EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Divide-and-Conquer: Cold-Start Bundle Recommendation via Mixture of Diffusion Experts

Ming Li, Lin Li, Xiaohui Tao, Dong Zhang, Jimmy Xiangji Huang

ACM Transactions on Information Systems · 30.06.2026 · 44 (5) · 1-32

DOI: 10.1145/3799250 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Information Systems, online erschienen am 23.05.2026. Verfasst von Ming Li und 4 weiteren Autor:innen. Die Arbeit nennt 77 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, China Scholarship Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cold-start bundle recommendation focuses on modeling new bundles with insufficient information to provide recommendations. Advanced bundle recommendation models usually learn bundle representations from multiple views (e.g., user-bundle interaction views) at both bundle and item levels. Consequently, the cold-start problem for bundles is more challenging than that for traditional items due to the dual-level multi-view complexity. For cold-start bundle recommendation, we propose a novel Mixture of Diffusion Experts (MoDiffE) framework, which employs a divide-and-conquer strategy and consists of three parts: (1) Division : The bundle cold-start problem is divided into view-specific but unified sub-problems: the poor representation of feature-missing bundles in prior-embedding models. (2) Conquest : Diffusion models uniformly solve all sub-problems by directly generating diffusion representations without depending on specific features. (3) Combination : A cold-aware hierarchical Mixture of Experts (MoE) is employed to adaptively combine results of the sub-problems into final recommendations. Additionally, MoDiffE proposes a cold-start gating augmentation method to enable gating for cold bundles. In experiments on three real-world datasets, MoDiffE significantly outperforms existing solutions in cold-start bundle recommendation. It achieves up to a 0.1027 Recall@20 improvement in cold-start scenarios and up to a 47.43% relative improvement in all-bundle scenarios.

Förderung

  • National Natural Science Foundation of China
  • China Scholarship Council

Zitieren

APA

Li, M., Li, L., Tao, X., Zhang, D., & Huang, J. X. (2026). Divide-and-Conquer: Cold-Start Bundle Recommendation via Mixture of Diffusion Experts. ACM Transactions on Information Systems, 44(5), 1-32. https://doi.org/10.1145/3799250

Vancouver

Li M, Li L, Tao X, Zhang D, Huang JX. Divide-and-Conquer: Cold-Start Bundle Recommendation via Mixture of Diffusion Experts. ACM Transactions on Information Systems. 2026;44(5):1-32. doi:10.1145/3799250

BibTeX
@article{Li2026,
  author = {Li, Ming and Li, Lin and Tao, Xiaohui and Zhang, Dong and Huang, Jimmy Xiangji},
  title = {Divide-and-Conquer: Cold-Start Bundle Recommendation via Mixture of Diffusion Experts},
  journal = {ACM Transactions on Information Systems},
  year = {2026},
  volume = {44},
  number = {5},
  pages = {1--32},
  doi = {10.1145/3799250}
}
Kostenlos starten →