知识嵌入增强的对比推荐模型
|
|
谢涛,葛慧丽,陈宁,汪晓锋,李延松,黄晓峰
|
Knowledge embedding-enhanced contrastive recommendation model
|
|
Tao XIE,Huili GE,Ning CHEN,Xiaofeng WANG,Yansong LI,Xiaofeng HUANG
|
|
| 表 2 基于Recall@K指标的推荐算法性能比较 |
| Tab.2 Performance comparison of recommendation algorithms based on Recall@K metrics |
|
| 模型 | Recall@10 | | Recall@20 | | Recall@30 | | Yelp2018 | Amazon-Book | MIND | | Yelp2018 | Amazon-Book | MIND | | Yelp2018 | Amazon-Book | MIND | | KGAT[26] | 0.036 5 | 0.089 2 | 0.051 8 | | 0.067 5 | 0.139 0 | 0.090 7 | | 0.082 7 | 0.163 8 | 0.120 3 | | KGIN[27] | 0.043 5 | 0.106 2 | 0.065 2 | | 0.071 2 | 0.143 6 | 0.104 4 | | 0.094 9 | 0.177 4 | 0.134 3 | | CKAN[28] | 0.039 1 | 0.087 8 | 0.059 7 | | 0.068 9 | 0.138 0 | 0.099 1 | | 0.085 3 | 0.162 2 | 0.128 5 | | KGCL[32] | 0.045 5 | 0.098 9 | 0.067 6 | | 0.075 6 | 0.149 6 | 0.107 3 | | 0.099 9 | 0.179 5 | 0.135 9 | | MGDCF[29] | 0.041 2 | 0.104 6 | 0.067 1 | | 0.079 1 | 0.155 0 | 0.106 6 | | 0.102 9 | 0.181 3 | 0.136 9 | | 本研究方法 | 0.051 9 | 0.115 2 | 0.071 9 | | 0.085 8 | 0.169 1 | 0.115 1 | | 0.112 3 | 0.203 7 | 0.141 2 |
|
|
|