Graph Neural Networks (GNNs) have been widely used to learn representations on graphs and tackle many real-world problems from a wide range of domains. In this paper we propose wsGAT, an extension of the Graph Attention Network (GAT) layers, meant to …
Networks measurement is essential to catch and quantify their features, behaviour and/or emerging phenomena. The goal of cohesiveness metric introduced here is to establish the level of cohesion among network nodes. It comes from the Black-Hole …
Combinatorial optimization problems arise in a wide range of applications from diverse domains. Many of these problems are NP-hard and designing efficient heuristics for them requires considerable time and experimentation. On the other hand, the …
Basics of PageRank algorithm have been widely adopted in its variations, tailored for specific scenarios. In this work, we consider the Black Hole metric, an extension of the original PageRank that leverages a (bogus) black hole node to reduce the …
Choosing an effective yet efficient solution to the link building problem means to select which nodes in a network should point a newcomer in order to increase its rank while limiting the cost of this operation (usually related to the number of such …
We propose a multi-stage learning approach for pruning the search space of maximum clique enumeration, a fundamental computationally difficult problem arising in various network analysis tasks. In each stage, our approach learns the characteristics …