Knowledge-Based Systems ( IF 7.2 ) Pub Date : 2020-11-16 , DOI: 10.1016/j.knosys.2020.106609 Yunxiao Qin , Weiguo Zhang , Chenxu Zhao , Zezheng Wang , Xiangyu Zhu , Jingping Shi , Guojun Qi , Zhen Lei
Recently, meta-learning has been shown to be a promising way to solve few-shot learning. In this paper, inspired by the human cognition process, which utilizes both prior-knowledge and visual attention when learning new knowledge, we present a novel paradigm of meta-learning approach that capitalizes on three developments to introduce attention mechanism and prior-knowledge to meta-learning. In our approach, prior-knowledge is responsible for helping the meta-learner express the input data in a high-level representation space, and the attention mechanism enables the meta-learner to focus on key data features in the representation space. Compared with the existing meta-learning approaches that pay little attention to prior-knowledge and visual attention, our approach alleviates the meta-learner’s few-shot cognition burden. Furthermore, we discover a Task-Over-Fitting (TOF) problem,1 which indicates that the meta-learner has poor generalization across different -shot learning tasks. To model the TOF problem, we propose a novel Cross-Entropy across Tasks (CET) metric.2 Extensive experiments demonstrate that our techniques improve the meta-learner to state-of-the-art performance on several few-shot learning benchmarks while also substantially alleviating the TOF problem.
中文翻译:
基于先验知识和注意力的元学习,适合几次学习
最近,元学习已被证明是解决一次性学习的一种有前途的方法。在本文中,受人类认知过程的启发,该过程在学习新知识时同时利用了先验知识和视觉注意,我们提出了一种新的元学习方法范式,该方法利用了三个方面的发展来介绍元数据的注意力机制和先验知识-学习。在我们的方法中,先验知识负责帮助元学习者在高级表示空间中表达输入数据,而注意力机制使元学习者能够专注于表示空间中的关键数据特征。与现有的元学习方法相比,该方法很少关注先验知识和视觉注意,相比之下,我们的方法减轻了元学习者的几率认知负担。此外,1表示元学习者对不同学习者的概括性较差镜头的学习任务。为了对TOF问题建模,我们提出了一种新颖的跨任务交叉熵(CET)指标。2广泛的实验表明,我们的技术可以在几个快照学习基准上将元学习器提高到最先进的性能,同时还可以大大缓解TOF问题。