EUVIMEDEUVIMED entdecken
Crossref

Multimodal Pre-training for Sequential Recommendation via Contrastive Learning

Lingzi Zhang, Xin Zhou, Zhiwei Zeng, Zhiqi Shen

ACM Transactions on Recommender Systems · 31.03.2025 · 3 (1) · 1-23

DOI: 10.1145/3682075 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Recommender Systems, online erschienen am 25.10.2024. Verfasst von Lingzi Zhang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 32-mal zitiert (Crossref) und nennt 72 Literaturangaben. Gefördert von: Alibaba Group through Alibaba Innovative Research (AIR) Program, Alibaba-NTU Singapore Joint Research Institute, Nanyang Technological University, Singapore.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sequential recommendation systems often suffer from data sparsity, leading to suboptimal performance. While multimodal content, such as images and text, has been utilized to mitigate this issue, its integration within sequential recommendation frameworks remains challenging. Current multimodal sequential recommendation models are often unable to effectively explore and capture correlations among behavior sequences of users and items across different modalities, either neglecting correlations among sequence representations or inadequately capturing associations between multimodal data and sequence data in their representations. To address this problem, we explore multimodal pre-training in the context of sequential recommendation, with the aim of enhancing fusion and utilization of multimodal information. We propose a novel Multimodal Pre-training for Sequential Recommendation (MP4SR) framework, which utilizes contrastive losses to capture the correlation among different modality sequences of users, as well as the correlation among different modality sequences of users and items. MP4SR consists of three key components: (1) multimodal feature extraction; (2) a backbone network, Multimodal Mixup Sequence Encoder (M 2 SE); and (3) pre-training tasks. After utilizing pre-trained encoders to generate initial multimodal features of items, M 2 SE adopts a complementary sequence mixup strategy to fuse different modality sequences, and leverages contrastive learning to capture modality interactions at the sequence-to-sequence and sequence-to-item levels. Extensive experiments on four real-world datasets demonstrate that MP4SR outperforms state-of-the-art approaches in both normal and cold-start settings. We further highlight the efficacy of incorporating multimodal pre-training in sequential recommendation representation learning, serving as an effective regularizer and optimizing the parameter space for the recommendation task.

Förderung

  • Alibaba Group through Alibaba Innovative Research (AIR) Program
  • Alibaba-NTU Singapore Joint Research Institute
  • Nanyang Technological University, Singapore

Zitieren

APA

Zhang, L., Zhou, X., Zeng, Z., & Shen, Z. (2025). Multimodal Pre-training for Sequential Recommendation via Contrastive Learning. ACM Transactions on Recommender Systems, 3(1), 1-23. https://doi.org/10.1145/3682075

Vancouver

Zhang L, Zhou X, Zeng Z, Shen Z. Multimodal Pre-training for Sequential Recommendation via Contrastive Learning. ACM Transactions on Recommender Systems. 2025;3(1):1-23. doi:10.1145/3682075

BibTeX
@article{Zhang2025,
  author = {Zhang, Lingzi and Zhou, Xin and Zeng, Zhiwei and Shen, Zhiqi},
  title = {Multimodal Pre-training for Sequential Recommendation via Contrastive Learning},
  journal = {ACM Transactions on Recommender Systems},
  year = {2025},
  volume = {3},
  number = {1},
  pages = {1--23},
  doi = {10.1145/3682075}
}
Kostenlos starten →