Link Prediction in Social Networks Role of Power Law Distribution [Paperback]

Thiswork presents link prediction similarity measures for social networks that exploitthe degree distribution of the networks. In the context of link prediction indense networks, the text proposes similarity measures based on Markov inequalitydegree thresholding (MIDTs), which only consider nodes whose degree is above a thresholdfor a possible link. Also presented are similarity measures based on cliques(CNC, AAC, RAC), which assign extra weight between nodes sharing a greater numberof cliques. Additionally, a locally adaptive (LA) similarity measure isproposed that assigns different weights to common nodes based on the degreedistribution of the local neighborhood and the degree distribution of thenetwork. In the context of link prediction in dense networks, the textintroduces a novel two-phase framework that adds edges to the sparse graph toforma boost graph.

Introduction

Link Prediction Using Degree Thresholding

Locally Adaptive Link Prediction

Two Phase Framework for Link Prediction

Applications of Link Prediction

Dr. Virinchi Srinivas is a Graduate Research Assistant inthe Department of Computer Science at the University of Maryland, College Park,MD, USA.

Dr. Pabitra Mitra is an Associate Professor in the Departmentof Computer Science and Engineering at the Indian Institute of Technology,Kharagpur, India.

Presents anaccessible explanation of the role of power law degree distribution in linkprediction

Describes arange of link prediction algorithms in an easy-to-understand manner