mlsanityData to 7 Oct 2026

Learning to generate imaginary tasks for improving generalization in meta-learning

arXiv 2206.04335 ↗First posted 9 Jun 2022cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

The success of meta-learning on existing benchmarks is predicated on the assumption that the distribution of meta-training tasks covers meta-testing tasks. Frequent violation of the assumption in applications with either insufficient tasks or a very narrow meta-training task distribution leads to memorization or learner overfitting. Recent solutions have pursued augmentation of meta-training tasks, while it is still an open question to generate both correct and sufficiently imaginary tasks. In this paper, we seek an approach that up-samples meta-training tasks from the task representation via a task up-sampling network. Besides, the resulting approach named Adversarial Task Up-sampling (ATU) suffices to generate tasks that can maximally contribute to the latest meta-learner by maximizing an adversarial loss. On few-shot sine regression and image classification datasets, we empirically validate the marked improvement of ATU over state-of-the-art task augmentation strategies in the meta-testing performance and also the quality of up-sampled tasks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 28 of its 37 references that are in the map. First posted on arXiv 9 Jun 2022.

Builds on

28 of 37 references.

References · 28

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  3. 2016Matching Networks for One Shot Learningcited by 2,246
  4. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  5. 2016HyperNetworkscited by 1,003
  6. 2016Learning to learn by gradient descent by gradient descentcited by 616
  7. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  8. 2018PCN: Point Completion Networkcited by 382
  9. 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 377
  10. 2019Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLcited by 359
  11. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 312
  12. 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
16 more
  1. 2018PU-Net: Point Cloud Upsampling Networkcited by 208
  2. 2018Task-Agnostic Meta-Learning for Few-shot Learningcited by 151
  3. 2017Learned Optimizers that Scale and Generalizecited by 109
  4. 2019Meta-Learning without Memorizationcited by 92
  5. 2019Hierarchically Structured Meta-learningcited by 67
  6. 2020Meta-Learning Requires Meta-Augmentationcited by 57
  7. 2020Improving Generalization in Meta-learning via Task Augmentationcited by 55
  8. 2019Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Taskscited by 48
  9. 2021Meta-Learning with Fewer Tasks through Task Interpolationcited by 45
  10. 2020Data Augmentation for Meta-Learningcited by 38
  11. 2019MetaFun: Meta-Learning with Iterative Functional Updatescited by 34
  12. 2021Meta-learning with an Adaptive Task Schedulercited by 27
  13. 2019Difficulty-aware Meta-learning for Rare Disease Diagnosiscited by 24
  14. 2020Task Augmentation by Rotating for Meta-Learningcited by 18
  15. 2019Automated Skin Lesion Classification Using Ensemble of Deep Neural Networks in ISIC 2018: Skin Lesion Analysis Towards Melanoma Detection Challengecited by 16
  16. 2020Regularizing Meta-Learning via Gradient Dropoutcited by 15

Built on by

Not cited yet.