{"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/n-gcn-multi-scale-graph-convolution-for-semi","title":"N-GCN: Multi-scale Graph Convolution for Semi-supervised Node Classification","arxiv_id":"1802.08888","date":"2018-02-24","proceeding":null,"authors":["Sami Abu-El-Haija","Amol Kapoor","Bryan Perozzi","Joonseok Lee"],"abstract":"Graph Convolutional Networks (GCNs) have shown significant improvements in\nsemi-supervised learning on graph-structured data. Concurrently, unsupervised\nlearning of graph embeddings has benefited from the information contained in\nrandom walks. In this paper, we propose a model: Network of GCNs (N-GCN), which\nmarries these two lines of work. At its core, N-GCN trains multiple instances\nof GCNs over node pairs discovered at different distances in random walks, and\nlearns a combination of the instance outputs which optimizes the classification\nobjective. Our experiments show that our proposed N-GCN model improves\nstate-of-the-art baselines on all of the challenging node classification tasks\nwe consider: Cora, Citeseer, Pubmed, and PPI. In addition, our proposed method\nhas other desirable properties, including generalization to recently proposed\nsemi-supervised learning methods such as GraphSAGE, allowing us to propose\nN-SAGE, and resilience to adversarial input perturbations.","url_abs":"http://arxiv.org/abs/1802.08888v1","url_pdf":"http://arxiv.org/pdf/1802.08888v1.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":"n-gcn-multi-scale-graph-convolution-for-semi","repo_url":"https://github.com/samihaija/mixhop","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"node-classification","task_name":"Node Classification"}],"methods":[{"method_slug":"graphsage","method_name":"GraphSAGE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-classification-on-citeseer","task":"Node Classification","dataset":"Citeseer","model":"N-GCN","rank_in_archive_order":44,"of":71,"metrics":{"Accuracy":"72.2%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora","task":"Node Classification","dataset":"Cora","model":"N-GCN","rank_in_archive_order":45,"of":73,"metrics":{"Accuracy":"83.0%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed","task":"Node Classification","dataset":"Pubmed","model":"N-GCN","rank_in_archive_order":44,"of":70,"metrics":{"Accuracy":"79.5%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.08888","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}