{"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/graph-capsule-convolutional-neural-networks","title":"Graph Capsule Convolutional Neural Networks","arxiv_id":"1805.08090","date":"2018-05-21","proceeding":null,"authors":["Saurabh Verma","Zhi-Li Zhang"],"abstract":"Graph Convolutional Neural Networks (GCNNs) are the most recent exciting\nadvancement in deep learning field and their applications are quickly spreading\nin multi-cross-domains including bioinformatics, chemoinformatics, social\nnetworks, natural language processing and computer vision. In this paper, we\nexpose and tackle some of the basic weaknesses of a GCNN model with a capsule\nidea presented in \\cite{hinton2011transforming} and propose our Graph Capsule\nNetwork (GCAPS-CNN) model. In addition, we design our GCAPS-CNN model to solve\nespecially graph classification problem which current GCNN models find\nchallenging. Through extensive experiments, we show that our proposed Graph\nCapsule Network can significantly outperforms both the existing state-of-art\ndeep learning methods and graph kernels on graph classification benchmark\ndatasets.","url_abs":"http://arxiv.org/abs/1805.08090v4","url_pdf":"http://arxiv.org/pdf/1805.08090v4.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":"graph-capsule-convolutional-neural-networks","repo_url":"https://github.com/vermaMachineLearning/Graph-Capsule-CNN-Networks","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"graph-classification","task_name":"Graph Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/graph-classification-on-dd","task":"Graph Classification","dataset":"D&D","model":"GCAPS-CNN","rank_in_archive_order":31,"of":53,"metrics":{"Accuracy":"77.62%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-imdb-b","task":"Graph Classification","dataset":"IMDb-B","model":"GCAPS-CNN","rank_in_archive_order":42,"of":51,"metrics":{"Accuracy":"71.69%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-nci1","task":"Graph Classification","dataset":"NCI1","model":"GCAPS-CNN","rank_in_archive_order":29,"of":69,"metrics":{"Accuracy":"82.72%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-proteins","task":"Graph Classification","dataset":"PROTEINS","model":"GCAPS-CNN","rank_in_archive_order":47,"of":103,"metrics":{"Accuracy":"76.40%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1805.08090","atlas_url":"https://app.syntology.ai/?focus=1805.08090","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}