论文标题
分层图胶囊网络
Hierarchical Graph Capsule Network
论文作者
论文摘要
图形神经网络（GNN）通过明确建模结构化数据的拓扑信息来汲取强度。但是，现有的GNN在捕获层次图表示中具有有限的能力，该表示在图形分类中起着重要作用。在本文中，我们创新提出了可以共同学习节点嵌入并提取图形层次结构的层次图胶囊网络（HGCN）。具体而言，通过识别每个节点基础的异质因素来确定脱离的图形胶囊，从而使它们的实例化参数代表同一实体的不同属性。为了学习层次表示形式，HGCN表征了下层胶囊（部分）和高级胶囊（整个）之间的零件关系关系，通过明确考虑零件之间的结构信息。实验研究证明了HGCN的有效性和每个组件的贡献。
Graph Neural Networks (GNNs) draw their strength from explicitly modeling the topological information of structured data. However, existing GNNs suffer from limited capability in capturing the hierarchical graph representation which plays an important role in graph classification. In this paper, we innovatively propose hierarchical graph capsule network (HGCN) that can jointly learn node embeddings and extract graph hierarchies. Specifically, disentangled graph capsules are established by identifying heterogeneous factors underlying each node, such that their instantiation parameters represent different properties of the same entity. To learn the hierarchical representation, HGCN characterizes the part-whole relationship between lower-level capsules (part) and higher-level capsules (whole) by explicitly considering the structure information among the parts. Experimental studies demonstrate the effectiveness of HGCN and the contribution of each component.
