{"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/exploring-the-similarity-of-representations","title":"Exploring the Similarity of Representations in Model-Agnostic Meta-Learning","arxiv_id":"2105.05757","date":"2021-05-12","proceeding":"ICLR Workshop Learning_to_Learn 2021 5","authors":["Thomas Goerttler","Klaus Obermayer"],"abstract":"In past years model-agnostic meta-learning (MAML) has been one of the most promising approaches in meta-learning. It can be applied to different kinds of problems, e.g., reinforcement learning, but also shows good results on few-shot learning tasks. Besides their tremendous success in these tasks, it has still not been fully revealed yet, why it works so well. Recent work proposes that MAML rather reuses features than rapidly learns. In this paper, we want to inspire a deeper understanding of this question by analyzing MAML's representation. We apply representation similarity analysis (RSA), a well-established method in neuroscience, to the few-shot learning instantiation of MAML. Although some part of our analysis supports their general results that feature reuse is predominant, we also reveal arguments against their conclusion. The similarity-increase of layers closer to the input layers arises from the learning task itself and not from the model. In addition, the representations after inner gradient steps make a broader change to the representation than the changes during meta-training.","url_abs":"https://arxiv.org/abs/2105.05757v1","url_pdf":"https://arxiv.org/pdf/2105.05757v1.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":"exploring-the-similarity-of-representations","repo_url":"https://github.com/ThomasGoerttler/similarity-analysis-of-maml","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[{"method_slug":"maml","method_name":"MAML"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.05757","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.05757"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ThomasGoerttler/similarity-analysis-of-maml","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":3,"unverified":5},"by_repo_kind":{"official":{"samples":8,"ran":3,"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":0,"samples":[{"code_sha256_prefix":"5c273c526536356d","entry":"centering","repo":"ThomasGoerttler/similarity-analysis-of-maml","repo_kind":"official","path":"cka.py","file_url":"https://github.com/ThomasGoerttler/similarity-analysis-of-maml/blob/HEAD/cka.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5c273c526536356d"}},{"code_sha256_prefix":"c633017bfba675e4","entry":"kernel_HSIC","repo":"ThomasGoerttler/similarity-analysis-of-maml","repo_kind":"official","path":"cka.py","file_url":"https://github.com/ThomasGoerttler/similarity-analysis-of-maml/blob/HEAD/cka.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c633017bfba675e4"}},{"code_sha256_prefix":"0f137cab706f1953","entry":"rbf","repo":"ThomasGoerttler/similarity-analysis-of-maml","repo_kind":"official","path":"cka.py","file_url":"https://github.com/ThomasGoerttler/similarity-analysis-of-maml/blob/HEAD/cka.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0f137cab706f1953"}},{"code_sha256_prefix":"2bdaad0e5c106937","entry":"calculate_RDM","repo":"ThomasGoerttler/similarity-analysis-of-maml","repo_kind":"official","path":"rsa.py","file_url":"https://github.com/ThomasGoerttler/similarity-analysis-of-maml/blob/HEAD/rsa.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2bdaad0e5c106937"}},{"code_sha256_prefix":"980919fe451414a1","entry":"get_images","repo":"ThomasGoerttler/similarity-analysis-of-maml","repo_kind":"official","path":"utils.py","file_url":"https://github.com/ThomasGoerttler/similarity-analysis-of-maml/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"980919fe451414a1"}},{"code_sha256_prefix":"c50c4337791765c9","entry":"rdm_of_rdms","repo":"ThomasGoerttler/similarity-analysis-of-maml","repo_kind":"official","path":"rsa.py","file_url":"https://github.com/ThomasGoerttler/similarity-analysis-of-maml/blob/HEAD/rsa.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c50c4337791765c9"}},{"code_sha256_prefix":"d22eb538fd47123f","entry":"reshape_elems_of_list","repo":"ThomasGoerttler/similarity-analysis-of-maml","repo_kind":"official","path":"mnist.py","file_url":"https://github.com/ThomasGoerttler/similarity-analysis-of-maml/blob/HEAD/mnist.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d22eb538fd47123f"}},{"code_sha256_prefix":"abbeec32c09f04da","entry":"rsa","repo":"ThomasGoerttler/similarity-analysis-of-maml","repo_kind":"official","path":"rsa.py","file_url":"https://github.com/ThomasGoerttler/similarity-analysis-of-maml/blob/HEAD/rsa.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"abbeec32c09f04da"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}