Metraipolis › archive › dc_bc1593566248
Beyond Semantic IDs: Atomic Creator Tokens for Large-Scale Generative Recommendation — arXiv:2611.00323
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.00323
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:41:48.366Z
- SHA-256 of the archived text
1c0838ca7c1e491562439b35a0ce52756a0b5592b1d6372318bf6608145a0b6e- Stable URL of this page
https://metraipolis.com/documento/dc_bc1593566248
How to cite
Beyond Semantic IDs: Atomic Creator Tokens for Large-Scale Generative Recommendation — arXiv:2611.00323 — arXiv (en), https://arxiv.org/abs/2611.00323 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bc1593566248 (Metraipolis archive dc_bc1593566248, sha256 1c0838ca7c1e491562439b35a0ce52756a0b5592b1d6372318bf6608145a0b6e)
BibTeX
@misc{dcbc1593566248,
title = {Beyond Semantic IDs: Atomic Creator Tokens for Large-Scale Generative Recommendation — arXiv:2611.00323},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.00323},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bc1593566248; sha256 1c0838ca7c1e491562439b35a0ce52756a0b5592b1d6372318bf6608145a0b6e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00323. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recommending creators that a user does not yet follow is a cold-start problem: from hundreds of thousands of popular creators and only a short trail of prior engagements, the system must predict the next creator worth surfacing. The prevailing generative recommendation recipe tokenizes each creator into a \emph{Semantic ID} (SID) by quantizing a frozen embedding and trains a language model to generate SIDs. We show that this SID layer, not the language model, is the binding constraint. The creator-to-SID map is many-to-one, so colliding creators must be resolved by a popularity tie-break that caps creator-level recall and favors already-popular creators, and the frozen quantizer stops the training gradient from reaching the creator representation. We propose Atomic Creator Token (ACT), which gives every creator its own vocabulary token trained end-to-end. The map is bijective, so collisions are impossible and inference is a direct top-$k$ over creator logits. In a controlled comparison on production data in which the token layer is the only variable, ACT improves creator-level Recall@15 by 19.8 points ($1.84\times$) over a matched SID baseline, still leads when the SID codebook is enlarged $64\times$, and serves at ${\sim}2.7\times$ lower per-user latency. The advantage carries over to the public KuaiRand dataset, where ACT is the only method that beats a global-popularity baseline, provided each creator token sees enough training examples. In a live A/B test, ACT is directionally positive on every reported metric against both the SID-enhanced and the classic production rankers.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.00323 — 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 2026-11-03T10:39:50.156Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).