{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/maml","slug":"maml","name":"MAML","full_name":"Model-Agnostic Meta-Learning","full_name_withheld":false,"description_markdown":"**MAML**, or **Model-Agnostic Meta-Learning**, is a model and task-agnostic algorithm for meta-learning that trains a model’s parameters such that a small number of gradient updates will lead to fast learning on a new task.\r\n\r\nConsider a model represented by a parametrized function $f\\_{\\theta}$ with parameters $\\theta$. When adapting to a new task $\\mathcal{T}\\_{i}$, the model’s parameters $\\theta$ become $\\theta'\\_{i}$. With MAML, the updated parameter vector $\\theta'\\_{i}$ is computed using one or more gradient descent updates on task $\\mathcal{T}\\_{i}$. For example, when using one gradient update,\r\n\r\n$$ \\theta'\\_{i} = \\theta - \\alpha\\nabla\\_{\\theta}\\mathcal{L}\\_{\\mathcal{T}\\_{i}}\\left(f\\_{\\theta}\\right) $$\r\n\r\nThe step size $\\alpha$ may be fixed as a hyperparameter or metalearned. The model parameters are trained by optimizing for the performance of $f\\_{\\theta'\\_{i}}$ with respect to $\\theta$ across tasks sampled from $p\\left(\\mathcal{T}\\_{i}\\right)$. More concretely the meta-objective is as follows:\r\n\r\n$$ \\min\\_{\\theta} \\sum\\_{\\mathcal{T}\\_{i} \\sim p\\left(\\mathcal{T}\\right)} \\mathcal{L}\\_{\\mathcal{T\\_{i}}}\\left(f\\_{\\theta'\\_{i}}\\right) = \\sum\\_{\\mathcal{T}\\_{i} \\sim p\\left(\\mathcal{T}\\right)} \\mathcal{L}\\_{\\mathcal{T\\_{i}}}\\left(f\\_{\\theta - \\alpha\\nabla\\_{\\theta}\\mathcal{L}\\_{\\mathcal{T}\\_{i}}\\left(f\\_{\\theta}\\right)}\\right) $$\r\n\r\nNote that the meta-optimization is performed over the model parameters $\\theta$, whereas the objective is computed using the updated model parameters $\\theta'$. In effect MAML aims to optimize the model parameters such that one or a small number of gradient steps on a new task will produce maximally effective behavior on that task. The meta-optimization across tasks is performed via stochastic gradient descent ([SGD](https://paperswithcode.com/method/sgd)), such that the model parameters $\\theta$ are updated as follows:\r\n\r\n$$ \\theta \\leftarrow \\theta - \\beta\\nabla\\_{\\theta} \\sum\\_{\\mathcal{T}\\_{i} \\sim p\\left(\\mathcal{T}\\right)} \\mathcal{L}\\_{\\mathcal{T\\_{i}}}\\left(f\\_{\\theta'\\_{i}}\\right)$$\r\n\r\nwhere $\\beta$ is the meta step size.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"http://arxiv.org/abs/1703.03400v3","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/cbfinn/maml/blob/a7f45f1bcd7457fe97b227a21e89b8a82cc5fa49/maml.py#L17","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Meta-Learning Algorithms","url":"/methods/category/meta-learning-algorithms","pwc_aliases":[]}],"n_papers_tagged":232,"archive_num_papers":null,"papers_newest_first":[{"paper":null,"slug":"joint-antenna-position-and-transmit-power","title":"Joint Antenna Position and Transmit Power Optimization for Pinching Antenna-Assisted ISAC Systems","date":"2025-03-17","arxiv_id":"2503.12872","n_code_links":0,"syntology":null},{"paper":null,"slug":"riemannian-geometric-based-meta-learning","title":"Riemannian Geometric-based Meta Learning","date":"2025-03-14","arxiv_id":"2503.10993","n_code_links":0,"syntology":null},{"paper":null,"slug":"resilient-uav-trajectory-planning-via-few","title":"Resilient UAV Trajectory Planning via Few-Shot Meta-Offline Reinforcement Learning","date":"2025-02-03","arxiv_id":"2502.01268","n_code_links":0,"syntology":null},{"paper":null,"slug":"age-and-power-minimization-via-meta-deep","title":"Age and Power Minimization via Meta-Deep Reinforcement Learning in UAV Networks","date":"2025-01-24","arxiv_id":"2501.14603","n_code_links":0,"syntology":null},{"paper":null,"slug":"tlxml-task-level-explanation-of-meta-learning","title":"TLXML: Task-Level Explanation of Meta-Learning via Influence Functions","date":"2025-01-24","arxiv_id":"2501.14271","n_code_links":0,"syntology":null},{"paper":null,"slug":"one-class-domain-adaptation-via-meta-learning","title":"One-Class Domain Adaptation via Meta-Learning","date":"2025-01-22","arxiv_id":"2501.13052","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-efficacy-of-meta-learning","title":"Exploring the Efficacy of Meta-Learning: Unveiling Superior Data Diversity Utilization of MAML Over Pre-training","date":"2025-01-15","arxiv_id":"2501.08506","n_code_links":0,"syntology":null},{"paper":null,"slug":"memory-reduced-meta-learning-with-guaranteed","title":"Memory-Reduced Meta-Learning with Guaranteed Convergence","date":"2024-12-16","arxiv_id":"2412.12030","n_code_links":0,"syntology":null},{"paper":null,"slug":"fast-adaptation-with-kernel-and-gradient","title":"Fast Adaptation with Kernel and Gradient based Meta Leaning","date":"2024-11-01","arxiv_id":"2411.00404","n_code_links":0,"syntology":null},{"paper":null,"slug":"meta-learning-driven-adaptive-codebook-design","title":"Meta-Learning-Driven Adaptive Codebook Design for Near-Field Communications","date":"2024-10-10","arxiv_id":"2410.08318","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-new-first-order-meta-learning-algorithm","title":"A New First-Order Meta-Learning Algorithm with Convergence Guarantees","date":"2024-09-05","arxiv_id":"2409.03682","n_code_links":0,"syntology":null},{"paper":"/paper/arcle-the-abstraction-and-reasoning-corpus","slug":"arcle-the-abstraction-and-reasoning-corpus","title":"ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning","date":"2024-07-30","arxiv_id":"2407.20806","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["confeitohs/arcle"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"agnostic-sharpness-aware-minimization","title":"Agnostic Sharpness-Aware Minimization","date":"2024-06-11","arxiv_id":"2406.07107","n_code_links":0,"syntology":null},{"paper":"/paper/cooperative-meta-learning-with-gradient","slug":"cooperative-meta-learning-with-gradient","title":"Cooperative Meta-Learning with Gradient Augmentation","date":"2024-06-07","arxiv_id":"2406.04639","n_code_links":1,"syntology":null},{"paper":null,"slug":"privacy-challenges-in-meta-learning-an","title":"Privacy Challenges in Meta-Learning: An Investigation on Model-Agnostic Meta-Learning","date":"2024-06-01","arxiv_id":"2406.00249","n_code_links":0,"syntology":null},{"paper":null,"slug":"maml-mot-multiple-object-tracking-based-on","title":"MAML MOT: Multiple Object Tracking based on Meta-Learning","date":"2024-05-12","arxiv_id":"2405.07272","n_code_links":0,"syntology":null},{"paper":null,"slug":"lasso-ridge-based-xgboost-and-deep-lstm-help","title":"Lasso Ridge based XGBoost and Deep_LSTM Help Tennis Players Perform better","date":"2024-05-11","arxiv_id":"2405.07030","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-fast-adaptability-of-neural","slug":"evaluating-fast-adaptability-of-neural","title":"Evaluating Fast Adaptability of Neural Networks for Brain-Computer Interface","date":"2024-04-14","arxiv_id":"2404.15350","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-to-learn-the-wave-angle-estimation","title":"Learning-to-Learn the Wave Angle Estimation","date":"2024-03-21","arxiv_id":"2403.14306","n_code_links":0,"syntology":null},{"paper":"/paper/zero-shot-ecg-classification-with-multimodal","slug":"zero-shot-ecg-classification-with-multimodal","title":"Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancement","date":"2024-03-11","arxiv_id":"2403.06659","n_code_links":2,"syntology":{"ran":8,"of":12,"n_ran_checked":5,"n_instrument":3,"unverified":4,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["cheliu-computation/merl"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/decomposed-meta-learning-for-few-shot","slug":"decomposed-meta-learning-for-few-shot","title":"Decomposed Meta-Learning for Few-Shot Sequence Labeling","date":"2024-03-04","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"forml-a-riemannian-hessian-free-method-for","title":"FORML: A Riemannian Hessian-free Method for Meta-learning on Stiefel Manifolds","date":"2024-02-28","arxiv_id":"2402.18605","n_code_links":0,"syntology":null},{"paper":null,"slug":"jointly-learning-representations-for-map","title":"Jointly Learning Representations for Map Entities via Heterogeneous Graph Contrastive Learning","date":"2024-02-09","arxiv_id":"2402.06135","n_code_links":0,"syntology":null},{"paper":"/paper/predicting-configuration-performance-in","slug":"predicting-configuration-performance-in","title":"Predicting Configuration Performance in Multiple Environments with Sequential Meta-learning","date":"2024-02-05","arxiv_id":"2402.03183","n_code_links":1,"syntology":null},{"paper":null,"slug":"rethinking-the-starting-point-enhancing","title":"Rethinking the Starting Point: Collaborative Pre-Training for Federated Downstream Tasks","date":"2024-02-03","arxiv_id":"2402.02225","n_code_links":0,"syntology":null},{"paper":null,"slug":"dk-slam-monocular-visual-slam-with-deep","title":"DK-SLAM: Monocular Visual SLAM with Deep Keypoint Learning, Tracking and Loop-Closing","date":"2024-01-17","arxiv_id":"2401.09160","n_code_links":0,"syntology":null},{"paper":null,"slug":"any-way-meta-learning","title":"Any-Way Meta Learning","date":"2024-01-10","arxiv_id":"2401.05097","n_code_links":0,"syntology":null},{"paper":"/paper/are-lstms-good-few-shot-learners","slug":"are-lstms-good-few-shot-learners","title":"Are LSTMs Good Few-Shot Learners?","date":"2023-10-22","arxiv_id":"2310.14139","n_code_links":1,"syntology":null},{"paper":"/paper/understanding-transfer-learning-and-gradient","slug":"understanding-transfer-learning-and-gradient","title":"Understanding Transfer Learning and Gradient-Based Meta-Learning Techniques","date":"2023-10-09","arxiv_id":"2310.06148","n_code_links":1,"syntology":null},{"paper":null,"slug":"task-aware-modulation-using-representation","title":"Task Aware Modulation using Representation Learning: An Approach for Few Shot Learning in Environmental Systems","date":"2023-10-07","arxiv_id":"2310.04727","n_code_links":0,"syntology":null},{"paper":null,"slug":"federated-conditional-stochastic-optimization","title":"Federated Conditional Stochastic Optimization","date":"2023-10-04","arxiv_id":"2310.02524","n_code_links":0,"syntology":null},{"paper":null,"slug":"multilingual-sentence-level-semantic-search","title":"Multilingual Sentence-Level Semantic Search using Meta-Distillation Learning","date":"2023-09-15","arxiv_id":"2309.08185","n_code_links":0,"syntology":null},{"paper":null,"slug":"convergence-of-gradient-based-maml-in-lqr","title":"Convergence of Gradient-based MAML in LQR","date":"2023-09-12","arxiv_id":"2309.06588","n_code_links":0,"syntology":null},{"paper":null,"slug":"bridging-the-reality-gap-of-reinforcement","title":"Bridging the Reality Gap of Reinforcement Learning based Traffic Signal Control using Domain Randomization and Meta Learning","date":"2023-07-21","arxiv_id":"2307.11357","n_code_links":0,"syntology":null},{"paper":"/paper/writer-adaptation-for-offline-text","slug":"writer-adaptation-for-offline-text","title":"Writer adaptation for offline text recognition: An exploration of neural network-based methods","date":"2023-07-11","arxiv_id":"2307.15071","n_code_links":1,"syntology":null},{"paper":null,"slug":"film-how-can-few-shot-image-classification","title":"FILM: How can Few-Shot Image Classification Benefit from Pre-Trained Language Models?","date":"2023-07-09","arxiv_id":"2307.04114","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-pre-training-truly-better-than-meta","title":"Is Pre-training Truly Better Than Meta-Learning?","date":"2023-06-24","arxiv_id":"2306.13841","n_code_links":0,"syntology":null},{"paper":"/paper/a-hierarchical-bayesian-model-for-deep-few","slug":"a-hierarchical-bayesian-model-for-deep-few","title":"A Hierarchical Bayesian Model for Deep Few-Shot Meta Learning","date":"2023-06-16","arxiv_id":"2306.09702","n_code_links":1,"syntology":null},{"paper":null,"slug":"meta-learning-for-vision-and-language-cross","title":"Meta-learning For Vision-and-language Cross-lingual Transfer","date":"2023-05-24","arxiv_id":"2305.14843","n_code_links":0,"syntology":null},{"paper":null,"slug":"generalizable-deep-learning-method-for","title":"Generalizable Deep Learning Method for Suppressing Unseen and Multiple MRI Artifacts Using Meta-learning","date":"2023-04-13","arxiv_id":"2304.06378","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-learn-with-indispensable","title":"Learning to Learn with Indispensable Connections","date":"2023-04-06","arxiv_id":"2304.02862","n_code_links":0,"syntology":null},{"paper":"/paper/meta-learning-with-a-geometry-adaptive","slug":"meta-learning-with-a-geometry-adaptive","title":"Meta-Learning with a Geometry-Adaptive Preconditioner","date":"2023-04-04","arxiv_id":"2304.01552","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["suhyun777/cvpr23-gap"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-comparison-of-small-sample-methods-for","slug":"a-comparison-of-small-sample-methods-for","title":"A comparison of small sample methods for Handshape Recognition","date":"2023-04-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"automated-federated-learning-in-mobile-edge","title":"Automated Federated Learning in Mobile Edge Networks -- Fast Adaptation and Convergence","date":"2023-03-23","arxiv_id":"2303.12999","n_code_links":0,"syntology":null},{"paper":null,"slug":"model-agnostic-meta-learning-for-natural","title":"Model-Agnostic Meta-Learning for Natural Language Understanding Tasks in Finance","date":"2023-03-06","arxiv_id":"2303.02841","n_code_links":0,"syntology":null},{"paper":"/paper/harnessing-simulation-for-molecular","slug":"harnessing-simulation-for-molecular","title":"Implicit Geometry and Interaction Embeddings Improve Few-Shot Molecular Property Prediction","date":"2023-02-04","arxiv_id":"2302.02055","n_code_links":1,"syntology":null},{"paper":null,"slug":"convergence-of-first-order-algorithms-for","title":"Convergence of First-Order Algorithms for Meta-Learning with Moreau Envelopes","date":"2023-01-17","arxiv_id":"2301.06806","n_code_links":0,"syntology":null},{"paper":null,"slug":"level-k-meta-learning-for-pedestrian-aware","title":"Cognitive Level-$k$ Meta-Learning for Safe and Pedestrian-Aware Autonomous Driving","date":"2022-12-17","arxiv_id":"2212.08800","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-energy-and-communication-efficiency","title":"On the Energy and Communication Efficiency Tradeoffs in Federated and Multi-Task Learning","date":"2022-12-02","arxiv_id":"2212.01049","n_code_links":0,"syntology":null},{"paper":null,"slug":"rethinking-the-number-of-shots-in-robust","title":"Rethinking the Number of Shots in Robust Model-Agnostic Meta-Learning","date":"2022-11-28","arxiv_id":"2211.15180","n_code_links":0,"syntology":null},{"paper":null,"slug":"meta-learning-of-neural-state-space-models","title":"Meta-Learning of Neural State-Space Models Using Data From Similar Systems","date":"2022-11-14","arxiv_id":"2211.07768","n_code_links":0,"syntology":null},{"paper":"/paper/metaloc-learning-to-learn-wireless","slug":"metaloc-learning-to-learn-wireless","title":"MetaLoc: Learning to Learn Wireless Localization","date":"2022-11-08","arxiv_id":"2211.04258","n_code_links":0,"syntology":null},{"paper":null,"slug":"boosting-natural-language-generation-from","title":"Boosting Natural Language Generation from Instructions with Meta-Learning","date":"2022-10-20","arxiv_id":"2210.11617","n_code_links":0,"syntology":null},{"paper":"/paper/incorporating-relevance-feedback-for","slug":"incorporating-relevance-feedback-for","title":"Incorporating Relevance Feedback for Information-Seeking Retrieval using Few-Shot Document Re-Ranking","date":"2022-10-19","arxiv_id":"2210.10695","n_code_links":1,"syntology":null},{"paper":"/paper/multi-modal-fusion-by-meta-initialization","slug":"multi-modal-fusion-by-meta-initialization","title":"Multi-Modal Fusion by Meta-Initialization","date":"2022-10-10","arxiv_id":"2210.04843","n_code_links":1,"syntology":null},{"paper":"/paper/hypernetwork-approach-to-bayesian-maml","slug":"hypernetwork-approach-to-bayesian-maml","title":"Hypernetwork approach to Bayesian MAML","date":"2022-10-06","arxiv_id":"2210.02796","n_code_links":1,"syntology":null},{"paper":null,"slug":"persa-fl-personalized-asynchronous-federated","title":"PersA-FL: Personalized Asynchronous Federated Learning","date":"2022-10-03","arxiv_id":"2210.01176","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-clustering-based-pseudo-labeling","slug":"rethinking-clustering-based-pseudo-labeling","title":"Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning","date":"2022-09-27","arxiv_id":"2209.13635","n_code_links":1,"syntology":null},{"paper":null,"slug":"mac-a-meta-learning-approach-for-feature","title":"MAC: A Meta-Learning Approach for Feature Learning and Recombination","date":"2022-09-20","arxiv_id":"2209.09613","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-study-on-representation-transfer-for-few-1","title":"A Study on Representation Transfer for Few-Shot Learning","date":"2022-09-05","arxiv_id":"2209.02073","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-game-theoretic-perspective-of","title":"A Game-Theoretic Perspective of Generalization in Reinforcement Learning","date":"2022-08-07","arxiv_id":"2208.03650","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-curse-of-low-task-diversity-on-the","title":"The Curse of Low Task Diversity: On the Failure of Transfer Learning to Outperform MAML and Their Empirical Equivalence","date":"2022-08-02","arxiv_id":"2208.01545","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-sleep-scoring-generalization-through","title":"Towards Sleep Scoring Generalization Through Self-Supervised Meta-Learning","date":"2022-07-27","arxiv_id":"2207.13801","n_code_links":0,"syntology":null},{"paper":null,"slug":"generating-pseudo-labels-adaptively-for-few","title":"Generating Pseudo-labels Adaptively for Few-shot Model-Agnostic Meta-Learning","date":"2022-07-09","arxiv_id":"2207.04217","n_code_links":0,"syntology":null},{"paper":"/paper/fewsol-a-dataset-for-few-shot-object-learning","slug":"fewsol-a-dataset-for-few-shot-object-learning","title":"FewSOL: A Dataset for Few-Shot Object Learning in Robotic Environments","date":"2022-07-06","arxiv_id":"2207.03333","n_code_links":3,"syntology":null},{"paper":"/paper/adaptive-fine-grained-sketch-based-image","slug":"adaptive-fine-grained-sketch-based-image","title":"Adaptive Fine-Grained Sketch-Based Image Retrieval","date":"2022-07-04","arxiv_id":"2207.01723","n_code_links":1,"syntology":null},{"paper":null,"slug":"provable-generalization-of-overparameterized","title":"Provable Generalization of Overparameterized Meta-learning Trained with SGD","date":"2022-06-18","arxiv_id":"2206.09136","n_code_links":0,"syntology":null},{"paper":null,"slug":"faster-optimization-based-meta-learning","title":"Faster Optimization-Based Meta-Learning Adaptation Phase","date":"2022-06-13","arxiv_id":"2206.05930","n_code_links":0,"syntology":null},{"paper":"/paper/sharp-maml-sharpness-aware-model-agnostic","slug":"sharp-maml-sharpness-aware-model-agnostic","title":"Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning","date":"2022-06-08","arxiv_id":"2206.03996","n_code_links":1,"syntology":null},{"paper":"/paper/hypermaml-few-shot-adaptation-of-deep-models","slug":"hypermaml-few-shot-adaptation-of-deep-models","title":"HyperMAML: Few-Shot Adaptation of Deep Models with Hypernetworks","date":"2022-05-31","arxiv_id":"2205.15745","n_code_links":1,"syntology":null},{"paper":"/paper/meta-ticket-finding-optimal-subnetworks-for","slug":"meta-ticket-finding-optimal-subnetworks-for","title":"Meta-ticket: Finding optimal subnetworks for few-shot learning within randomly initialized neural networks","date":"2022-05-31","arxiv_id":"2205.15619","n_code_links":1,"syntology":null},{"paper":null,"slug":"know-where-you-re-going-meta-learning-for","title":"Know Where You're Going: Meta-Learning for Parameter-Efficient Fine-Tuning","date":"2022-05-25","arxiv_id":"2205.12453","n_code_links":0,"syntology":null},{"paper":null,"slug":"improved-meta-learning-for-low-resource","title":"Improved Meta Learning for Low Resource Speech Recognition","date":"2022-05-11","arxiv_id":"2205.06182","n_code_links":0,"syntology":null},{"paper":"/paper/metaaudio-a-few-shot-audio-classification","slug":"metaaudio-a-few-shot-audio-classification","title":"MetaAudio: A Few-Shot Audio Classification Benchmark","date":"2022-04-05","arxiv_id":"2204.02121","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["cheggan/metaaudio-a-few-shot-audio-classification-benchmark"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"selecting-task-with-optimal-transport-self","title":"Selecting task with optimal transport self-supervised learning for few-shot classification","date":"2022-04-01","arxiv_id":"2204.00289","n_code_links":0,"syntology":null},{"paper":null,"slug":"negative-inner-loop-learning-rates-learn","title":"Negative Inner-Loop Learning Rates Learn Universal Features","date":"2022-03-18","arxiv_id":"2203.10185","n_code_links":0,"syntology":null},{"paper":"/paper/global-convergence-of-maml-and-theory","slug":"global-convergence-of-maml-and-theory","title":"Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning","date":"2022-03-17","arxiv_id":"2203.09137","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":1,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yitewang/metantk-nas"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/model-agnostic-multitask-fine-tuning-for-few","slug":"model-agnostic-multitask-fine-tuning-for-few","title":"Rethinking Task Sampling for Few-shot Vision-Language Transfer Learning","date":"2022-03-09","arxiv_id":"2203.04904","n_code_links":1,"syntology":null},{"paper":"/paper/what-matters-for-meta-learning-vision","slug":"what-matters-for-meta-learning-vision","title":"What Matters For Meta-Learning Vision Regression Tasks?","date":"2022-03-09","arxiv_id":"2203.04905","n_code_links":2,"syntology":null},{"paper":"/paper/is-bayesian-model-agnostic-meta-learning","slug":"is-bayesian-model-agnostic-meta-learning","title":"Is Bayesian Model-Agnostic Meta Learning Better than Model-Agnostic Meta Learning, Provably?","date":"2022-03-06","arxiv_id":"2203.03059","n_code_links":1,"syntology":null},{"paper":null,"slug":"metava-curriculum-meta-learning-and-pre-fine","title":"MetaVA: Curriculum Meta-learning and Pre-fine-tuning of Deep Neural Networks for Detecting Ventricular Arrhythmias based on ECGs","date":"2022-02-25","arxiv_id":"2202.12450","n_code_links":0,"syntology":null},{"paper":null,"slug":"maml-and-anil-provably-learn-representations","title":"MAML and ANIL Provably Learn Representations","date":"2022-02-07","arxiv_id":"2202.03483","n_code_links":0,"syntology":null},{"paper":"/paper/platinum-semi-supervised-model-agnostic-meta","slug":"platinum-semi-supervised-model-agnostic-meta","title":"PLATINUM: Semi-Supervised Model Agnostic Meta-Learning using Submodular Mutual Information","date":"2022-01-30","arxiv_id":"2201.12928","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hugo101/platinum"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/the-effect-of-diversity-in-meta-learning-1","slug":"the-effect-of-diversity-in-meta-learning-1","title":"The Effect of Diversity in Meta-Learning","date":"2022-01-27","arxiv_id":"2201.11775","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["RamnathKumar181/Task-Diversity-meta-learning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/meta-learning-spiking-neural-networks-with","slug":"meta-learning-spiking-neural-networks-with","title":"Meta-learning Spiking Neural Networks with Surrogate Gradient Descent","date":"2022-01-26","arxiv_id":"2201.10777","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":5,"n_instrument":2,"unverified":2,"pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":null,"slug":"representation-change-in-model-agnostic-meta","title":"Representation Change in Model-Agnostic Meta-Learning","date":"2022-01-17","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"2112-13906","title":"Does CLIP Benefit Visual Question Answering in the Medical Domain as Much as it Does in the General Domain?","date":"2021-12-27","arxiv_id":"2112.13906","n_code_links":0,"syntology":null},{"paper":"/paper/does-maml-only-work-via-feature-re-use-a-data","slug":"does-maml-only-work-via-feature-re-use-a-data","title":"Does MAML Only Work via Feature Re-use? A Data Centric Perspective","date":"2021-12-24","arxiv_id":"2112.13137","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-curse-of-zero-task-diversity-on-the","title":"The Curse of Zero Task Diversity: On the Failure of Transfer Learning to Outperform MAML and their Empirical Equivalence","date":"2021-12-24","arxiv_id":"2112.13121","n_code_links":0,"syntology":null},{"paper":null,"slug":"implicit-neural-representations-for-image","title":"Implicit Neural Representations for Image Compression","date":"2021-12-08","arxiv_id":"2112.04267","n_code_links":0,"syntology":null},{"paper":"/paper/curriculum-meta-learning-for-few-shot","slug":"curriculum-meta-learning-for-few-shot","title":"Curriculum Meta-Learning for Few-shot Classification","date":"2021-12-06","arxiv_id":"2112.02913","n_code_links":1,"syntology":null},{"paper":"/paper/camera-distortion-aware-3d-human-pose-1","slug":"camera-distortion-aware-3d-human-pose-1","title":"Camera Distortion-aware 3D Human Pose Estimation in Video with Optimization-based Meta-Learning","date":"2021-11-30","arxiv_id":"2111.15056","n_code_links":1,"syntology":null},{"paper":null,"slug":"confounder-identification-free-causal-visual","title":"Confounder Identification-free Causal Visual Feature Learning","date":"2021-11-26","arxiv_id":"2111.13420","n_code_links":0,"syntology":null},{"paper":null,"slug":"daml-chinese-named-entity-recognition-with-a","title":"DAML: Chinese Named Entity Recognition with a fusion method of data-augmentation and meta-learning","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/maml-cl-edited-model-agnostic-meta-learning","slug":"maml-cl-edited-model-agnostic-meta-learning","title":"MAML-CL: Edited Model-Agnostic Meta-Learning for Continual Learning","date":"2021-11-16","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"meta-learning-via-language-model-in-context-1","title":"Meta-learning via Language Model In-context Tuning","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"accelerating-gradient-based-meta-learner","title":"Accelerating Gradient-based Meta Learner","date":"2021-10-27","arxiv_id":"2110.14459","n_code_links":0,"syntology":null},{"paper":"/paper/contextual-gradient-scaling-for-few-shot","slug":"contextual-gradient-scaling-for-few-shot","title":"Contextual Gradient Scaling for Few-Shot Learning","date":"2021-10-20","arxiv_id":"2110.10353","n_code_links":1,"syntology":null},{"paper":null,"slug":"meta-learning-with-adjoint-methods","title":"Meta-Learning with Adjoint Methods","date":"2021-10-16","arxiv_id":"2110.08432","n_code_links":0,"syntology":null},{"paper":"/paper/meta-learning-via-language-model-in-context","slug":"meta-learning-via-language-model-in-context","title":"Meta-learning via Language Model In-context Tuning","date":"2021-10-15","arxiv_id":"2110.07814","n_code_links":1,"syntology":null}],"papers_shown":100,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":232,"with_a_code_link":90,"where_syntology_ran_a_sample":28,"not_listed_spam_title":0,"listed":232,"listed_where_code_ran":28,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":18,"every_run_a_failure_of_syntologys_instrument":10,"listed_with_a_run_with_no_instrument_failure":18,"listed_every_run_a_failure_of_syntologys_instrument":10,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":28,"papers_where_code_ran_first_page":"/method/maml/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"archive","page":2,"of":3,"url":"/method/maml/papers/2","json":"/method/maml/papers/2.json","rows":100},{"order":"archive","page":3,"of":3,"url":"/method/maml/papers/3","json":"/method/maml/papers/3.json","rows":32},{"order":"ran","page":1,"of":1,"url":"/method/maml/papers/ran/1","json":"/method/maml/papers/ran/1.json","rows":28}],"tasks":[{"task":"/task/meta-learning","name":"Meta-Learning","papers":208},{"task":"/task/few-shot-learning","name":"Few-Shot Learning","papers":71},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":23},{"task":"/task/image-classification","name":"Image Classification","papers":22},{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":21},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":20},{"task":"/task/image-classification","name":"image-classification","papers":20},{"task":"/task/few-shot-image-classification","name":"Few-Shot Image Classification","papers":17},{"task":"/task/reinforcement-learning-2","name":"reinforcement-learning","papers":17},{"task":"/task/classification","name":"General Classification","papers":16},{"task":"/task/classification-1","name":"Classification","papers":12},{"task":"/task/diversity","name":"Diversity","papers":11},{"task":"/task/federated-learning","name":"Federated Learning","papers":11},{"task":"/task/model","name":"model","papers":11},{"task":"/task/meta-reinforcement-learning","name":"Meta Reinforcement Learning","papers":9},{"task":"/task/representation-learning","name":"Representation Learning","papers":9},{"task":"/task/domain-adaptation","name":"Domain Adaptation","papers":7},{"task":"/task/regression-1","name":"regression","papers":7},{"task":"/task/continual-learning","name":"Continual Learning","papers":6},{"task":"/task/language-modeling","name":"Language Modeling","papers":6}],"tasks_shown":20,"n_tasks":218,"usage_by_year":[{"year":"2017","papers":2},{"year":"2018","papers":11},{"year":"2019","papers":27},{"year":"2020","papers":45},{"year":"2021","papers":61},{"year":"2022","papers":39},{"year":"2023","papers":20},{"year":"2024","papers":20},{"year":"2025","papers":7}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/maml"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=MAML","read_at":"2026-10-05T00:58:54+00:00","query":"MAML","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":null,"repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'MAML' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["Q-MAML","La-MAML","MAML-KT","UNICORN-MAML","Minimax MAML","Stiefel-MAML","MAML-ProtoNet","implicit MAML"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"1ad200d92984f3bed9500123d0c05dd562f549e4e44594e0242e31d8d28cd325","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}