An Automorphic Distance Metric and Its Application to Node Embedding for Role Mining
Metadatos
Mostrar el registro completo del ítemEditorial
Hindawi
Fecha
2021-10-13Referencia bibliográfica
Víctor Martínez, Fernando Berzal, Juan-Carlos Cubero, "An Automorphic Distance Metric and Its Application to Node Embedding for Role Mining", Complexity, vol. 2021, Article ID 5571006, 17 pages, 2021. [https://doi.org/10.1155/2021/5571006]
Patrocinador
Spanish Government TIN2012-36951; European Commission TIN2012-36951; program "Ayudas para contratos predoctorales para la formacion de doc 2013" BES-2013-064699; project "BIGDATAMED: Analisis de datos en Medicina, de las historias clinicas al BIGDATA" B-TIC-145-UGR18 P18RT-1765Resumen
Role is a fundamental concept in the analysis of the behavior and function of interacting entities in complex networks. Role
discovery is the task of uncovering the hidden roles of nodes within a network. Node roles are commonly defined in terms of
equivalence classes. Two nodes have the same role if they fall within the same equivalence class. Automorphic equivalence, where
two nodes are equivalent when they can swap their labels to form an isomorphic graph, captures this notion of role. )e binary
concept of equivalence is too restrictive, and nodes in real-world networks rarely belong to the same equivalence class. Instead, a
relaxed definition in terms of similarity or distance is commonly used to compute the degree to which two nodes are equivalent. In
this paper, we propose a novel distance metric called automorphic distance, which measures how far two nodes are from being
automorphically equivalent. We also study its application to node embedding, showing how our metric can be used to generate
role-preserving vector representations of nodes. Our experiments confirm that the proposed automorphic distance metric
outperforms a state-of-the-art automorphic equivalence-based metric and different state-of-the-art techniques for the generation
of node embeddings in different role-related tasks.