标题： 基于温度的图神经网络几何深度学习分析 显示英文标题

标题： Geometric Deep Learning: a Temperature Based Analysis of Graph Neural Networks

摘要： 我们考察一个几何深度学习模型作为热力学系统，将权重视为非量子和非相对论的粒子。 我们采用[7]中先前定义的温度概念，并研究其在GCN和GAT模型的各个层中的情况。 讨论了我们发现的潜在未来应用。 显示英文摘要

摘要： We examine a Geometric Deep Learning model as a thermodynamic system treating the weights as non-quantum and non-relativistic particles. We employ the notion of temperature previously defined in [7] and study it in the various layers for GCN and GAT models. Potential future applications of our findings are discussed.