Metraipolis › archive › dc_dba0646d256c

VADER: Filtered Vector Search with Declarative Recall — arXiv:2609.38053

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.38053
License (as archived)
CC0-1.0
Archived
2026-10-07T19:16:20.051Z
SHA-256 of the archived text
ad37fd6809518f959aab564fcb6be348cdf0ac3b2c6f90fe15aeb91dd802cdf3
Stable URL of this page
https://metraipolis.com/documento/dc_dba0646d256c

How to cite

VADER: Filtered Vector Search with Declarative Recall — arXiv:2609.38053 — arXiv (en), https://arxiv.org/abs/2609.38053 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dba0646d256c (Metraipolis archive dc_dba0646d256c, sha256 ad37fd6809518f959aab564fcb6be348cdf0ac3b2c6f90fe15aeb91dd802cdf3)
BibTeX
@misc{dcdba0646d256c,
  title = {VADER: Filtered Vector Search with Declarative Recall — arXiv:2609.38053},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38053},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dba0646d256c; sha256 ad37fd6809518f959aab564fcb6be348cdf0ac3b2c6f90fe15aeb91dd802cdf3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38053. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Approximate filtered vector search (FVS), a core operation in many data management tasks that combine structured data with vector embeddings, exhibits increased complexity due to the characteristics of filtering predicates. Each predicate is defined by selectivity (i.e., the fraction of vectors that satisfy the predicate) and correlation (i.e., the relationship between the filter and the vector space), which can significantly affect search difficulty even for the same query vector. This poses a key challenge for users aiming to integrate vector search with structured data, as efficient execution often requires extensive manual tuning of algorithm parameters. In this paper, we present VADER, the first approach that eliminates hyperparameter tuning by introducing declarative recall for approximate filtered vector search. With declarative recall, users specify a desired recall target, and VADER executes FVS queries to meet this target without requiring manual configuration. VADER achieves this by employing a filter-aware recall predictor that generalizes across varying selectivities and correlations without explicit tuning, and by performing early termination once the predicted recall reaches the user-defined target. Through extensive experimental evaluation, we show that VADER achieves near-optimal early termination, while providing significant speedups of up to 53% faster and improved result quality of 28% compared to the best-performing baseline.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.DB).
Categorie arXiv: Databases (cs.DB).
Pagina del lavoro: https://arxiv.org/abs/2609.38053 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T18:42:16.911Z dalla pagina https://arxiv.org/catchup/cs.DB/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).