Machine Learning

How Well is Human Attention Preserved in fMRI-Based Visual Brain Decoding?

This paper investigates the preservation of human visual attention in brain activity patterns captured through fMRI during visual decoding tasks. We explore how well attention mechanisms are reflected in neural responses and propose computational …

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 …

Geometric 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 network, we employ geometric deep learning to extract a sub-network on …

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 …