LengthPath: The Length Reward of Knowledge Graph Reasoning Based on Deep Reinforcement Learning

• Published in: 2024 International Joint Conference on Neural Networks (IJCNN) pp. 1 - 8
• Main Authors: Ling-Xiao, Xu, Lin, Feng, Zi-Hao, Li, Ling, Yue, Qiu-Ping, Shuai, Jie-Wei, Li
• Format: Conference Proceeding
• Language: English
• Published: IEEE 30.06.2024
• Subjects: Cognition; Deep reinforcement learning; Knowledge Graph Reasoning; Knowledge graphs; length reward; Neural networks; Reinforcement Learning; Semantics; Statistical analysis; Trajectory

Knowledge Graph (KG) always suffers from incompleteness. Knowledge Graph Reasoning (KGR) aims to predict the unknown entity or find reasoning paths for relations over incomplete KG. However, multi-hop reasoning still facing challenges, because the process of reasoning usually experiences the neighbo...