{"url":"/task/meta-learning","name":"Meta-Learning","slug":"meta-learning","description_markdown":"Meta-learning is a methodology considered with \"learning to learn\" machine learning algorithms.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://arxiv.org/pdf/1703.03400v3.pdf) )</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":3569,"papers_with_code":1408,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":17,"subtasks":3,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/meta-learning-on-ml10","slug":"meta-learning-on-ml10","dataset":"ML10","dataset_url":null,"rows_in_archive":6,"metrics":["Meta-test success rate","Meta-train success rate","Meta-test success rate (zero-shot)"],"first_row_in_archive_order":{"model":"MAML","paper_title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","paper_url":"/paper/meta-world-a-benchmark-and-evaluation-for","paper_date":"2019-10-24","arxiv_id":"1910.10897","code_links":[{"title":"rlworkgroup/metaworld","url":"https://github.com/rlworkgroup/metaworld"},{"title":"farama-foundation/metaworld","url":"https://github.com/farama-foundation/metaworld"},{"title":"avivne/bilinear-transduction","url":"https://github.com/avivne/bilinear-transduction"},{"title":"uoe-agents/sami","url":"https://github.com/uoe-agents/sami"},{"title":"RamnathKumar181/Adversarial-Learning-Dynamics-in-RL","url":"https://github.com/RamnathKumar181/Adversarial-Learning-Dynamics-in-RL"},{"title":"yiwc/robotics-world","url":"https://github.com/yiwc/robotics-world"},{"title":"mazpie/mime","url":"https://github.com/mazpie/mime"},{"title":"EdNiehues/simulacao-de-projeto-para-mapeamento","url":"https://github.com/EdNiehues/simulacao-de-projeto-para-mapeamento"},{"title":"CAVED123/METAWORLD","url":"https://github.com/CAVED123/METAWORLD"}],"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}}},{"leaderboard":"/sota/meta-learning-on-mt50","slug":"meta-learning-on-mt50","dataset":"MT50","dataset_url":null,"rows_in_archive":4,"metrics":["Average Success Rate"],"first_row_in_archive_order":{"model":"SoftModule","paper_title":"Multi-Task Reinforcement Learning with Soft Modularization","paper_url":"/paper/multi-task-reinforcement-learning-with-soft","paper_date":"2020-03-30","arxiv_id":"2003.13661","code_links":[{"title":"RchalYang/Soft-Module","url":"https://github.com/RchalYang/Soft-Module"}],"syntology":null}},{"leaderboard":"/sota/meta-learning-on-ml45","slug":"meta-learning-on-ml45","dataset":"ML45","dataset_url":null,"rows_in_archive":2,"metrics":["Meta-test success rate (zero-shot)","Meta-train success rate"],"first_row_in_archive_order":{"model":"MZ+Recon","paper_title":"Procedural Generalization by Planning with Self-Supervised World Models","paper_url":"/paper/procedural-generalization-by-planning-with-1","paper_date":"2021-11-02","arxiv_id":"2111.01587","code_links":[],"syntology":null}},{"leaderboard":"/sota/meta-learning-on-omniglot-1-shot-20-way","slug":"meta-learning-on-omniglot-1-shot-20-way","dataset":"OMNIGLOT - 1-Shot, 20-way","dataset_url":null,"rows_in_archive":1,"metrics":["% Test Accuracy"],"first_row_in_archive_order":{"model":"Metadrop","paper_title":"Meta Dropout: Learning to Perturb Latent Features for Generalization","paper_url":"/paper/meta-dropout-learning-to-perturb-latent","paper_date":"2020-05-01","arxiv_id":null,"code_links":[{"title":"haebeom-lee/metadrop","url":"https://github.com/haebeom-lee/metadrop"},{"title":"joeljosephjin/metadrop-pytorch","url":"https://github.com/joeljosephjin/metadrop-pytorch"}],"syntology":null}}],"datasets":[{"url":"/dataset/meta-dataset","name":"Meta-Dataset","full_name":"","num_papers_in_archive":128},{"url":"/dataset/m4","name":"M4","full_name":"","num_papers_in_archive":110},{"url":"/dataset/blendedmvs","name":"BlendedMVS","full_name":"","num_papers_in_archive":105},{"url":"/dataset/meta-world-benchmark","name":"Meta-World Benchmark","full_name":"","num_papers_in_archive":73},{"url":"/dataset/tydiqa-goldp","name":"TyDiQA-GoldP","full_name":"TyDiQA-GoldP","num_papers_in_archive":38},{"url":"/dataset/mq2007","name":"MQ2007","full_name":"","num_papers_in_archive":32},{"url":"/dataset/extremeweather","name":"ExtremeWeather","full_name":"","num_papers_in_archive":21},{"url":"/dataset/kuzushiji-49","name":"Kuzushiji-49","full_name":"","num_papers_in_archive":10},{"url":"/dataset/codebrim","name":"CODEBRIM","full_name":"COncrete DEfect BRidge IMage Dataset","num_papers_in_archive":9},{"url":"/dataset/europeana-newspapers","name":"Europeana Newspapers","full_name":"","num_papers_in_archive":5},{"url":"/dataset/figr-8","name":"FIGR-8","full_name":"","num_papers_in_archive":4},{"url":"/dataset/mex","name":"MEx","full_name":"","num_papers_in_archive":3},{"url":"/dataset/prostate-mri-segmentation-dataset","name":"Prostate MRI Segmentation Dataset","full_name":null,"num_papers_in_archive":3},{"url":"/dataset/l-bird","name":"L-Bird","full_name":"Large-Bird","num_papers_in_archive":2},{"url":"/dataset/tom-in-amc","name":"ToM-in-AMC","full_name":"","num_papers_in_archive":2},{"url":"/dataset/chinese-literature-ner-re","name":"Chinese Literature NER RE","full_name":"","num_papers_in_archive":1},{"url":"/dataset/meta-omnium","name":"Meta Omnium","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/few-shot-learning","name":"Few-Shot Learning"},{"url":"/task/sample-probing","name":"Sample Probing"},{"url":"/task/universal-meta-learning","name":"universal meta-learning"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":1408,"tagged_in_all":3569,"items":[{"url":"/paper/model-agnostic-meta-learning-for-fast","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","date":"2017-03-09","arxiv_id":"1703.03400","repositories_listed":85,"syntology":{"n":154,"n_ran":86,"n_unverified":68,"n_pointer_only":57}},{"url":"/paper/prototypical-networks-for-few-shot-learning","title":"Prototypical Networks for Few-shot Learning","date":"2017-03-15","arxiv_id":"1703.05175","repositories_listed":43,"syntology":{"n":64,"n_ran":49,"n_unverified":15,"n_pointer_only":18}},{"url":"/paper/meta-dataset-a-dataset-of-datasets-for","title":"Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples","date":"2019-03-07","arxiv_id":"1903.03096","repositories_listed":15,"syntology":{"n":11,"n_ran":4,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/on-first-order-meta-learning-algorithms","title":"On First-Order Meta-Learning Algorithms","date":"2018-03-08","arxiv_id":"1803.02999","repositories_listed":13,"syntology":{"n":42,"n_ran":24,"n_unverified":18,"n_pointer_only":13}},{"url":"/paper/learning-to-compare-relation-network-for-few","title":"Learning to Compare: Relation Network for Few-Shot Learning","date":"2017-11-16","arxiv_id":"1711.06025","repositories_listed":13,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/a-new-meta-baseline-for-few-shot-learning","title":"Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning","date":"2020-03-09","arxiv_id":"2003.04390","repositories_listed":10,"syntology":{"n":12,"n_ran":8,"n_unverified":4,"n_pointer_only":1}},{"url":"/paper/how-to-train-your-maml","title":"How to train your MAML","date":"2018-10-22","arxiv_id":"1810.09502","repositories_listed":10,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/meta-learning-for-semi-supervised-few-shot","title":"Meta-Learning for Semi-Supervised Few-Shot Classification","date":"2018-03-02","arxiv_id":"1803.00676","repositories_listed":10,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/meta-pseudo-labels","title":"Meta Pseudo Labels","date":"2020-03-23","arxiv_id":"2003.10580","repositories_listed":9,"syntology":{"n":14,"n_ran":5,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/meta-world-a-benchmark-and-evaluation-for","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","date":"2019-10-24","arxiv_id":"1910.10897","repositories_listed":9,"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/learning-to-reweight-examples-for-robust-deep","title":"Learning to Reweight Examples for Robust Deep Learning","date":"2018-03-24","arxiv_id":"1803.09050","repositories_listed":9,"syntology":null},{"url":"/paper/meta-sgd-learning-to-learn-quickly-for-few","title":"Meta-SGD: Learning to Learn Quickly for Few-Shot Learning","date":"2017-07-31","arxiv_id":"1707.09835","repositories_listed":9,"syntology":null},{"url":"/paper/learning-to-reinforcement-learn","title":"Learning to reinforcement learn","date":"2016-11-17","arxiv_id":"1611.05763","repositories_listed":9,"syntology":{"n":15,"n_ran":3,"n_unverified":12,"n_pointer_only":12}},{"url":"/paper/learning-meta-face-recognition-in-unseen","title":"Learning Meta Face Recognition in Unseen Domains","date":"2020-03-17","arxiv_id":"2003.07733","repositories_listed":8,"syntology":null},{"url":"/paper/learning-to-learn-by-gradient-descent-by","title":"Learning to learn by gradient descent by gradient descent","date":"2016-06-14","arxiv_id":"1606.04474","repositories_listed":8,"syntology":{"n":13,"n_ran":4,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/meta-learning-a-real-time-tabular-automl","title":"TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second","date":"2022-07-05","arxiv_id":"2207.01848","repositories_listed":7,"syntology":{"n":4,"n_ran":1,"n_unverified":3,"n_pointer_only":1}},{"url":"/paper/meta-learning-with-differentiable-convex","title":"Meta-Learning with Differentiable Convex Optimization","date":"2019-04-07","arxiv_id":"1904.03758","repositories_listed":7,"syntology":null},{"url":"/paper/leaf-a-benchmark-for-federated-settings","title":"LEAF: A Benchmark for Federated Settings","date":"2018-12-03","arxiv_id":"1812.01097","repositories_listed":7,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/simpleshot-revisiting-nearest-neighbor","title":"SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning","date":"2019-11-12","arxiv_id":"1911.04623","repositories_listed":6,"syntology":{"n":9,"n_ran":3,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/meta-learning-with-implicit-gradients","title":"Meta-Learning with Implicit Gradients","date":"2019-09-10","arxiv_id":"1909.04630","repositories_listed":6,"syntology":{"n":36,"n_ran":27,"n_unverified":9,"n_pointer_only":10}},{"url":"/paper/meta-learning-representations-for-continual","title":"Meta-Learning Representations for Continual Learning","date":"2019-05-29","arxiv_id":"1905.12588","repositories_listed":6,"syntology":null},{"url":"/paper/few-shot-adversarial-learning-of-realistic","title":"Few-Shot Adversarial Learning of Realistic Neural Talking Head Models","date":"2019-05-20","arxiv_id":"1905.08233","repositories_listed":6,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/promp-proximal-meta-policy-search","title":"ProMP: Proximal Meta-Policy Search","date":"2018-10-16","arxiv_id":"1810.06784","repositories_listed":6,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/collaborative-distillation-meta-learning-for","title":"DevFormer: A Symmetric Transformer for Context-Aware Device Placement","date":"2022-05-26","arxiv_id":"2205.13225","repositories_listed":5,"syntology":{"n":23,"n_ran":13,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/towards-mental-time-travel-a-hierarchical","title":"Towards mental time travel: a hierarchical memory for reinforcement learning agents","date":"2021-05-28","arxiv_id":"2105.14039","repositories_listed":5,"syntology":{"n":6,"n_ran":3,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/evolving-reinforcement-learning-algorithms-1","title":"Evolving Reinforcement Learning Algorithms","date":"2021-01-08","arxiv_id":"2101.03958","repositories_listed":5,"syntology":null},{"url":"/paper/united-we-stand-transfer-graph-neural","title":"Transfer Graph Neural Networks for Pandemic Forecasting","date":"2020-09-10","arxiv_id":"2009.08388","repositories_listed":5,"syntology":null},{"url":"/paper/learning-with-amigo-adversarially-motivated","title":"Learning with AMIGo: Adversarially Motivated Intrinsic Goals","date":"2020-06-22","arxiv_id":"2006.12122","repositories_listed":5,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/frustratingly-simple-few-shot-object","title":"Frustratingly Simple Few-Shot Object Detection","date":"2020-03-16","arxiv_id":"2003.06957","repositories_listed":5,"syntology":{"n":11,"n_ran":3,"n_unverified":8,"n_pointer_only":11}},{"url":"/paper/learning-to-continually-learn","title":"Learning to Continually Learn","date":"2020-02-21","arxiv_id":"2002.09571","repositories_listed":5,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}}],"syntology_records":23,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}