Link prediction methods anticipate the likelihood of a future connection between two nodes
in a given network. The methods are essential in social networks to infer social interactions …

Abstract Graph Neural Networks (GNNs, in short) are a powerful computational tool to jointly
learn graph structure and node/edge features. They achieved an unprecedented accuracy in …

The evolutionary behavior of temporal networks has gained the attention of researchers with
its ubiquitous applications in a variety of real-world scenarios. Learning evolutionary …

Complex networks have a large number of nodes and edges, which prevents the
understanding of network structure and the discovery of valid information. This paper …

Time series has a wide range of applications in various fields. Recently, a new math tool,
named as visibility graph, is developed to transform the time series into complex networks …

Online social networks, World Wide Web, media, and technological networks, and other
types of so-called information networks are ubiquitous nowadays. These information …

The problem of link prediction has recently gained a lot of attention from various domains,
including sociology, anthropology, information science, and computer science. In this …

As most real-world networks evolve over time, link prediction over such dynamic networks
has become a challenging issue. Recent researches focus towards network embedding to …

Dynamic link prediction is an important component of the dynamic network analysis with
many real-world applications. Currently, most advancements focus on analyzing link-defined …

An important branch of a social network analysis is the identification of missing links and the
prediction of future connections in the networks. The problem, known as the link prediction …