小样本学习(Few-Shot Learning,以下简称 FSL )用于解决当可用的数据量比较少时,如何提升神经网络的性能。在 FSL 中,经常用到的一类方法被称为 Meta-learning。和普通的神经网络的训练方法一样,Meta-learning 也包含训练过程和测试过程,但是它的训练过程被称作 Meta-training 和 Meta-testing。

VIP内容

简介:小样本学习(Few-shot Learning)近年来吸引了大量的关注,但是针对多标签问题(Multi-label)的研究还相对较少。在本文中,我们以用户意图检测任务为切入口,研究了的小样本多标签分类问题。对于多标签分类的SOTA方法往往会先估计标签-样本相关性得分,然后使用阈值来选择多个关联的标签。 为了在只有几个样本的Few-shot场景下确定合适的阈值,我们首先在数据丰富的多个领域上学习通用阈值设置经验,然后采用一种基于非参数学习的校准(Calibration)将阈值适配到Few-shot的领域上。 为了更好地计算标签-样本相关性得分,我们将标签名称嵌入作为表示(Embedding)空间中的锚点,以优化不同类别的表示,使它们在表示空间中更好的彼此分离。 在两个数据集上进行的实验表明,所提出的模型在1-shot和5-shot实验均明显优于最强的基线模型(baseline)。

https://www.zhuanzhi.ai/paper/caf3b2b72106ee93d00ddbe2416c4e1a

成为VIP会员查看完整内容
0
21

最新内容

Current deep reinforcement learning (RL) algorithms are still highly task-specific and lack the ability to generalize to new environments. Lifelong learning (LLL), however, aims at solving multiple tasks sequentially by efficiently transferring and using knowledge between tasks. Despite a surge of interest in lifelong RL in recent years, the lack of a realistic testbed makes robust evaluation of LLL algorithms difficult. Multi-agent RL (MARL), on the other hand, can be seen as a natural scenario for lifelong RL due to its inherent non-stationarity, since the agents' policies change over time. In this work, we introduce a multi-agent lifelong learning testbed that supports both zero-shot and few-shot settings. Our setup is based on Hanabi -- a partially-observable, fully cooperative multi-agent game that has been shown to be challenging for zero-shot coordination. Its large strategy space makes it a desirable environment for lifelong RL tasks. We evaluate several recent MARL methods, and benchmark state-of-the-art LLL algorithms in limited memory and computation regimes to shed light on their strengths and weaknesses. This continual learning paradigm also provides us with a pragmatic way of going beyond centralized training which is the most commonly used training protocol in MARL. We empirically show that the agents trained in our setup are able to coordinate well with unseen agents, without any additional assumptions made by previous works.

0
0
下载
预览

最新论文

Current deep reinforcement learning (RL) algorithms are still highly task-specific and lack the ability to generalize to new environments. Lifelong learning (LLL), however, aims at solving multiple tasks sequentially by efficiently transferring and using knowledge between tasks. Despite a surge of interest in lifelong RL in recent years, the lack of a realistic testbed makes robust evaluation of LLL algorithms difficult. Multi-agent RL (MARL), on the other hand, can be seen as a natural scenario for lifelong RL due to its inherent non-stationarity, since the agents' policies change over time. In this work, we introduce a multi-agent lifelong learning testbed that supports both zero-shot and few-shot settings. Our setup is based on Hanabi -- a partially-observable, fully cooperative multi-agent game that has been shown to be challenging for zero-shot coordination. Its large strategy space makes it a desirable environment for lifelong RL tasks. We evaluate several recent MARL methods, and benchmark state-of-the-art LLL algorithms in limited memory and computation regimes to shed light on their strengths and weaknesses. This continual learning paradigm also provides us with a pragmatic way of going beyond centralized training which is the most commonly used training protocol in MARL. We empirically show that the agents trained in our setup are able to coordinate well with unseen agents, without any additional assumptions made by previous works.

0
0
下载
预览
Top