论文标题
图结构主题神经网络
Graph Structural-topic Neural Network
论文作者
论文摘要
图形卷积网络（GCN）通过有效收集节点的局部特征，取得了巨大的成功。但是，GCN通常更多地关注节点特征，而少于邻域内的图形结构，尤其是高阶结构模式。但是，这种局部结构模式被证明表明了许多领域的节点特性。此外，它不仅是单个模式，而且在所有这些模式上的分布都很重要，因为网络很复杂，每个节点的邻域由各种节点和结构模式的混合物组成。相应地，在本文中，我们提出了图形结构主题神经网络，缩写的Graphstone，这是一种使用图形主题模型的GCN模型，以便结构主题从概率方面广泛地捕获指示图形结构，而不是仅仅是概率的方面而不是一些结构。具体而言，我们使用匿名步行和图形锚式LDA在图形上构建主题模型，这是一种LDA变体，首先选择重要的结构模式，以减轻复杂性并有效地产生结构性主题。此外，我们设计了多视图GCN来统一节点特征和结构主题特征，并利用结构主题来指导聚合。我们通过定量和定性实验评估我们的模型，在该实验中，我们的模型表现出有希望的性能，高效率和清晰的解释性。
Graph Convolutional Networks (GCNs) achieved tremendous success by effectively gathering local features for nodes. However, commonly do GCNs focus more on node features but less on graph structures within the neighborhood, especially higher-order structural patterns. However, such local structural patterns are shown to be indicative of node properties in numerous fields. In addition, it is not just single patterns, but the distribution over all these patterns matter, because networks are complex and the neighborhood of each node consists of a mixture of various nodes and structural patterns. Correspondingly, in this paper, we propose Graph Structural-topic Neural Network, abbreviated GraphSTONE, a GCN model that utilizes topic models of graphs, such that the structural topics capture indicative graph structures broadly from a probabilistic aspect rather than merely a few structures. Specifically, we build topic models upon graphs using anonymous walks and Graph Anchor LDA, an LDA variant that selects significant structural patterns first, so as to alleviate the complexity and generate structural topics efficiently. In addition, we design multi-view GCNs to unify node features and structural topic features and utilize structural topics to guide the aggregation. We evaluate our model through both quantitative and qualitative experiments, where our model exhibits promising performance, high efficiency, and clear interpretability.
