{"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/an-end-to-end-deep-learning-architecture-for","title":"An End-to-End Deep Learning Architecture for Graph Classification","arxiv_id":null,"date":"2018-04-29","proceeding":"AAAI-18 2018 4","authors":["Muhan Zhang","Zhicheng Cui","Marion Neumann","Yixin Chen"],"abstract":"Neural networks are typically designed to deal with data in tensor forms. In this paper, we propose a novel neural network architecture accepting graphs of arbitrary structure. Given a dataset containing graphs in the form of (G,y) where G is a graph and y is its class, we aim to develop neural networks that read the graphs directly and learn a classification function. There are two main challenges: 1) how to extract useful features characterizing the rich information encoded in a graph for classification purpose, and 2) how to sequentially read a graph in a meaningful and consistent order. To address the first challenge, we design a localized graph convolution model and show its connection with two graph kernels. To address the second challenge, we design a novel SortPooling layer which sorts graph vertices in a consistent order so that traditional neural networks can be trained on the graphs. Experiments on benchmark graph classification datasets demonstrate that the proposed architecture achieves highly competitive performance with state-of-the-art graph kernels and other graph neural network methods. Moreover, the architecture allows end-to-end gradient-based training with original graphs, without the need to first transform graphs into vectors.","url_abs":"https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/viewPaper/17146","url_pdf":"https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/viewFile/17146/16755","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":"an-end-to-end-deep-learning-architecture-for","repo_url":"https://github.com/muhanzhang/DGCNN","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"torch","reach":null},{"paper_slug":"an-end-to-end-deep-learning-architecture-for","repo_url":"https://github.com/Ki-Seki/DGCNN-updated","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"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"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dgcnn","method_name":"DGCNN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/graph-classification-on-collab","task":"Graph Classification","dataset":"COLLAB","model":"DGCNN","rank_in_archive_order":27,"of":39,"metrics":{"Accuracy":"73.76%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-collab","task":"Graph Classification","dataset":"COLLAB","model":"DGCNN (sum)","rank_in_archive_order":33,"of":39,"metrics":{"Accuracy":"69.45%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-dd","task":"Graph Classification","dataset":"D&D","model":"DGCNN","rank_in_archive_order":18,"of":53,"metrics":{"Accuracy":"79.37%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-dd","task":"Graph Classification","dataset":"D&D","model":"DGCNN (sum)","rank_in_archive_order":22,"of":53,"metrics":{"Accuracy":"78.72%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-imdb-b","task":"Graph Classification","dataset":"IMDb-B","model":"DGCNN","rank_in_archive_order":46,"of":51,"metrics":{"Accuracy":"70.03%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-imdb-b","task":"Graph Classification","dataset":"IMDb-B","model":"DGCNN (sum)","rank_in_archive_order":50,"of":51,"metrics":{"Accuracy":"51.69%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-imdb-m","task":"Graph Classification","dataset":"IMDb-M","model":"DGCNN","rank_in_archive_order":31,"of":36,"metrics":{"Accuracy":"47.83%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-imdb-m","task":"Graph Classification","dataset":"IMDb-M","model":"DGCNN (sum)","rank_in_archive_order":35,"of":36,"metrics":{"Accuracy":"42.76%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-mutag","task":"Graph Classification","dataset":"MUTAG","model":"DGCNN","rank_in_archive_order":59,"of":74,"metrics":{"Accuracy":"85.83%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-nci1","task":"Graph Classification","dataset":"NCI1","model":"DGCNN (sum)","rank_in_archive_order":63,"of":69,"metrics":{"Accuracy":"69.00%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-proteins","task":"Graph Classification","dataset":"PROTEINS","model":"DGCNN","rank_in_archive_order":54,"of":103,"metrics":{"Accuracy":"76.26%"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}