PLATON: Top-down R-tree Packing with Learned Partition Policy

Summary: PLATON: top-down R-tree packing with a learned partition policy tuned to data/workload. Uses Monte Carlo Tree Search with tuned exploration, plus early termination and level-wise sampling to achieve linear-time packing and beat fixed indexes. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: 6817
Venue: SIGMOD
Year: 2023
Pagerank: 5.1845938e-05
Overall Rank: 9,974 | 31.57%
DOI: 10.1145/3626742

Incoming Non-self Citations Over Time

Authors

1. Jingyi Yang (Nanyang Technological University)
2. Gao Cong (Nanyang Technological University)

BibTeX Citation

@inproceedings{yang_sigmod23,
        title = {{PLATON: Top-down R-tree Packing with Learned Partition Policy}},
        author = {Yang, Jingyi and Cong, Gao},
        series = {{SIGMOD} '23},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3626742},
        url = {https://dl.acm.org/doi/10.1145/3626742},
        year = {2023}
}

Incoming Citations (Sorted by Pagerank)

Showing 2 of 2 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
10,378	High Performance or Low Memory? An Updatable Learned Index Framework for Time-Space Tradeoff	2026	SIGMOD	5.093636e-05
11,193	BT-Tree: A Reinforcement Learning Based Index for Big Trajectory Data	2024	SIGMOD	5.093636e-05

Outgoing Citations (Sorted by Pagerank)

Showing 24 of 24 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
2	R-Trees: A Dynamic Index Structure For Spatial Searching	1984	SIGMOD	0.0020210012
4	The R*-tree: An Efficient and Robust Access Method for Points and Rectangles	1990	SIGMOD	0.001157935
42	The R+-Tree: A Dynamic Multi-Dimensional Index for Objects	1987	VLDB	0.00046170812
43	The Case for Learned Index Structures	2018	SIGMOD	0.00046060254
116	Direct Spatial Search on Pictorial Databases Using Packed R-trees	1985	SIGMOD	0.0003221055
154	Neo: A Learned Query Optimizer	2019	VLDB	0.00028726181
378	Bao: Making Learned Query Optimization Practical	2021	SIGMOD	0.00019638121
447	ALEX: An Updatable Adaptive Learned Index	2020	SIGMOD	0.00018322593
477	The PGM-index: a fully-dynamic compressed learned index with provable worst-case bounds	2020	VLDB	0.00017851226
726	Client-Server Paradise	1994	VLDB	0.0001460632
873	Learning Multi-dimensional Indexes	2020	SIGMOD	0.00013481915
1,135	Qd-tree: Learning Data Layouts for Big Data Analytics	2020	SIGMOD	0.00012032847
1,174	Tsunami: A Learned Multi-dimensional Index for Correlated Data and Skewed Workloads	2021	VLDB	0.00011817414
1,418	LISA: A Learned Index Structure for Spatial Data	2020	SIGMOD	0.00010835539
1,840	Effectively Learning Spatial Indices	2020	VLDB	9.6404567e-05
2,910	APEX: A High-Performance Learned Index on Persistent Memory	2022	VLDB	7.9700885e-05
2,974	A Revised R*-tree in Comparison with Related Index Structures	2009	SIGMOD	7.9083221e-05
3,035	Instance-Optimized Data Layouts for Cloud Analytics Workloads	2021	SIGMOD	7.8297746e-05
4,516	The Price of Tailoring the Index to Your Data: Poisoning Attacks on Learned Index Structures	2022	SIGMOD	6.6489359e-05
4,751	The RLR-Tree: A Reinforcement Learning Based R-Tree for Spatial Data	2023	SIGMOD	6.5241784e-05
5,148	LSched: A Workload-Aware Learned Query Scheduler for Analytical Database Systems	2022	SIGMOD	6.3465986e-05
5,974	Towards instance-optimized data systems	2021	VLDB	6.0230488e-05
7,151	Theoretically Optimal and Empirically Efficient R-trees with Strong Parallelizability	2018	VLDB	5.6873519e-05
8,200	Waffle: A Workload-Aware and Query-Sensitive Framework for Disk-Based Spatial Indexing	2023	VLDB	5.4677285e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	2	R-Trees: A Dynamic Index Structure For Spatial Searching	1984	SIGMOD
2	7,151	Theoretically Optimal and Empirically Efficient R-trees with Strong Parallelizability	2018	VLDB
3	4,751	The RLR-Tree: A Reinforcement Learning Based R-Tree for Spatial Data	2023	SIGMOD
4	1,373	A Model for the Prediction of R-tree Performance	1996	PODS
5	145	Efficient Processing of Spatial Joins Using R-trees	1993	SIGMOD
6	7,939	A Trajectory Splitting Model for Efficient Spatio-Temporal Indexing	2005	VLDB
7	957	The TPR*-Tree: An Optimized Spatio-Temporal Access Method for Predictive Queries	2003	VLDB
8	2,341	Parallel R-trees	1992	SIGMOD
9	9,887	Adaptive Indexing of Objects with Spatial Extent	2023	VLDB
10	4	The R*-tree: An Efficient and Robust Access Method for Points and Rectangles	1990	SIGMOD