Predicting Properties of Nodes via Community-Aware Features

arXiv:2311.04730v2 Announce Type: replace-cross
Abstract: This paper shows how information about the network's community structure can be used to define node features with high predictive power for classification tasks. To do so, we define a family of community-aware node features and investigate their properties. Those features are designed to ensure that they can be efficiently computed even for large graphs. We show that community-aware node features contain information that cannot be completely recovered by classical node features or node embeddings …

abstract arxiv classification community cs.lg cs.si family features information math.co network node nodes paper power predictive shows tasks type via