MCRPL: A Pretrain, Prompt & Fine-tune Paradigm for Non-overlapping Many-to-one Cross-domain Recommendation.
Hao LiuLei GuoLei ZhuYongqiang JiangMin GaoHongzhi YinPublished in: CoRR (2024)
Keyphrases
- cross domain
- fine tune
- fine tuning
- sentiment classification
- transfer learning
- knowledge transfer
- domain adaptation
- text categorization
- collaborative filtering
- multiple domains
- recommender systems
- cross domain learning
- target domain
- information retrieval
- feature extraction
- data sets
- labeled data
- e government
- support vector
- neural network
- real time