However, current GNN models (and GCNs in particular) are known to be constrained by various phenomena that limit their expressive power and ability to generalize to more complex graph datasets.
no code implementations • 27 Oct 2021 • Renming Liu, Semih Cantürk, Frederik Wenkel, Dylan Sandfelder, Devin Kreuzer, Anna Little, Sarah McGuire, Leslie O'Bray, Michael Perlmutter, Bastian Rieck, Matthew Hirn, Guy Wolf, Ladislav Rampášek
Graph neural networks (GNNs) have attracted much attention due to their ability to leverage the intrinsic geometries of the underlying data.
Geometric scattering has recently gained recognition in graph representation learning, and recent work has shown that integrating scattering features in graph convolution networks (GCNs) can alleviate the typical oversmoothing of features in node representation learning.
We propose a new graph neural network (GNN) module, based on relaxations of recently proposed geometric scattering transforms, which consist of a cascade of graph wavelet filters.
Graph convolutional networks (GCNs) have shown promising results in processing graph data by extracting structure-aware features.