Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Mita, Airi"'
Graphs are useful for representing various realworld objects. However, graph neural networks (GNNs) tend to suffer from over-smoothing, where the representations of nodes of different classes become similar as the number of layers increases, leading
Externí odkaz:
http://arxiv.org/abs/2410.15640
