Huang Yicong, Yu Zhuliang
College of Automation Science and Technology, South China University of Technology, Guangzhou 510641, China.
Entropy (Basel). 2022 Jan 19;24(2):152. doi: 10.3390/e24020152.
Latent variable models (LVMs) for neural population spikes have revealed informative low-dimensional dynamics about the neural data and have become powerful tools for analyzing and interpreting neural activity. However, these approaches are unable to determine the neurophysiological meaning of the inferred latent dynamics. On the other hand, emerging evidence suggests that dynamic functional connectivities (DFC) may be responsible for neural activity patterns underlying cognition or behavior. We are interested in studying how DFC are associated with the low-dimensional structure of neural activities. Most existing LVMs are based on a point process and fail to model evolving relationships. In this work, we introduce a dynamic graph as the latent variable and develop a Variational Dynamic Graph Latent Variable Model (VDGLVM), a representation learning model based on the variational information bottleneck framework. VDGLVM utilizes a graph generative model and a graph neural network to capture dynamic communication between nodes that one has no access to from the observed data. The proposed computational model provides guaranteed behavior-decoding performance and improves LVMs by associating the inferred latent dynamics with probable DFC.
用于神经群体尖峰的潜在变量模型（LVM）揭示了有关神经数据的信息丰富的低维动力学，并且已成为分析和解释神经活动的强大工具。然而，这些方法无法确定推断出的潜在动力学的神经生理学意义。另一方面，新出现的证据表明，动态功能连接性（DFC）可能是认知或行为背后的神经活动模式的原因。我们有兴趣研究DFC如何与神经活动的低维结构相关联。大多数现有的LVM基于点过程，无法对不断演变的关系进行建模。在这项工作中，我们引入动态图作为潜在变量，并开发了变分动态图潜在变量模型（VDGLVM），这是一种基于变分信息瓶颈框架的表示学习模型。VDGLVM利用图生成模型和图神经网络来捕捉节点之间的动态通信，而这些通信是无法从观测数据中获得的。所提出的计算模型提供了有保证的行为解码性能，并通过将推断出的潜在动力学与可能的DFC相关联来改进LVM。
