Learned Static Function Data Structures
Summary: Learned static functions: ML predicts per-key value distributions, then encodes each value with a key-specific prefix code stored in a static function structure. Breaks the zero-order entropy barrier for point queries, yielding major space savings over compressed static functions. (summarized by gpt-5.4-mini on Apr 12 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Stefan Hermann (Karlsruhe Institute of Technology)
- 2. Hans-Peter Lehmann (Karlsruhe Institute of Technology)
- 3. Giorgio Vinciguerra (University of Pisa)
- 4. Stefan Walzer (Karlsruhe Institute of Technology)
BibTeX Citation
@article{hermann_vldb26,
title = {{Learned Static Function Data Structures}},
author = {Hermann, Stefan and Lehmann, Hans-Peter and Vinciguerra, Giorgio and Walzer, Stefan},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {5},
pages = {917--930},
doi = {10.14778/3796195.3796205},
url = {https://doi.org/10.14778/3796195.3796205},
year = {2026}
}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 7 of 7 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 42 | The Case for Learned Index Structures | 2018 | SIGMOD | 0.00046185549 |
| 466 | The PGM-index: a fully-dynamic compressed learned index with provable worst-case bounds | 2020 | VLDB | 0.0001794793 |
| 1,661 | Efficient Parallel Lists Intersection and Index Compression Algorithms using Graphics Processing Units | 2011 | VLDB | 0.00010048073 |
| 2,623 | SPARTAN: A Model-Based Semantic Compression System for Massive Data Tables | 2001 | SIGMOD | 8.312935e-05 |
| 3,101 | DeepSqueeze: Deep Semantic Compression for Tabular Data | 2020 | SIGMOD | 7.7356703e-05 |
| 4,076 | LeCo: Lightweight Compression via Learning Serial Correlations | 2024 | SIGMOD | 6.9012899e-05 |
| 4,796 | Can Learned Models Replace Hash Functions? | 2023 | VLDB | 6.4847588e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 3,643 | Stable Learned Bloom Filters for Data Streams | 2020 | VLDB |
| 2 | 9,561 | Experimental Analysis of Large-scale Learnable Vector Storage Compression | 2024 | VLDB |
| 3 | 4,556 | Stacked Filters: Learning to Filter by Structure | 2021 | VLDB |
| 4 | 3,861 | A General and Efficient Querying Method for Learning to Hash | 2018 | SIGMOD |
| 5 | 7,987 | Efficient and Tunable Similar Set Retrieval | 2001 | SIGMOD |
| 6 | 42 | The Case for Learned Index Structures | 2018 | SIGMOD |
| 7 | 11,630 | New Wine in an Old Bottle: Data-Aware Hash Functions for Bloom Filters | 2022 | VLDB |
| 8 | 4,796 | Can Learned Models Replace Hash Functions? | 2023 | VLDB |
| 9 | 11,700 | Learning Algorithms for Automatic Data Structure Design | 2021 | SIGMOD |
| 10 | 8,870 | Entropy-Learned Hashing: Constant Time Hashing with Controllable Uniformity | 2022 | SIGMOD |