EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Knowledge-Enhanced Hyperbolic Attention Network for Trustworthy Sequential Recommendation

Shanming Wei, Shunmei Meng, Qianmu Li

ACM Transactions on Knowledge Discovery from Data · 31.07.2026 · 20 (6) · 1-21

DOI: 10.1145/3806830 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Knowledge Discovery from Data, online erschienen am 07.07.2026. Verfasst von Shanming Wei und 2 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: 2025 Jiangsu Frontier Technology R&D Project, 2024 Jiangsu Frontier Technology R&D Project, 2023 National First-Batch Cyber Talent Support Project on AI-based counterfeit detection and recommendation technologies..

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sequential recommendation aims to predict users’ next actions by modeling temporal dependencies in interaction sequences. However, existing attention- or graph-based models often struggle to jointly capture hierarchical semantics, long-range dependencies, and multi-relational knowledge, leading to suboptimal performance in sparse and cold-start scenarios. In this article, we propose KHARec, a knowledge-enhanced hyperbolic attention network that unifies geometric representation learning and temporal modeling for trustworthy sequential recommendation. KHARec consists of a hyperbolic fine-grain module that encodes hierarchical semantics from knowledge graphs, a Transformer-based coarse-grain module that models global dependencies with an FFT-based filter, and a learnable gating mechanism for adaptive feature fusion. Extensive experiments on three benchmark datasets demonstrate that KHARec consistently outperforms state-of-the-art sequential and knowledge-aware baselines in terms of HR@K and NDCG@K, while maintaining near-linear computational complexity. Further analyses verify the model’s robustness under sparsity and cold-start conditions and its superior capability in handling long-tail items. Overall, KHARec provides an interpretable and efficient framework for integrating hyperbolic reasoning and attention-based sequence modeling in large-scale recommendation environments.

Förderung

  • 2025 Jiangsu Frontier Technology R&D Project
  • 2024 Jiangsu Frontier Technology R&D Project
  • 2023 National First-Batch Cyber Talent Support Project on AI-based counterfeit detection and recommendation technologies.

Zitieren

APA

Wei, S., Meng, S., & Li, Q. (2026). Knowledge-Enhanced Hyperbolic Attention Network for Trustworthy Sequential Recommendation. ACM Transactions on Knowledge Discovery from Data, 20(6), 1-21. https://doi.org/10.1145/3806830

Vancouver

Wei S, Meng S, Li Q. Knowledge-Enhanced Hyperbolic Attention Network for Trustworthy Sequential Recommendation. ACM Transactions on Knowledge Discovery from Data. 2026;20(6):1-21. doi:10.1145/3806830

BibTeX
@article{Wei2026,
  author = {Wei, Shanming and Meng, Shunmei and Li, Qianmu},
  title = {Knowledge-Enhanced Hyperbolic Attention Network for Trustworthy Sequential Recommendation},
  journal = {ACM Transactions on Knowledge Discovery from Data},
  year = {2026},
  volume = {20},
  number = {6},
  pages = {1--21},
  doi = {10.1145/3806830}
}
Kostenlos starten →