论文标题
理论上表现力和边缘感知图学习
Theoretically Expressive and Edge-aware Graph Learning
论文作者
论文摘要
我们提出了一个新的图神经网络，结合了该领域的最新进展。我们通过证明该模型比图形同构网络和封闭式图神经网络更一般而提供理论贡献，因为它可以近似相同的功能并处理任意边缘值。然后，我们展示了单个节点信息如何通过图不变的图流动。
We propose a new Graph Neural Network that combines recent advancements in the field. We give theoretical contributions by proving that the model is strictly more general than the Graph Isomorphism Network and the Gated Graph Neural Network, as it can approximate the same functions and deal with arbitrary edge values. Then, we show how a single node information can flow through the graph unchanged.
