{"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/semi-supervised-learning-on-graphs-with","title":"Semi-supervised Learning on Graphs with Generative Adversarial Nets","arxiv_id":"1809.00130","date":"2018-09-01","proceeding":null,"authors":["Ming Ding","Jie Tang","Jie Zhang"],"abstract":"We investigate how generative adversarial nets (GANs) can help\nsemi-supervised learning on graphs. We first provide insights on working\nprinciples of adversarial learning over graphs and then present GraphSGAN, a\nnovel approach to semi-supervised learning on graphs. In GraphSGAN, generator\nand classifier networks play a novel competitive game. At equilibrium,\ngenerator generates fake samples in low-density areas between subgraphs. In\norder to discriminate fake samples from the real, classifier implicitly takes\nthe density property of subgraph into consideration. An efficient adversarial\nlearning algorithm has been developed to improve traditional normalized graph\nLaplacian regularization with a theoretical guarantee. Experimental results on\nseveral different genres of datasets show that the proposed GraphSGAN\nsignificantly outperforms several state-of-the-art methods. GraphSGAN can be\nalso trained using mini-batch, thus enjoys the scalability advantage.","url_abs":"http://arxiv.org/abs/1809.00130v1","url_pdf":"http://arxiv.org/pdf/1809.00130v1.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":"semi-supervised-learning-on-graphs-with","repo_url":"https://github.com/BradleyFeSt/graphSGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"semi-supervised-learning-on-graphs-with","repo_url":"https://github.com/dm-thu/GraphSGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1809.00130","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}