论文标题
基于优化的元学习适应阶段更快
Faster Optimization-Based Meta-Learning Adaptation Phase
论文作者
论文摘要
神经网络需要大量的注释数据才能学习。元学习算法提出了一种将训练样本数量减少到少数的方法。最突出的基于优化的元学习算法之一是模型敏捷的元学习（MAML）。但是，适应MAML新任务的关键过程非常慢。在这项工作中，我们提出了对MAML元学习算法的改进。我们介绍了lambda模式，通过这些模式，我们限制了在适应阶段在网络中更新的重量。这使得可以跳过某些梯度计算。选择最快的模式给定允许的质量降解阈值参数。在某些情况下，通过仔细的模式选择可以提高质量。进行的实验表明，通过Lambda适应模式选择，可以在以下领域显着改善MAML方法：自适应时间已减少了3倍，而精度损失最小；一步适应的准确性已大大提高。
Neural networks require a large amount of annotated data to learn. Meta-learning algorithms propose a way to decrease the number of training samples to only a few. One of the most prominent optimization-based meta-learning algorithms is Model-Agnostic Meta-Learning (MAML). However, the key procedure of adaptation to new tasks in MAML is quite slow. In this work we propose an improvement to MAML meta-learning algorithm. We introduce Lambda patterns by which we restrict which weight are updated in the network during the adaptation phase. This makes it possible to skip certain gradient computations. The fastest pattern is selected given an allowed quality degradation threshold parameter. In certain cases, quality improvement is possible by a careful pattern selection. The experiments conducted have shown that via Lambda adaptation pattern selection, it is possible to significantly improve the MAML method in the following areas: adaptation time has been decreased by a factor of 3 with minimal accuracy loss; accuracy for one-step adaptation has been substantially improved.
