Metraipolis › archive › dc_9711fb90bb74
Towards a Unified Framework of Optimal Input-Side Dimensional Configuration for Deep CTR Prediction — arXiv:2610.35695
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.35695
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T08:03:23.868Z
- SHA-256 of the archived text
dea6f936b39f328229fcc8c7cf100ae713320851572d955cd1a4de99a0e2af84- Stable URL of this page
https://metraipolis.com/documento/dc_9711fb90bb74
How to cite
Towards a Unified Framework of Optimal Input-Side Dimensional Configuration for Deep CTR Prediction — arXiv:2610.35695 — arXiv (en), https://arxiv.org/abs/2610.35695 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9711fb90bb74 (Metraipolis archive dc_9711fb90bb74, sha256 dea6f936b39f328229fcc8c7cf100ae713320851572d955cd1a4de99a0e2af84)
BibTeX
@misc{dc9711fb90bb74,
title = {Towards a Unified Framework of Optimal Input-Side Dimensional Configuration for Deep CTR Prediction — arXiv:2610.35695},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.35695},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9711fb90bb74; sha256 dea6f936b39f328229fcc8c7cf100ae713320851572d955cd1a4de99a0e2af84},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.35695. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Deep click-through rate (CTR) prediction has achieved substantial success through increasingly expressive feature interaction architectures. However, predictive performance also depends on how input-side information is configured before interaction modeling. Existing studies have shown that selecting informative samples, features, or embedding units can improve prediction accuracy. Nevertheless, they primarily optimize these selection mechanisms independently along a single input-side dimension, overlooking their shared basic form and the inherent dependencies across input levels, thereby limiting the effectiveness of input-side dimensional configuration. To address this issue, we propose OptIDC, a unified framework for Optimal Input-side Dimensional Configuration in deep CTR prediction. OptIDC jointly learns sample, feature, and embedding-unit level configurations within a unified framework by integrating their corresponding selection mechanisms. To explicitly coordinate selection decisions across different levels, OptIDC further introduces a selection-weighted Optimal Transport mechanism that aligns coarse- and fine-grained selections via transport over finite measures, thereby alleviating cross-level selection conflicts while preserving the semantics of each input level. Moreover, OptIDC is model-agnostic and can be seamlessly integrated into existing CTR models. Extensive experiments on four real-world benchmark datasets demonstrate that OptIDC consistently achieves higher AUC than existing input-side selection methods, validating the effectiveness of unified input-side dimensional configuration. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.35695 — 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 2026-10-27T07:55:31.010Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).