{"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/arch-efficient-adversarial-regularized","title":"ARCH: Efficient Adversarial Regularized Training with Caching","arxiv_id":"2109.07048","date":"2021-09-15","proceeding":"Findings (EMNLP) 2021 11","authors":["Simiao Zuo","Chen Liang","Haoming Jiang","Pengcheng He","Xiaodong Liu","Jianfeng Gao","Weizhu Chen","Tuo Zhao"],"abstract":"Adversarial regularization can improve model generalization in many natural language processing tasks. However, conventional approaches are computationally expensive since they need to generate a perturbation for each sample in each epoch. We propose a new adversarial regularization method ARCH (adversarial regularization with caching), where perturbations are generated and cached once every several epochs. As caching all the perturbations imposes memory usage concerns, we adopt a K-nearest neighbors-based strategy to tackle this issue. The strategy only requires caching a small amount of perturbations, without introducing additional training time. We evaluate our proposed method on a set of neural machine translation and natural language understanding tasks. We observe that ARCH significantly eases the computational burden (saves up to 70% of computational time in comparison with conventional approaches). More surprisingly, by reducing the variance of stochastic gradients, ARCH produces a notably better (in most of the tasks) or comparable model generalization. Our code is available at https://github.com/SimiaoZuo/Caching-Adv.","url_abs":"https://arxiv.org/abs/2109.07048v2","url_pdf":"https://arxiv.org/pdf/2109.07048v2.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":"arch-efficient-adversarial-regularized","repo_url":"https://github.com/SimiaoZuo/Caching-Adv","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"arch","method_name":"ARCH"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}