Date:  16th January 2020 (Thursday)

 

Time:  10:00 am – 12:00 pm

 

Location: 3105 Lambton Tower

 

 

Link Prediction (LP) in social networks is referred to as predicting the likelihood of a link formation in social networks in the near future. There are several types of Social Networks that are available such as human interaction network, biological network, protein-to-protein interaction network, and so on. Earlier Link Prediction researches used heuristics methods, including Common Neighbors, Adamic Adar, Resource Allocation, and many other similarity score methods. Even though heuristics methods perform better in some types of social networks, their performance is limited in other types of social networks. Finding the best heuristics for a given type of social network is a trial and error process. Recent state-of-the-art research, WLNM and SEAL showed that with deep learning techniques and subgraphing, the heuristics selection could be automated and increase the accuracy of Link Prediction. However, WLNM and SEAL have some limitations and still having performance lack in some types of social networks. The objective of this paper is to introduce a novel framework that overcomes the limitations of state-of-the-art methods and improves the accuracy of link prediction over various types of social networks. We propose a link prediction framework called PLACN that analyzes common neighbors-based subgraphs using deep learning technique to predict links. PLACN is equipped with two new algorithms that are a subgraph extraction algorithm that efficiently extracts common neighbors of targeted nodes and a proposed new node labeling algorithm based on hop number and average path weight that creates consistent node orders over subgraphs. In addition to the algorithms, we derived a formula based on network properties to find an optimal number node for a given social network. PLACN converts the Link Prediction problem into an Image Classification problem and utilizes a Convolutional Neural Network to classify the links. We tested the proposed PLACN on seven different types of real-work networks and compared the performance against heuristics, latent methods, and state-of-the-art methods. Our results show that PLACN outperformed the compared Link Prediction methods while reaching above 96% AUC in tested benchmark social networks.

 

 

Internal Reader: Dr.  Jianguo Lu

 

External Reader: Dr.  Abdulkadir Hussein

 

Advisor: Dr.  Ziad Kobti

 

Chair: Dr. Pooya Moradian Zadeh