{"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/meta-learning-requires-meta-augmentation","title":"Meta-Learning Requires Meta-Augmentation","arxiv_id":"2007.05549","date":"2020-07-10","proceeding":"NeurIPS 2020 12","authors":["Janarthanan Rajendran","Alex Irpan","Eric Jang"],"abstract":"Meta-learning algorithms aim to learn two components: a model that predicts targets for a task, and a base learner that quickly updates that model when given examples from a new task. This additional level of learning can be powerful, but it also creates another potential source for overfitting, since we can now overfit in either the model or the base learner. We describe both of these forms of metalearning overfitting, and demonstrate that they appear experimentally in common meta-learning benchmarks. We then use an information-theoretic framework to discuss meta-augmentation, a way to add randomness that discourages the base learner and model from learning trivial solutions that do not generalize to new tasks. We demonstrate that meta-augmentation produces large complementary benefits to recently proposed meta-regularization techniques.","url_abs":"https://arxiv.org/abs/2007.05549v2","url_pdf":"https://arxiv.org/pdf/2007.05549v2.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":"meta-learning-requires-meta-augmentation","repo_url":"https://github.com/google-research/google-research","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[{"method_slug":"meta-augmentation","method_name":"Meta-augmentation"}],"datasets_introduced":[],"methods_introduced":[{"slug":"meta-augmentation","name":"Meta-augmentation","full_name":"Meta-augmentation"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.05549","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}