Refine my results

Document type


Specific Collection



Università della Svizzera italiana

Graph neural networks : operators and architectures

Grattarola, Daniele ; Alippi, Cesare (Dir.) ; Livi, Lorenzo (Codir.)

Thèse de doctorat : Università della Svizzera italiana, 2021 ; 2021INFO014.

This thesis explores the field of graph neural networks, a class of deep learning models designed to learn representations of graphs. We organise the work into two parts. In the first part, we focus on the essential building blocks of graph neural networks. We present three novel operators for learning graph representations: one graph convolutional layer and two methods for pooling. We put...