Metraipolis › archive › dc_ced1e6893fa1

ZeroGR: Filtering-First Constrained Decoding for Generative Recommendation — arXiv:2611.04715

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04715
License (as archived)
CC0-1.0
Archived
2026-11-04T12:55:30.018Z
SHA-256 of the archived text
81141b4e60e74bc5abe5d81de93ce7d3c9eb0354899911bc48e9cff3404b93a1
Stable URL of this page
https://metraipolis.com/documento/dc_ced1e6893fa1

How to cite

ZeroGR: Filtering-First Constrained Decoding for Generative Recommendation — arXiv:2611.04715 — arXiv (en), https://arxiv.org/abs/2611.04715 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ced1e6893fa1 (Metraipolis archive dc_ced1e6893fa1, sha256 81141b4e60e74bc5abe5d81de93ce7d3c9eb0354899911bc48e9cff3404b93a1)
BibTeX
@misc{dcced1e6893fa1,
  title = {ZeroGR: Filtering-First Constrained Decoding for Generative Recommendation — arXiv:2611.04715},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04715},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ced1e6893fa1; sha256 81141b4e60e74bc5abe5d81de93ce7d3c9eb0354899911bc48e9cff3404b93a1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04715. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generative recommendation is gaining traction in production, retrieving items by generating their identifiers one token at a time. The generated sequences must identify relevant catalog items, so constrained decoding couples relevance scoring with validity filtering. Because most possible sequences are invalid, scoring before filtering wastes computation on candidates that will be discarded. Our evaluation shows that filtering first can avoid this work with negligible impact on recommendation quality. We present ZeroGR, a filtering-first constrained decoding system for generative recommendation. ZeroGR uses a step-sliced filtering index to reduce GPU memory use by tailoring data representations to each decoding step. Its execution engine adopts shared-slot execution to accelerate data exchange across stages and hybrid projection to adapt computation to workload patterns, thereby reducing execution overhead. During index refreshes, ZeroGR applies layout-guided streaming construction to speed up updates and limit serving interference. Extensive evaluation shows that ZeroGR accelerates the filtering and scoring pipeline by up to $9.9\times$ over representative baselines while reducing GPU index memory use and accelerating index reconstruction.

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/2611.04715 — 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 2026-11-04T12:33:32.135Z dalla pagina https://arxiv.org/list/cs.IR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).