Enhancing Recommendation Systems with Multi-Modal Transformers in Cross-Domain Scenarios

Authors
  • Ankai Liang

Keywords:
Array
Abstract

This study proposes a cross-domain recommendation algorithm based on the multi-modal Transformer. Combining cross-domain features and multi-modal data, it improves the recommendation quality of the recommendation system under complex user needs. Experimental results show that compared with traditional collaborative filtering, matrix decomposition and other models, the algorithm in this paper performs well in indicators such as NDCG and Recall. Ablation experiments further verified the contribution of cross-domain features and multi-modal data to model performance, showing significant improvements in the accuracy and diversity of the complete model. Specifically, cross-domain features help the model share user behavior information between different domains, and multi-modal data improves the personalization and coverage of recommendations through rich feature expressions. Research shows that the combination of cross-domain and multi-modality can enhance the robustness and adaptability of recommendation systems and provide richer user preference expressions for recommendation systems. Future research directions include exploring more efficient deep learning architecture to further improve the personalization and response speed of the recommendation system.

References
Cover Image
Downloads
Published
2024-10-30
Section
Articles
License
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Academic Scholar Hub Press also operates under the Creative Commons Licence CC-BY 4.0. This allows for copy and redistribute the material in any medium or format for any purpose, even commercially. The premise is that you must provide appropriate citation information.

How to Cite

Liang, A. (2024). Enhancing Recommendation Systems with Multi-Modal Transformers in Cross-Domain Scenarios. Journal of Computer Technology and Software, 3(7). https://doi.org/10.5281/zenodo.14172353

Similar Articles

1-10 of 196

You may also start an advanced similarity search for this article.

Most read articles by the same author(s)