Metraipolis › archive › dc_554a97cfde69

Federated Vector Retrieval across Heterogeneous VectorDBs — arXiv:2611.01514

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.01514
License (as archived): CC0-1.0
Archived: 2026-11-03T11:39:44.144Z
SHA-256 of the archived text: 38244392e49a42a8d199fc67c12ea700f225f67d83dc36ca4718241cd180b54f
Stable URL of this page: https://metraipolis.com/documento/dc_554a97cfde69

How to cite

Federated Vector Retrieval across Heterogeneous VectorDBs — arXiv:2611.01514 — arXiv (en), https://arxiv.org/abs/2611.01514 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_554a97cfde69 (Metraipolis archive dc_554a97cfde69, sha256 38244392e49a42a8d199fc67c12ea700f225f67d83dc36ca4718241cd180b54f)

BibTeX

@misc{dc554a97cfde69,
  title = {Federated Vector Retrieval across Heterogeneous VectorDBs — arXiv:2611.01514},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01514},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_554a97cfde69; sha256 38244392e49a42a8d199fc67c12ea700f225f67d83dc36ca4718241cd180b54f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01514. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vector databases are now core infrastructure for AI retrieval systems, yet many real deployments must serve queries over multiple independently constructed vectorDBs built with different embedding models. This creates a systems problem of federated retrieval over heterogeneous vectorDBs: vectors and similarity scores are not directly comparable across embedding spaces, while fully resolving this incompatibility through corpus-wide re-embedding and re-indexing is often operationally prohibitive. Existing methods therefore face a difficult trade-off between retrieval quality, construction cost, and query throughput. We present HVMap, a lightweight compatibility layer for federated retrieval across heterogeneous vectorDBs. Instead of rebuilding databases into a unified space, HVMap learns bidirectional mappings between embedding spaces using a fuzzy contrastive loss, enabling calibrated cross-database scoring without corpus migration or index reconstruction. HVMap is system-agnostic and further scales to multi-vectorDB settings while preserving ranking fidelity through a hub-based architecture. We evaluate HVMap in open-domain, cross-domain, and scale-out settings, and also construct a new benchmark for heterogeneous cross-domain federation. Across these settings, HVMap consistently achieves a better quality--cost--throughput trade-off than baselines, achieving up to 3.59X higher nDCG@10, up to 2.01X higher query throughput, and construction time as low as 0.3% of baseline methods. These results show that HVMap makes heterogeneous vectorDB federation practical at scale.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.IR, nuovi lavori del giorno).
Categorie arXiv: Databases (cs.DB) ; Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2611.01514 — 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 2026-11-03T11:06:22.205Z dalla pagina https://arxiv.org/list/cs.IR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).