论文标题
图，实体和阶梯混合物
Graphs, Entities, and Step Mixture
论文作者
论文摘要
现有的图形神经网络的方法通常会遭受过度厚度的问题，而不管社区如何聚集。大多数方法还侧重于固定图的跨传输场景，从而导致看不见的图的概括不良。为了解决这些问题，我们提出了一个新的图神经网络，该网络既考虑基于边缘的邻域关系和基于节点的实体特征，即通过随机步行（GESM）带有台阶混合物的图形实体。 GESM通过随机步行采用各种步骤的混合物来减轻过度厚度的问题，注意根据节点信息动态反映相互关系，并基于结构的正则化来增强嵌入表示表示。通过密集的实验，我们表明所提出的GESM在八个基准图数据集上实现了最先进的或可比的性能，其中包括跨性和归纳性学习任务。此外，我们从经验上证明了考虑全球信息的重要性。
Existing approaches for graph neural networks commonly suffer from the oversmoothing issue, regardless of how neighborhoods are aggregated. Most methods also focus on transductive scenarios for fixed graphs, leading to poor generalization for unseen graphs. To address these issues, we propose a new graph neural network that considers both edge-based neighborhood relationships and node-based entity features, i.e. Graph Entities with Step Mixture via random walk (GESM). GESM employs a mixture of various steps through random walk to alleviate the oversmoothing problem, attention to dynamically reflect interrelations depending on node information, and structure-based regularization to enhance embedding representation. With intensive experiments, we show that the proposed GESM achieves state-of-the-art or comparable performances on eight benchmark graph datasets comprising transductive and inductive learning tasks. Furthermore, we empirically demonstrate the significance of considering global information.
