Metraipolis › archive › dc_6edd75e9bb70

LIFT: A Lifecycle-aware Interaction Factorization Transformer for Unified Retrieval and Ranking — arXiv:2610.10556

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.10556
License (as archived)
CC0-1.0
Archived
2026-10-09T06:29:54.346Z
SHA-256 of the archived text
8505b690cabfd714b58dd99af4fc3dc9a834d84b7e2cceb14773e290c90de8a9
Stable URL of this page
https://metraipolis.com/documento/dc_6edd75e9bb70

How to cite

LIFT: A Lifecycle-aware Interaction Factorization Transformer for Unified Retrieval and Ranking — arXiv:2610.10556 — arXiv (en), https://arxiv.org/abs/2610.10556 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6edd75e9bb70 (Metraipolis archive dc_6edd75e9bb70, sha256 8505b690cabfd714b58dd99af4fc3dc9a834d84b7e2cceb14773e290c90de8a9)
BibTeX
@misc{dc6edd75e9bb70,
  title = {LIFT: A Lifecycle-aware Interaction Factorization Transformer for Unified Retrieval and Ranking — arXiv:2610.10556},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10556},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6edd75e9bb70; sha256 8505b690cabfd714b58dd99af4fc3dc9a834d84b7e2cceb14773e290c90de8a9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10556. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Cascaded recommender systems use the same user history for retrieval and ranking, while the two stages have access to different information at different points of an interaction. We propose the Lifecycle-aware Interaction Factorization Transformer (LIFT), which decomposes each interaction into ordered Request, Item, Context, and Action states and models them as a causal sequence. Retrieval reads the Request state, while ranking reads the Context state, allowing both tasks to share history modeling while preserving stage-specific information. LIFT instantiates this representation with Role-Conditioned Attention and a lightweight Pre-LN Bias. On ML-20M and Taobao, LIFT achieves the highest Joint Score among the evaluated joint models, improving over the strongest baselines by 4.9% and 3.6%, respectively. Loss-weight sweeps show favorable retrieval--ranking trade-offs, while ablations and scaling analyses further examine lifecycle sequence construction, model components, and capacity settings.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.IR, nuovi lavori del giorno).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2610.10556 — 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 2026-10-09T05:54:51.492Z dalla pagina https://arxiv.org/list/cs.IR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).