This review analyzes community search strategies and evaluation metrics in heterogeneous information networks, indicating their potential applications in fraud detection and team formation.
Heterogeneous information networks (HINs) comprise vertices and edges with different types, representing different objects and links, so as to abstract and model the real world more completely and naturally. Rich structural and semantic information contained in HINs provides new opportunities and challenges to discover hidden patterns in HINs. Community Search (CS) over HINs, aiming to find a subgraph that satisfies the given conditions, provides important support for various applications such as team formation, personalized recommendation, fraud detection, group identification, etc., and many CS approaches have been proposed recently. This study introduces types of HINs, CS constraints, search strategies, proposes a novel taxonomy of CS over HINs, and reviews the CS models as well as solutions over different HINs. It then analyzes and compares the characteristics of different models and solutions, and summarizes evaluation metrics generally used in literature. This survey aims to provide valuable insights on the latest progress of CS over HINs, facilitating researchers conduct in-depth research in this field.
No takes yet. Share an insight, caveat, or question.
Zhou et al. (2025) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: