SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.06707 · ICML · 2020

Learning to Learn Kernels with Variational Random Features

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

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We introduce kernels with random Fourier features in the meta-learning framework for few-shot learning. 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 LSTMbased inference network effectively integrates the context information of previous tasks with taskspecific information, generating informative and adaptive features. The learned MetaVRF is able to 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 can deliver much better, or at least competitive, performance compared to existing metalearning alternatives.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2006.06707")
get_code_for_paper("2006.06707")
have("2006.06707")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2006.06707.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2006.06707.svg)](https://syntology.ai/paper/2006.06707)

Connect an agent — have() is free.