A community structure that is often present in complex networks plays an important role not only in their formation but also shapes dynamics of these networks, affecting properties of their nodes. In this paper, we propose a family of community-aware node features and then investigate their properties. We show that they have high predictive power for classification tasks. We also verify that they contain information that cannot be recovered neither by classical node features nor by node embeddings (both classical as well as structural).

翻译：通常存在于复杂网络中的社区结构不仅在网络形成中起重要作用，还会塑造这些网络的动力学特性，进而影响其节点的属性。本文提出了一组社区感知的节点特征，并研究了它们的特性。我们证明这些特征在分类任务中具有较高的预测能力。同时验证了它们所包含的信息既无法通过经典节点特征恢复，也无法通过节点嵌入（包括经典嵌入和结构嵌入）恢复。