PairNorm: Tackling Oversmoothing in GNNs
PairNorm: Tackling Oversmoothing in GNNs
复制标题
DOI：
--
复制
发表时间：
2019-09
期刊：
影响因子：
--
通讯作者：
Lingxiao Zhao;L. Akoglu
中科院分区：
文献类型：
--
作者：
Lingxiao Zhao;L. Akoglu
图神经网络（GNNs）的性能随着层数的增加而逐渐下降。这种衰减部分归因于过度平滑，重复的图卷积最终使节点嵌入无法区分。我们仔细研究了两种不同的解释，旨在量化过度平滑。我们的主要贡献是PairNorm，这是一个新的规范化层，它基于对图卷积算子的仔细分析，可以防止所有节点嵌入变得过于相似。此外，PairNorm具有快速、易于实现的特点，不需要对网络架构进行任何更改，也不需要任何额外的参数，并且广泛适用于任何GNN。在真实世界图上的实验表明，PairNorm使更深的GCN、GAT和SGC模型对过度平滑更鲁棒，并显著提高了受益于更深GNN的新问题设置的性能。此https URL中提供了代码。
The performance of graph neural nets (GNNs) is known to gradually decrease with increasing number of layers. This decay is partly attributed to oversmoothing, where repeated graph convolutions eventually make node embeddings indistinguishable. We take a closer look at two different interpretations, aiming to quantify oversmoothing. Our main contribution is PairNorm, a novel normalization layer that is based on a careful analysis of the graph convolution operator, which prevents all node embeddings from becoming too similar. What is more, PairNorm is fast, easy to implement without any change to network architecture nor any additional parameters, and is broadly applicable to any GNN. Experiments on real-world graphs demonstrate that PairNorm makes deeper GCN, GAT, and SGC models more robust against oversmoothing, and significantly boosts performance for a new problem setting that benefits from deeper GNNs. Code is available at this https URL.