{"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-autoencoders-for-few-shot","title":"Meta-learning autoencoders for few-shot prediction","arxiv_id":"1807.09912","date":"2018-07-26","proceeding":null,"authors":["Tailin Wu","John Peurifoy","Isaac L. Chuang","Max Tegmark"],"abstract":"Compared to humans, machine learning models generally require significantly\nmore training examples and fail to extrapolate from experience to solve\npreviously unseen challenges. To help close this performance gap, we augment\nsingle-task neural networks with a meta-recognition model which learns a\nsuccinct model code via its autoencoder structure, using just a few informative\nexamples. The model code is then employed by a meta-generative model to\nconstruct parameters for the task-specific model. We demonstrate that for\npreviously unseen tasks, without additional training, this Meta-Learning\nAutoencoder (MeLA) framework can build models that closely match the true\nunderlying models, with loss significantly lower than given by fine-tuned\nbaseline networks, and performance that compares favorably with\nstate-of-the-art meta-learning algorithms. MeLA also adds the ability to\nidentify influential training examples and predict which additional data will\nbe most valuable to acquire to improve model prediction.","url_abs":"http://arxiv.org/abs/1807.09912v1","url_pdf":"http://arxiv.org/pdf/1807.09912v1.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-autoencoders-for-few-shot","repo_url":"https://github.com/tailintalent/mela","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}