UNIFY: Unified Index for Range Filtered Approximate Nearest Neighbors Search
Summary: UNIFY: a unified proximity-graph index (SIG) that segments data by attribute values so any segment combination's proximity graph is a SIG subgraph, enabling seamless pre/post/hybrid RF-ANNS without per-range index builds. HSIG adds an HNSW-like hierarchy for logarithmic hybrid filtering and fuses skip-list/compressed HNSW edges to support efficient pre/post filtering; yields state-of-the-art RF-ANNS across range sizes. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Anqi Liang
- 2. Pengcheng Zhang
- 3. Bin Yao
- 4. Zhongpu Chen
- 5. Yitong Song
- 6. Guangxu Cheng
Incoming Citations (Sorted by Pagerank)
Showing 4 of 4 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,052 | Attribute Filtering in Approximate Nearest Neighbor Search: An In-depth Experimental Study | 2026 | SIGMOD | 4.1945683e-05 |
| 10,054 | Beyond Vector Search: Querying With and Without Predicates | 2026 | SIGMOD | 4.1945683e-05 |
| 10,129 | WoW: A Window-to-Window Incremental Index for Range-Filtering Approximate Nearest Neighbor Search | 2026 | SIGMOD | 4.1945683e-05 |
| 10,273 | An Experimental Evaluation of Hybrid Querying on Vectors | 2026 | VLDB | 4.1945683e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 16 of 16 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next