EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Disentangled Dynamic Graph Attention Network for Out-of-Distribution Sequential Recommendation

Zeyang Zhang, Xin Wang, Haibo Chen, Haoyang Li, Wenwu Zhu

ACM Transactions on Information Systems · 31.01.2025 · 43 (1) · 1-42

DOI: 10.1145/3701988 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Information Systems, online erschienen am 02.12.2024. Verfasst von Zeyang Zhang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 178 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, China National Postdoctoral Program for Innovative Talents.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sequential recommendation, leveraging user-item interaction histories to provide personalized and timely suggestions, has drawn significant research interest recently. With the power of exploiting spatio-temporal dynamics, Dynamic Graph Neural Networks (DyGNNs) show great potential in sequential recommendation by modeling the dynamic relationship between users and items. However, spatio-temporal distribution shifts naturally exist in out-of-distribution sequential recommendation, where both user-item relationships and temporal sequences demonstrate pattern shifts. The out-of-distribution scenarios may lead to the failure of existing DyGNNs in handling spatio-temporal distribution shifts in sequential recommendation, given that the patterns they exploit tend to be variant w.r.t labels under distribution shifts. In this article, we propose Disentangled Intervention-based Dynamic graph Attention networks with Invariance Promotion ( I-DIDA ) to handle spatio-temporal distribution shifts in sequential recommendation by discovering and utilizing invariant patterns , i.e., structures and features whose predictive abilities are stable across distribution shifts. Specifically, we first propose a disentangled spatio-temporal attention network to capture the variant and invariant patterns. By utilizing the disentangled patterns, we design a spatio-temporal intervention mechanism to create multiple interventional distributions and an environment inference module to infer the latent spatio-temporal environments, and minimize the invariance loss to leverage the invariant patterns with stable predictive abilities under distribution shifts. Extensive experiments demonstrate the superiority of our method over state-of-the-art sequential recommendation baselines under distribution shifts.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • China National Postdoctoral Program for Innovative Talents
  • China Postdoctoral Science Foundation

Zitieren

APA

Zhang, Z., Wang, X., Chen, H., Li, H., & Zhu, W. (2025). Disentangled Dynamic Graph Attention Network for Out-of-Distribution Sequential Recommendation. ACM Transactions on Information Systems, 43(1), 1-42. https://doi.org/10.1145/3701988

Vancouver

Zhang Z, Wang X, Chen H, Li H, Zhu W. Disentangled Dynamic Graph Attention Network for Out-of-Distribution Sequential Recommendation. ACM Transactions on Information Systems. 2025;43(1):1-42. doi:10.1145/3701988

BibTeX
@article{Zhang2025,
  author = {Zhang, Zeyang and Wang, Xin and Chen, Haibo and Li, Haoyang and Zhu, Wenwu},
  title = {Disentangled Dynamic Graph Attention Network for Out-of-Distribution Sequential Recommendation},
  journal = {ACM Transactions on Information Systems},
  year = {2025},
  volume = {43},
  number = {1},
  pages = {1--42},
  doi = {10.1145/3701988}
}
Kostenlos starten →