DeepLink: A novel link prediction framework based on deep learning

Abstract

Recently, link prediction has attracted more attentions from various disciplines such as computer science, bioinformatics and economics. In this problem, unknown links between nodes are discovered based on numerous information such as network topology, profile information and user generated contents. Most of the previous researchers have focused on the structural features of the networks. While the recent researches indicate that contextual information can change the network topology. Although, there are number of valuable researches which combine structural and content information, but they face with the scalability issue due to feature engineering. Because, majority of the extracted features are obtained by a supervised or semi supervised algorithm. Moreover, the existing features are not general enough to indicate good performance on different networks with heterogeneous structures. Besides, most of the previous researches are presented for undirected and unweighted networks.In this paper, a novel link prediction framework called "DeepLink" is presented based on deep learning techniques. In contrast to the previous researches which fail to automatically extract best features for the link prediction, deep learning reduces the manual feature engineering. In this framework, both the structural and content information of the nodes are employed. The framework can use different structural feature vectors, which are prepared by various link prediction methods. It considers all proximity orders that are presented in a network during the structural feature learning. We have evaluated the performance of DeepLink on two real social network datasets including Telegram and irBlogs. On both datasets, the proposed framework outperforms several structural and hybrid approaches for link prediction problem.

Application of an Improved Link Prediction Algorithm Based on Complex Network in Industrial Structure Adjustment

“…The path analysis of the similarity algorithm is divided into global path and local path. The global path considers the impact of the overall network on the path, and the local path considers only the influencing factors between nodes in the path [27][28][29][30]. At present, the local path index is often used for similarity measurement, as shown in Formula (3) [3].…”

Role-Aware Information Spread in Online Social Networks

“…Deep learning methods have achieved state-of-the-art results in several graph-based downstream tasks such as node classification [143][144][145] and link prediction [145,146] that were not used for user role identification. Most deep learning methods mainly use autoencoders and GCNs that generally consist of an encoder, a similarity function, and a decoder.…”

Link Prediction in Facebook using Web Scrapping and Deep Learning Techniques

“…In [1] link prediction is to find the missing link on a social network from the existing nodes and links. Link prediction is used for applications such as to find interactions between proteins, recommendation systems, security domain, co-authorship network.…”