Abstract
Unveiling the homophilic/heterophilic behaviors that characterize the wiring patterns of complex networks is an important task in social network analysis, often approached studying the assortative mixing of node attributes. Recent works have underlined that a global measure to quantify node homophily necessarily provides a partial, often deceiving, picture of the reality. Moving from such literature, in this work, we propose a novel measure, namely Conformity, designed to overcome such limitation by providing a node-centric quantification of assortative mixing patterns. Different from the measures proposed so far, Conformity is designed to be path-aware, thus allowing for a more detailed evaluation of the impact that nodes at different degrees of separations have on the homophilic embeddedness of a target. Experimental analysis on synthetic and real data allowed us to observe that Conformity can unveil valuable insights from node-attributed graphs.
Highlights
During the last decades, network science has become one of the fastest growing multidisciplinary research fields
Such a measure aims to classify a whole network in a range that goes among two extremes: disassortative mixing, where nodes are likely to be connected if they are anticorrelated w.r.t. a given property, and assortative mixing, where, nodes are likely to be connected if they share a given property
This work introduced Conformity, a novel strategy to measure the homophilic mixing of network nodes w.r.t. their categorical attributes
Summary
SPECIAL ISSUE ON LEARNING COMPLEX COUPLINGS AND INTERACTIONS trying to measure its impact and propose a mechanistic explanation to its existence. Some recent extensions or alternative approaches, like ProNe11 or the VA-Index,[12] are able to cope with pairs of attributes or vector of features, shedding light, more than Newman’s coefficient, on the phenomenon of similarity between two or more attributes based on network structure Such global and aggregated measures flatten and simplify a heterogeneous context in one only score, and avoid the presence of outliers or different mixing interactions characterizing different zones of networks and perhaps single nodes. We aim to design a local proxy to measure the degree of homophilic embeddedness of network nodes w.r.t. the attributes they carry Such a task has been recently approached by Peel et al.[5] to overcome the limitation of classical approaches that usually propose a single aggregate score to characterize the overall assortativity of network nodes. The data paper that discusses the origin of the Karate Club network dataset[20] help us in providing a neat justification for such Conformity value: node 8 identifies a weak supporter of “Mr Hi,” who joined with the “John A.”’s faction, after the split, for personal advantage, so he represents a bridge between the two opposite sides of the Karate Club dispute
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
