EUVIMEDEUVIMED entdecken
Crossref

MoToRec: Sparse-Regularized Multimodal Tokenization for Cold-Start Recommender

Jialin Liu, Zhaorui Zhang, Ray C.C. Cheung

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (18) · 15324-15332

DOI: 10.1609/aaai.v40i18.38558 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Jialin Liu und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Graph neural networks (GNNs) have revolutionized recommender systems by effectively modeling complex user-item interactions, yet data sparsity and the item cold-start problem significantly impair performance, particularly for new items with limited or no interaction history. While multimodal content offers a promising solution, existing methods result in suboptimal representations for new items due to noise and entanglement in sparse data. To address this, we transform multimodal recommendation into discrete semantic tokenization. We present Sparse-Regularized Multimodal Tokenization for Cold-Start Recommender Systems (MoToRec), a framework centered on a sparsely-regularized Residual Quantized Variational Autoencoder (RQ-VAE) that generates a compositional semantic code of discrete, interpretable tokens, promoting disentangled representations. MoToRec’s architecture is enhanced by three synergistic components: (1) a sparsely regularized RQ-VAE that promotes disentangled representations, (2) a novel adaptive rarity amplification that promotes prioritized learning for cold-start items, and (3) a hierarchical multi-source graph encoder for robust signal fusion with collaborative signals. Extensive experiments on three large-scale datasets demonstrate MoToRec’s superiority over state-of-the-art methods in both overall and cold-start scenarios. Our work validates that discrete tokenization provides an effective and scalable alternative for mitigating the long-standing cold-start challenge.

Zitieren

APA

Liu, J., Zhang, Z., & Cheung, R. C. (2026). MoToRec: Sparse-Regularized Multimodal Tokenization for Cold-Start Recommender. Proceedings of the AAAI Conference on Artificial Intelligence, 40(18), 15324-15332. https://doi.org/10.1609/aaai.v40i18.38558

Vancouver

Liu J, Zhang Z, Cheung RC. MoToRec: Sparse-Regularized Multimodal Tokenization for Cold-Start Recommender. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(18):15324-15332. doi:10.1609/aaai.v40i18.38558

BibTeX
@article{Liu2026,
  author = {Liu, Jialin and Zhang, Zhaorui and Cheung, Ray C.C.},
  title = {MoToRec: Sparse-Regularized Multimodal Tokenization for Cold-Start Recommender},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {18},
  pages = {15324--15332},
  doi = {10.1609/aaai.v40i18.38558}
}
Kostenlos starten →