用图距离定义意外度，让知识图谱推理更符合大脑原理。
Graph Distance as Surprise: Free Energy Minimization in Knowledge Graph Reasoning
- 用最短路径距离衡量实体间的意外程度
- 将神经科学中的自由能原理引入知识图谱推理
- 适合对认知模型和图神经网络感兴趣的读者
本文提出，知识图谱（KG）中的推理可由意外度最小化引导。图中距离越近的实体，其意外度越低。该思想将神经科学中的自由能原理（FEP）与知识图谱系统相连接，其中知识图谱作为智能体的生成模型。我们通过有向图的最短路径距离形式化意外度，并构建基于知识图谱的智能体框架。图距离在图神经网络中体现为消息传递深度，在基于模型的强化学习中则表现为世界模型的轨迹。本研究探索距离带来的意外度是否可拓展至近期发现的语法通过树结构最小化意外度与自由能的工作。
原文摘要 · Abstract (English)
In this work, we propose that reasoning in knowledge graph (KG) networks can be guided by surprise minimization. Entities that are close in graph distance will have lower surprise than those farther apart. This connects the Free Energy Principle (FEP) from neuroscience to KG systems, where the KG serves as the agent's generative model. We formalize surprise using the shortest-path distance in directed graphs and provide a framework for KG-based agents. Graph distance appears in graph neural networks as message passing depth and in model-based reinforcement learning as world model trajectories. This work-in-progress study explores whether distance-based surprise can extend recent work showing that syntax minimizes surprise and free energy via tree structures.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。