{"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/on-generalization-of-graph-autoencoders-with","title":"On Generalization of Graph Autoencoders with Adversarial Training","arxiv_id":"2107.02658","date":"2021-07-06","proceeding":null,"authors":["Tianjin Huang","Yulong Pei","Vlado Menkovski","Mykola Pechenizkiy"],"abstract":"Adversarial training is an approach for increasing model's resilience against adversarial perturbations. Such approaches have been demonstrated to result in models with feature representations that generalize better. However, limited works have been done on adversarial training of models on graph data. In this paper, we raise such a question { does adversarial training improve the generalization of graph representations. We formulate L2 and L1 versions of adversarial training in two powerful node embedding methods: graph autoencoder (GAE) and variational graph autoencoder (VGAE). We conduct extensive experiments on three main applications, i.e. link prediction, node clustering, graph anomaly detection of GAE and VGAE, and demonstrate that both L2 and L1 adversarial training boost the generalization of GAE and VGAE.","url_abs":"https://arxiv.org/abs/2107.02658v2","url_pdf":"https://arxiv.org/pdf/2107.02658v2.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":"on-generalization-of-graph-autoencoders-with","repo_url":"https://github.com/Juintin/GAE-AT","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"graph-anomaly-detection","task_name":"Graph Anomaly Detection"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"node-clustering","task_name":"Node Clustering"}],"methods":[{"method_slug":"vgae","method_name":"VGAE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2107.02658","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}