NaviX: A Native Vector Index Design for Graph DBMSs With Robust Predicate-Agnostic Search Performance
Summary: NaviX embeds a disk-based HNSW vector index natively in a graph DBMS, reusing its storage and query processing. Its adaptive, prefiltering kNN algorithm exploits local selectivity to remain robust across predicate selectivities and vector–predicate correlations. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Gaurav Sehgal (University of Waterloo)
- 2. Semih Salihoglu (University of Waterloo)
BibTeX Citation
@article{sehgal_vldb25,
title = {{NaviX: A Native Vector Index Design for Graph DBMSs With Robust Predicate-Agnostic Search Performance}},
author = {Sehgal, Gaurav and Salihoglu, Semih},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {11},
pages = {4438--4450},
doi = {10.14778/3749646.3749704},
url = {https://doi.org/10.14778/3749646.3749704},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 3 of 3 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,193 | An In-Depth Study of Filter-Agnostic Vector Search on a PostgreSQL Database System: [Experiments & Analysis] | 2026 | SIGMOD | 5.093636e-05 |
| 10,242 | FAVOR: Efficient Filter-Agnostic Vector ANNS Based on Selectivity-Aware Exclusion Distances | 2026 | SIGMOD | 5.093636e-05 |
| 10,279 | PathSeer: Adaptive Neighbor Handling for Efficient Filtered ANN Search | 2026 | SIGMOD | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 12 of 12 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next