mlsanityData to 7 Oct 2026

MetaFun: Meta-Learning with Iterative Functional Updates

arXiv 1912.02738 ↗First posted 5 Dec 2019stat.ML cs.LGcited by 34

Not on the map. Why?

Abstract (arXiv)

We develop a functional encoder-decoder approach to supervised meta-learning, where labeled data is encoded into an infinite-dimensional functional representation rather than a finite-dimensional one. Furthermore, rather than directly producing the representation, we learn a neural update rule resembling functional gradient descent which iteratively improves the representation. The final representation is used to condition the decoder to make predictions on unlabeled data. Our approach is the first to demonstrates the success of encoder-decoder style meta-learning methods like conditional neural processes on large-scale few-shot classification benchmarks such as miniImageNet and tieredImageNet, where it achieves state-of-the-art performance.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 9; 2023: 6; 2024: 4; 2025: 3; 2026: 1.

34 papers.

Sort:

By area:

  1. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  2. 2022Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modelingcited by 126
  3. 2021Rectifying the Shortcut Learning of Background for Few-Shot Learningcited by 51
  4. 2023A Closer Look at Few-shot Classification Againcited by 46
  5. 2022Few-Shot Diffusion Modelscited by 37
  6. 2024Online Adaptation of Language Models with a Memory of Amortized Contextscited by 35
  7. 2022The Neural Process Family: Survey, Applications and Perspectivescited by 23
  8. 2021Group Equivariant Conditional Neural Processescited by 16
  9. 2022Neural Processes with Stochastic Attention: Paying more attention to the context datasetcited by 16
  10. 2021Non-Gaussian Gaussian Processes for Few-Shot Regressioncited by 12
  11. 2021Learning to Rectify for Robust Learning with Noisy Labelscited by 12
  12. 2022Scalable PAC-Bayesian Meta-Learning via the PAC-Optimal Hyper-Posterior: From Theory to Practicecited by 11
22 more
  1. 2023MetaNO: How to Transfer Your Knowledge on Learning Hidden Physicscited by 10
  2. 2024Task-Adapter: Task-specific Adaptation of Image Models for Few-shot Action Recognitioncited by 8
  3. 2023Deep Stochastic Processes via Functional Markov Transition Operatorscited by 7
  4. 2021SCHA-VAE: Hierarchical Context Aggregation for Few-Shot Generationcited by 6
  5. 2021Few-shot Learning for Topic Modelingcited by 5
  6. 2023Meta-learning of Physics-informed Neural Networks for Efficiently Solving Newly Given PDEscited by 5
  7. 2023Modality-Agnostic Self-Supervised Learning with Meta-Learned Masked Auto-Encodercited by 5
  8. 2024Spectral Convolutional Conditional Neural Processescited by 4
  9. 2021Gaussian Process Meta Few-shot Classifier Learning via Linear Discriminant Laplace Approximationcited by 3
  10. 2023Meta-learning of semi-supervised learning from tasks with heterogeneous attribute spacescited by 3
  11. 2024Context-Aware Multimodal Pretrainingcited by 3
  12. 2025Curvature Learning for Generalization of Hyperbolic Neural Networkscited by 3
  13. 2022Meta-free few-shot learning via representation learning with weight averagingcited by 2
  14. 2021Meta-Learning for Koopman Spectral Analysis with Short Time-seriescited by 1
  15. 2021Meta-learning for Matrix Factorization without Shared Rows or Columnscited by 1
  16. 2021Meta-CPR: Generalize to Unseen Large Number of Agents with Communication Pattern Recognition Modulecited by 1
  17. 2022BaseTransformers: Attention over base data-points for One Shot Learningcited by 1
  18. 2021Meta-learning One-class Classifiers with Eigenvalue Solvers for Supervised Anomaly Detectioncited by 0
  19. 2022Learning to generate imaginary tasks for improving generalization in meta-learningcited by 0
  20. 2025Task-Adapter++: Task-specific Adaptation with Order-aware Alignment for Few-shot Action Recognitioncited by 0
  21. 2025Toward Better Generalization in Few-Shot Learning through the Meta-Component Combinationcited by 0
  22. 2026Revisiting Neural Processes via Fourier Transform and Volterra Seriescited by 0