{"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/a-simple-neural-attentive-meta-learner","title":"A Simple Neural Attentive Meta-Learner","arxiv_id":"1707.03141","date":"2017-07-11","proceeding":"ICLR 2018 1","authors":["Nikhil Mishra","Mostafa Rohaninejad","Xi Chen","Pieter Abbeel"],"abstract":"Deep neural networks excel in regimes with large amounts of data, but tend to\nstruggle when data is scarce or when they need to adapt quickly to changes in\nthe task. In response, recent work in meta-learning proposes training a\nmeta-learner on a distribution of similar tasks, in the hopes of generalization\nto novel but related tasks by learning a high-level strategy that captures the\nessence of the problem it is asked to solve. However, many recent meta-learning\napproaches are extensively hand-designed, either using architectures\nspecialized to a particular application, or hard-coding algorithmic components\nthat constrain how the meta-learner solves the task. We propose a class of\nsimple and generic meta-learner architectures that use a novel combination of\ntemporal convolutions and soft attention; the former to aggregate information\nfrom past experience and the latter to pinpoint specific pieces of information.\nIn the most extensive set of meta-learning experiments to date, we evaluate the\nresulting Simple Neural AttentIve Learner (or SNAIL) on several\nheavily-benchmarked tasks. On all tasks, in both supervised and reinforcement\nlearning, SNAIL attains state-of-the-art performance by significant margins.","url_abs":"http://arxiv.org/abs/1707.03141v3","url_pdf":"http://arxiv.org/pdf/1707.03141v3.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":"a-simple-neural-attentive-meta-learner","repo_url":"https://github.com/RobvanGastel/meta-rl-algorithms","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-simple-neural-attentive-meta-learner","repo_url":"https://github.com/eambutu/snail-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"a-simple-neural-attentive-meta-learner","repo_url":"https://github.com/Michedev/snail","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"a-simple-neural-attentive-meta-learner","repo_url":"https://github.com/seujung/SNAIL-gluon","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mxnet","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"few-shot-image-classification","task_name":"Few-Shot Image Classification"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dilated-causal-convolution","method_name":"Dilated Causal Convolution"},{"method_slug":"snail","method_name":"SNAIL"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[{"slug":"snail","name":"SNAIL","full_name":"Simple Neural Attention Meta-Learner"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.03141","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.03141"}},"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/eambutu/snail-pytorch","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Michedev/snail","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/seujung/SNAIL-gluon","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/RobvanGastel/meta-rl-algorithms","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"ran":0,"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":"c007865f9041ab01","entry":"build_snail","repo":"Michedev/snail","repo_kind":"listed","path":"models.py","file_url":"https://github.com/Michedev/snail/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"c007865f9041ab01"}},{"code_sha256_prefix":"0fafdb171d15f3cb","entry":"build_snail_miniimagenet","repo":"Michedev/snail","repo_kind":"listed","path":"models.py","file_url":"https://github.com/Michedev/snail/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"0fafdb171d15f3cb"}},{"code_sha256_prefix":"1938016f58351893","entry":"build_snail_omniglot","repo":"Michedev/snail","repo_kind":"listed","path":"models.py","file_url":"https://github.com/Michedev/snail/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"1938016f58351893"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}