Publications

Latent Geometry-Driven Network Automata for Complex Network Dismantling

Complex networks model the structure and function of critical technological, biological, and communication systems. Network …
DOI URL

Saliency Matters: From Nodes to Objects

Due to their intrinsic capabilities in capturing, modeling, and representing relationships between pieces of information, graphs have …

Machine Learning Supernovae’s Progenitor Characterization

In this work, we present a Deep Learning framework to predict the progenitor star’s characteristics of Supernovae (SNe) from their …
DOI URL

Edge Dismantling with Geometric Reinforcement Learning

The robustness of networks plays a crucial role in various applications. Network dismantling, the process of strategically removing …
DOI URL

Robustness and resilience of complex networks

Complex networks are ubiquitous: a cell, the human brain, a group of people and the Internet are all examples of interconnected …
PDF Code Dataset DOI URL

Learning fine-grained search space pruning and heuristics for combinatorial optimization

Combinatorial optimization problems arise naturally in a wide range of applications from diverse domains. Many of these problems are …
DOI URL

CoreGDM: 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 …
DOI URL

Geometric 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 …
DOI URL

Network Topology to Predict Bibliometrics Indices: A Case Study

Link Prediction in Time Varying Social Networks

Insights into countries’ exposure and vulnerability to food trade shocks from network-based simulations

In the context of a global food system, the dynamics associated to international food trade have become key determinants of food …
PDF DOI
Insights into countries’ exposure and vulnerability to food trade shocks from network-based simulations

Efficient Node PageRank Improvement via Link Building using Geometric Deep Learning

Centrality is a relevant topic in the field of network research, due to its various theoretical and practical implications. In general, …
PDF DOI

Correlation between researchers’ centrality and h-index: a case study

Analysis of the co-authorship sub-networks of Italian academic researchers

(Unintended) Consequences of export restrictions on medical goods during the Covid-19 pandemic

The outbreak of the Covid-19 pandemic led several governments to impose restrictions on the export of medical supplies. Despite being …
DOI URL
(Unintended) Consequences of export restrictions on medical goods during the Covid-19 pandemic

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 …
PDF Code Dataset DOI
Machine learning dismantling and early-warning signals of disintegration in complex systems

wsGAT: 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 …
Code DOI URL arXiv

Relations Between Entropy and Accuracy Trends in Complex Artificial Neural Networks

mGNN: 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 …
PDF Code

Food Recommendation in a Worksite Canteen.

Analysis of the Co-authorship Sub-networks of Italian Academic Researchers

A Network-Based Analysis of a Worksite Canteen Dataset

Group Cohesion Assessment in Networks

Networks measurement is essential to catch and quantify their features, behaviour and/or emerging phenomena. The goal of cohesiveness …
DOI

Learning fine-grained search space pruning and heuristics for combinatorial optimization

Combinatorial optimization problems arise in a wide range of applications from diverse domains. Many of these problems are NP-hard and …
arXiv

Strategies comparison in link building problem

A network-based analysis to understand food-habits of a multi-company canteen's customers

A PageRank Inspired Approach to Measure Network Cohesiveness

Basics of PageRank algorithm have been widely adopted in its variations, tailored for specific scenarios. In this work, we consider the …
DOI

Strategies Comparison in Link Building Problem

Choosing an effective yet efficient solution to the link building problem means to select which nodes in a network should point a …
DOI

Network robustness improvement via long-range links

Many systems are today modelled as complex networks, since this representation has been proven being an effective approach for …
DOI

Long distance connections for ranking and robustness enhancement in networks

Learning Multi-Stage Sparsification for Maximum Clique Enumeration

We propose a multi-stage learning approach for pruning the search space of maximum clique enumeration, a fundamental computationally …
arXiv

Long Distance In-Links for Ranking Enhancement

Ranking is a widely used technique to classify nodes in networks according to their relevance. Increasing one’s rank is a desiderable …
DOI

Exploiting Long Distance Connections to Strengthen Network Robustness

Network fault tolerance (also known as resilience or robustness) is becoming a highly relevant topic, expecially in real networks, …
DOI

Climbing Ranking Position via Long-Distance Backlinks

The best attachment consists in finding a good strategy that allows a node inside a network to achieve a high rank. This is an open …
DOI