The Impact of Global Structural Information in Graph Neural Networks Applications

TL;DR

This paper investigates whether incorporating global structural information into Graph Neural Networks improves their performance, finding that such information significantly benefits common graph tasks and proposing a regularization method for further gains.

Contribution

It empirically demonstrates the benefits of global structural information in GNNs and introduces a novel regularization strategy to enhance accuracy.

Findings

Global information improves GNN performance on multiple tasks

Regularization strategy yields over 5% accuracy increase

Global structure knowledge addresses limitations of local neighborhood aggregation

Abstract

Graph Neural Networks (GNNs) rely on the graph structure to define an aggregation strategy where each node updates its representation by combining information from its neighbours. A known limitation of GNNs is that, as the number of layers increases, information gets smoothed and squashed and node embeddings become indistinguishable, negatively affecting performance. Therefore, practical GNN models employ few layers and only leverage the graph structure in terms of limited, small neighbourhoods around each node. Inevitably, practical GNNs do not capture information depending on the global structure of the graph. While there have been several works studying the limitations and expressivity of GNNs, the question of whether practical applications on graph structured data require global structural knowledge or not, remains unanswered. In this work, we empirically address this question by giving access to global information to several GNN models, and observing the impact it has on downstream performance. Our results show that global information can in fact provide significant benefits for common graph-related tasks. We further identify a novel regularization strategy that leads to an average accuracy improvement of more than 5% on all considered tasks.