Unsupervised Meta-Learning through Latent-Space Interpolation in Generative Models
Abstract
Unsupervised meta-learning approaches rely on synthetic meta-tasks that are created using techniques such as random selection, clustering and/or augmentation. Unfortunately, clustering and augmentation are domain-dependent, and thus they require either manual tweaking or expensive learning. In this work, we describe an approach that generates meta-tasks using generative models. A critical component is a novel approach of sampling from the latent space that generates objects grouped into synthetic classes forming the training and validation data of a meta-task. We find that the proposed approach, LAtent Space Interpolation Unsupervised Meta-learning (LASIUM), outperforms or is competitive with current unsupervised learning baselines on few-shot classification tasks on the most widely used benchmark datasets. In addition, the approach promises to be applicable without manual tweaking over a wider range of domains than previous approaches.
Cite
@article{arxiv.2006.10236,
title = {Unsupervised Meta-Learning through Latent-Space Interpolation in Generative Models},
author = {Siavash Khodadadeh and Sharare Zehtabian and Saeed Vahidian and Weijia Wang and Bill Lin and Ladislau Bölöni},
journal= {arXiv preprint arXiv:2006.10236},
year = {2020}
}