MetaLearningAlgorithmType

Enums · AiDotNet.MetaLearning

Specifies the type of meta-learning algorithm used for few-shot learning and quick adaptation.

For Beginners

Meta-learning algorithms are designed to “learn how to learn.” Instead of learning a single task, they learn to quickly adapt to new tasks with minimal data. This enum lists all supported meta-learning algorithms in the framework.

How It Works

Algorithm Categories:

  • Optimization-based: MAML, Reptile, Meta-SGD, iMAML, ANIL, BOIL, LEO
  • Metric-based: ProtoNets, MatchingNetworks, RelationNetwork, TADAM
  • Memory-based: MANN, NTM
  • Hybrid/Advanced: CNAP, SEAL, GNNMeta, MetaOptNet
  • Neural Processes: CNP, NP, ANP, ConvCNP, ConvNP, TNP, SwinTNP, TETNP, EquivCNP, SteerCNP, RCNP, LBANP
  • Foundation Model Era: MetaLoRA, LoRARecycle, ICMFusion, MetaLoRABank, AutoLoRA, MetaDiff, MetaDM, MetaDDPM
  • Bayesian Extensions: PACOH, MetaPACOH, BMAML, BayProNet, SImPa
  • Cross-Domain: MetaFDMixup, FreqPrior, MetaCollaborative, SDCL, FreqPrompt, OpenMAMLPlus
  • Meta-RL: PEARL, DREAM, DiscoRL, InContextRL, HyperNetMetaRL, ContextMetaRL
  • Continual/Online: ACL, iTAML, SparseMAML, MbPA, OML, MOCA
  • Task Augmentation: MetaTask, ATAML, MPTS, DynamicTaskSampling, UnsupervisedMetaLearn
  • Cross-domain / Transductive: LFT, BayTransProto, JMP, ETPN, ActiveTransFSL
  • Hypernetwork: TaskCondHyperNet, HyperCLIP, RecurrentHyperNet, HyperNeRFMeta

Fields

Field Summary
MetaLearningAlgorithmType ACL ACL - Adaptive Continual Learning with meta-learning (2024).
MetaLearningAlgorithmType ANIL Almost No Inner Loop (Raghu et al., 2020).
MetaLearningAlgorithmType ANP Attentive Neural Process (Kim et al., ICLR 2019).
MetaLearningAlgorithmType ATAML ATAML - Attentive Task-Agnostic Meta-Learning (Jiang et al., 2018).
MetaLearningAlgorithmType AWGIM AWGIM - Attentive Weights Generation for few-shot learning via Information Maximization (Guo & Cheung, CVPR 2020).
MetaLearningAlgorithmType ActiveTransFSL ActiveTransFSL - Active Transductive Few-Shot Learning (2024).
MetaLearningAlgorithmType AutoLoRA AutoLoRA - Automatic LoRA rank and configuration selection (2024).
MetaLearningAlgorithmType BMAML BMAML - Bayesian MAML (Yoon et al., NeurIPS 2018).
MetaLearningAlgorithmType BOIL Body Only Inner Loop (Oh et al., 2021).
MetaLearningAlgorithmType BayProNet BayProNet - Bayesian Prototypical Networks (2024).
MetaLearningAlgorithmType BayTransProto BayTransProto - Bayesian Transductive Prototypical Networks (2024).
MetaLearningAlgorithmType CAML CAML - Context-Aware Meta-Learning (Fifty et al., NeurIPS 2023).
MetaLearningAlgorithmType CAVIA Fast Context Adaptation via Meta-Learning (Zintgraf et al., ICML 2019).
MetaLearningAlgorithmType CNAP Conditional Neural Adaptive Processes (Requeima et al., 2019).
MetaLearningAlgorithmType CNP Conditional Neural Process (Garnelo et al., ICML 2018).
MetaLearningAlgorithmType ConstellationNet ConstellationNet - Structured part-based few-shot learning (Xu et al., ICLR 2021).
MetaLearningAlgorithmType ContextMetaRL Context Meta-RL - Context-based Meta-Reinforcement Learning (2024).
MetaLearningAlgorithmType ConvCNP Convolutional Conditional Neural Process (Gordon et al., ICLR 2020).
MetaLearningAlgorithmType ConvNP Convolutional Neural Process (Foong et al., 2020).
MetaLearningAlgorithmType DKT DKT - Deep Kernel Transfer (Patacchiola et al., ICLR 2020).
MetaLearningAlgorithmType DPGN DPGN - Distribution Propagation Graph Network (Yang et al., CVPR 2020).
MetaLearningAlgorithmType DREAM DREAM - Decoupled Reward-Environment Adaptation Meta-learning (2022).
MetaLearningAlgorithmType DeepEMD DeepEMD - Earth Mover’s Distance for few-shot learning (Zhang et al., CVPR 2020).
MetaLearningAlgorithmType DiscoRL DiscoRL - Discovering Meta-RL Objectives (2024).
MetaLearningAlgorithmType DynamicTaskSampling Dynamic Task Sampling - Adaptive task distribution during meta-training (2024).
MetaLearningAlgorithmType EPNet EPNet - Embedding Propagation Network (Rodriguez et al., CVPR 2020).
MetaLearningAlgorithmType ETPN ETPN - Enhanced Transductive Prototypical Networks (2024).
MetaLearningAlgorithmType EquivCNP Equivariant Conditional Neural Process (Kawano et al., 2021).
MetaLearningAlgorithmType FEAT FEAT - Few-shot Embedding Adaptation with Transformer (Ye et al., CVPR 2020).
MetaLearningAlgorithmType FRN FRN - Few-shot Classification via Feature Map Reconstruction (Wertheimer et al., CVPR 2021).
MetaLearningAlgorithmType FewTURE FewTURE - Few-shot Transformer with Uncertainty and Reliable Estimation (Hiller et al., ECCV 2022).
MetaLearningAlgorithmType FreqPrior FreqPrior - Frequency-based Prior for cross-domain few-shot learning (2024).
MetaLearningAlgorithmType FreqPrompt FreqPrompt - Frequency-aware Prompt tuning for cross-domain FSL (2024).
MetaLearningAlgorithmType GNNMeta Graph Neural Network for Meta-Learning.
MetaLearningAlgorithmType HyperCLIP HyperCLIP - Hypernetwork with CLIP-based task encoding (2024).
MetaLearningAlgorithmType HyperMAML HyperMAML - Hypernetwork-based MAML initialization.
MetaLearningAlgorithmType HyperNeRFMeta HyperNeRF Meta - Hypernetwork for Meta-learning Neural Radiance Fields (2024).
MetaLearningAlgorithmType HyperNetMetaRL HyperNet Meta-RL - Hypernetwork-based Meta-Reinforcement Learning (2024).
MetaLearningAlgorithmType HyperShot HyperShot - Kernel hypernetwork for few-shot learning.
MetaLearningAlgorithmType ICMFusion ICM Fusion - In-Context Model Fusion (2024).
MetaLearningAlgorithmType InContextRL In-Context RL - Reinforcement learning through in-context learning (2023).
MetaLearningAlgorithmType JMP JMP - Joint Meta-learning and Propagation for transductive FSL (2024).
MetaLearningAlgorithmType LBANP Latent Bottleneck Attentive Neural Process (Feng et al., ICML 2023).
MetaLearningAlgorithmType LEO Latent Embedding Optimization (Rusu et al., 2019).
MetaLearningAlgorithmType LFT LFT - Learned Feature-Wise Transformation (Tseng et al., ICLR 2020).
MetaLearningAlgorithmType LaplacianShot LaplacianShot - Laplacian Regularized Few-Shot Learning (Ziko et al., ICML 2020).
MetaLearningAlgorithmType LoRARecycle LoRA-Recycle - Recycling LoRA adapters across tasks (2024).
MetaLearningAlgorithmType MAML Model-Agnostic Meta-Learning (Finn et al., 2017).
MetaLearningAlgorithmType MAMLPlusPlus MAML++ - How to Train Your MAML (Antoniou et al., ICLR 2019).
MetaLearningAlgorithmType MANN Memory-Augmented Neural Network (Santoro et al., 2016).
MetaLearningAlgorithmType MCL MCL - Meta-learning with Contrastive Learning.
MetaLearningAlgorithmType MOCA MOCA - Meta-learning Online Continual Adaptation (2024).
MetaLearningAlgorithmType MPTS MPTS - Meta-learning with Prioritized Task Sampling (2024).
MetaLearningAlgorithmType MatchingNetworks Matching Networks for One Shot Learning (Vinyals et al., 2016).
MetaLearningAlgorithmType MbPA MbPA - Memory-based Parameter Adaptation (Sprechmann et al., ICLR 2018).
MetaLearningAlgorithmType MetaBaseline Meta-Baseline - Simple pre-train then meta-train with cosine classifier (Chen et al., ICLR 2021).
MetaLearningAlgorithmType MetaCollaborative MetaCollaborative - Collaborative meta-learning across multiple source domains (2024).
MetaLearningAlgorithmType MetaDDPM MetaDDPM - Meta Denoising Diffusion Probabilistic Model (2024).
MetaLearningAlgorithmType MetaDM MetaDM - Meta Diffusion Model for few-shot generation (2024).
MetaLearningAlgorithmType MetaDiff MetaDiff - Meta-learning with Diffusion Models (2024).
MetaLearningAlgorithmType MetaFDMixup Meta-FDMixup - Feature Distribution Mixup for cross-domain few-shot learning (2021).
MetaLearningAlgorithmType MetaLoRA Meta-LoRA - Meta-learning with Low-Rank Adaptation (2024).
MetaLearningAlgorithmType MetaLoRABank Meta-LoRA Bank - Library of meta-learned LoRA modules (2024).
MetaLearningAlgorithmType MetaOptNet Meta-learning with differentiable convex optimization (Lee et al., 2019).
MetaLearningAlgorithmType MetaPACOH Meta-PACOH - Extended PACOH with hierarchical Bayesian meta-learning (2023).
MetaLearningAlgorithmType MetaSGD Meta-SGD with per-parameter learning rates (Li et al., 2017).
MetaLearningAlgorithmType MetaTask MetaTask - Meta-learning task generation for improved generalization (2024).
MetaLearningAlgorithmType NP Neural Process (Garnelo et al., 2018).
MetaLearningAlgorithmType NPBML NPBML - Neural Process-Based Meta-Learning.
MetaLearningAlgorithmType NTM Neural Turing Machine for meta-learning.
MetaLearningAlgorithmType OML OML - Online Meta-Learning (Javed & White, 2019).
MetaLearningAlgorithmType OpenMAML Open-MAML - MAML extended for open-set recognition.
MetaLearningAlgorithmType OpenMAMLPlus Open-MAML++ - Enhanced MAML for open-set cross-domain recognition (2024).
MetaLearningAlgorithmType PACOH PACOH - PAC-Bayesian Meta-Learning with Optimal Hyperparameters (Rothfuss et al., ICLR 2021).
MetaLearningAlgorithmType PEARL PEARL - Probabilistic Embeddings for Actor-critic RL (Rakelly et al., ICML 2019).
MetaLearningAlgorithmType PMF PMF - Pre-train, Meta-train, Fine-tune (Hu et al., ICLR 2022).
MetaLearningAlgorithmType PTMAP PT+MAP - Power Transform + Maximum A Posteriori (Hu et al., ICLR 2021).
MetaLearningAlgorithmType ProtoNets Prototypical Networks (Snell et al., 2017).
MetaLearningAlgorithmType R2D2 R2-D2 - Meta-learning with Differentiable Closed-form Solvers (Bertinetto et al., ICLR 2019).
MetaLearningAlgorithmType RCNP Recurrent Conditional Neural Process (2024).
MetaLearningAlgorithmType RecurrentHyperNet Recurrent HyperNet - Hypernetwork with recurrent task encoding (2024).
MetaLearningAlgorithmType RelationNetwork Relation Network for few-shot learning (Sung et al., 2018).
MetaLearningAlgorithmType Reptile Reptile meta-learning algorithm (Nichol et al., 2018).
MetaLearningAlgorithmType SDCL SDCL - Self-Distillation Contrastive Learning for cross-domain FSL (2024).
MetaLearningAlgorithmType SEAL Self-Explanatory Attention Learning.
MetaLearningAlgorithmType SIB SIB - Sequential Information Bottleneck (Hu et al., 2020).
MetaLearningAlgorithmType SImPa SImPa - statistical implicit PAC-Bayes meta-learning (Nguyen, Do and Carneiro, arXiv:2003.02455).
MetaLearningAlgorithmType SNAIL SNAIL - Simple Neural Attentive Meta-Learner (Mishra et al., ICLR 2018).
MetaLearningAlgorithmType SetFeat SetFeat - Matching Feature Sets for Few-Shot Classification (Afrasiyabi et al., CVPR 2022).
MetaLearningAlgorithmType SimpleShot SimpleShot - Nearest-centroid classification with feature normalization (Wang et al., 2019).
MetaLearningAlgorithmType SparseMAML SparseMAML - Learning where to learn: gradient sparsity in meta and continual learning (von Oswald et al., NeurIPS 2021).
MetaLearningAlgorithmType SteerCNP Steerable Conditional Neural Process (Holderrieth et al., 2021).
MetaLearningAlgorithmType SwinTNP Swin Transformer Neural Process (2024).
MetaLearningAlgorithmType TADAM Task-Dependent Adaptive Metric (Oreshkin et al., 2018).
MetaLearningAlgorithmType TETNP Translation-Equivariant Transformer Neural Process (2024).
MetaLearningAlgorithmType TIM TIM - Transductive Information Maximization (Boudiaf et al., NeurIPS 2020).
MetaLearningAlgorithmType TNP Transformer Neural Process (Nguyen & Grover, ICML 2023).
MetaLearningAlgorithmType TaskCondHyperNet Task-Conditioned HyperNet - Hypernetwork conditioned on task representations (2024).
MetaLearningAlgorithmType UnsupervisedMetaLearn Unsupervised Meta-Learning - Meta-learning without task labels (Hsu et al., 2019).
MetaLearningAlgorithmType VERSA VERSA - Versatile and Efficient Few-shot Learning (Gordon et al., ICLR 2019).
MetaLearningAlgorithmType WarpGrad Warped Gradient Descent meta-learning (Flennerhag et al., ICLR 2020).
MetaLearningAlgorithmType iMAML Implicit MAML with implicit gradients (Rajeswaran et al., 2019).
MetaLearningAlgorithmType iTAML iTAML - Incremental Task-Agnostic Meta-Learning (Rajasegaran et al., 2020).
int value__