mlsanityData to 14 Oct 2026

Adaptation-Agnostic Meta-Training

arXiv 2108.10557 ↗First posted 24 Aug 2021cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Many meta-learning algorithms can be formulated into an interleaved process, in the sense that task-specific predictors are learned during inner-task adaptation and meta-parameters are updated during meta-update. The normal meta-training strategy needs to differentiate through the inner-task adaptation procedure to optimize the meta-parameters. This leads to a constraint that the inner-task algorithms should be solved analytically. Under this constraint, only simple algorithms with analytical solutions can be applied as the inner-task algorithms, limiting the model expressiveness. To lift the limitation, we propose an adaptation-agnostic meta-training strategy. Following our proposed strategy, we can apply stronger algorithms (e.g., an ensemble of different types of algorithms) as the inner-task algorithm to achieve superior performance comparing with popular baselines. The source code is available at https://github.com/jiaxinchen666/AdaptationAgnosticMetaLearning.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 28 references that are in the map. First posted on arXiv 24 Aug 2021.

Builds on

20 of 28 references.

References · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  5. 2016Matching Networks for One Shot Learningcited by 2,255
  6. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  7. 2019A Closer Look at Few-shot Classificationcited by 684
  8. 2019Meta-Learning with Implicit Gradientscited by 525
  9. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  10. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  11. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  12. 2018Bilevel Programming for Hyperparameter Optimization and Meta-Learningcited by 405
8 more
  1. 2018Meta-learning with differentiable closed-form solverscited by 397
  2. 2019Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLcited by 359
  3. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  4. 2018Probabilistic Model-Agnostic Meta-Learningcited by 256
  5. 2018Recasting Gradient-Based Meta-Learning as Hierarchical Bayescited by 180
  6. 2018Meta-Learning Probabilistic Inference For Predictioncited by 110
  7. 2017Meta Learning Shared Hierarchiescited by 93
  8. 2016Deep Multi-task Representation Learning: A Tensor Factorisation Approachcited by 69

Built on by

Not cited yet.