Abstract
This paper describes graph link level features. We describe three different kinds of them. We discuss distance-based characteristics that consumers might use, such as the shortest path between two nodes, which does not account for neighborhood overlaps. Then we discuss neighborhood overlap metrics like Common neighbors, Jaccard coefficient, and the Adamic-Adar index that measures how many neighbors a pair of nodes share in a fine-grained manner. The issue with this is that the metric will return a value of 0 for nodes that are more than two hops away or that do not have any neighbors. The global neighborhood overlap metrics, for instance, like Katz use the global graph structure to give us a score for a pair of nodes, and the Katz index counts the number of pets of all lands between a pair of nodes where these paths are discounted exponentially with their length.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: International Journal For Multidisciplinary Research
Disclaimer: 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.