Methods › General › Meta-Learning Algorithms › MAML
Model-Agnostic Meta-Learning
MAML
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
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.
Consider a model represented by a parametrized function f_θ with parameters θ. When adapting to a new task 𝒯ᵢ, the model’s parameters θ become θ′ᵢ. With MAML, the updated parameter vector θ′ᵢ is computed using one or more gradient descent updates on task 𝒯ᵢ. For example, when using one gradient update,
θ′ᵢ = θ- α∇_θℒ_(𝒯ᵢ)(f_θ)
The step size α may be fixed as a hyperparameter or metalearned. The model parameters are trained by optimizing for the performance of f_(θ′ᵢ) with respect to θ across tasks sampled from p(𝒯ᵢ). More concretely the meta-objective is as follows:
min_θ ∑_(𝒯ᵢ ∼p(𝒯)) ℒ_(𝒯ᵢ)(f_(θ′ᵢ)) = ∑_(𝒯ᵢ ∼p(𝒯)) ℒ_(𝒯ᵢ)(f_(θ- α∇_θℒ_(𝒯ᵢ)(f_θ)))
Note that the meta-optimization is performed over the model parameters θ, whereas the objective is computed using the updated model parameters θ′. 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), such that the model parameters θ are updated as follows:
θ←θ- β∇_θ ∑_(𝒯ᵢ ∼p(𝒯)) ℒ_(𝒯ᵢ)(f_(θ′ᵢ))
where β is the meta step size.
In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.
Near matches the lookup lists, each a different name: Q-MAML; La-MAML; MAML-KT; UNICORN-MAML; Minimax MAML; Stiefel-MAML; MAML-ProtoNet; implicit MAML.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 232 · with a code link: 90 · where Syntology ran a sample: 28 (18 with a run with no instrument failure, 10 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (28 of 232 tagged: 18 with a run with no instrument failure, 10 where every run was a failure of Syntology's instrument)
Page 1 of 3: papers 1 to 100 of 232, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Joint Antenna Position and Transmit Power Optimization for Pinching Antenna-Assisted ISAC Systems 17 Mar 2025 · 0 repositories · arXiv:2503.12872
-
Riemannian Geometric-based Meta Learning 14 Mar 2025 · 0 repositories · arXiv:2503.10993
-
Resilient UAV Trajectory Planning via Few-Shot Meta-Offline Reinforcement Learning 3 Feb 2025 · 0 repositories · arXiv:2502.01268
-
Age and Power Minimization via Meta-Deep Reinforcement Learning in UAV Networks 24 Jan 2025 · 0 repositories · arXiv:2501.14603
-
TLXML: Task-Level Explanation of Meta-Learning via Influence Functions 24 Jan 2025 · 0 repositories · arXiv:2501.14271
-
One-Class Domain Adaptation via Meta-Learning 22 Jan 2025 · 0 repositories · arXiv:2501.13052
-
Exploring the Efficacy of Meta-Learning: Unveiling Superior Data Diversity Utilization of MAML Over Pre-training 15 Jan 2025 · 0 repositories · arXiv:2501.08506
-
Memory-Reduced Meta-Learning with Guaranteed Convergence 16 Dec 2024 · 0 repositories · arXiv:2412.12030
-
Fast Adaptation with Kernel and Gradient based Meta Leaning 1 Nov 2024 · 0 repositories · arXiv:2411.00404
-
Meta-Learning-Driven Adaptive Codebook Design for Near-Field Communications 10 Oct 2024 · 0 repositories · arXiv:2410.08318
-
A New First-Order Meta-Learning Algorithm with Convergence Guarantees 5 Sep 2024 · 0 repositories · arXiv:2409.03682
-
ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning 30 Jul 2024 · 1 repository · arXiv:2407.20806Syntology official (archive's flag): 1 ran · 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 (of 1 harvested sample)
-
Agnostic Sharpness-Aware Minimization 11 Jun 2024 · 0 repositories · arXiv:2406.07107
-
Cooperative Meta-Learning with Gradient Augmentation 7 Jun 2024 · 1 repository · arXiv:2406.04639
-
Privacy Challenges in Meta-Learning: An Investigation on Model-Agnostic Meta-Learning 1 Jun 2024 · 0 repositories · arXiv:2406.00249
-
MAML MOT: Multiple Object Tracking based on Meta-Learning 12 May 2024 · 0 repositories · arXiv:2405.07272
-
Lasso Ridge based XGBoost and Deep_LSTM Help Tennis Players Perform better 11 May 2024 · 0 repositories · arXiv:2405.07030
-
Evaluating Fast Adaptability of Neural Networks for Brain-Computer Interface 14 Apr 2024 · 1 repository · arXiv:2404.15350
-
Learning-to-Learn the Wave Angle Estimation 21 Mar 2024 · 0 repositories · arXiv:2403.14306
-
Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancement 11 Mar 2024 · 2 repositories · arXiv:2403.06659Syntology official (archive's flag): 8 ran · 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 (of 12 harvested samples)
-
Decomposed Meta-Learning for Few-Shot Sequence Labeling 4 Mar 2024 · 1 repository
-
FORML: A Riemannian Hessian-free Method for Meta-learning on Stiefel Manifolds 28 Feb 2024 · 0 repositories · arXiv:2402.18605
-
Jointly Learning Representations for Map Entities via Heterogeneous Graph Contrastive Learning 9 Feb 2024 · 0 repositories · arXiv:2402.06135
-
Predicting Configuration Performance in Multiple Environments with Sequential Meta-learning 5 Feb 2024 · 1 repository · arXiv:2402.03183
-
Rethinking the Starting Point: Collaborative Pre-Training for Federated Downstream Tasks 3 Feb 2024 · 0 repositories · arXiv:2402.02225
-
DK-SLAM: Monocular Visual SLAM with Deep Keypoint Learning, Tracking and Loop-Closing 17 Jan 2024 · 0 repositories · arXiv:2401.09160
-
Any-Way Meta Learning 10 Jan 2024 · 0 repositories · arXiv:2401.05097
-
Are LSTMs Good Few-Shot Learners? 22 Oct 2023 · 1 repository · arXiv:2310.14139
-
Understanding Transfer Learning and Gradient-Based Meta-Learning Techniques 9 Oct 2023 · 1 repository · arXiv:2310.06148
-
Task Aware Modulation using Representation Learning: An Approach for Few Shot Learning in Environmental Systems 7 Oct 2023 · 0 repositories · arXiv:2310.04727
-
Federated Conditional Stochastic Optimization 4 Oct 2023 · 0 repositories · arXiv:2310.02524
-
Multilingual Sentence-Level Semantic Search using Meta-Distillation Learning 15 Sep 2023 · 0 repositories · arXiv:2309.08185
-
Convergence of Gradient-based MAML in LQR 12 Sep 2023 · 0 repositories · arXiv:2309.06588
-
Bridging the Reality Gap of Reinforcement Learning based Traffic Signal Control using Domain Randomization and Meta Learning 21 Jul 2023 · 0 repositories · arXiv:2307.11357
-
Writer adaptation for offline text recognition: An exploration of neural network-based methods 11 Jul 2023 · 1 repository · arXiv:2307.15071
-
FILM: How can Few-Shot Image Classification Benefit from Pre-Trained Language Models? 9 Jul 2023 · 0 repositories · arXiv:2307.04114
-
Is Pre-training Truly Better Than Meta-Learning? 24 Jun 2023 · 0 repositories · arXiv:2306.13841
-
A Hierarchical Bayesian Model for Deep Few-Shot Meta Learning 16 Jun 2023 · 1 repository · arXiv:2306.09702
-
Meta-learning For Vision-and-language Cross-lingual Transfer 24 May 2023 · 0 repositories · arXiv:2305.14843
-
Generalizable Deep Learning Method for Suppressing Unseen and Multiple MRI Artifacts Using Meta-learning 13 Apr 2023 · 0 repositories · arXiv:2304.06378
-
Learning to Learn with Indispensable Connections 6 Apr 2023 · 0 repositories · arXiv:2304.02862
-
Meta-Learning with a Geometry-Adaptive Preconditioner 4 Apr 2023 · 1 repository · arXiv:2304.01552Syntology official (archive's flag): 2 ran · 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 (of 3 harvested samples)
-
A comparison of small sample methods for Handshape Recognition 1 Apr 2023 · 1 repository
-
Automated Federated Learning in Mobile Edge Networks -- Fast Adaptation and Convergence 23 Mar 2023 · 0 repositories · arXiv:2303.12999
-
Model-Agnostic Meta-Learning for Natural Language Understanding Tasks in Finance 6 Mar 2023 · 0 repositories · arXiv:2303.02841
-
Implicit Geometry and Interaction Embeddings Improve Few-Shot Molecular Property Prediction 4 Feb 2023 · 1 repository · arXiv:2302.02055
-
Convergence of First-Order Algorithms for Meta-Learning with Moreau Envelopes 17 Jan 2023 · 0 repositories · arXiv:2301.06806
-
Cognitive Level-k Meta-Learning for Safe and Pedestrian-Aware Autonomous Driving 17 Dec 2022 · 0 repositories · arXiv:2212.08800
-
On the Energy and Communication Efficiency Tradeoffs in Federated and Multi-Task Learning 2 Dec 2022 · 0 repositories · arXiv:2212.01049
-
Rethinking the Number of Shots in Robust Model-Agnostic Meta-Learning 28 Nov 2022 · 0 repositories · arXiv:2211.15180
-
Meta-Learning of Neural State-Space Models Using Data From Similar Systems 14 Nov 2022 · 0 repositories · arXiv:2211.07768
-
MetaLoc: Learning to Learn Wireless Localization 8 Nov 2022 · 0 repositories · arXiv:2211.04258
-
Boosting Natural Language Generation from Instructions with Meta-Learning 20 Oct 2022 · 0 repositories · arXiv:2210.11617
-
Incorporating Relevance Feedback for Information-Seeking Retrieval using Few-Shot Document Re-Ranking 19 Oct 2022 · 1 repository · arXiv:2210.10695
-
Multi-Modal Fusion by Meta-Initialization 10 Oct 2022 · 1 repository · arXiv:2210.04843
-
Hypernetwork approach to Bayesian MAML 6 Oct 2022 · 1 repository · arXiv:2210.02796
-
PersA-FL: Personalized Asynchronous Federated Learning 3 Oct 2022 · 0 repositories · arXiv:2210.01176
-
Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning 27 Sep 2022 · 1 repository · arXiv:2209.13635
-
MAC: A Meta-Learning Approach for Feature Learning and Recombination 20 Sep 2022 · 0 repositories · arXiv:2209.09613
-
A Study on Representation Transfer for Few-Shot Learning 5 Sep 2022 · 0 repositories · arXiv:2209.02073
-
A Game-Theoretic Perspective of Generalization in Reinforcement Learning 7 Aug 2022 · 0 repositories · arXiv:2208.03650
-
The Curse of Low Task Diversity: On the Failure of Transfer Learning to Outperform MAML and Their Empirical Equivalence 2 Aug 2022 · 0 repositories · arXiv:2208.01545
-
Towards Sleep Scoring Generalization Through Self-Supervised Meta-Learning 27 Jul 2022 · 0 repositories · arXiv:2207.13801
-
Generating Pseudo-labels Adaptively for Few-shot Model-Agnostic Meta-Learning 9 Jul 2022 · 0 repositories · arXiv:2207.04217
-
FewSOL: A Dataset for Few-Shot Object Learning in Robotic Environments 6 Jul 2022 · 3 repositories · arXiv:2207.03333
-
Adaptive Fine-Grained Sketch-Based Image Retrieval 4 Jul 2022 · 1 repository · arXiv:2207.01723
-
Provable Generalization of Overparameterized Meta-learning Trained with SGD 18 Jun 2022 · 0 repositories · arXiv:2206.09136
-
Faster Optimization-Based Meta-Learning Adaptation Phase 13 Jun 2022 · 0 repositories · arXiv:2206.05930
-
Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning 8 Jun 2022 · 1 repository · arXiv:2206.03996
-
HyperMAML: Few-Shot Adaptation of Deep Models with Hypernetworks 31 May 2022 · 1 repository · arXiv:2205.15745
-
Meta-ticket: Finding optimal subnetworks for few-shot learning within randomly initialized neural networks 31 May 2022 · 1 repository · arXiv:2205.15619
-
Know Where You're Going: Meta-Learning for Parameter-Efficient Fine-Tuning 25 May 2022 · 0 repositories · arXiv:2205.12453
-
Improved Meta Learning for Low Resource Speech Recognition 11 May 2022 · 0 repositories · arXiv:2205.06182
-
MetaAudio: A Few-Shot Audio Classification Benchmark 5 Apr 2022 · 1 repository · arXiv:2204.02121Syntology official (archive's flag): 1 ran · 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 (of 1 harvested sample) · 1 pointer-only (licence)
-
Selecting task with optimal transport self-supervised learning for few-shot classification 1 Apr 2022 · 0 repositories · arXiv:2204.00289
-
Negative Inner-Loop Learning Rates Learn Universal Features 18 Mar 2022 · 0 repositories · arXiv:2203.10185
-
Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning 17 Mar 2022 · 1 repository · arXiv:2203.09137Syntology official (archive's flag): 4 ran · 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 (of 4 harvested samples)
-
Rethinking Task Sampling for Few-shot Vision-Language Transfer Learning 9 Mar 2022 · 1 repository · arXiv:2203.04904
-
What Matters For Meta-Learning Vision Regression Tasks? 9 Mar 2022 · 2 repositories · arXiv:2203.04905
-
Is Bayesian Model-Agnostic Meta Learning Better than Model-Agnostic Meta Learning, Provably? 6 Mar 2022 · 1 repository · arXiv:2203.03059
-
MetaVA: Curriculum Meta-learning and Pre-fine-tuning of Deep Neural Networks for Detecting Ventricular Arrhythmias based on ECGs 25 Feb 2022 · 0 repositories · arXiv:2202.12450
-
MAML and ANIL Provably Learn Representations 7 Feb 2022 · 0 repositories · arXiv:2202.03483
-
PLATINUM: Semi-Supervised Model Agnostic Meta-Learning using Submodular Mutual Information 30 Jan 2022 · 1 repository · arXiv:2201.12928Syntology official (archive's flag): 3 ran · 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 (of 4 harvested samples) · 4 pointer-only (licence)
-
The Effect of Diversity in Meta-Learning 27 Jan 2022 · 1 repository · arXiv:2201.11775Syntology official (archive's flag): 3 ran · 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 (of 3 harvested samples) · 3 pointer-only (licence)
-
Meta-learning Spiking Neural Networks with Surrogate Gradient Descent 26 Jan 2022 · 1 repository · arXiv:2201.10777Syntology 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 (of 9 harvested samples) · 1 pointer-only (licence)
-
Representation Change in Model-Agnostic Meta-Learning 17 Jan 2022 · 0 repositories
-
Does CLIP Benefit Visual Question Answering in the Medical Domain as Much as it Does in the General Domain? 27 Dec 2021 · 0 repositories · arXiv:2112.13906
-
Does MAML Only Work via Feature Re-use? A Data Centric Perspective 24 Dec 2021 · 1 repository · arXiv:2112.13137
-
The Curse of Zero Task Diversity: On the Failure of Transfer Learning to Outperform MAML and their Empirical Equivalence 24 Dec 2021 · 0 repositories · arXiv:2112.13121
-
Implicit Neural Representations for Image Compression 8 Dec 2021 · 0 repositories · arXiv:2112.04267
-
Curriculum Meta-Learning for Few-shot Classification 6 Dec 2021 · 1 repository · arXiv:2112.02913
-
Camera Distortion-aware 3D Human Pose Estimation in Video with Optimization-based Meta-Learning 30 Nov 2021 · 1 repository · arXiv:2111.15056
-
Confounder Identification-free Causal Visual Feature Learning 26 Nov 2021 · 0 repositories · arXiv:2111.13420
-
DAML: Chinese Named Entity Recognition with a fusion method of data-augmentation and meta-learning 16 Nov 2021 · 0 repositories
-
MAML-CL: Edited Model-Agnostic Meta-Learning for Continual Learning 16 Nov 2021 · 1 repository
-
Meta-learning via Language Model In-context Tuning 16 Nov 2021 · 0 repositories
-
Accelerating Gradient-based Meta Learner 27 Oct 2021 · 0 repositories · arXiv:2110.14459
-
Contextual Gradient Scaling for Few-Shot Learning 20 Oct 2021 · 1 repository · arXiv:2110.10353
-
Meta-Learning with Adjoint Methods 16 Oct 2021 · 0 repositories · arXiv:2110.08432
-
Meta-learning via Language Model In-context Tuning 15 Oct 2021 · 1 repository · arXiv:2110.07814
Tasks archive 2025-07-28
20 shown of 218 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections