Please wait a minute...
购物车 申请加入邮件组 English
高级检索 图表检索
Frontiers of Computer Science

ISSN 2095-2228

ISSN 2095-2236(Online)

CN 10-1014/TP

邮发代号 80-970

2019 Impact Factor: 1.275

热点文章  |  下载排行  |  浏览排行
在线投稿 免费RSS订阅
Frontiers of Computer Science  2025, Vol. 19 Issue (4): 194328   https://doi.org/10.1007/s11704-024-40039-z
  本期目录
Large language models make sample-efficient recommender systems
Jianghao LIN1, Xinyi DAI2, Rong SHAN1, Bo CHEN2, Ruiming TANG2, Yong YU1, Weinan ZHANG1()
1. Computer Science and Technology, Shanghai Jiao Tong University, Shanghai 200240, China
2. Huawei Noah’s Ark Lab, Shenzhen 518129, China
 全文: PDF(245 KB)   HTML
收稿日期: 2024-01-09      出版日期: 2024-09-20
Corresponding Author(s): Weinan ZHANG   
 引用本文:   
. [J]. Frontiers of Computer Science, 2025, 19(4): 194328.
Jianghao LIN, Xinyi DAI, Rong SHAN, Bo CHEN, Ruiming TANG, Yong YU, Weinan ZHANG. Large language models make sample-efficient recommender systems. Front. Comput. Sci., 2025, 19(4): 194328.
 链接本文:  
https://academic.hep.com.cn/fcs/CN/10.1007/s11704-024-40039-z
https://academic.hep.com.cn/fcs/CN/Y2025/V19/I4/194328
Fig.1  
ModelBookCrossingMovieLens-1M
AUC ↑Log Loss ↓Rel.ImprAUC ↑Log Loss ↓Rel.Impr
DeepFM0.74960.59531.05%0.79150.54841.49%
AutoInt0.74810.68401.26%0.79290.54531.31%
DCNv20.74720.68161.38%0.79310.54641.29%
GRU4Rec0.74790.59301.28%0.79260.54531.35%
Caser0.74780.59901.30%0.79180.54641.45%
SASRec0.74820.59341.24%0.79340.54601.25%
DIN0.74770.68111.31%0.79620.54250.89%
SIM0.75410.58930.45%0.79920.53870.51%
CTR-BERT0.74480.59381.71%0.79310.54571.29%
PTab0.74290.61541.97%0.79550.54280.98%
P50.74380.61281.84%0.79370.54781.21%
LaserLLM only0.7575*0.5919?0.8033*0.5362*?
LaserLLM+CRM0.75080.5848*?0.79960.5375?
Tab.1  
DatasetDCNv2SIMPTabLaserLLM onlyLaserLLM+CRM
BookCrossing2.34×10?42.45×10?45.23×10?37.89×10?12.77×10?4
MovieLens-1M1.65×10?42.07×10?43.95×10?37.42×10?12.34×10?4
Tab.2  
MetricSIMMistral-7BVicuna-7BVicuna-13B
LLM onlyLLM+CRMLLM onlyLLM+CRMLLM onlyLLM+CRM
AUC0.79920.80050.79900.80160.79970.80330.7996
LogLoss0.53870.53880.53850.53650.53720.53620.5375
Tab.3  
1 J, Zhang K, Bao Y, Zhang W, Wang F, Feng X He . Large language models for recommendation: progresses and future directions. In: Proceedings of the ACM on Web Conference 2024. 2024, 1268−1271
2 X, Pan L, Wu F, Long A Ma . Exploiting user behavior learning for personalized trajectory recommendations. Frontiers of Computer Science, 2022, 16( 3): 163610
3 MindSpore, 2020
[1] Highlights Download
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed