Geometric Deep Learning Network Dismantling
A focused seminar on Geometric Deep Learning applied to Network Dismantling
Marco Grassia
•
•
1 min readEdge Dismantling with Geometric Reinforcement Learning
The robustness of networks plays a crucial role in various applications. Network dismantling, the process of strategically removing nodes or edges to maximize damage, is a known …
Conference
Marco Grassia, Giuseppe Mangioni
•
•
1 min readGeometric deep learning sub-network extraction for maximum clique enumeration
In this paper we propose a method based on geometric deep learning to reduce the computational complexity of the Maximum Clique Enumeration (MCE) problem. Specifically, given a …
Journal
Vincenza Carchiolo, Marco Grassia, Michele Malgeri, Giuseppe Mangioni
•
•
1 min readCoreGDM: Geometric Deep Learning Network Decycling and Dismantling
Network dismantling deals with the removal of nodes or edges to disrupt the largest connected component of a network. In this work we introduce CoreGDM, a trainable algorithm for …
Conference
Marco Grassia, Giuseppe Mangioni
•
•
1 min readGeometric Deep Learning Graph Pruning to Speed-Up the Run-Time of Maximum Clique Enumerarion Algorithms
In this paper we propose a method to reduce the running time to solve the Maximum Clique Enumeration (MCE) problem. Specifically, given a network we employ geometric deep learning …
Conference
Andrea Arciprete, Vincenza Carchiolo, Daniela Chiavetta, Marco Grassia et al.
•
•
1 min readWarm-up: Network analysis with Python
From data to network analysis with Python
Marco Grassia
•
•
17 min read
Machine learning dismantling and early-warning signals of disintegration in complex systems
From physics to engineering, biology and social science, natural and artificial systems are characterized by interconnected topologies whose features – e.g., heterogeneous …
Journal
Marco Grassia, Manlio De Domenico, Giuseppe Mangioni
•
•
1 min readwsGAT: Weighted and Signed Graph Attention Networks for Link Prediction
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 …
Conference
Marco Grassia, Giuseppe Mangioni
•
•
1 min readmGNN: Generalizing the Graph Neural Networks to the Multilayer Case
Networks are a powerful tool to model complex systems, and the definition of many Graph Neural Networks (GNN), Deep Learning algorithms that can handle networks, has opened a new …
Journal
Marco Grassia, Manlio De Domenico, Giuseppe Mangioni
•
•
1 min read