EUVIMEDEUVIMED entdecken
Crossref

SGP4SR: Separated-Modality Guided User Preference Learning for Multimodal Sequential Recommendation

Changhong Li, Zhiqiang Guo, Guohui Li, Zhong Yang, Chuhang Hong

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (18) · 15054-15062

DOI: 10.1609/aaai.v40i18.38528 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Changhong Li und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the booming development of multimodal data (e.g., image, text) on internet platforms, multimodal sequential recommendation methods continue to emerge. Most existing methods incorporate item modal features as auxiliary information, typically concatenating them to learn unified user representations. However, these methods directly use modal features for representation learning, neglecting the impact of inherent modal noise. We argue that internal-modal noise and cross-modal noise hinder the acquisition of more accurate user representations. To address this problem, we propose SGP4SR - Separated-modality Guided user Preference learning for multimodal Sequential Recommendation. Globally, the user preference modeling is carried out from a separated-modality perspective to alleviate cross-modal noise. Locally, for each individual modality, we use item relationship graphs and user interest centers, aggregated with ID embeddings, to replace direct modal features, thereby mitigating internal-modal noise. Finally, user representations from both separated-modality and multimodal perspectives participate in prediction independently. In experiments conducted on four real-world datasets, our method outperforms state-of-the-art approaches, achieving an average performance improvement of up to 8.84% over the best baseline. The comprehensive experiments further validate the superior noise tolerance and robustness of our method.

Zitieren

APA

Li, C., Guo, Z., Li, G., Yang, Z., & Hong, C. (2026). SGP4SR: Separated-Modality Guided User Preference Learning for Multimodal Sequential Recommendation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(18), 15054-15062. https://doi.org/10.1609/aaai.v40i18.38528

Vancouver

Li C, Guo Z, Li G, Yang Z, Hong C. SGP4SR: Separated-Modality Guided User Preference Learning for Multimodal Sequential Recommendation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(18):15054-15062. doi:10.1609/aaai.v40i18.38528

BibTeX
@article{Li2026,
  author = {Li, Changhong and Guo, Zhiqiang and Li, Guohui and Yang, Zhong and Hong, Chuhang},
  title = {SGP4SR: Separated-Modality Guided User Preference Learning for Multimodal Sequential Recommendation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {18},
  pages = {15054--15062},
  doi = {10.1609/aaai.v40i18.38528}
}
Kostenlos starten →