Beyond Vector Search: Querying With and Without Predicates
Summary: Proposes an all‑in‑one k‑ANN framework for queries q=(v_q,c_q) that efficiently supports empty, categorical, and numerical predicates on vector‑annotated items, addressing gaps in prior methods. Matches or outperforms specialized vector/predicate engines and is validated by extensive accuracy and performance experiments. (summarized by gpt-5-mini on Feb 11 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Jiadong Xie (Chinese University of Hong Kong)
- 2. Jeffrey Xu Yu (Hong Kong University of Science and Technology)
- 3. Siyi Teng (Chinese University of Hong Kong)
- 4. Yingfan Liu (Xidian University)
BibTeX Citation
@inproceedings{xie_sigmod26,
title = {{Beyond Vector Search: Querying With and Without Predicates}},
author = {Xie, Jiadong and Yu, Jeffrey Xu and Teng, Siyi and Liu, Yingfan},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3769765},
url = {https://dl.acm.org/doi/10.1145/3769765},
year = {2026}
}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 14 of 14 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next