Metraipolis › archive › dc_d7ea13524f7c

Time-Decayed Vector Search in the Rhythm of TANGO: Jointly Modeling Semantic Similarity and Temporal Freshness — arXiv:2609.00548

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.00548
License (as archived)
CC0-1.0
Archived
2026-10-17T07:18:45.579Z
SHA-256 of the archived text
72bcaa6191457de9ee6e52901bb8af39f2db84bb569af0f499a7895e10d5715f
Stable URL of this page
https://metraipolis.com/documento/dc_d7ea13524f7c

How to cite

Time-Decayed Vector Search in the Rhythm of TANGO: Jointly Modeling Semantic Similarity and Temporal Freshness — arXiv:2609.00548 — arXiv (en), https://arxiv.org/abs/2609.00548 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d7ea13524f7c (Metraipolis archive dc_d7ea13524f7c, sha256 72bcaa6191457de9ee6e52901bb8af39f2db84bb569af0f499a7895e10d5715f)
BibTeX
@misc{dcd7ea13524f7c,
  title = {Time-Decayed Vector Search in the Rhythm of TANGO: Jointly Modeling Semantic Similarity and Temporal Freshness — arXiv:2609.00548},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00548},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d7ea13524f7c; sha256 72bcaa6191457de9ee6e52901bb8af39f2db84bb569af0f499a7895e10d5715f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00548. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vector search typically measures relevance through semantic similarity under a fixed scoring function. However, in a growing range of applications, relevance may evolve over time, making temporal freshness an additional signal beyond semantic similarity. In this paper, we formalize time-decayed vector search (TDVS), which incorporates continuous temporal decay into the search objective so that relevance is jointly determined by semantic similarity and temporal freshness. We design Score-Preserving Temporal Reduction (STR) that enables existing Maximum Inner Product Search indexes to directly support TDVS. We further present Chronos, a TDVS-native framework that derives an exact metric formulation and introduces Query-Orthogonal TimeLift to control data--data geometry while preserving all query--data scores and rankings. Building on Chronos, we propose TANGO, a hierarchical graph index that adopts layer-specific TimeLift geometries to preserve temporal locality at the base layer while strengthening long-range semantic connectivity in upper layers. TANGO traverses the hierarchy using the exact TDVS score, caches temporal factors to reduce computation, and supports efficient online insertion. Extensive experiments show that TANGO achieves up to 3.5$\times$ higher query throughput and 4.05$\times$ faster index construction than state-of-the-art graph-based competitors. TANGO also maintains its advantage over all competitors across diverse temporal settings and enables efficient online insertion, demonstrating its robustness and practicality.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-02 in cs.DB).
Categorie arXiv: Databases (cs.DB).
Pagina del lavoro: https://arxiv.org/abs/2609.00548 — 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 2026-10-17T07:06:49.782Z dalla pagina https://arxiv.org/catchup/cs.DB/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).