Doctoral thesis

Graph neural networks : operators and architectures

  • Grattarola, Daniele
  • Alippi, Cesare (degree supervisor)
  • Livi, Lorenzo (degree committee member)
    10.12.2021

225 p

Thèse de doctorat: Università della Svizzera italiana, 2021

English 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... Show more…
Language
  • English
Classification
Computer science
License
License undefined
Identifiers
Persistent URL
https://susi.usi.ch/usi/documents/319253