NaviX: A Native Vector Index Design for Graph DBMSs With Robust Predicate-Agnostic Search Performance
Summary: NaviX: native, disk-backed HNSW index inside graph DBMSs for unified vector + structured/graph queries. Prefiltering with an adaptive per-node local-selectivity heuristic yields predicate-agnostic kNN search robust to selectivity/correlation, outperforming pre/postfilter baselines. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Gaurav Sehgal
- 2. Semih Salihoğlu
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 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