Meta Learning,元学习,也叫 Learning to Learn(学会学习)。是继Reinforcement Learning(增强学习)之后又一个重要的研究分支。

知识荟萃

综述

基础算法

元强化学习

应用

视觉应用

其它应用

数据集

视频课程

书籍

代码

领域专家


初步版本,水平有限,有错误或者不完善的地方,欢迎大家提建议和补充,会一直保持更新,本文为专知内容组原创内容,未经允许不得转载,如需转载请发送邮件至fangquanyi@gmail.com 或 联系微信专知小助手(Rancho_Fang)

敬请关注http://www.zhuanzhi.ai 和关注专知公众号,获取第一手AI相关知识

最近更新:2019-12-10

VIP内容

神经序列标记被广泛应用于许多自然语言处理(NLP)任务,如命名实体识别(NER)和用于对话系统和语义分析的槽标记。最近,大规模的预训练语言模型在这些任务中显示出了显著的成功,只要对大量特定任务的标记数据进行微调。然而,获取这样大规模的标记训练数据不仅代价昂贵,而且由于数据访问和隐私限制,在许多敏感用户应用中可能不可行。如果序列标记任务需要在标记级进行这样的注释,这种情况就会加剧。在这项工作中,我们提出以解决标签短缺的神经序列标记模型。具体来说,我们提出了一个元自训练框架,它利用很少的手工标注标签来训练神经序列模型。自训练是一种通过迭代知识交换从大量无标记数据中学习的有效机制,而元学习有助于自适应样本重加权,以减少噪声伪标记带来的误差传播。在6个基准数据集上的大量实验表明了该方法的有效性,其中包括2个用于大规模多语言NER的基准数据集和4个用于面向任务的对话系统的槽标记数据集。在每个任务中,每个类别只有10个标注的例子,该方法比目前最先进的方法提高了10%,证明了其在有限的训练标签体系中的有效性。

https://www.microsoft.com/en-us/research/uploads/prod/2020/10/MetaST_Few_shot_KDD_2021.pdf

成为VIP会员查看完整内容
0
15

最新论文

Bi-Level Optimization (BLO) is originated from the area of economic game theory and then introduced into the optimization community. BLO is able to handle problems with a hierarchical structure, involving two levels of optimization tasks, where one task is nested inside the other. In machine learning and computer vision fields, despite the different motivations and mechanisms, a lot of complex problems, such as hyper-parameter optimization, multi-task and meta-learning, neural architecture search, adversarial learning and deep reinforcement learning, actually all contain a series of closely related subproblms. In this paper, we first uniformly express these complex learning and vision problems from the perspective of BLO. Then we construct a best-response-based single-level reformulation and establish a unified algorithmic framework to understand and formulate mainstream gradient-based BLO methodologies, covering aspects ranging from fundamental automatic differentiation schemes to various accelerations, simplifications, extensions and their convergence and complexity properties. Last but not least, we discuss the potentials of our unified BLO framework for designing new algorithms and point out some promising directions for future research.

0
0
下载
预览
Top