{"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/role-action-embeddings-scalable","title":"Role action embeddings: scalable representation of network positions","arxiv_id":"1811.08019","date":"2018-11-19","proceeding":null,"authors":["George Berry"],"abstract":"We consider the question of embedding nodes with similar local neighborhoods\ntogether in embedding space, commonly referred to as \"role embeddings.\" We\npropose RAE, an unsupervised framework that learns role embeddings. It combines\na within-node loss function and a graph neural network (GNN) architecture to\nplace nodes with similar local neighborhoods close in embedding space. We also\npropose a faster way of generating negative examples called neighbor shuffling,\nwhich quickly creates negative examples directly within batches. These\ntechniques can be easily combined with existing GNN methods to create\nunsupervised role embeddings at scale. We then explore role action embeddings,\nwhich summarize the non-structural features in a node's neighborhood, leading\nto better performance on node classification tasks. We find that the model\narchitecture proposed here provides strong performance on both graph and node\nclassification tasks, in some cases competitive with semi-supervised methods.","url_abs":"http://arxiv.org/abs/1811.08019v2","url_pdf":"http://arxiv.org/pdf/1811.08019v2.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":"role-action-embeddings-scalable","repo_url":"https://github.com/georgeberry/role-action-embeddings","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-neural-network","task_name":"Graph Neural Network"},{"task_slug":"node-classification","task_name":"Node 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}