Replace or Augment: Rethinking the Role of Learned Indexes in Relational Databases
Summary: MirrorBtr reframes learned indexes as lightweight B-Tree augmentations, accelerating traversals without replacing or restructuring the index. Integrated into InnoDB, it adapts to updates with low space and synchronization costs, achieving up to 7.45× query throughput. (summarized by gpt-6-luna on Oct 08 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Zhipeng Chen (Nanjing University)
- 2. Meng Li (Nanjing University)
- 3. Hancheng Wang (Nanjing University)
- 4. Junhan Lv (Nanjing University)
- 5. Haipeng Dai (Nanjing University)
- 6. Siqiang Luo (Nanyang Technological University)
BibTeX Citation
@article{chen_vldb27,
title = {{Replace or Augment: Rethinking the Role of Learned Indexes in Relational Databases}},
author = {Chen, Zhipeng and Li, Meng and Wang, Hancheng and Lv, Junhan and Dai, Haipeng and Luo, Siqiang},
journal = {PVLDB},
series = {{VLDB} '27},
volume = {20},
number = {1},
pages = {1--15},
doi = {10.14778/3845598.3845599},
url = {https://doi.org/10.14778/3845598.3845599},
year = {2027}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 39 of 39 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 2,582 | Are Updatable Learned Indexes Ready? | 2022 | VLDB |
| 2 | 6,867 | Accelerating String-key Learned Index Structures via Memoization-based Incremental Training | 2024 | VLDB |
| 3 | 11,001 | Demonstrating Indexing for Near-Sorted Data | 2026 | VLDB |
| 4 | 8,382 | Tuning Hierarchical Learned Indexes on Disk and Beyond | 2022 | SIGMOD |
| 5 | 8,865 | Adaptive Index Structures | 2002 | VLDB |
| 6 | 1,525 | Updatable Learned Index with Precise Positions | 2021 | VLDB |
| 7 | 835 | Benchmarking Learned Indexes | 2021 | VLDB |
| 8 | 6,613 | Making In-Memory Learned Indexes Efficient on Disk | 2024 | SIGMOD |
| 9 | 5,378 | Updatable Learned Indexes Meet Disk-Resident DBMS - From Evaluations to Design Choices | 2023 | SIGMOD |
| 10 | 3,621 | Learned Index: A Comprehensive Experimental Evaluation | 2023 | VLDB |