Fea2Fea: Exploring Structural Feature Correlations via Graph Neural Networks
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 31 of its 41 references that are in the map. First posted on arXiv 24 Jun 2021.
Builds on
31 of 41 references.
References · 31
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2017Graph Attention Networkscited by 8,854
- 2017Inductive Representation Learning on Large Graphscited by 6,284
- 2018How Powerful are Graph Neural Networks?cited by 4,355
- 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
- 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
- 2020Learning to Simulate Complex Physics with Graph Networkscited by 867
- 2015Gated Graph Sequence Neural Networkscited by 792
- 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
- 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
- 2020Benchmarking Graph Neural Networkscited by 672
- 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
19 more
- 2016Molecular Graph Convolutions: Moving Beyond Fingerprintscited by 238
- 2021Identity-aware Graph Neural Networkscited by 197
- 2019Graph Neural Networks with convolutional ARMA filterscited by 185
- 2020Design Space for Graph Neural Networkscited by 182
- 2020Scaling Graph Neural Networks with Approximate PageRankcited by 174
- 2018DeepInf: Social Influence Prediction with Deep Learningcited by 128
- 2020A Survey on The Expressive Power of Graph Neural Networkscited by 111
- 2018Attention-based Graph Neural Network for Semi-supervised Learningcited by 100
- 2018SimGNN: A Neural Network Approach to Fast Graph Similarity Computationcited by 89
- 2018Learning Multimodal Graph-to-Graph Translation for Molecular Optimizationcited by 87
- 2017Recurrent Relational Networkscited by 71
- 2018Modeling Semantics with Gated Graph Neural Networks for Knowledge Base Question Answeringcited by 30
- 2018Semi-supervised User Geolocation via Graph Convolutional Networkscited by 27
- 2019MR-GNN: Multi-Resolution and Dual Graph Neural Network for Predicting Structured Entity Interactionscited by 24
- 2019On Node Features for Graph Neural Networkscited by 20
- 2018Spectral Multigraph Networks for Discovering and Fusing Relationships in Moleculescited by 9
- 2019Joint embedding of structure and features via graph convolutional networkscited by 8
- 2020Two-stage Training of Graph Neural Networks for Graph Classificationcited by 4
- 2020Revisiting graph neural networks and distance encoding from a practical viewcited by 4
Built on by
Citing papers per year: 2024: 1.
1 paper.