Unsupervised Learning via Meta-Learning
This addresses the challenge of learning effective representations without labeled data for downstream tasks, though it appears incremental as it builds on existing meta-learning and unsupervised techniques.
The paper tackles the problem of unsupervised learning by proposing a meta-learning method that optimizes for learning downstream tasks from small amounts of labeled data, using automatically constructed tasks from unlabeled data. It shows improved performance over four prior methods across four image datasets.
A central goal of unsupervised learning is to acquire representations from unlabeled data or experience that can be used for more effective learning of downstream tasks from modest amounts of labeled data. Many prior unsupervised learning works aim to do so by developing proxy objectives based on reconstruction, disentanglement, prediction, and other metrics. Instead, we develop an unsupervised meta-learning method that explicitly optimizes for the ability to learn a variety of tasks from small amounts of data. To do so, we construct tasks from unlabeled data in an automatic way and run meta-learning over the constructed tasks. Surprisingly, we find that, when integrated with meta-learning, relatively simple task construction mechanisms, such as clustering embeddings, lead to good performance on a variety of downstream, human-specified tasks. Our experiments across four image datasets indicate that our unsupervised meta-learning approach acquires a learning algorithm without any labeled data that is applicable to a wide range of downstream classification tasks, improving upon the embedding learned by four prior unsupervised learning methods.