits superior performance in both index construction and query processing. We also design spatial query algorithms based on a filtering-refinement mechanism and data update algorithms based on buffers and flag arrays to support efficient query processing and index maintenance. Extensive experiments on real-world and synthetic datasets demonstrated that, compared to baselines, TBSI achieved up to 23.4 times speedup in build time, up to 24.3 times reduction in index size, up to 5.9 times improvement in range queries, and up to 4.5 times improvement in kNN queries. Also, TBSI exhibited robust adaptability to dynamic data updates. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of International Journal of Geographical Information Science is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=194641328
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1080/13658816.2025.2581211
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 29
        StartPage: 1943
    Subjects:
      – SubjectFull: Quadtrees
        Type: general
      – SubjectFull: Indexing
        Type: general
      – SubjectFull: Data management
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Geospatial data
        Type: general
      – SubjectFull: Transformer models
        Type: general
      – SubjectFull: Search algorithms
        Type: general
    Titles:
      – TitleFull: TBSI: a Transformer-based spatial learned index for efficient construction and query.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Hu, Yusen
      – PersonEntity:
          Name:
            NameFull: Tang, Peng
      – PersonEntity:
          Name:
            NameFull: Meng, Yuhang
      – PersonEntity:
          Name:
            NameFull: Hu, Linshu
      – PersonEntity:
          Name:
            NameFull: Zhang, Feng
      – PersonEntity:
          Name:
            NameFull: Liu, Renyi
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 07
              Text: Jul2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 13658816
          Numbering:
            – Type: volume
              Value: 40
            – Type: issue
              Value: 7
          Titles:
            – TitleFull: International Journal of Geographical Information Science
              Type: main
ResultId 1