{"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/modular-meta-learning-in-abstract-graph","title":"Modular meta-learning in abstract graph networks for combinatorial generalization","arxiv_id":"1812.07768","date":"2018-12-19","proceeding":null,"authors":["Ferran Alet","Maria Bauza","Alberto Rodriguez","Tomas Lozano-Perez","Leslie P. Kaelbling"],"abstract":"Modular meta-learning is a new framework that generalizes to unseen datasets\nby combining a small set of neural modules in different ways. In this work we\npropose abstract graph networks: using graphs as abstractions of a system's\nsubparts without a fixed assignment of nodes to system subparts, for which we\nwould need supervision. We combine this idea with modular meta-learning to get\na flexible framework with combinatorial generalization to new tasks built in.\nWe then use it to model the pushing of arbitrarily shaped objects from little\nor no training data.","url_abs":"http://arxiv.org/abs/1812.07768v1","url_pdf":"http://arxiv.org/pdf/1812.07768v1.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":"modular-meta-learning-in-abstract-graph","repo_url":"https://github.com/FerranAlet/modular-metalearning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1812.07768","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}