Learning to Learn Kernels with Variational Random Features

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

TL;DR: A novel meta-learning approach for few-shot classification and regression that achieves strong performance with meta variational random features by leveraging variational inference to learn adaptive kernels.

Abstract: Meta-learning for few-shot learning involves a meta-learner that acquires shared knowledge from a set of prior tasks to improve the performance of a base-learner on new tasks with a small amount of data. Kernels are commonly used in machine learning due to their strong nonlinear learning capacity, which have not yet been fully investigated in the meta-learning scenario for few-shot learning. In this work, we explore kernel approximation with random Fourier features in the meta-learning framework for few-shot learning. We propose learning adaptive kernels by meta variational random features (MetaVRF), which is formulated as a variational inference problem. To explore shared knowledge across diverse tasks, our MetaVRF deploys an LSTM inference network to generate informative features, which can establish kernels of highly representational power with low spectral sampling rates, while also being able to quickly adapt to specific tasks for improved performance. We evaluate MetaVRF on a variety of few-shot learning tasks for both regression and classification. Experimental results demonstrate that our MetaVRF can deliver much better or competitive performance than recent meta-learning algorithms.

Keywords: Meta-learning, few-shot learning, Random Fourier Feature, Kernel learning