• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Du, Yongping (Du, Yongping.) (学者:杜永萍) | Niu, Jinyu (Niu, Jinyu.) | Wang, Yuxin (Wang, Yuxin.) | Jin, Xingnan (Jin, Xingnan.)

收录:

EI Scopus SCIE

摘要:

Sequential models based on deep learning are widely used in sequential recommendation task, but the increase of model parameters results in a higher latency in the inference stage, which limits the real-time performance of the model. In order to make the model strike a balance between efficiency and effectiveness, the knowledge distillation technology is adopted to transfer the pre-trained knowledge from the large teacher model to the small student model. We propose a multi-stage knowledge distillation method based on interest knowledge, including interest representation knowledge and interest drift knowledge. In the process of knowledge transfer, expert distillation is designed to transform the knowledge dimension of student model to alleviate the loss of original knowledge information. Specially, curriculum learning is introduced for multistage knowledge learning, which further makes the teacher model effectively transfer the knowledge to the student model with limited ability. The proposed method on three real-world datasets including MovieLen-1M, Amazon Game and Steam datasets. The experimental results demonstrate that our method is superior to the other compared distillation method significantly and multi-stage learning makes the student model achieve the knowledge step by step for improvement.

关键词:

Model compression Interest drift Knowledge distillation Multi-stage learning Sequential recommendation

作者机构:

  • [ 1 ] [Du, Yongping]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 2 ] [Niu, Jinyu]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 3 ] [Wang, Yuxin]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 4 ] [Jin, Xingnan]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China

通讯作者信息:

  • [Du, Yongping]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China;;

查看成果更多字段

相关关键词:

相关文章:

来源 :

INFORMATION SCIENCES

ISSN: 0020-0255

年份: 2024

卷: 654

8 . 1 0 0

JCR@2022

被引次数:

WoS核心集被引频次:

SCOPUS被引频次: 6

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 1

归属院系:

在线人数/总访问数:431/4950366
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司