Fea2Fea: Exploring Structural Feature Correlations via Graph Neural Networks

Autor:	Xie, Jiaqing, Ying, Rex
Rok vydání:	2021
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence Computer Science - Social and Information Networks
Druh dokumentu:	Working Paper
DOI:	10.1007/978-3-030-93736-2_19
Popis:	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. Comment: In proceddings of ECML-PKDD 2021 workshop
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2106.13061 Zobrazit plný text záznamu View this record from Arxiv