Database Paper Browser

Back to papers

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

Summary: LIDER: a clustering-based hierarchical learned index for high-dimensional dense passage retrieval that reduces embeddings to 1D keys via extended SortingKeys-LSH + key re-scaling and an adapted RMI core. Outperforms ANN baselines (~1.2x speed) with higher retrieval quality and better speed–quality trade-offs. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID
13017
Venue
VLDB
Year
2023
Pagerank
4.7089636e-05
Overall Rank
7,549 | 47.54%
DOI
10.14778/3565816.3565819

Incoming Non-self Citations Over Time

Authors

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
101 The Case for Learned Index Structures 2018 SIGMOD 0.00049778866
399 Multi-Probe LSH: Efficient Indexing for High-Dimensional Similarity Search 2007 VLDB 0.00024359304
796 SageDB: A Learned Database System 2019 CIDR 0.00016541749
1,225 SK-LSH : An Efficient Index Structure for Approximate Nearest Neighbor Search 2014 VLDB 0.00013182109
1,464 Learning Multi-dimensional Indexes 2020 SIGMOD 0.0001184772
Previous Page 1 / 1 Next

Semantically Similar Papers