Datasets
Sequential Recommendation
AI Paradigm
Data Regeneration
Recommender Systems
Dataset Regeneration for Sequential Recommendation
| Key | Value |
|---|---|
| Authors | Mingjia Yin, Hao Wang, Wei Guo, Yong Liu, Suojuan Zhang, Sirui Zhao, Defu Lian, Enhong Chen |
| Published | 2024-05-28 |
| Link | Read more |
| Keywords | Datasets, Sequential Recommendation, AI Paradigm, Data Regeneration, Recommender Systems |
| Category | cs.IR |
The sequential recommender (SR) system is crucial for capturing evolving user preferences. DR4SR focuses on a data-centric paradigm, regenerating datasets with high generalizability and personalization for target models. The framework demonstrates significant performance improvements across widely used datasets. Read more
- Enhancing Recommender Systems: DR4SR enhances model-centric methods by improving dataset quality.
- Data Personalization: DR4SR+ incorporates a model-aware dataset personalizer for tailored datasets.
- Analysis Insights: Comprehensive analyses reveal the potential of the data-centric paradigm.
- Future Impact: DR4SR can advance various AI applications by optimizing training data.
Personalized AI news from scientific papers.