{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/fea2fea-exploring-structural-feature","title":"Fea2Fea: Exploring Structural Feature Correlations via Graph Neural Networks","arxiv_id":"2106.13061","date":"2021-06-24","proceeding":null,"authors":["Jiaqing Xie","Rex Ying"],"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.","url_abs":"https://arxiv.org/abs/2106.13061v4","url_pdf":"https://arxiv.org/pdf/2106.13061v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"fea2fea-exploring-structural-feature","repo_url":"https://github.com/JIAQING-XIE/Fea2Fea","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"feature-correlation","task_name":"Feature Correlation"},{"task_slug":"graph-classification","task_name":"Graph Classification"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"structual-feature-correlation","task_name":"Structual Feature Correlation"}],"methods":[{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/graph-classification-on-enzymes","task":"Graph Classification","dataset":"ENZYMES","model":"Fea2Fea-s2","rank_in_archive_order":42,"of":54,"metrics":{"Accuracy":"48.5"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-nci1","task":"Graph Classification","dataset":"NCI1","model":"Fea2Fea-s3","rank_in_archive_order":52,"of":69,"metrics":{"Accuracy":"74.9%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-proteins","task":"Graph Classification","dataset":"PROTEINS","model":"Fea2Fea-s2","rank_in_archive_order":25,"of":103,"metrics":{"Accuracy":"77.8%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-pubmed","task":"Graph Classification","dataset":"Pubmed","model":"Fea2Fea-s3","rank_in_archive_order":1,"of":1,"metrics":{"Test Accuracy":"78.5"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}