owenonline / Knowledge-Graph-Reasoning-with-Self-supervised-Reinforcement-LearningLinks

Reinforcement learning (RL) is an effective method to find reasoning pathways in incomplete knowledge graphs (KGs). To overcome the challenges of sparse rewards and the explore-exploit dilemma, a self-supervised pretraining method is proposed to warm up the policy network before the RL training stage. The seeding paths used in the supervised pre…
19Updated 10 months ago

Alternatives and similar repositories for Knowledge-Graph-Reasoning-with-Self-supervised-Reinforcement-Learning

Users that are interested in Knowledge-Graph-Reasoning-with-Self-supervised-Reinforcement-Learning are comparing it to the libraries listed below

Sorting: