Fea2Fea: Exploring Structural Feature Correlations via Graph Neural Networks

24 Jun 2021  ·  Jiaqing Xie, Rex Ying ·

Structural features are important features in a geometrical graph. Although there are some correlation analysis of features based on covariance, there is no relevant research on structural feature correlation analysis with graph neural networks. In this paper, we introuduce graph feature to feature (Fea2Fea) prediction pipelines in a low dimensional space to explore some preliminary results on structural feature correlation, which is based on graph neural network. The results show that there exists high correlation between some of the structural features. An irredundant feature combination with initial node features, which is filtered by graph neural network has improved its classification accuracy in some graph-based tasks. We compare differences between concatenation methods on connecting embeddings between features and show that the simplest is the best. We generalize on the synthetic geometric graphs and certify the results on prediction difficulty between structural features.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Graph Classification ENZYMES Fea2Fea-s2 Accuracy 48.5 # 27
Graph Classification NCI1 Fea2Fea-s3 Accuracy 74.9% # 31
Graph Classification PROTEINS Fea2Fea-s2 Accuracy 77.8% # 14
Graph Classification Pubmed Fea2Fea-s3 Test Accuracy 78.5 # 1

Methods


No methods listed for this paper. Add relevant methods here