CORE

CORE is a plug-and-play conversational agent for any recommender system built upon PyTorch. CORE is

• Comprehensive: CORE provides data manager, offline trainer, and online checker.

• Flexible: CORE could be integrated into any recommender system.

• Efficient: CORE is built upon an online decision tree algorithm instead of heavily learning algorithms.

Documentation:

• Conversational Agent with Online-Checking Mode and Offline-Training Mode
• Data Manager to Manage Data Circuits for Bridging Online and Offline Modes
• Offline Trainer to Tune Recommendation Methods
• Online Checker to Query User Preference on Top-N Items or Attributes

Examples

• Example I: Deep Interest Network as Trainer

API Documentation

• Key APIs across CORE

Citing

If you find CORE useful, please cite it in your publications.

@software{CORE,
  author = {Jiarui Jin, Xianyu Chen, Fanghua Ye, Mengyue Yang, Yue Feng, Weinan Zhang, Yong Yu, and Jun Wang},
  title = {CORE: A Plug-and-Play Conversational Agent for Recommender System},
  year = {2023},
  publisher = {GitHub},
  journal = {GitHub repository},
  version = {0.0},
  howpublished = {\url{https://github.com/CORE-Labet/CORE}},
}