Graph neural networks (GNNs) have demonstrated significant promise in modelling relational data and have been widely applied in various fields of interest. The key mechanism behind GNNs is the so-called message passing where information is being iteratively aggregated to central nodes from their neighbourhood. Such a scheme has been found to be intrinsically linked to a physical process known as heat diffusion, where the propagation of GNNs naturally corresponds to the evolution of heat density. Analogizing the process of message passing to the heat dynamics allows to fundamentally understand the power and pitfalls of GNNs and consequently informs better model design. Recently, there emerges a plethora of works that proposes GNNs inspired from the continuous dynamics formulation, in an attempt to mitigate the known limitations of GNNs, such as oversmoothing and oversquashing. In this survey, we provide the first systematic and comprehensive review of studies that leverage the continuous perspective of GNNs. To this end, we introduce foundational ingredients for adapting continuous dynamics to GNNs, along with a general framework for the design of graph neural dynamics. We then review and categorize existing works based on their driven mechanisms and underlying dynamics. We also summarize how the limitations of classic GNNs can be addressed under the continuous framework. We conclude by identifying multiple open research directions.

图神经网络（GNNs）在建模关系型数据方面表现出显著的潜力，并被广泛应用于各个领域。图神经网络的关键机制是所谓的消息传递，其中信息从邻域迭代地聚合到中心节点。将消息传递过程类比为热扩散动力学可以从根本上理解GNNs的优势和局限，并进而指导模型设计。最近，出现了大量使用连续动态学的GNNs的作品，旨在解决GNNs已知的局限性，如过度平滑和过度压缩。在这项调查中，我们首次系统全面地审查了使用连续动态学视角的研究。为此，我们介绍了适应GNNs的连续动态学的基本要素，以及对图神经动力学设计的一般框架。然后，我们根据它们的驱动机制和基础动力学对现有作品进行了回顾和分类。我们还总结了如何在连续框架下解决经典GNNs的局限性。最后，我们确定了多个开放的研究方向。

从连续动力学到图神经网络：神经扩散与更多