Metraipolis › archive › dc_7bb30b172dfa

HELIX: Purified and Unified - Rethinking Feature Interaction and Sequence Modeling for Large-Scale Recommendation — arXiv:2609.37183

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.37183
License (as archived): CC0-1.0
Archived: 2026-10-07T18:37:46.598Z
SHA-256 of the archived text: d6167b8d66c99adc4261c90f328d622d27497aa25f5941cbee445e3d59cd9c80
Stable URL of this page: https://metraipolis.com/documento/dc_7bb30b172dfa

How to cite

HELIX: Purified and Unified - Rethinking Feature Interaction and Sequence Modeling for Large-Scale Recommendation — arXiv:2609.37183 — arXiv (en), https://arxiv.org/abs/2609.37183 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7bb30b172dfa (Metraipolis archive dc_7bb30b172dfa, sha256 d6167b8d66c99adc4261c90f328d622d27497aa25f5941cbee445e3d59cd9c80)

BibTeX

@misc{dc7bb30b172dfa,
  title = {HELIX: Purified and Unified - Rethinking Feature Interaction and Sequence Modeling for Large-Scale Recommendation — arXiv:2609.37183},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37183},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7bb30b172dfa; sha256 d6167b8d66c99adc4261c90f328d622d27497aa25f5941cbee445e3d59cd9c80},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37183. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Industrial recommendation ranking models typically scale along two modeling axes: feature interaction over heterogeneous user, item, context, and cross features, and sequence modeling over long, informative, and multi-type user behavior histories. We find that scaling either capability in isolation is insufficient, as each exhibits a limited scaling ceiling and a suboptimal scaling-law slope. We conjecture that achieving a more favorable scaling-law slope requires jointly scaling both axes. To support this, we present HELIX, a purified and unified architecture for large-scale recommendation. HELIX interleaves sequence retrieval and feature interaction while enforcing one-way information flow from reusable sequence states to candidate-conditioned mix-tokens. This design preserves cross-depth communication between the two modeling axes while keeping user-side sequence computation amortizable, enabling flexible and asymmetric scaling of sequence modeling and feature interaction. Deployed in TikTok's e-commerce recommendation system, HELIX consistently improves offline CTR AUC, CVR AUC, and other ranking metrics. In online A/B tests, it achieves an approximately 6% increase in e-commerce video GMV per user.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.37183 — 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 2026-10-07T18:04:00.987Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).