{"url":"/method/meta-augmentation","slug":"meta-augmentation","name":"Meta-augmentation","full_name":"Meta-augmentation","full_name_withheld":false,"description_markdown":"**Meta-augmentation** helps generate more varied tasks for a single example in meta-learning. It can be distinguished from data augmentation in classic machine learning as follows. For data augmentation in classical machine learning, the aim is to generate more varied examples, within a single task. Meta-augmentation has the exact opposite aim: we wish to generate more varied tasks,\r\nfor a single example, to force the learner to quickly learn a new task from feedback. In meta-augmentation, adding randomness discourages the base learner and model from learning trivial solutions that do not generalize to new tasks.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Meta-Learning Requires Meta-Augmentation","paper":"/paper/meta-learning-requires-meta-augmentation","first_author":"Janarthanan Rajendran","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/meta-learning-requires-meta-augmentation"},"source":{"url":"https://arxiv.org/abs/2007.05549v2","title":"Meta-Learning Requires Meta-Augmentation","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Meta-Learning Algorithms","url":"/methods/category/meta-learning-algorithms","pwc_aliases":[]}],"n_papers_tagged":4,"archive_num_papers":4,"papers_newest_first":[{"paper":"/paper/meta-optimized-contrastive-learning-for","title":"Meta-optimized Contrastive Learning for Sequential Recommendation","date":"2023-04-16","arxiv_id":"2304.07763","n_code_links":1,"syntology":{"ran":3,"of":3,"unverified":0,"pointer_only":0}},{"paper":null,"title":"Smooth Mathematical Function from Compact Neural Networks","date":"2022-12-31","arxiv_id":"2301.00181","n_code_links":0,"syntology":null},{"paper":"/paper/diverse-preference-augmentation-with-multiple","title":"Diverse Preference Augmentation with Multiple Domains for Cold-start Recommendations","date":"2022-04-01","arxiv_id":"2204.00327","n_code_links":1,"syntology":null},{"paper":"/paper/meta-learning-requires-meta-augmentation","title":"Meta-Learning Requires Meta-Augmentation","date":"2020-07-10","arxiv_id":"2007.05549","n_code_links":1,"syntology":null}],"papers_shown":4,"tasks":[{"task":"/task/meta-learning","name":"Meta-Learning","papers":3},{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1},{"task":"/task/domain-adaptation","name":"Domain Adaptation","papers":1},{"task":"/task/sequential-recommendation","name":"Sequential Recommendation","papers":1},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":1},{"task":"/task/regression-1","name":"regression","papers":1}],"tasks_shown":7,"n_tasks":7,"usage_by_year":[{"year":"2020","papers":1},{"year":"2022","papers":2},{"year":"2023","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/meta-augmentation"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}