@inproceedings{yuanlai-etal-2024-ji,
    title = "基于交互行为语义模式增强的{ID}推荐方法(Enhanced {ID} Recommendation Method Utilizing Semantic Patterns of Interactive Behaviors)",
    author = "Yuanlai, Wang  and
      Yu, Bai  and
      Peng, Lian",
    editor = "Sun, Maosong  and
      Liang, Jiye  and
      Han, Xianpei  and
      Liu, Zhiyuan  and
      He, Yulan",
    booktitle = "Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)",
    month = jul,
    year = "2024",
    address = "Taiyuan, China",
    publisher = "Chinese Information Processing Society of China",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.ccl-1.45/",
    pages = "577--587",
    language = "zho",
    abstract = "``基于ID的推荐是一种依赖用户或物品的唯一标识符进行推荐的经典推荐方法,这种方法经常面临用户物品交互数据稀疏、符号ID缺失语义信息等问题。该文针对上述问题,假设不同领域的用户-物品交互行为之间存在潜在的模式关联,提出了一种基于交互行为语义模式增强的ID推荐方法。该方法在目标域推荐任务中引入辅助域信息,基于图神经网络对辅助域和目标域信息进行联合编码表示,通过引入交互行为语义模式,将辅助域的用户-物品交互信息以及物品描述信息迁移至目标域,从而实现目标域ID推荐中的交互行为语义增强。在8个公开数据集上的实验结果表明,相比目前的SOTA模型,本文方法表现出更好的推荐效果,其Recall@20与NDCG@20分别具有3{\%} {\ensuremath{\sim}} 30{\%}、1{\%} {\ensuremath{\sim}} 40{\%}的提升。''"
}