Viet-Anh on Software Logo

What is: GCNII?

SourceSimple and Deep Graph Convolutional Networks
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

GCNII is an extension of a Graph Convolution Networks with two new techniques, initial residual and identify mapping, to tackle the problem of oversmoothing -- where stacking more layers and adding non-linearity tends to degrade performance. At each layer, initial residual constructs a skip connection from the input layer, while identity mapping adds an identity matrix to the weight matrix.