论文标题
重新考虑图形神经网络的图形正则化
Rethinking Graph Regularization for Graph Neural Networks
论文作者
论文摘要
Graph Laplacian正则化项通常用于半监督表示的学习中，以提供$ F（x）$的图形结构信息。但是，随着图形神经网络（GNN）的最新流行，将图形结构$ a $直接编码到模型中，即$ f（a，x）$，已成为更常见的方法。尽管我们表明图形拉普拉斯正则化对现有的GNN几乎没有任何好处，并提出了一个简单但非平凡的laplacian正则化变体，称为传播指导（P-REG），以提高现有GNN模型的性能。我们提供了正式的分析，以表明P-REG不仅注入了额外的信息（传统的图形拉普拉斯正规化未捕获）到GNN中，而且具有等于无限深度图卷积网络的能力。我们证明，P-REG可以有效地提高在许多不同数据集中节点级和图形任务上现有GNN模型的性能。
The graph Laplacian regularization term is usually used in semi-supervised representation learning 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 brings little-to-no benefit to existing GNNs, and 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. We demonstrate that P-reg can effectively boost the performance of existing GNN models on both node-level and graph-level tasks across many different datasets.
