On the Impact of Communities on Semi-supervised Classification Using Graph Neural Networks

Abstract

Graph Neural Networks (GNNs) are effective in many applications. Still, there is a limited understanding of the effect of common graph structures on the learning process of GNNs. In this work, we systematically study the impact of community structure on the performance of GNNs in semi-supervised node classification on graphs. Following an ablation study on six datasets, we measure the performance of GNNs on the original graphs, and the change in performance in the presence and the absence of community structure. Our results suggest that communities typically have a major impact on the learning process and classification performance. For example, in cases where the majority of nodes from one community share a single classification label, breaking up community structure results in a significant performance drop. On the other hand, for cases where labels show low correlation with communities, we find that the graph structure is rather irrelevant to the learning process, and a feature-only baseline becomes hard to beat. With our work, we provide deeper insights in the abilities and limitations of GNNs, including a set of general guidelines for model selection based on the graph structure.

References in corpus (12)

• Fast unfolding of communities in large networks
• The structure and function of complex networks
• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Stochastic blockmodels and community structure in networks
• Simplifying Graph Convolutional Networks
• Pitfalls of Graph Neural Network Evaluation
• Predict then Propagate: Graph Neural Networks meet Personalized PageRank
• Scaling Graph Neural Networks with Approximate PageRank
• On community structure in complex networks: challenges and opportunities
• Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking
• "Like Sheep Among Wolves": Characterizing Hateful Users on Twitter

Cited by in corpus (1)

• Structack: Structure-based Adversarial Attacks on Graph Neural Networks