Modeling High-Order Interactions Across Multi-Interests for Micro-Video Reommendation (Student Abstract)

Dong Yao, Shengyu Zhang, Zhou Zhao, Wenyan Fan, Jieming Zhu, Xiuqiang He, Fei Wu

AAAI 2021 pp. 15945-15946

doi:10.1609/AAAI.V35I18.17969 /aaai/2021/yao2021aaai-modeling/

Abstract

Personalized recommendation system has become pervasive in various video platform.Many effective methods have been proposed, but most of them didn’t capture the user’s multilevel interest trait and dependencies between their viewed micro-videos well. To solve these problems, we propose a Self-over-Co Attention module to enhance user’s interest representation. In particular, we ﬁrst use co-attention to model correlation patterns across different levels and then use self attention to modelcorrelation patterns within a speciﬁc level. Experimental results on ﬁltered public datasets verify that our presented module is useful.

PDF AAAI Semantic Scholar

Cite

Text

Yao et al. "Modeling High-Order Interactions Across Multi-Interests for Micro-Video Reommendation (Student Abstract)." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I18.17969

Markdown

[Yao et al. "Modeling High-Order Interactions Across Multi-Interests for Micro-Video Reommendation (Student Abstract)." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/yao2021aaai-modeling/) doi:10.1609/AAAI.V35I18.17969

BibTeX

@inproceedings{yao2021aaai-modeling,
  title     = {{Modeling High-Order Interactions Across Multi-Interests for Micro-Video Reommendation (Student Abstract)}},
  author    = {Yao, Dong and Zhang, Shengyu and Zhao, Zhou and Fan, Wenyan and Zhu, Jieming and He, Xiuqiang and Wu, Fei},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2021},
  pages     = {15945-15946},
  doi       = {10.1609/AAAI.V35I18.17969},
  url       = {https://mlanthology.org/aaai/2021/yao2021aaai-modeling/}
}