Knowledge Commons of Institute of Automation,CAS
GBERT: Pre-training User representations for Ephemeral Group Recommendation | |
Song Zhang![]() ![]() | |
2022-10 | |
会议名称 | Proceedings of the 31st ACM International Conference on Information and Knowledge Management (CIKM'22) |
页码 | 2631-2639 |
会议日期 | October 17–21, 2022 |
会议地点 | Atlanta, GA, USA |
摘要 | Due to the prevalence of group activities on social networks, group recommendations have received an increasing number of attentions. Most group recommendation methods concentrated on dealing with persistent groups, while little attention has paid to ephemeral groups. Ephemeral groups are formed ad-hoc for one-time activities, and therefore they suffer severely from data sparsity and cold-start problems. To deal with such problems, we propose a pre-training and fine-tuning method called GBERT for improved group recommendations, which employs BERT to enhance the expressivity and capture group-specific preferences of members. In the pre-training stage, GBERT employs three pre-training tasks to alleviate data sparsity and cold-start problem, and learn better user representations. In the fine-tuning stage, an influence-based regulation objective is designed to regulate user and group representations by allocating weights according to each member's influence. Extensive experiments on three public datasets demonstrate its superiority over the state-of-the-art methods for ephemeral group recommendations. |
收录类别 | EI |
七大方向——子方向分类 | 知识表示与推理 |
国重实验室规划方向分类 | 社会系统建模与计算 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/57067 |
专题 | 多模态人工智能系统全国重点实验室_互联网大数据与信息安全 |
作者单位 | Institute of Automation, Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Song Zhang,Nan Zheng,Danli Wang. GBERT: Pre-training User representations for Ephemeral Group Recommendation[C],2022:2631-2639. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
GBERT下载版.pdf(1281KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论