{"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/demo-net-degree-specific-graph-neural","title":"DEMO-Net: Degree-specific Graph Neural Networks for Node and Graph Classification","arxiv_id":"1906.02319","date":"2019-06-05","proceeding":null,"authors":["Jun Wu","Jingrui He","Jiejun Xu"],"abstract":"Graph data widely exist in many high-impact applications. Inspired by the success of deep learning in grid-structured data, graph neural network models have been proposed to learn powerful node-level or graph-level representation. However, most of the existing graph neural networks suffer from the following limitations: (1) there is limited analysis regarding the graph convolution properties, such as seed-oriented, degree-aware and order-free; (2) the node's degree-specific graph structure is not explicitly expressed in graph convolution for distinguishing structure-aware node neighborhoods; (3) the theoretical explanation regarding the graph-level pooling schemes is unclear. To address these problems, we propose a generic degree-specific graph neural network named DEMO-Net motivated by Weisfeiler-Lehman graph isomorphism test that recursively identifies 1-hop neighborhood structures. In order to explicitly capture the graph topology integrated with node attributes, we argue that graph convolution should have three properties: seed-oriented, degree-aware, order-free. To this end, we propose multi-task graph convolution where each task represents node representation learning for nodes with a specific degree value, thus leading to preserving the degree-specific graph structure. In particular, we design two multi-task learning methods: degree-specific weight and hashing functions for graph convolution. In addition, we propose a novel graph-level pooling/readout scheme for learning graph representation provably lying in a degree-specific Hilbert kernel space. The experimental results on several node and graph classification benchmark data sets demonstrate the effectiveness and efficiency of our proposed DEMO-Net over state-of-the-art graph neural network models.","url_abs":"https://arxiv.org/abs/1906.02319v1","url_pdf":"https://arxiv.org/pdf/1906.02319v1.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":"demo-net-degree-specific-graph-neural","repo_url":"https://github.com/jwu4sml/DEMO-Net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"graph-classification","task_name":"Graph Classification"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"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":"DEMO-Net(weight)","rank_in_archive_order":51,"of":54,"metrics":{"Accuracy":"27.2"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-blogcatalog-1","task":"Node Classification","dataset":"BlogCatalog","model":"DEMO-Net(weight)","rank_in_archive_order":2,"of":6,"metrics":{"Accuracy":"84.9"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-brazil-air-traffic","task":"Node Classification","dataset":"Brazil Air-Traffic","model":"DEMO-Net(weight)","rank_in_archive_order":2,"of":7,"metrics":{"Accuracy":"0.543 ± 0.034"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-europe-air-traffic","task":"Node Classification","dataset":"Europe Air-Traffic","model":"DEMO-Net(weight)","rank_in_archive_order":3,"of":7,"metrics":{"Accuracy":"45.9"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-facebook","task":"Node Classification","dataset":"Facebook","model":"DEMO-Net(weight)","rank_in_archive_order":4,"of":8,"metrics":{"Accuracy":"91.9"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-flickr","task":"Node Classification","dataset":"Flickr","model":"DEMO-Net(weight)","rank_in_archive_order":2,"of":8,"metrics":{"Accuracy":"0.656 ± 0.000"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-usa-air-traffic","task":"Node Classification","dataset":"USA Air-Traffic","model":"DEMO-Net(weight)","rank_in_archive_order":2,"of":7,"metrics":{"Accuracy":"64.7"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-wiki-vote","task":"Node Classification","dataset":"Wiki-Vote","model":"DEMO-Net(weight)","rank_in_archive_order":1,"of":6,"metrics":{"Accuracy":"99.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1906.02319","atlas_url":"https://app.syntology.ai/?focus=1906.02319","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}