{"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/learning-graph-level-representations-with","title":"Learning Graph-Level Representations with Recurrent Neural Networks","arxiv_id":"1805.07683","date":"2018-05-20","proceeding":null,"authors":["Yu Jin","Joseph F. JaJa"],"abstract":"Recently a variety of methods have been developed to encode graphs into\nlow-dimensional vectors that can be easily exploited by machine learning\nalgorithms. The majority of these methods start by embedding the graph nodes\ninto a low-dimensional vector space, followed by using some scheme to aggregate\nthe node embeddings. In this work, we develop a new approach to learn\ngraph-level representations, which includes a combination of unsupervised and\nsupervised learning components. We start by learning a set of node\nrepresentations in an unsupervised fashion. Graph nodes are mapped into node\nsequences sampled from random walk approaches approximated by the\nGumbel-Softmax distribution. Recurrent neural network (RNN) units are modified\nto accommodate both the node representations as well as their neighborhood\ninformation. Experiments on standard graph classification benchmarks\ndemonstrate that our proposed approach achieves superior or comparable\nperformance relative to the state-of-the-art algorithms in terms of convergence\nspeed and classification accuracy. We further illustrate the effectiveness of\nthe different components used by our approach.","url_abs":"http://arxiv.org/abs/1805.07683v4","url_pdf":"http://arxiv.org/pdf/1805.07683v4.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":"learning-graph-level-representations-with","repo_url":"https://github.com/yuj-umd/graphRNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"graph-classification","task_name":"Graph Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}