论文标题
普遍的增强元学习以进行几次优化
Generalized Reinforcement Meta Learning for Few-Shot Optimization
论文作者
论文摘要
我们提出了一个基于少量学习问题的基于通用且灵活的增强学习（RL）的元学习框架。在培训期间，它通过利用损失表面中的稳定模式来学习最佳的优化算法，以产生学习者（排名/分类器等）。我们的方法隐含地估算了缩放损耗函数的梯度，同时保留了参数更新的一般属性。除了在几个射击任务上提供改进的性能外，我们的框架还可以轻松扩展到进行网络体系结构搜索。我们进一步提出了一种新型的双重编码器，基于亲和力得分的解码器拓扑，可实现额外的性能。在内部数据集，MQ2007和AWA2上进行的实验表明，我们的方法在准确性和NDCG指标上分别优于现有的替代方法，分别高出21％，8％和4％。在迷你imagenet数据集上，我们的方法与原型网络实现了可比的结果。经验评估表明，我们的方法提供了一个统一有效的框架。
We present a generic and flexible Reinforcement Learning (RL) based meta-learning framework for the problem of few-shot learning. During training, it learns the best optimization algorithm to produce a learner (ranker/classifier, etc) by exploiting stable patterns in loss surfaces. Our method implicitly estimates the gradients of a scaled loss function while retaining the general properties intact for parameter updates. Besides providing improved performance on few-shot tasks, our framework could be easily extended to do network architecture search. We further propose a novel dual encoder, affinity-score based decoder topology that achieves additional improvements to performance. Experiments on an internal dataset, MQ2007, and AwA2 show our approach outperforms existing alternative approaches by 21%, 8%, and 4% respectively on accuracy and NDCG metrics. On Mini-ImageNet dataset our approach achieves comparable results with Prototypical Networks. Empirical evaluations demonstrate that our approach provides a unified and effective framework.
