Network Analysis

This study examines how community structures in graphs affect Graph Neural Networks (GNNs) in node classification tasks. Through experiments on six datasets, researchers found that community structures significantly impact GNN performance. When nodes in a community mostly share the same label, disrupting the community structure dramatically reduces performance. Conversely, when labels don’t correlate with communities, graph structure becomes less relevant and simple feature-based models perform comparably. The research provides insights and guidelines for selecting appropriate models based on graph structure characteristics.

This study uses regular equivalence in trust networks to improve recommendations for cold-start users in Collaborative Filtering systems. By applying this network science measure to user trust relationships, the researchers create a similarity matrix that helps select better user neighbors for recommendation purposes. Testing on the Epinions dataset shows their approach outperforms related methods in recommendation accuracy for new users with few ratings.