A Proposal of Multi-Layer Perceptron with Graph Gating Unit for Graph Representation Learning and its Application to Surrogate Model for FEM

1 code implementation • JSAI 2022 • Nakai Yu, Okuda Hiroshi

In this paper, by presenting a novel GNN model, based on stacking feedforward neural networks with gating structures using GCNs, I tried to solve the over-smoothing problem and thereby overcome the difficulty of GNNs learning large graphs.

Graph Representation Learning Node Classification