{"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-based-semi-supervised-learning-for","title":"Graph-based semi-supervised learning for relational networks","arxiv_id":"1612.05001","date":"2016-12-15","proceeding":null,"authors":["Leto Peel"],"abstract":"We address the problem of semi-supervised learning in relational networks,\nnetworks in which nodes are entities and links are the relationships or\ninteractions between them. Typically this problem is confounded with the\nproblem of graph-based semi-supervised learning (GSSL), because both problems\nrepresent the data as a graph and predict the missing class labels of nodes.\nHowever, not all graphs are created equally. In GSSL a graph is constructed,\noften from independent data, based on similarity. As such, edges tend to\nconnect instances with the same class label. Relational networks, however, can\nbe more heterogeneous and edges do not always indicate similarity. For\ninstance, instead of links being more likely to connect nodes with the same\nclass label, they may occur more frequently between nodes with different class\nlabels (link-heterogeneity). Or nodes with the same class label do not\nnecessarily have the same type of connectivity across the whole network\n(class-heterogeneity), e.g. in a network of sexual interactions we may observe\nlinks between opposite genders in some parts of the graph and links between the\nsame genders in others. Performing classification in networks with different\ntypes of heterogeneity is a hard problem that is made harder still when we do\nnot know a-priori the type or level of heterogeneity. Here we present two\nscalable approaches for graph-based semi-supervised learning for the more\ngeneral case of relational networks. We demonstrate these approaches on\nsynthetic and real-world networks that display different link patterns within\nand between classes. Compared to state-of-the-art approaches, ours give better\nclassification performance without prior knowledge of how classes interact. In\nparticular, our two-step label propagation algorithm gives consistently good\naccuracy and runs on networks of over 1.6 million nodes and 30 million edges in\naround 12 seconds.","url_abs":"http://arxiv.org/abs/1612.05001v1","url_pdf":"http://arxiv.org/pdf/1612.05001v1.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-based-semi-supervised-learning-for","repo_url":"https://github.com/adalld/ecmlpkdd2020","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"graph-based-semi-supervised-learning-for","repo_url":"https://github.com/adalld/wi2020","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1612.05001","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}