DBScholar

Back to papers

LIDER: An Efficient High-dimensional Learned Index for Large-scale Dense Passage Retrieval

Summary: LIDER replaces ANN search with a hierarchical learned index: SK-LSH and key rescaling map high-dimensional embeddings to sortable 1D keys, while RMI predicts locations. It delivers faster, higher-quality retrieval and improved speed–quality trade-offs at scale. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID
13204
Venue
VLDB
Year
2023
Pagerank
5.6625991e-05
Overall Rank
7,254 | 50.24%
DOI
10.14778/3565816.3565819

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@article{wang_vldb23,
        title = {{LIDER: An Efficient High-dimensional Learned Index for Large-scale Dense Passage Retrieval}},
        author = {Wang, Yifan and Ma, Haodi and Wang, Daisy Zhe},
        journal = {PVLDB},
        series = {{VLDB} '23},
        volume = {16},
        number = {2},
        pages = {154--166},
        doi = {10.14778/3565816.3565819},
        url = {https://doi.org/10.14778/3565816.3565819},
        year = {2023}
}

Incoming Citations (Sorted by Pagerank)

Showing 4 of 4 citing papers.

Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 5 of 5 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
287 Multi-Probe LSH: Efficient Indexing for High-Dimensional Similarity Search 2007 VLDB 0.00022323585
568 SageDB: A Learned Database System 2019 CIDR 0.0001641553
873 Learning Multi-dimensional Indexes 2020 SIGMOD 0.00013481915
990 SK-LSH: An Efficient Index Structure for Approximate Nearest Neighbor Search 2014 VLDB 0.00012796562
Previous Page 1 / 1 Next

Semantically Similar Papers