mlsanityData to 7 Oct 2026

Alpha MAML: Adaptive Model-Agnostic Meta-Learning

arXiv 1905.07435 ↗First posted 17 May 2019cs.LG cs.AI stat.MLcited by 25

Not on the map. Why?

Abstract (arXiv)

Model-agnostic meta-learning (MAML) is a meta-learning technique to train a model on a multitude of learning tasks in a way that primes the model for few-shot learning of new tasks. The MAML algorithm performs well on few-shot learning problems in classification, regression, and fine-tuning of policy gradients in reinforcement learning, but comes with the need for costly hyperparameter tuning for training stability. We address this shortcoming by introducing an extension to MAML, called Alpha MAML, to incorporate an online hyperparameter adaptation scheme that eliminates the need to tune meta-learning and learning rates. Our results with the Omniglot database demonstrate a substantial reduction in the need to tune MAML training hyperparameters and improvement to training stability with less sensitivity to hyperparameter choice.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 1; 2023: 8; 2024: 1; 2025: 2; 2026: 1.

25 papers.

Sort:

  1. 2021Personalized Federated Learning using Hypernetworkscited by 210
  2. 2021Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyondcited by 151
  3. 2021Personalized Federated Learning with Gaussian Processescited by 76
  4. 2023Advances and Challenges in Meta-Learning: A Technical Reviewcited by 65
  5. 2021Domain Invariant Representation Learning with Domain Density Transformationscited by 53
  6. 2021Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learningcited by 49
  7. 2023An Introduction to Bi-level Optimization: Foundations and Applications in Signal Processing and Machine Learningcited by 39
  8. 2021Generalization of Model-Agnostic Meta-Learning Algorithms: Recurring and Unseen Taskscited by 36
  9. 2023Meta-learning approaches for few-shot learning: A survey of recent advancescited by 25
  10. 2023Learning to Learn from APIs: Black-Box Data-Free Meta-Learningcited by 18
  11. 2021PAC-Bayes Bounds for Meta-learning with Data-Dependent Priorcited by 11
  12. 2022Task Discovery: Finding the Tasks that Neural Networks Generalize oncited by 9
13 more
  1. 2023A Partially Supervised Reinforcement Learning Framework for Visual Active Searchcited by 8
  2. 2021Memory-Based Optimization Methods for Model-Agnostic Meta-Learning and Personalized Federated Learningcited by 6
  3. 2023Convergence of Gradient-based MAML in LQRcited by 5
  4. 2021Embedding Adaptation is Still Needed for Few-Shot Learningcited by 2
  5. 2021Bayesian Active Meta-Learning for Few Pilot Demodulation and Equalizationcited by 2
  6. 2023Generalizing Supervised Deep Learning MRI Reconstruction to Multiple and Unseen Contrasts using Meta-Learning Hypernetworkscited by 2
  7. 2021Meta Adversarial Perturbationscited by 1
  8. 2023Towards Personalized Preprocessing Pipeline Searchcited by 1
  9. 2024Meta-Learning Neural Procedural Biasescited by 1
  10. 2025Benchmarking for Practice: Few-Shot Time-Series Crop-Type Classification on the EuroCropsML Datasetcited by 1
  11. 2025Heterogeneity-Oblivious Robust Federated Learningcited by 1
  12. 2021Graceful Degradation and Related Fieldscited by 0
  13. 2026Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive Agentcited by 0