Interpreting Temporal Knowledge Graph Reasoning (Student Abstract)

Temporal knowledge graph reasoning is an essential task that holds immense value in diverse real-world applications. Existing studies mainly focus on leveraging structural and sequential dependencies, excelling in tasks like entity and link prediction. However, they confront a notable interpretability gap in their predictions, a pivotal facet for comprehending model behavior. In this study, we propose an innovative method, LSGAT, which not only exhibits remarkable precision in entity predictions but also enhances interpretability by identifying pivotal historical events influencing event predictions. LSGAT enables concise explanations for prediction outcomes, offering valuable insights into the otherwise enigmatic "black box" reasoning process. Through an exploration of the implications of the most influential events, it facilitates a deeper understanding of the underlying mechanisms governing predictions.

Authors

• Bin Chen Harbin Institute of Technology, Shenzhen Research Center of Artificial Intelligence, Peng Cheng Laboratory
• Kai Yang School of Computer Science and Technology, Tongji University, China
• Wenxin Tai University of Electronic Science and Technology of China, Chengdu, Sichuan 610054, China Kash Institute of Electronics and Information Industry, Kashgar 844000, China
• Zhangtao Cheng University of Electronic Science and Technology of China
• Leyuan Liu University of Electronic Science and Technology of China
• Ting Zhong University of Electronic Science and Technology of China
• Fan Zhou University of Electronic Science and Technology of China

Keywords

• Applications Of AI
• Data Mining
• Knowledge Discovery
• Knowledge Representation