WISK: A Workload-aware Learned Index for Spatial Keyword Queries

Summary: WISK is a workload-aware learned index for spatial keyword queries, adapting to the workload distribution. It partitions data into cost-minimizing blocks (NP-hard) and builds an RL-guided hierarchy to prune, achieving up to 8x speedups with similar storage. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: hcd0755cfea77364a
Venue: SIGMOD
Year: 2023
Pagerank: 5.359172e-05
Overall Rank: 8,219 | 44.91%
DOI: 10.1145/3589332

Incoming Non-self Citations Over Time

Authors

1. Yufan Sheng (University of New South Wales)
2. Xin Cao (University of New South Wales)
3. Yixiang Fang (Chinese University of Hong Kong)
4. Kaiqi Zhao (University of Auckland)
5. Jianzhong Qi (University of Melbourne)
6. Gao Cong (Nanyang Technological University)
7. Wenjie Zhang (University of New South Wales)

BibTeX Citation

@inproceedings{sheng_sigmod23,
        title = {{WISK: A Workload-aware Learned Index for Spatial Keyword Queries}},
        author = {Sheng, Yufan and Cao, Xin and Fang, Yixiang and Zhao, Kaiqi and Qi, Jianzhong and Cong, Gao and Zhang, Wenjie},
        series = {{SIGMOD} '23},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3589332},
        url = {https://dl.acm.org/doi/10.1145/3589332},
        year = {2023}
}

Incoming Citations (Sorted by Pagerank)

Showing 6 of 6 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
6,889	Accelerating String-key Learned Index Structures via Memoization-based Incremental Training	2024	VLDB	5.6393954e-05
10,552	LINE: A Learned Index with Group-Enhanced Leaves and Cache-Optimized Inner Tree	2026	SIGMOD	4.9605343e-05
10,649	High Performance or Low Memory? An Updatable Learned Index Framework for Time-Space Tradeoff	2026	SIGMOD	4.9605343e-05
10,728	LM-Tree: A Hybrid Learned Index for Similarity Search in Metric Spaces	2026	SIGMOD	4.9605343e-05
11,127	A Workload-Aware Encrypted Index for Efficient Privacy-Preserving Range Queries	2026	VLDB	4.9605343e-05
11,321	ACE: A Cardinality Estimator for Set-Valued Queries	2025	VLDB	4.9605343e-05

Outgoing Citations (Sorted by Pagerank)

Showing 28 of 28 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
4	The R*-tree: An Efficient and Robust Access Method for Points and Rectangles	1990	SIGMOD	0.0011386412
13	Mining Association Rules between Sets of Items in Large Databases	1993	SIGMOD	0.0006440069
40	The Case for Learned Index Structures	2018	SIGMOD	0.00046249672
165	Mining Frequent Patterns without Candidate Generation	2000	SIGMOD	0.00027323925
372	STHoles: A Multidimensional Workload-Aware Histogram	2001	SIGMOD	0.00019768921
427	ALEX: An Updatable Adaptive Learned Index	2020	SIGMOD	0.00018429918
458	Query-based Workload Forecasting for Self-Driving Database Management Systems	2018	SIGMOD	0.00017870238
461	The PGM-index: a fully-dynamic compressed learned index with provable worst-case bounds	2020	VLDB	0.00017835351
834	Benchmarking Learned Indexes	2021	VLDB	0.00013539098
870	Learning Multi-dimensional Indexes	2020	SIGMOD	0.0001332034
1,039	Fine-grained Partitioning for Aggressive Data Skipping	2014	SIGMOD	0.00012349128
1,064	Are We Ready For Learned Cardinality Estimation?	2021	VLDB	0.00012181459
1,132	Qd-tree: Learning Data Layouts for Big Data Analytics	2020	SIGMOD	0.00011873466
1,190	Tsunami: A Learned Multi-dimensional Index for Correlated Data and Skewed Workloads	2021	VLDB	0.00011564169
1,239	Efficient Query Processing in Geographic Web Search Engines	2006	SIGMOD	0.00011374405
1,445	LISA: A Learned Index Structure for Spatial Data	2020	SIGMOD	0.00010607118
1,480	Efficient Processing of Top-k Spatial Preference Queries	2011	VLDB	0.00010511472
1,529	Updatable Learned Index with Precise Positions	2021	VLDB	0.00010320909
1,867	Efficient Retrieval of the Top-k Most Relevant Spatial Web Objects	2009	VLDB	9.4581343e-05
1,884	Effectively Learning Spatial Indices	2020	VLDB	9.422145e-05
2,913	AI Meets Database: AI4DB and DB4AI	2021	SIGMOD	7.855786e-05
3,054	Spatial Keyword Query Processing: An Experimental Evaluation	2013	VLDB	7.6909799e-05
4,508	LearnedSQLGen: Constraint-aware SQL Generation using Reinforcement Learning	2022	SIGMOD	6.5553854e-05
4,592	Collective Spatial Keyword Querying	2011	SIGMOD	6.5016975e-05
4,879	The RLR-Tree: A Reinforcement Learning Based R-Tree for Spatial Data	2023	SIGMOD	6.3567479e-05
4,990	Budget-aware Index Tuning with Reinforcement Learning	2022	SIGMOD	6.3120056e-05
7,355	Selectivity Functions of Range Queries are Learnable*	2022	SIGMOD	5.529034e-05
7,581	Selectivity Estimation on Streaming Spatio-Textual Data Using Local Correlations	2015	VLDB	5.4753678e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	4,821	Reverse Spatial and Textual k Nearest Neighbor Search	2011	SIGMOD
2	7,742	Efficient Computation of Top-k Frequent Terms over Spatio-temporal Ranges	2017	SIGMOD
3	6,360	Clue-based Spatio-textual Query	2017	VLDB
4	11,802	TASK: An Efficient Framework for Instant Error-tolerant Spatial Keyword Queries on Road Networks	2023	VLDB
5	9,688	Indexing for Keyword Search with Structured Constraints	2023	PODS
6	3,739	An Efficient Query Indexing Mechanism for Filtering Geo-Textual Data	2013	SIGMOD
7	3,535	Collective Spatial Keyword Queries: A Distance Owner-Driven Approach	2013	SIGMOD
8	11,746	Effectiveness Perspectives and a Deep Relevance Model for Spatial Keyword Queries	2023	SIGMOD
9	3,054	Spatial Keyword Query Processing: An Experimental Evaluation	2013	VLDB
10	1,867	Efficient Retrieval of the Top-k Most Relevant Spatial Web Objects	2009	VLDB