Metraipolis › archive › dc_1750ca2db688

EPIC: Explicit Posterior Item Conditioning for Semantic ID Diffusion Recommendation — arXiv:2609.03522

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03522
License (as archived)
CC0-1.0
Archived
2026-10-17T02:08:39.883Z
SHA-256 of the archived text
3fa6bff8f1115674898927a1c4c409a492303894567ac0b76a1809edc76b3852
Stable URL of this page
https://metraipolis.com/documento/dc_1750ca2db688

How to cite

EPIC: Explicit Posterior Item Conditioning for Semantic ID Diffusion Recommendation — arXiv:2609.03522 — arXiv (en), https://arxiv.org/abs/2609.03522 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1750ca2db688 (Metraipolis archive dc_1750ca2db688, sha256 3fa6bff8f1115674898927a1c4c409a492303894567ac0b76a1809edc76b3852)
BibTeX
@misc{dc1750ca2db688,
  title = {EPIC: Explicit Posterior Item Conditioning for Semantic ID Diffusion Recommendation — arXiv:2609.03522},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03522},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1750ca2db688; sha256 3fa6bff8f1115674898927a1c4c409a492303894567ac0b76a1809edc76b3852},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03522. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Semantic ID (SID) generative recommendation predicts the next item by generating a short tuple of discrete tokens. Recent masked-diffusion methods improve this process through bidirectional context and flexible decoding, yet recommendation ultimately requires selecting among complete catalog items. At each denoising step, a partial SID can correspond to multiple feasible items, while existing methods primarily reason through position-wise token predictions. We propose Explicit Posterior Item Conditioning (EPIC), which introduces explicit item-level competition into SID denoising. EPIC constructs a personalized posterior over feasible candidate items using the current generation context and the user's recent interactions, then projects this distribution back to unresolved SID positions to guide subsequent token decisions. The pretrained backbone remains frozen and requires no additional decoder forward pass. Experiments on four Amazon benchmarks show consistent improvements over strong baselines, while diagnostic analyses indicate that the gains primarily arise from personalized transition evidence that preserves promising item hypotheses during denoising.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.LG).
Categorie arXiv: Information Retrieval (cs.IR) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.03522 — 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 2026-10-17T01:47:25.624Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).