Rule mining over knowledge graphs via reinforcement learning

作者：

Highlights：

• We propose a reinforcement learning algorithm for rule generation.

• We propose an efficient rule mining algorithm guided by the trained RL agent.

• Our method achieves the state-of-the-art performance on serveral benchmark datasets.

摘要

•We propose a reinforcement learning algorithm for rule generation.•We propose an efficient rule mining algorithm guided by the trained RL agent.•Our method achieves the state-of-the-art performance on serveral benchmark datasets.

论文关键词：Rule mining,Reinforcement learning,Representation learning

论文评审过程：Received 5 September 2021, Revised 22 January 2022, Accepted 3 February 2022, Available online 10 February 2022, Version of Record 24 February 2022.

论文官网地址：https://doi.org/10.1016/j.knosys.2022.108371