{"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/distributional-adversarial-networks","title":"Distributional Adversarial Networks","arxiv_id":"1706.09549","date":"2017-06-29","proceeding":"ICLR 2018 1","authors":["Chengtao Li","David Alvarez-Melis","Keyulu Xu","Stefanie Jegelka","Suvrit Sra"],"abstract":"We propose a framework for adversarial training that relies on a sample\nrather than a single sample point as the fundamental unit of discrimination.\nInspired by discrepancy measures and two-sample tests between probability\ndistributions, we propose two such distributional adversaries that operate and\npredict on samples, and show how they can be easily implemented on top of\nexisting models. Various experimental results show that generators trained with\nour distributional adversaries are much more stable and are remarkably less\nprone to mode collapse than traditional models trained with pointwise\nprediction discriminators. The application of our framework to domain\nadaptation also results in considerable improvement over recent\nstate-of-the-art.","url_abs":"http://arxiv.org/abs/1706.09549v3","url_pdf":"http://arxiv.org/pdf/1706.09549v3.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":"distributional-adversarial-networks","repo_url":"https://github.com/ChengtaoLi/dan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}