arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.06707cs.LGstat.ML
收藏

学习具有变分随机特征的核

Learning to Learn Kernels with Variational Random Features

Inception Institute of Artificial Intelligence(起源人工智能研究院);Informatics Institute, University of Amsterdam(阿姆斯特丹大学信息学研究所);School of Software, Shandong University(山东大学软件学院);College of Computer Science, Nankai University(南开大学计算机学院);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)

Xiantong Zhen, Haoliang Sun, Yingjun Du, Jun Xu, Yilong Yin, Ling Shao, Cees Snoek

摘要:

在这项工作中,我们在元学习框架中引入具有随机傅立叶特征的内核,以利用其强大的少样本学习能力。我们提出了Meta变分随机特征(MetaVRF)学习自适应内核的基础学习者,这是在一个潜在的变量模型,通过治疗的随机特征的基础作为潜在的变量。我们制定的MetaVRF优化作为一个变分推理问题,推导出一个证据下界下的元学习框架。为了整合来自相关任务的共享知识,我们提出了一种后验的上下文推理,它是由LSTM架构建立的。基于LSTM的推理网络可以有效地将先前任务的上下文信息与任务特定信息相结合,生成信息丰富的自适应特征。学习后的MetaVRF可以以相对低的频谱采样率产生具有高表示能力的内核,并且还能够快速适应新任务。在各种Few-Shot回归和分类任务上的实验结果表明,与现有的元学习替代方案相比,MetaVRF提供了更好的性能,或者至少具有竞争力。

英文摘要:

In this work, we introduce kernels with random Fourier features in the meta-learning framework to leverage their strong few-shot learning ability. We propose meta variational random features (MetaVRF) to learn adaptive kernels for the base-learner, which is developed in a latent variable model by treating the random feature basis as the latent variable. We formulate the optimization of MetaVRF as a variational inference problem by deriving an evidence lower bound under the meta-learning framework. To incorporate shared knowledge from related tasks, we propose a context inference of the posterior, which is established by an LSTM architecture. The LSTM-based inference network can effectively integrate the context information of previous tasks with task-specific information, generating informative and adaptive features. The learned MetaVRF can produce kernels of high representational power with a relatively low spectral sampling rate and also enables fast adaptation to new tasks. Experimental results on a variety of few-shot regression and classification tasks demonstrate that MetaVRF delivers much better, or at least competitive, performance compared to existing meta-learning alternatives.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑