mlsanityData to 14 Oct 2026

Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning

arXiv 2110.03909 ↗First posted 8 Oct 2021cs.LG cs.CVcited by 49

Not on the map. Why?

Abstract (arXiv)

In few-shot learning scenarios, the challenge is to generalize and perform well on new unseen examples when only very few labeled examples are available for each task. Model-agnostic meta-learning (MAML) has gained the popularity as one of the representative few-shot learning methods for its flexibility and applicability to diverse problems. However, MAML and its variants often resort to a simple loss function without any auxiliary loss function or regularization terms that can help achieve better generalization. The problem lies in that each application and task may require different auxiliary loss function, especially when tasks are diverse and distinct. Instead of attempting to hand-design an auxiliary loss function for each application and task, we introduce a new meta-learning framework with a loss function that adapts to each task. Our proposed framework, named Meta-Learning with Task-Adaptive Loss Function (MeTAL), demonstrates the effectiveness and the flexibility across various domains, such as few-shot classification and few-shot regression.

Key facts. Cited by 49 papers in the map (data through 14 Oct 2026). Builds on 48 of its 67 references that are in the map. First posted on arXiv 8 Oct 2021.

Builds on

48 of 67 references.

References · 48

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  6. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  7. 2016Matching Networks for One Shot Learningcited by 2,255
  8. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  9. 2018On First-Order Meta-Learning Algorithmscited by 1,018
  10. 2019A Closer Look at Few-shot Classificationcited by 684
  11. 2016Learning to learn by gradient descent by gradient descentcited by 620
  12. 2019Meta-Learning with Implicit Gradientscited by 525
36 more
  1. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  2. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  3. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  4. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  5. 2018Meta-learning with differentiable closed-form solverscited by 397
  6. 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 379
  7. 2018How Does Batch Normalization Help Optimization?cited by 357
  8. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 315
  9. 2018How to train your MAMLcited by 309
  10. 2017Meta Networkscited by 269
  11. 2018Probabilistic Model-Agnostic Meta-Learningcited by 256
  12. 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 211
  13. 2018Recasting Gradient-Based Meta-Learning as Hierarchical Bayescited by 180
  14. 2018Meta-Gradient Reinforcement Learningcited by 159
  15. 2018Task-Agnostic Meta-Learning for Few-shot Learningcited by 151
  16. 2020Interventional Few-Shot Learningcited by 112
  17. 2019Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulationcited by 103
  18. 2019Meta-Learning with Warped Gradient Descentcited by 98
  19. 2020Meta-Learning with Adaptive Hyperparameterscited by 79
  20. 2020Discovering Reinforcement Learning Algorithmscited by 77
  21. 2019Hierarchically Structured Meta-learningcited by 68
  22. 2019Improving Generalization in Meta Reinforcement Learning using Learned Objectivescited by 68
  23. 2019Meta-Learning via Learned Losscited by 60
  24. 2020Meta-Gradient Reinforcement Learning with an Objective Discovered Onlinecited by 52
  25. 2020Empirical Bayes Transductive Meta-Learning with Synthetic Gradientscited by 48
  26. 2020Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Taskscited by 47
  27. 2019An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learningcited by 38
  28. 2019Learning to Forget for Meta-Learningcited by 35
  29. 2018Meta-Tracker: Fast and Robust Online Adaptation for Visual Object Trackerscited by 34
  30. 2017CREST: Convolutional Residual Learning for Visual Trackingcited by 29
  31. 2020Adaptive Task Sampling for Meta-Learningcited by 29
  32. 2017Learning to Learn: Meta-Critic Networks for Sample Efficient Learningcited by 28
  33. 2019Alpha MAML: Adaptive Model-Agnostic Meta-Learningcited by 25
  34. 2021Meta-Learning with Neural Tangent Kernelscited by 15
  35. 2019Learning to learn via Self-Critiquecited by 6
  36. 2019Meta Dropout: Learning to Perturb Features for Generalizationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 12; 2023: 21; 2024: 9; 2025: 4; 2026: 3.

49 papers.

Sort:

By area:

  1. 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 126
  2. 2023MetaDiff: Meta-Learning with Conditional Diffusion for Few-Shot Learningcited by 40
  3. 2022Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learningcited by 27
  4. 2024Task-driven Image Fusion with Learnable Fusion Losscited by 25
  5. 2023Supervised Masked Knowledge Distillation for Few-Shot Transformerscited by 23
  6. 2022Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroidcited by 20
  7. 2023From Google Gemini to OpenAI Q* (Q-Star): A Survey of Reshaping the Generative Artificial Intelligence (AI) Research Landscapecited by 18
  8. 2023ReFusion: Learning Image Fusion from Reconstruction with Learnable Loss via Meta-Learningcited by 15
  9. 2024CrackNex: a Few-shot Low-light Crack Segmentation Model Based on Retinex Theory for UAV Inspectionscited by 12
  10. 2023Meta-Learning with a Geometry-Adaptive Preconditionercited by 11
  11. 2023LFS-GAN: Lifelong Few-Shot Image Generationcited by 11
  12. 2022Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classificationcited by 10
37 more
  1. 2022Learning Symbolic Model-Agnostic Loss Functions via Meta-Learningcited by 9
  2. 2022Robust Meta-learning with Sampling Noise and Label Noise via Eigen-Reptilecited by 6
  3. 2023Sample-Level Weighting for Multi-Task Learning with Auxiliary Taskscited by 6
  4. 2022Few-Shot Learning of Compact Models via Task-Specific Meta Distillationcited by 5
  5. 2023Meta-Learning Adaptive Loss Functionscited by 4
  6. 2023Hebbian and Gradient-based Plasticity Enables Robust Memory and Rapid Learning in RNNscited by 4
  7. 2023Meta-DM: Applications of Diffusion Models on Few-Shot Learningcited by 4
  8. 2025Curvature Learning for Generalization of Hyperbolic Neural Networkscited by 4
  9. 2023Improve Noise Tolerance of Robust Loss via Noise-Awarenesscited by 3
  10. 2023Meta-Learning with Adaptive Weighted Loss for Imbalanced Cold-Start Recommendationcited by 3
  11. 2023Few-shot Classification via Ensemble Learning with Multi-Order Statisticscited by 3
  12. 2023Task Aware Modulation using Representation Learning: An Approach for Few Shot Learning in Environmental Systemscited by 3
  13. 2022MetaDT: Meta Decision Tree with Class Hierarchy for Interpretable Few-Shot Learningcited by 2
  14. 2023Meta-Auxiliary Network for 3D GAN Inversioncited by 2
  15. 2023Generalizing Supervised Deep Learning MRI Reconstruction to Multiple and Unseen Contrasts using Meta-Learning Hypernetworkscited by 2
  16. 2023L2T-DLN: Learning to Teach with Dynamic Loss Networkcited by 2
  17. 2023AdaCCD: Adaptive Semantic Contrasts Discovery Based Cross Lingual Adaptation for Code Clone Detectioncited by 2
  18. 2024Meta-Learning with Heterogeneous Taskscited by 2
  19. 2025Hyperbolic Dual Feature Augmentation for Open-Environmentcited by 2
  20. 2025Geometry-aware Distance Measure for Diverse Hierarchical Structures in Hyperbolic Spacescited by 2
  21. 2026SpurAudio: A Benchmark for Studying Shortcut Learning in Few-Shot Audio Classificationcited by 2
  22. 2022Learning Compositional Representations for Effective Low-Shot Generalizationcited by 1
  23. 2022Positive Pair Distillation Considered Harmful: Continual Meta Metric Learning for Lifelong Object Re-Identificationcited by 1
  24. 2022Disentangled Generation with Information Bottleneck for Few-Shot Learningcited by 1
  25. 2024Task Attribute Distance for Few-Shot Learning: Theoretical Analysis and Applicationscited by 1
  26. 2024Meta-Learning Neural Procedural Biasescited by 1
  27. 2024Knowledge Adaptation Network for Few-Shot Class-Incremental Learningcited by 1
  28. 2022Fine-grained Few-shot Recognition by Deep Object Parsingcited by 0
  29. 2023Task-Adaptive Pseudo Labeling for Transductive Meta-Learningcited by 0
  30. 2023Unsupervised augmentation optimization for few-shot medical image segmentationcited by 0
  31. 2023Successive Model-Agnostic Meta-Learning for Few-Shot Fault Time Series Prognosiscited by 0
  32. 2024Local Descriptors Weighted Adaptive Threshold Filtering For Few-Shot Learningcited by 0
  33. 2024Reading ability detection using eye-tracking data with LSTM-based few-shot learningcited by 0
  34. 2024Memory-Reduced Meta-Learning with Guaranteed Convergencecited by 0
  35. 2025Adapting to the Unknown: Robust Meta-Learning for Zero-Shot Financial Time Series Forecastingcited by 0
  36. 2026Distribution-Free Pretraining of Classification Losses via Evolutionary Dynamicscited by 0
  37. 2026Learning to Recover Task Experts from a Multi-Task Merged Modelcited by 0