Metraipolis › archive › dc_b2bc508a53ce
CORAL: Cross-modal Vector Retrieval via Incremental Graph Construction at Scale — arXiv:2610.11230
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.11230
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:35:34.116Z
- SHA-256 of the archived text
2174add908bb49373f0ed488c39cf932e7714662c0c7c5e83e2208f3901ba776- Stable URL of this page
https://metraipolis.com/documento/dc_b2bc508a53ce
How to cite
CORAL: Cross-modal Vector Retrieval via Incremental Graph Construction at Scale — arXiv:2610.11230 — arXiv (en), https://arxiv.org/abs/2610.11230 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b2bc508a53ce (Metraipolis archive dc_b2bc508a53ce, sha256 2174add908bb49373f0ed488c39cf932e7714662c0c7c5e83e2208f3901ba776)
BibTeX
@misc{dcb2bc508a53ce,
title = {CORAL: Cross-modal Vector Retrieval via Incremental Graph Construction at Scale — arXiv:2610.11230},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.11230},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b2bc508a53ce; sha256 2174add908bb49373f0ed488c39cf932e7714662c0c7c5e83e2208f3901ba776},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11230. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Cross-modal vector retrieval is widely used in multimodal systems, such as search engines and vector databases. It typically operates in out-of-distribution (OOD) settings, where query vectors follow a distribution that differs from that of the vectors stored in the database. In such cases, conventional indexes suffer significant performance degradation, and even methods specially designed for OOD remain limited by inefficient use of query modal characteristics, restricted GPU parallelism, and inadequate support for dynamic updates. We present CORAL, a novel GPU-accelerated graph-based vector index for scalable cross-modal retrieval, featuring hierarchical memory management that spans GPU, CPU, and disk. Specifically, CORAL incrementally incorporates the characteristics of query modality and terminates index construction timely. Crucially, it introduces coverage-aware adaptive pruning to address the imbalanced coverage of the query vector's neighbors. Moreover, CORAL presents a fully neighborhood-aware projection approach to efficiently utilize GPUs for highly parallel index construction, and a targeted connectivity enhancement method to refine the index structure. Besides, CORAL also supports modal-semantics-based vector insertion and topology-repairing deletion that restore node connectivity. Experimental results demonstrate that CORAL outperforms existing methods with up to 1.6 times the throughput at matched recall while reducing construction time by up to 56%. Furthermore, it exhibits remarkable resilience under dynamic updates and remains effective at the billion scale. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.DB, nuovi lavori del giorno). Categorie arXiv: Databases (cs.DB). Pagina del lavoro: https://arxiv.org/abs/2610.11230 — 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 2026-10-09T05:55:36.499Z dalla pagina https://arxiv.org/list/cs.DB/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).