The Case for Learned Index Structures

Summary: Indexes treated as models; learned indexes proposed as replacements for B-Tree, Hash, and Bitmap indexes. The paper analyzes theoretical conditions under which learned indexes outperform traditional ones and reports initial results, signaling ML-driven data management as a design paradigm. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: 5556
Venue: SIGMOD
Year: 2018
Pagerank: 0.00049778866
Overall Rank: 101 | 99.30%
DOI: 10.1145/3183713.3196909

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 50 of 206 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
4,404	TreeLine: An Update-In-Place Key-Value Store for Modern Storage	2023	VLDB	6.2052645e-05
4,431	Lightweight and Accurate Cardinality Estimation by Neural Network Gaussian Process	2022	SIGMOD	6.1870601e-05
4,448	Stable Learned Bloom Filters for Data Streams	2020	VLDB	6.1741316e-05
4,464	LOGER: A Learned Optimizer towards Generating Efficient and Robust Query Execution Plans	2023	VLDB	6.1552798e-05
4,572	Leaper: A Learned Prefetcher for Cache Invalidation in LSM-tree based Storage Engines	2020	VLDB	6.068399e-05
4,592	Auto-WLM: Machine Learning Enhanced Workload Management in Amazon Redshift	2023	SIGMOD	6.056004e-05
4,687	Deploying a Steered Query Optimizer in Production at Microsoft	2022	SIGMOD	5.9915268e-05
4,830	CARMI: A Cache-Aware Learned Index with a Cost-based Construction Algorithm	2022	VLDB	5.8884997e-05
4,836	Proteus: A Self-Designing Range Filter	2022	SIGMOD	5.8849277e-05
4,909	A Method for Optimizing Opaque Filter Queries	2020	SIGMOD	5.8354189e-05
4,993	Stacked Filters: Learning to Filter by Structure	2021	VLDB	5.7749409e-05
5,072	Learned Index: A Comprehensive Experimental Evaluation	2023	VLDB	5.7121108e-05
5,154	Hist-Tree: Those Who Ignore It Are Doomed to Learn	2021	CIDR	5.6548237e-05
5,250	One Model to Rule them All: Towards Zero-Shot Learning for Databases	2022	CIDR	5.6007779e-05
5,310	The Price of Tailoring the Index to Your Data: Poisoning Attacks on Learned Index Structures	2022	SIGMOD	5.5713508e-05
5,316	Cuckoo Index: A Lightweight Secondary Index Structure	2020	VLDB	5.5688295e-05
5,323	Can Learned Models Replace Hash Functions?	2023	VLDB	5.5671086e-05
5,327	DILI: A Distribution-Driven Learned Index	2023	VLDB	5.5660777e-05
5,463	The RLR-Tree: A Reinforcement Learning Based R-Tree for Spatial Data	2023	SIGMOD	5.4920768e-05
5,528	Warper: Efficiently Adapting Learned Cardinality Estimators to Data and Workload Drifts	2022	SIGMOD	5.4571136e-05
5,579	Spitz: A Verifiable Database System	2020	VLDB	5.4224124e-05
5,601	PLIN: A Persistent Learned Index for Non-Volatile Memory with High Performance and Instant Recovery	2023	VLDB	5.4158958e-05
5,630	Monotonic Cardinality Estimation of Similarity Selection: A Deep Learning Approach	2020	SIGMOD	5.4010111e-05
5,655	NFL: Robust Learned Index via Distribution Transformation	2022	VLDB	5.3877506e-05
5,682	LSched: A Workload-Aware Learned Query Scheduler for Analytical Database Systems	2022	SIGMOD	5.3752251e-05
5,749	InfiniFilter: Expanding Filters to Infinity and Beyond	2023	SIGMOD	5.3420354e-05
5,769	Oasis: An Optimal Disjoint Segmented Learned Range Filter	2024	VLDB	5.3326049e-05
5,799	Learned Approximate Query Processing: Make it Light, Accurate and Fast	2021	CIDR	5.3219666e-05
5,801	Dissecting, Designing, and Optimizing LSM-based Data Stores	2022	SIGMOD	5.3217858e-05
5,844	Stage: Query Execution Time Prediction in Amazon Redshift	2024	SIGMOD	5.3060581e-05
5,868	GRF: A Global Range Filter for LSM-Trees with Shape Encoding	2024	SIGMOD	5.2928769e-05
5,886	COMPASS: Online Sketch-based Query Optimization for In-Memory Databases	2021	SIGMOD	5.2847297e-05
5,925	HMAB: Self-Driving Hierarchy of Bandits for Integrated Physical Database Design Tuning	2023	VLDB	5.2669029e-05
6,241	Helios: Hyperscale Indexing for the Cloud & Edge	2020	VLDB	5.1357476e-05
6,298	Towards instance-optimized data systems	2021	VLDB	5.1182917e-05
6,365	Pre-training Summarization Models of Structured Datasets for Cardinality Estimation	2022	VLDB	5.0892829e-05
6,395	Range Search over Encrypted Multi-Attribute Data	2023	VLDB	5.0766624e-05
6,440	From Auto-tuning One Size Fits All to Self-designed and Learned Data-intensive Systems	2019	SIGMOD	5.0546781e-05
6,441	An Eight-Dimensional Systematic Evaluation of Optimized Search Algorithms on Modern Processors	2018	VLDB	5.0546366e-05
6,442	Updatable Learned Indexes Meet Disk-Resident DBMS - From Evaluations to Design Choices	2023	SIGMOD	5.0541252e-05
6,488	FILM: a Fully Learned Index for Larger-than-Memory Databases	2023	VLDB	5.0378878e-05
6,723	A Critical Analysis of Recursive Model Indexes	2022	VLDB	4.9449538e-05
6,753	Breaking It Down: An In-depth Study of Index Advisors	2024	VLDB	4.9345582e-05
6,774	A Unified Transferable Model for ML-Enhanced DBMS	2022	CIDR	4.9253635e-05
6,806	LMSFC: A Novel Multidimensional Index based on Learned Monotonic Space Filling Curves	2023	VLDB	4.917024e-05
6,860	Detect, Distill and Update: Learned DB Systems Facing Out of Distribution Data	2023	SIGMOD	4.9008421e-05
6,883	PilotScope: Steering Databases with Machine Learning Drivers	2024	VLDB	4.8918682e-05
6,962	Replicated Layout for In-Memory Database Systems	2022	VLDB	4.8771234e-05
7,389	Making In-Memory Learned Indexes Efficient on Disk	2024	SIGMOD	4.7386163e-05
7,392	MOST: Model-Based Compression with Outlier Storage for Time Series Data	2023	SIGMOD	4.737456e-05

Outgoing Citations (Sorted by Pagerank)

Showing 18 of 18 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
32	Differential Files: Their Application To The Maintenance Of Large Data Bases	1976	SIGMOD	0.00077553033
44	The Design Of Postgres	1986	SIGMOD	0.00071946446
104	Making B+-Trees Cache Conscious in Main Memory	2000	SIGMOD	0.00049475932
235	A Study of Index Structures for Main Memory Database Management Systems	1986	VLDB	0.00031980259
367	Small Materialized Aggregates: A Light Weight Index Structure for Data Warehousing	1998	VLDB	0.00025518228
382	FAST: Fast Architecture Sensitive Tree Search on Modern CPUs and GPUs	2010	SIGMOD	0.00024888997
715	Building a Database on S3	2008	SIGMOD	0.00017636409
1,212	RDF-3X: a RISC-style Engine for RDF	2008	VLDB	0.00013255692
1,300	Reducing the Storage Overhead of Main-Memory OLTP Databases with Hybrid Indexes	2016	SIGMOD	0.00012711153
1,468	Adaptive Range Filters for Cold Data: Avoiding Trips to Siberia	2013	VLDB	0.00011831457
1,692	A Seven-Dimensional Analysis of Hashing Methods and its Implications on Query Processing	2016	VLDB	0.00010887129
1,706	SCADS: Scale-Independent Storage for Social Computing Applications	2009	CIDR	0.00010806188
1,813	The End of a Myth: Distributed Transactions Can Scale	2017	VLDB	0.00010452333
1,875	An Architecture for Compiling UDF-centric Workflows	2015	VLDB	0.00010243959
1,909	BF-Tree: Approximate Tree Indexing	2014	VLDB	0.00010123661
3,760	A Hybrid B+-tree as Solution for In-Memory Indexing on CPU-GPU Heterogeneous Computing Platforms	2016	SIGMOD	6.7790524e-05
3,906	Two Birds, One Stone: A Fast, yet Lightweight, Indexing Scheme for Modern Database Systems	2017	VLDB	6.6413008e-05
4,886	The Wavelet Trie: Maintaining an Indexed Sequence of Strings in Compressed Space	2012	PODS	5.8508915e-05

Semantically Similar Papers

Overall Rank	Paper	Year	Venue	Pagerank
8,811	Tuning Hierarchical Learned Indexes on Disk and Beyond	2022	SIGMOD	4.4398976e-05
5,154	Hist-Tree: Those Who Ignore It Are Doomed to Learn	2021	CIDR	5.6548237e-05
9,745	Why Are Learned Indexes So Effective but Sometimes Ineffective?	2025	VLDB	4.2856385e-05
6,442	Updatable Learned Indexes Meet Disk-Resident DBMS - From Evaluations to Design Choices	2023	SIGMOD	5.0541252e-05
2,550	Updatable Learned Index with Precise Positions	2021	VLDB	8.5569576e-05
4,056	Are Updatable Learned Indexes Ready?	2022	VLDB	6.4905689e-05
2,676	Effectively Learning Spatial Indices	2020	VLDB	8.326321e-05
7,389	Making In-Memory Learned Indexes Efficient on Disk	2024	SIGMOD	4.7386163e-05
5,072	Learned Index: A Comprehensive Experimental Evaluation	2023	VLDB	5.7121108e-05
1,438	Benchmarking Learned Indexes	2021	VLDB	0.00011965956