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

arXiv: https://arxiv.org/abs/2206.04335 · HTML: https://mlsanity.com/paper/2206.04335/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 37 references that are in the map.
- First posted on arXiv 9 Jun 2022.

## Builds on (most cited first, 28 of 28)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [Learning to learn by gradient descent by gradient descent](https://mlsanity.com/paper/1606.04474/) (2016)
- [Meta-Learning with Latent Embedding Optimization](https://mlsanity.com/paper/1807.05960/) (2018)
- [PCN: Point Completion Network](https://mlsanity.com/paper/1808.00671/) (2018)
- [Meta-SGD: Learning to Learn Quickly for Few-Shot Learning](https://mlsanity.com/paper/1707.09835/) (2017)
- [Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML](https://mlsanity.com/paper/1909.09157/) (2019)
- [Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples](https://mlsanity.com/paper/1903.03096/) (2019)
- [Meta-Transfer Learning for Few-Shot Learning](https://mlsanity.com/paper/1812.02391/) (2018)
- [PU-Net: Point Cloud Upsampling Network](https://mlsanity.com/paper/1801.06761/) (2018)
- [Task-Agnostic Meta-Learning for Few-shot Learning](https://mlsanity.com/paper/1805.07722/) (2018)
- [Learned Optimizers that Scale and Generalize](https://mlsanity.com/paper/1703.04813/) (2017)
- [Meta-Learning without Memorization](https://mlsanity.com/paper/1912.03820/) (2019)
- [Hierarchically Structured Meta-learning](https://mlsanity.com/paper/1905.05301/) (2019)
- [Meta-Learning Requires Meta-Augmentation](https://mlsanity.com/paper/2007.05549/) (2020)
- [Improving Generalization in Meta-learning via Task Augmentation](https://mlsanity.com/paper/2007.13040/) (2020)
- [Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Tasks](https://mlsanity.com/paper/1905.12917/) (2019)
- [Meta-Learning with Fewer Tasks through Task Interpolation](https://mlsanity.com/paper/2106.02695/) (2021)
- [Data Augmentation for Meta-Learning](https://mlsanity.com/paper/2010.07092/) (2020)
- [MetaFun: Meta-Learning with Iterative Functional Updates](https://mlsanity.com/paper/1912.02738/) (2019)
- [Meta-learning with an Adaptive Task Scheduler](https://mlsanity.com/paper/2110.14057/) (2021)
- [Difficulty-aware Meta-learning for Rare Disease Diagnosis](https://mlsanity.com/paper/1907.00354/) (2019)
- [Task Augmentation by Rotating for Meta-Learning](https://mlsanity.com/paper/2003.00804/) (2020)
- [Automated Skin Lesion Classification Using Ensemble of Deep Neural Networks in ISIC 2018: Skin Lesion Analysis Towards Melanoma Detection Challenge](https://mlsanity.com/paper/1901.10802/) (2019)
- [Regularizing Meta-Learning via Gradient Dropout](https://mlsanity.com/paper/2004.05859/) (2020)

## 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.