PairNorm: Tackling Oversmoothing in GNNs

TL;DR

PairNorm is a simple, effective normalization layer designed to prevent oversmoothing in deep GNNs, improving their robustness and performance without altering architecture or adding parameters.

Contribution

Introduction of PairNorm, a normalization technique that mitigates oversmoothing in GNNs, applicable to various models and easy to implement.

Findings

PairNorm improves the performance of deep GCN, GAT, and SGC models.

It effectively prevents node embeddings from becoming indistinguishable.

Enhances robustness and accuracy in real-world graph tasks.

Abstract

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 https://github.com/LingxiaoShawn/PairNorm.