ALEX: An Updatable Adaptive Learned Index

Summary: Presents ALEX, an updatable adaptive learned index for mixed read/write workloads. Blends learned indexing with conventional storage to support updates; delivers up to 4.1x read speed and dramatically smaller index footprints vs B+Trees. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: 5988
Venue: SIGMOD
Year: 2020
Pagerank: 0.00018322593
Overall Rank: 447 | 96.94%
DOI: 10.1145/3318464.3389711

Incoming Non-self Citations Over Time

Authors

1. Jialin Ding (Massachusetts Institute of Technology)
2. Umar Farooq Minhas (Microsoft)
3. Jia Yu (Arizona State University)
4. Chi Wang (Microsoft)
5. Jaeyoung Do (Microsoft)
6. Yinan Li (Microsoft)
7. Hantian Zhang (Georgia Institute of Technology)
8. Badrish Chandramouli (Microsoft)
9. Johannes Gehrke (Microsoft)
10. Donald Kossmann (Microsoft)
11. David Lomet (Microsoft)
12. Tim Kraska (Massachusetts Institute of Technology)

BibTeX Citation

@inproceedings{ding_sigmod20,
        title = {{ALEX: An Updatable Adaptive Learned Index}},
        author = {Ding, Jialin and Minhas, Umar Farooq and Yu, Jia and Wang, Chi and Do, Jaeyoung and Li, Yinan and Zhang, Hantian and Chandramouli, Badrish and Gehrke, Johannes and Kossmann, Donald and Lomet, David and Kraska, Tim},
        series = {{SIGMOD} '20},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3318464.3389711},
        url = {https://dl.acm.org/doi/10.1145/3318464.3389711},
        year = {2020}
}

Incoming Citations (Sorted by Pagerank)

Showing 1 of 101 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
11,702	LES3: Learning-based Exact Set Similarity Search	2021	VLDB	5.093636e-05

Outgoing Citations (Sorted by Pagerank)

Showing 17 of 17 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
43	The Case for Learned Index Structures	2018	SIGMOD	0.00046060254
67	Making B+-Trees Cache Conscious in Main Memory	2000	SIGMOD	0.00038461275
84	Learned Cardinalities: Estimating Correlated Joins with Deep Learning	2019	CIDR	0.00035838391
154	Neo: A Learned Query Optimizer	2019	VLDB	0.00028726181
204	Cache Conscious Indexing for Decision-Support in Main Memory	1999	VLDB	0.00025342994
278	FAST: Fast Architecture Sensitive Tree Search on Modern CPUs and GPUs	2010	SIGMOD	0.00022476841
461	Query-based Workload Forecasting for Self-Driving Database Management Systems	2018	SIGMOD	0.00018068441
545	Improving Index Performance through Prefetching	2001	SIGMOD	0.00016766463
568	SageDB: A Learned Database System	2019	CIDR	0.0001641553
697	Selectivity Estimation for Range Predicates using Lightweight Models	2019	VLDB	0.00014888851
790	FITing-Tree: A Data-aware Index Structure	2019	SIGMOD	0.0001401445
873	Learning Multi-dimensional Indexes	2020	SIGMOD	0.00013481915
1,135	Qd-tree: Learning Data Layouts for Big Data Analytics	2020	SIGMOD	0.00012032847
1,492	BF-Tree: Approximate Tree Indexing	2014	VLDB	0.00010588267
2,213	Designing Succinct Secondary Indexing Mechanism by Exploiting Column Correlations	2019	SIGMOD	8.9410226e-05
2,222	Efficiently Searching In-Memory Sorted Arrays: Revenge of the Interpolation Search?	2019	SIGMOD	8.9255716e-05
2,950	An Adaptive Packed-Memory Array	2006	PODS	7.9260861e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	10,458	From Learning to Recycling: A Log-Structured Learned-Less Index	2026	SIGMOD
2	8,214	Tuning Hierarchical Learned Indexes on Disk and Beyond	2022	SIGMOD
3	1,551	Updatable Learned Index with Precise Positions	2021	VLDB
4	6,687	Making In-Memory Learned Indexes Efficient on Disk	2024	SIGMOD
5	10,277	On Self-Designing Learned Indexes	2026	SIGMOD
6	8,039	Algorithmic Complexity Attacks on Dynamic Learned Indexes	2024	VLDB
7	2,806	Are Updatable Learned Indexes Ready?	2022	VLDB
8	3,792	Learned Index: A Comprehensive Experimental Evaluation	2023	VLDB
9	847	Benchmarking Learned Indexes	2021	VLDB
10	5,423	Updatable Learned Indexes Meet Disk-Resident DBMS - From Evaluations to Design Choices	2023	SIGMOD