Metraipolis › archive › dc_6063600ac0ca

PriCoRec: A Privacy-Aware Cloud-Device Collaborative Framework for Ad Recommendation under Feature Constraints — arXiv:2608.14429

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.14429
License (as archived)
CC0-1.0
Archived
2026-10-19T04:01:48.780Z
SHA-256 of the archived text
3b75491cb4d9d7d43a50e54601dd3428b4b22d27506a8b893623b010573bd7c9
Stable URL of this page
https://metraipolis.com/documento/dc_6063600ac0ca

How to cite

PriCoRec: A Privacy-Aware Cloud-Device Collaborative Framework for Ad Recommendation under Feature Constraints — arXiv:2608.14429 — arXiv (en), https://arxiv.org/abs/2608.14429 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6063600ac0ca (Metraipolis archive dc_6063600ac0ca, sha256 3b75491cb4d9d7d43a50e54601dd3428b4b22d27506a8b893623b010573bd7c9)
BibTeX
@misc{dc6063600ac0ca,
  title = {PriCoRec: A Privacy-Aware Cloud-Device Collaborative Framework for Ad Recommendation under Feature Constraints — arXiv:2608.14429},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14429},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6063600ac0ca; sha256 3b75491cb4d9d7d43a50e54601dd3428b4b22d27506a8b893623b010573bd7c9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14429. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Privacy regulations increasingly restrict cloud processing of sensitive user data (e.g., age, gender), hindering traditional cloud-only recommendation models. To mitigate this challenge, we propose a Privacy-aware Collaborative cloud-device ads Recommendation framework (PriCoRec) which personalizes recommendations while keeping sensitive features on-device. While separating recommendation into cloud-based and on-device stages enables privacy-aware deployment, naive splitting suffers from degraded shortlist quality and inefficient on-device inference due to limited private features. We therefore design a collaborative framework that comprises a cloud-based pre-ranking stage using cloud-accessible features, and an on-device ranking stage that locally incorporates highly personalized features. We introduce a diversity regularizer to pre-ranking to improve candidate quality. Moreover, to control device power consumption and computational cost, we incorporate a cloud-guided training mechanism that enhances device model performance while keeping the model lightweight. Experiments demonstrate that the proposed framework maintains strong recommendation performance while keeping sensitive features on-device.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-17 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2608.14429 — 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 2026-10-19T03:57:39.957Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).