# Expert Training: Task Hardness Aware Meta-Learning for Few-Shot Classification

arXiv: https://arxiv.org/abs/2007.06240 · HTML: https://mlsanity.com/paper/2007.06240/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jul 2020.

## Built on by (most cited first, 6 of 6)

- [PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition](https://mlsanity.com/paper/2109.04145/) (2021)
- [Exploring Task Difficulty for Few-Shot Relation Extraction](https://mlsanity.com/paper/2109.05473/) (2021)
- [Uniform Sampling over Episode Difficulty](https://mlsanity.com/paper/2108.01662/) (2021)
- [Hardness-guided domain adaptation to recognise biomedical named entities under low-resource scenarios](https://mlsanity.com/paper/2211.05980/) (2022)
- [Task Attended Meta-Learning for Few-Shot Learning](https://mlsanity.com/paper/2106.10642/) (2021)
- [Oops, I Sampled it Again: Reinterpreting Confidence Intervals in Few-Shot Learning](https://mlsanity.com/paper/2409.02850/) (2024)

## Abstract (arXiv)

Deep neural networks are highly effective when a large number of labeled samples are available but fail with few-shot classification tasks. Recently, meta-learning methods have received much attention, which train a meta-learner on massive additional tasks to gain the knowledge to instruct the few-shot classification. Usually, the training tasks are randomly sampled and performed indiscriminately, often making the meta-learner stuck into a bad local optimum. Some works in the optimization of deep neural networks have shown that a better arrangement of training data can make the classifier converge faster and perform better. Inspired by this idea, we propose an easy-to-hard expert meta-training strategy to arrange the training tasks properly, where easy tasks are preferred in the first phase, then, hard tasks are emphasized in the second phase. A task hardness aware module is designed and integrated into the training procedure to estimate the hardness of a task based on the distinguishability of its categories. In addition, we explore multiple hardness measurements including the semantic relation, the pairwise Euclidean distance, the Hausdorff distance, and the Hilbert-Schmidt independence criterion. Experimental results on the miniImageNet and tieredImageNetSketch datasets show that the meta-learners can obtain better results with our expert training strategy.