RecBole is a unified, comprehensive and efficient recommendation library. We have implemented more than 100 recommender system models, covering four common recommender system categories in RecBole and eight toolkits of RecBole2.0, including: General Recommendation, Sequential Recommendation, Context-aware Recommendation, Knowledge-based Recommendation and subpackages, which can support the basic research in recommender systems.
For each category, we selected some typical models to conduct a hyper-parameter search on multiple datasets. The following are our hyper-parameter search results and the configuration files of the corresponding datasets:
- Hyper-parameter Search Results
- General Recommendation
- Sequential Recommendation
- Context-aware Recommendation
- Knowledge-aware Recommendation
- Data information and configuration