Fea2Fea: Exploring Structural Feature Correlations via Graph Neural Networks

Abstract

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.

arXiv commentIn proceddings of ECML-PKDD 2021 workshop

References in corpus (21)

• Semi-Supervised Classification with Graph Convolutional Networks
• Molecular Graph Convolutions: Moving Beyond Fingerprints
• DeepInf: Social Influence Prediction with Deep Learning
• Learning to Simulate Complex Physics with Graph Networks
• Graph Neural Networks with convolutional ARMA filters
• Gated Graph Sequence Neural Networks
• Predict then Propagate: Graph Neural Networks meet Personalized PageRank
• Scaling Graph Neural Networks with Approximate PageRank
• TUDataset: A collection of benchmark datasets for learning with graphs
• Attention-based Graph Neural Network for Semi-supervised Learning
• Benchmarking Graph Neural Networks
• Design Space for Graph Neural Networks
• Learning Multimodal Graph-to-Graph Translation for Molecular Optimization
• MCNE: An End-to-End Framework for Learning Multiple Conditional Network Representations of Social Network
• MR-GNN: Multi-Resolution and Dual Graph Neural Network for Predicting Structured Entity Interactions
• DeepGCNs: Can GCNs Go as Deep as CNNs?
• A Survey on The Expressive Power of Graph Neural Networks
• Modeling Semantics with Gated Graph Neural Networks for Knowledge Base Question Answering
• Joint embedding of structure and features via graph convolutional networks
• Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules
• On Node Features for Graph Neural Networks