Machine Learning

Edge 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 NP-hard problem. While heuristics for node removal exist, edge network …

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 NP-hard and designing efficient heuristics for them requires considerable time, effort and experimentation. On the …

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 introduce CoreGDM, a trainable algorithm for network dismantling via node-removal. The approach is based on …

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 a network we employ geometric deep learning in order to find a simpler network on which running the algorithm to …

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 connectivity, mesoscale organization, hierarchy – affect their robustness to …

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 that can handle networks, has opened a new way to approach many real-world problems that would be hardly or even …

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 range of domains. In this paper we propose wsGAT, an extension of the Graph Attention Network (GAT) layers, meant to …

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 designing efficient heuristics for them requires considerable time and experimentation. On the other hand, the …

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 difficult problem arising in various network analysis tasks. In each stage, our approach learns the characteristics …