Learned index for spatial queries

Haixin Wang, Xiaoyi Fu, Jianliang XU, Hua Lu

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

53 Citations (Scopus)


With the pervasiveness of location-based services (LBS), spatial data processing has received considerable attention in the research of database system management. Among various spatial query techniques, index structures play a key role in data access and query processing. However, existing spatial index structures (e.g., R-Tree) mainly focus on partitioning data space or data objects. In this paper, we explore the potential to construct the spatial index structure by learning the distribution of the data. We design a new data-driven spatial index structure, namely learned Z-order Model (ZM) index, which combines the Z-order space filling curve and the staged learning model. Experimental results on both real and synthetic datasets show that our learned index significantly reduces the memory cost and performs more efficiently than R-Tree in most scenarios.

Original languageEnglish
Title of host publicationProceedings - 2019 20th International Conference on Mobile Data Management, MDM 2019
Number of pages6
ISBN (Electronic)9781728133638
Publication statusPublished - Jun 2019
Event20th International Conference on Mobile Data Management, MDM 2019 - Hong Kong, Hong Kong
Duration: 10 Jun 201913 Jun 2019

Publication series

NameProceedings - IEEE International Conference on Mobile Data Management
ISSN (Print)1551-6245


Conference20th International Conference on Mobile Data Management, MDM 2019
Country/TerritoryHong Kong
CityHong Kong

Scopus Subject Areas

  • Engineering(all)

User-Defined Keywords

  • Learned index
  • Learned ZM index
  • Z Order Curve


Dive into the research topics of 'Learned index for spatial queries'. Together they form a unique fingerprint.

Cite this