Link Prediction in Social Networks: Role of Power Law Distribution

by Srinivas Virinchi, Pabitra Mitra

This
work presents link prediction similarity measures for social networks that exploit
the degree distribution of the networks. In the context of link prediction in
dense networks, the text proposes similarity measures based on Markov inequality
degree thresholding (MIDTs), which only consider nodes whose degree is above a threshold
for a possible link. Also presented are similarity measures based on cliques
(CNC, AAC, RAC), which assign extra weight between nodes sharing a greater number
of cliques. Additionally, a locally adaptive (LA) similarity measure is
proposed that assigns different weights to common nodes based on the degree
distribution of the local neighborhood and the degree distribution of the
network. In the context of link prediction in dense networks, the text
introduces a novel two-phase framework that adds edges to the sparse graph to
forma boost graph.

123 pages, Kindle Edition

Published January 22, 2016