Rethinking Graph Regularization For Graph Neural Networks

09/04/2020 ∙ by Han Yang, et al. ∙ 23

The graph Laplacian regularization term is usually used in semi-supervised node classification to provide graph structure information for a model f(X). However, with the recent popularity of graph neural networks (GNNs), directly encoding graph structure A into a model, i.e., f(A, X), has become the more common approach. While we show that graph Laplacian regularization f(X)^⊤Δ f(X) brings little-to-no benefit to existing GNNs, we propose a simple but non-trivial variant of graph Laplacian regularization, called Propagation-regularization (P-reg), to boost the performance of existing GNN models. We provide formal analyses to show that P-reg not only infuses extra information (that is not captured by the traditional graph Laplacian regularization) into GNNs, but also has the capacity equivalent to an infinite-depth graph convolutional network. The code is available at



There are no comments yet.


page 1

page 2

page 3

page 4

Code Repositories


Rethinking Graph Regularization for Graph Neural Networks.

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.