EUVIMEDEUVIMED entdecken
Crossref

UNGER: Generative Recommendation with A Unified Code via Semantic and Collaborative Integration

Longtao Xiao, Haozhao Wang, Cheng Wang, Linfei Ji, Yifan Wang, Jieming Zhu, Zhenhua Dong, Rui Zhang, Ruixuan Li

ACM Transactions on Information Systems · 28.02.2026 · 44 (2) · 1-31

DOI: 10.1145/3773771 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Information Systems, online erschienen am 23.12.2025. Verfasst von Longtao Xiao und 8 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 76 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Major Science and Technology Project of Hubei.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the rise of generative paradigms, generative recommendation has garnered increasing attention. The core component is the item code , generally derived by quantizing collaborative or semantic representations to serve as candidate items identifiers in the context. However, existing methods typically construct separate codes for each modality, leading to higher computational and storage costs and hindering the integration of their complementary strengths. Considering this limitation, we seek to integrate two different modalities into a unified code , fully unleashing the potential of complementary nature among modalities. Nevertheless, the integration remains challenging: the integrated embedding obtained by the common concatenation method would lead to underutilization of collaborative knowledge, thereby resulting in limited effectiveness. To address this, we propose a novel method, named UNGER, which integrates semantic and collaborative knowledge into a UNified code for Generative Recommendation . Specifically, we propose to adaptively learn an integrated embedding through the joint optimization of cross-modality knowledge alignment and next-item prediction tasks. Subsequently, to mitigate the information loss caused by the quantization process, we introduce an intra-modality knowledge distillation task, using the integrated embeddings as supervised signals to compensate. Extensive experiments on three widely used benchmarks demonstrate the superiority of our approach compared to existing methods.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Major Science and Technology Project of Hubei
  • Hubei Science and Technology Talent Service Project
  • Ant Group through CCF-Ant Research Fund
  • HPC Platform of Huazhong University of Science and Technology

Zitieren

APA

Xiao, L., Wang, H., Wang, C., Ji, L., Wang, Y., Zhu, J., Dong, Z., Zhang, R., & Li, R. (2026). UNGER: Generative Recommendation with A Unified Code via Semantic and Collaborative Integration. ACM Transactions on Information Systems, 44(2), 1-31. https://doi.org/10.1145/3773771

Vancouver

Xiao L, Wang H, Wang C, Ji L, Wang Y, Zhu J, et al. UNGER: Generative Recommendation with A Unified Code via Semantic and Collaborative Integration. ACM Transactions on Information Systems. 2026;44(2):1-31. doi:10.1145/3773771

BibTeX
@article{Xiao2026,
  author = {Xiao, Longtao and Wang, Haozhao and Wang, Cheng and Ji, Linfei and Wang, Yifan and Zhu, Jieming and Dong, Zhenhua and Zhang, Rui and Li, Ruixuan},
  title = {UNGER: Generative Recommendation with A Unified Code via Semantic and Collaborative Integration},
  journal = {ACM Transactions on Information Systems},
  year = {2026},
  volume = {44},
  number = {2},
  pages = {1--31},
  doi = {10.1145/3773771}
}
Kostenlos starten →