Functional microcircuits are useful for studying interactions among neural dynamics of neighboring neurons during cognition and emotion. A functional microcircuit is a group of neurons that are spatially close, and that exhibit synchronized neural activities. For computational analysis, functional microcircuits are represented by graphs, which pose special challenges when applied as input to machine learning algorithms. Graph embedding, which involves the conversion of graph data into low dimensional vector spaces, is a general method for addressing these challenges. In this paper, we discuss limitations of conventional graph embedding methods that make them ill-suited to the study of functional microcircuits. We then develop a novel graph embedding framework, called Weighted Graph Embedding with Vertex Identity Awareness (WGEVIA), that overcomes these limitations. Additionally, we introduce a dataset, called the five vertices dataset, that helps in assessing how well graph embedding methods are suited to functional microcircuit analysis. We demonstrate the utility of WGEVIA through extensive experiments involving real and simulated microcircuit data.

中文翻译：

---

WGEVIA：微电路数据的图级嵌入方法


功能微电路对于研究认知和情感过程中相邻神经元的神经动力学之间的相互作用非常有用。功能性微电路是一组空间上靠近的神经元，并且表现出同步的神经活动。对于计算分析，功能微电路由图形表示，当用作机器学习算法的输入时，这会带来特殊的挑战。图嵌入涉及将图数据转换为低维向量空间，是解决这些挑战的通用方法。在本文中，我们讨论了传统图嵌入方法的局限性，这些局限性使其不适合功能微电路的研究。然后，我们开发了一种新颖的图嵌入框架，称为具有顶点身份感知的加权图嵌入（WGEVIA），它克服了这些限制。此外，我们引入了一个称为五顶点数据集的数据集，它有助于评估图嵌入方法是否适合功能微电路分析。我们通过涉及真实和模拟微电路数据的大量实验展示了 WGEVIA 的实用性。