Through experiments on various meta-learning methods, task samplers, and few-shot learning tasks, this paper arrives at three conclusions. Firstly, there are no universal task sampling strategies to guarantee the performance of meta-learning models. Secondly, task diversity can cause the models to either underfit or overfit during training. Lastly, the generalization performance of the models are influenced by task divergence, task entropy, and task difficulty. In response to these findings, we propose a novel task sampler called Adaptive Sampler (ASr). ASr is a plug-and-play task sampler that takes task divergence, task entropy, and task difficulty to sample tasks. To optimize ASr, we rethink and propose a simple and general meta-learning algorithm. Finally, a large number of empirical experiments demonstrate the effectiveness of the proposed ASr.

通过对不同的元学习方法、任务采样器和少样本学习任务进行实验，本文得出三个结论：首先，没有通用的任务采样策略可以保证元学习模型的性能；其次，任务多样性可能导致模型在训练过程中出现欠拟合或过拟合的情况；最后，模型的泛化性能受到任务差异、任务熵和任务难度的影响。为了应对这些发现，我们提出了一种新颖的任务采样器，称为自适应采样器（ASr）。ASr是一种即插即用的任务采样器，利用任务差异、任务熵和任务难度进行任务采样。为了优化ASr，我们重新思考并提出了一个简单而通用的元学习算法。最后，大量的实证实验证明了所提出的ASr的有效性。

元学习任务采样学习