Title | ||
---|---|---|
Hierarchical Representation Learning in Graph Neural Networks With Node Decimation Pooling |
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. In this work, we propose the Node Decimation Pooling (NDP), a pooling operator for GNNs that generates coarser graphs while preserving the overall graph topology. During training, the ... |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/TNNLS.2020.3044146 | IEEE Transactions on Neural Networks and Learning Systems |
Keywords | DocType | Volume |
Laplace equations,Partitioning algorithms,Symmetric matrices,Clustering algorithms,Training,Topology,Task analysis | Journal | 33 |
Issue | ISSN | Citations |
5 | 2162-237X | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Filippo Maria Bianchi | 1 | 160 | 15.76 |
Daniele Grattarola | 2 | 8 | 1.83 |
Lorenzo Livi | 3 | 304 | 25.67 |
Cesare Alippi | 4 | 1040 | 115.84 |