Feature Based Link Prediction Model Using Deep Learning

3 Pages Posted: 7 Apr 2020

See all articles by Ankita Singh

Ankita Singh

University School of Information Communication & Technology,

Nanhay Singh

Aambedkar Institute of Advanced Communication Technologies and Research

Date Written: April 4, 2020

Abstract

Link Prediction in social network defines as the task to estimate the probability that a link exists between two nodes or not and it has been used widely in different areas. Many approaches have used machine learning to predict new links between two nodes and have focused on structural features of a network. In this paper we use have also used feature based model and proposed a Deep Learning model to identify a link. The DNN Classifier has been compared with traditional classifier and for performance evaluation two datasets, Karate club dataset and Dolphin dataset has been considered. The experimental result stipulates that the proposed Deep learning approach gives better performance regarding predicting a link when compared with other classifiers.

Suggested Citation

Singh, Ankita and Singh, Nanhay, Feature Based Link Prediction Model Using Deep Learning (April 4, 2020). Proceedings of the International Conference on Innovative Computing & Communications (ICICC) 2020, Available at SSRN: https://ssrn.com/abstract=3568410 or http://dx.doi.org/10.2139/ssrn.3568410

Ankita Singh (Contact Author)

University School of Information Communication & Technology, ( email )

India

Nanhay Singh

Aambedkar Institute of Advanced Communication Technologies and Research ( email )

India

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
105
Abstract Views
866
Rank
664,543
PlumX Metrics