A user behavior-aware multi-task learning model for enhanced short video recommendation

被引:0
|
作者
Wu, Yuewei [1 ]
Fu, Ruiling [1 ]
Xing, Tongtong [1 ]
Yu, Zhenyu [1 ]
Yin, Fulian [1 ,2 ]
机构
[1] School of Information and Communication Engineering, Communication University of China, Beijing,100024, China
[2] State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing,100024, China
关键词
Adversarial machine learning;
D O I
10.1016/j.neucom.2024.129076
中图分类号
学科分类号
摘要
In the rapidly evolving landscape of digital media consumption, accurately predicting user preferences and behaviors is critical for the effectiveness of recommendation systems, especially for short video content. Traditional recommendation methods often ignore the association between multiple user behavior types and struggle with dynamically adapting to user behavior changes, leading to suboptimal personalization and user engagement. To address these issues, this paper introduces a user behavior-aware multi-task learning model for enhanced short video recommendation (UBA-SVR) by leveraging insights into dynamic user interactions. In our approach, we construct a user behavior-aware transformer to comprehensively capture users’ dynamic interests and generate the fusion feature representation. Subsequently, we introduce a hierarchical knowledge extraction framework to process features in multi-stage and adopt a task-aware attention mechanism within the tower network structure to facilitate effective information sharing and differentiation among tasks. Furthermore, we employ a dynamic joint loss optimization strategy to adaptively adjust the loss weights for different tasks to promote collaborative enhancement. Extensive experiments on two real-world datasets demonstrate that the proposed method achieves significant improvements in multiple prediction tasks simultaneously. © 2024 Elsevier B.V.
引用
收藏
相关论文
共 50 条
  • [1] BVAE: Behavior-aware Variational Autoencoder for Multi-Behavior Multi-Task Recommendation
    Rao, Qianzhen
    Liu, Yang
    Pan, Weike
    Zhong, Ming
    [J]. PROCEEDINGS OF THE 17TH ACM CONFERENCE ON RECOMMENDER SYSTEMS, RECSYS 2023, 2023, : 625 - 636
  • [2] A Behavior-Aware Graph Convolution Network Model for Video Recommendation
    Zhuo, Wei
    Liu, Kunchi
    Xue, Taofeng
    Jin, Beihong
    Li, Beibei
    Dong, Xinzhou
    Chen, He
    Pan, Wenhai
    Zhang, Xuejian
    Zhou, Shuo
    [J]. WEB AND BIG DATA, APWEB-WAIM 2021, PT II, 2021, 12859 : 279 - 294
  • [3] UBAR: User Behavior-Aware Recommendation with knowledge graph
    Wu, Xing
    Li, Yisong
    Wang, Jianjia
    Qian, Quan
    Guo, Yike
    [J]. KNOWLEDGE-BASED SYSTEMS, 2022, 254
  • [4] Multi-task feature and structure learning for user-preference based knowledge-aware recommendation
    Shu, Hang
    Huang, Jun
    [J]. NEUROCOMPUTING, 2023, 532 : 43 - 55
  • [5] Attribute-aware multi-task recommendation
    Wang, Suhua
    Zhang, Lisa
    Yu, Mengying
    Wang, Yuling
    Ma, Zhiqiang
    Zhao, Yu
    [J]. JOURNAL OF SUPERCOMPUTING, 2021, 77 (05): : 4419 - 4437
  • [6] Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation
    Wang, Hongwei
    Zhang, Fuzheng
    Zhao, Miao
    Li, Wenjie
    Xie, Xing
    Guo, Minyi
    [J]. WEB CONFERENCE 2019: PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE (WWW 2019), 2019, : 2000 - 2010
  • [7] Knowledge-Enhanced Multi-task Learning for Course Recommendation
    Ban, Qimin
    Wu, Wen
    Hu, Wenxin
    Lin, Hui
    Zheng, Wei
    He, Liang
    [J]. DATABASE SYSTEMS FOR ADVANCED APPLICATIONS, DASFAA 2022, PT II, 2022, : 85 - 101
  • [8] Attribute-aware multi-task recommendation
    Suhua Wang
    Lisa Zhang
    Mengying Yu
    Yuling Wang
    Zhiqiang Ma
    Yu Zhao
    [J]. The Journal of Supercomputing, 2021, 77 : 4419 - 4437
  • [9] Expressive user embedding from churn and recommendation multi-task learning
    Bai, Huajun
    Liu, Davide
    Hirtz, Thomas
    Boulenger, Alexandre
    [J]. COMPANION OF THE WORLD WIDE WEB CONFERENCE, WWW 2023, 2023, : 37 - 40
  • [10] Personalized Behavior-Aware Transformer for Multi-Behavior Sequential Recommendation
    Su, Jiajie
    Chen, Chaochao
    Lin, Zibin
    Li, Xi
    Liu, Weiming
    Zheng, Xiaolin
    [J]. PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2023, 2023, : 6321 - 6331