Motif-aware Sequential Recommendation
文献类型:会议论文
作者 | Cui Zeyu1,2; Cai Yinjiang1,2; Wu Shu1,2; Ma Xibo1,2; Wang Liang1,2 |
出版日期 | 2021-07-11 |
会议日期 | 2021-7-11 |
会议地点 | Virtual Event, Canada |
关键词 | Sequential recommendation Graph structure Motif |
DOI | 10.1145/3404835.3463115 |
英文摘要 | Sequential recommendation is intended to model the dynamic behavior regularity through users' behavior sequences. Recently, various deep learning techniques are applied to model the relation of items in the sequences. Despite their effectiveness, we argue that the aforementioned methods only consider the macro-structure of the behavior sequence, but neglect the micro-structure in the sequence which is important to sequential recommendation. To address the above limitation, we propose a novel model called Motif-aware Sequential Recommendation (MoSeR), which captures the motifs hidden in behavior sequences to model the micro-structure features. MoSeR extracts the motifs that contain both the last behavior and the target item. These motifs reflect the topological relations among local items in the form of directed graphs. Thus our method can make a more accurate prediction with the awareness of the inherent patterns between local items. Extensive experiments on three benchmark datasets demonstrate that our model outperforms the state-of-the-art sequential recommendation models. |
会议录 | Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval |
语种 | 英语 |
源URL | [http://ir.ia.ac.cn/handle/173211/44807] |
专题 | 自动化研究所_智能感知与计算研究中心 |
通讯作者 | Wu Shu |
作者单位 | 1.University of Chinese Academy of Sciences 2.Chinese Acdemy of Science, Institute of Automation |
推荐引用方式 GB/T 7714 | Cui Zeyu,Cai Yinjiang,Wu Shu,et al. Motif-aware Sequential Recommendation[C]. 见:. Virtual Event, Canada. 2021-7-11. |
入库方式: OAI收割
来源:自动化研究所
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。