S. Khodadadeh, S. Zehtabian, S. Vahidian, Weijia Wang, Bill Lin, and L. Bölöni

Unsupervised Meta-Learning through Latent-Space Interpolation in Generative Models


Cite as:

S. Khodadadeh, S. Zehtabian, S. Vahidian, Weijia Wang, Bill Lin, and L. Bölöni. Unsupervised Meta-Learning through Latent-Space Interpolation in Generative Models. arXiv preprint arXiv:2006.10236, 2020.

Download:

(unavailable)

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.

BibTeX:

@article{Khodadadeh-2020-LASIUM,
  author = "S. Khodadadeh and S. Zehtabian and S. Vahidian and Weijia Wang and Bill Lin and L. B{\"o}l{\"o}ni",
  title = "Unsupervised Meta-Learning through Latent-Space Interpolation in Generative Models",
  journal={arXiv preprint arXiv:2006.10236},
  year={2020},
  xxxbooktitle = "submitted to ICLR-2021",
  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.
  },
}

Generated by bib2html.pl (written by Patrick Riley, Lotzi Boloni ) on Fri Jan 29, 2021 20:15:22