首页|融入时间信息的预训练序列推荐方法

融入时间信息的预训练序列推荐方法

扫码查看
序列推荐旨在根据用户与项目的历史交互序列,学习用户动态偏好,为用户推荐后续可能感兴趣的项 目.基于预训练模型在适应下游任务方面具有优势,预训练机制在序列推荐中备受关注.现有序列推荐预训练方法忽略了现实中时间对用户交互行为的影响,为了更好地捕获用户与项 目交互的时间语义,提出了融入时间信息的预训练序列推荐模型TPTS-Rec(Time-aware Pre-Training method for Sequence Recommendation).首先,在嵌入层引入时间嵌入矩阵以获取用户交互项 目与时间的关联信息.然后,在自注意力层采用同一时间点采样的方法以学习项目间的时间关联信息.最后,在微调阶段从时间维度扩增用户交互序列长度以缓解数据稀疏性问题.在真实数据集上的对比实验结果表明,与基线模型相比,所提模型TPTS-Rec的推荐效果有显著提升.
Time-aware Pre-training Method for Sequence Recommendation
Sequence recommendation aims to learn users'dynamic preferences and recommend the next items which users may be interested in by analyzing historical interaction sequences between users and items.The pre-training model has attracted atten-tions from researchers in sequence recommendation due to its advantage of being adapted for downstream tasks.The existing pre-training methods for sequence recommendation ignore the impact of time on user interaction behaviors in real life.To better cap-ture the time semantics of interactions between users and items,this paper proposes a novel model TPTS-Rec(time-aware pre-training method for sequence recommendation).First,the time embedding matrix is introduced in the embedding layer to obtain the correlations between items and time in user interaction sequences.Then,the same time sampling method is presented in the self-attention layer to learn the time correlations between items.Finally,in the fine-tuning stage,user interaction sequences are amplified from the time dimension to alleviate the data sparsity.Experiment results on real datasets show that the proposed TPTS-Rec model outperforms the baseline models.

Sequence recommendationPre-trainingSelf-supervised learningMutual information maximizationTime attribute

陈稳中、陈红梅、周丽华、方圆

展开 >

云南大学信息学院 昆明 650500

云南大学云南省智能系统与计算重点实验室 昆明 650500

云南大学西南天文研究所 昆明 650500

序列推荐 预训练 自监督学习 互信息最大化 时间属性

国家自然科学基金国家自然科学基金云南省中青年学术和技术带头人后备人才项目云南省基础研究计划重点项目云南省智能系统与计算重点实验室开放基金

6226605062276227202205AC160033202201AS070015ISC22Z02

2024

计算机科学
重庆西南信息有限公司(原科技部西南信息中心)

计算机科学

CSTPCD北大核心
影响因子:0.944
ISSN:1002-137X
年,卷(期):2024.51(5)
  • 30