Learning Prototype-oriented Set Representations for Meta-Learning

Abstract

Learning from set-structured data is a fundamental problem that has recently attracted increasing attention, where a series of summary networks are introduced to deal with the set input. In fact, many meta-learning problems can be treated as set-input tasks. Most existing summary networks aim to design different architectures for the input set in order to enforce permutation invariance. However, scant attention has been paid to the common cases where different sets in a meta-distribution are closely related and share certain statistical properties. Viewing each set as a distribution over a set of global prototypes, this paper provides a novel prototype-oriented optimal transport (POT) framework to improve existing summary networks. To learn the distribution over the global prototypes, we minimize its regularized optimal transport distance to the set empirical distribution over data points, providing a natural unsupervised way to improve the summary network. Since our plug-and-play framework can be applied to many meta-learning problems, we further instantiate it to the cases of few-shot classification and implicit meta generative modeling. Extensive experiments demonstrate that our framework significantly improves the existing summary networks on learning more powerful summary statistics from sets and can be successfully integrated into metric-based few-shot classification and generative modeling applications, providing a promising tool for addressing set-input and meta-learning problems.

References in corpus (14)

• Sequence to Sequence Learning with Neural Networks
• Conditional Generative Adversarial Nets
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Data Augmentation Generative Adversarial Networks
• DenseNet: Implementing Efficient ConvNet Descriptor Pyramids
• On First-Order Meta-Learning Algorithms
• FIGR: Few-shot Image Generation with Reptile
• On Learning Sets of Symmetric Elements
• On the Limitations of Representing Functions on Sets
• DAWSON: A Domain Adaptive Few Shot Generation Framework
• Set-to-Sequence Methods in Machine Learning: a Review
• DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Delta