The RLR-tree: a reinforcement learning based R-tree for spatial data

• Main Authors: Gu, Tu, Feng, Kaiyu, Cong, Gao, Long, Cheng, Wang, Zheng, Wang, Sheng
• Other Authors: Interdisciplinary Graduate School (IGS)
• Format: Conference or Workshop Item
• Language: English
• Published: 2023
• Subjects: Engineering::Computer science and engineering::Data; Spatial Data; Spatial Query Processing; Learned Index; Reinforcement Learning; Deep Learning
• Online Access: https://hdl.handle.net/10356/166210; https://2023.sigmod.org/
• Institution: Nanyang Technological University

Learned indexes have been proposed to replace classic index structures like B-Tree with machine learning (ML) models. They require to replace both the indexes and query processing algorithms currently deployed by the databases, and such a radical departure is likely to encounter challenges and obstacles. In contrast, we propose a fundamentally different way of using ML techniques to build a better R-Tree without the need to change the structure or query processing algorithms of traditional R-Tree. Specifically, we develop reinforcement learning (RL) based models to decide how to choose a subtree for insertion and how to split a node when building and updating an R-Tree, instead of relying on hand-crafted heuristic rules currently used by the R-Tree and its variants. Experiments on real and synthetic datasets with up to more than 100 million spatial objects show that our RL based index outperforms the R-Tree and its variants in terms of query processing time.