Blar i NORCE vitenarkiv på forfatter "Grattarola, Daniele"

Viser treff 1-2 av 2

    • Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling 

      Bianchi, Filippo Maria; Grattarola, Daniele; Livi, Lorenzo; Alippi, Cesare (Peer reviewed; Journal article, 2020)
      Abstract—In graph neural networks (GNNs), pooling operators compute local summaries of input graphs to capture their global properties, and they are fundamental for building deep GNNs that learn hierarchical representations. ...

    • Spectral Clustering with Graph Neural Networks for Graph Pooling 

      Bianchi, Filippo Maria; Grattarola, Daniele; Alippi, Cesare (Peer reviewed; Journal article, 2020)
      Spectral clustering (SC) is a popular clustering technique to find strongly connected communities on a graph. SC can be used in Graph Neural Networks (GNNs) to implement pooling operations that aggregate nodes belonging ...