{"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/concept-learners-for-generalizable-few-shot","title":"Concept Learners for Few-Shot Learning","arxiv_id":"2007.07375","date":"2020-07-14","proceeding":"ICLR 2021 1","authors":["Kaidi Cao","Maria Brbic","Jure Leskovec"],"abstract":"Developing algorithms that are able to generalize to a novel task given only a few labeled examples represents a fundamental challenge in closing the gap between machine- and human-level performance. The core of human cognition lies in the structured, reusable concepts that help us to rapidly adapt to new tasks and provide reasoning behind our decisions. However, existing meta-learning methods learn complex representations across prior labeled tasks without imposing any structure on the learned representations. Here we propose COMET, a meta-learning method that improves generalization ability by learning to learn along human-interpretable concept dimensions. Instead of learning a joint unstructured metric space, COMET learns mappings of high-level concepts into semi-structured metric spaces, and effectively combines the outputs of independent concept learners. We evaluate our model on few-shot tasks from diverse domains, including fine-grained image classification, document categorization and cell type annotation on a novel dataset from a biological domain developed in our work. COMET significantly outperforms strong meta-learning baselines, achieving 6-15% relative improvement on the most challenging 1-shot learning tasks, while unlike existing methods providing interpretations behind the model's predictions.","url_abs":"https://arxiv.org/abs/2007.07375v3","url_pdf":"https://arxiv.org/pdf/2007.07375v3.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":"concept-learners-for-generalizable-few-shot","repo_url":"https://github.com/snap-stanford/comet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"concept-learners-for-generalizable-few-shot","repo_url":"https://github.com/hu-my/taskattributedistance","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.07375","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.07375"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/snap-stanford/comet","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hu-my/taskattributedistance","reach":null}],"summary":{"ran":1,"unverified":2},"by_repo_kind":{"listed":{"samples":3,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"1abe27c0e2b65879","entry":"MetaTemplate","repo":"hu-my/taskattributedistance","repo_kind":"listed","path":"methods/apnet.py","file_url":"https://github.com/hu-my/taskattributedistance/blob/HEAD/methods/apnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1abe27c0e2b65879"}},{"code_sha256_prefix":"101a661a49543aae","entry":"APNetTemplate","repo":"hu-my/taskattributedistance","repo_kind":"listed","path":"methods/apnet.py","file_url":"https://github.com/hu-my/taskattributedistance/blob/HEAD/methods/apnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"101a661a49543aae"}},{"code_sha256_prefix":"14bf3c730d8963a8","entry":"APNet_w_attrLoc","repo":"hu-my/taskattributedistance","repo_kind":"listed","path":"methods/apnet.py","file_url":"https://github.com/hu-my/taskattributedistance/blob/HEAD/methods/apnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"14bf3c730d8963a8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}