Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Learning to Learn Without Labels
Luke Metz, Niru Maheswaranathan, Brian Cheung, Jascha Sohl-Dickstein
Feb 12, 2018 (modified: Feb 12, 2018)ICLR 2018 Workshop Submissionreaders: everyone
Abstract:A major goal of unsupervised learning is for algorithms to learn representations of data, useful for subsequent tasks, without access to supervised labels or other high-level attributes. Typically, these algorithms minimize a surrogate objective, such as reconstruction error or likelihood of a generative model, with the hope that representations useful for subsequent tasks will arise as a side effect (e.g. semi-supervised classification). In this work, we propose using meta-learning to learn an unsupervised learning rule, and meta-optimize the learning rule directly to produce good representations for a desired task. Here, our desired task (meta-objective) is the performance of the representation on semi-supervised classification, and we meta-learn an algorithm -- an unsupervised weight update rule -- that produces representations that perform well under this meta-objective. We examine the performance of the learned algorithm on several datasets and show that it learns useful features, generalizes across both network architectures and a wide array of datasets, and outperforms existing unsupervised learning techniques.
TL;DR:We present a method to meta-learn an algorithm for unsupervised learning.
Keywords:Meta-Learning, unsupervised learning, learning to learn
Enter your feedback below and we'll get back to you as soon as possible.