Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning

TL;DR

This paper introduces Transductive Propagation Network (TPN), a meta-learning framework that propagates labels across test sets to improve few-shot learning by leveraging data manifold structures.

Contribution

The paper presents a novel transductive meta-learning method that jointly learns feature embedding and graph construction for label propagation in few-shot learning.

Findings

TPN outperforms existing methods on benchmark datasets.

Achieves state-of-the-art results in few-shot classification.

Effectively leverages data manifold structures for label propagation.

Abstract

The goal of few-shot learning is to learn a classifier that generalizes well even when trained with a limited number of training instances per class. The recently introduced meta-learning approaches tackle this problem by learning a generic classifier across a large number of multiclass classification tasks and generalizing the model to a new task. Yet, even with such meta-learning, the low-data problem in the novel classification task still remains. In this paper, we propose Transductive Propagation Network (TPN), a novel meta-learning framework for transductive inference that classifies the entire test set at once to alleviate the low-data problem. Specifically, we propose to learn to propagate labels from labeled instances to unlabeled test instances, by learning a graph construction module that exploits the manifold structure in the data. TPN jointly learns both the parameters of feature embedding and the graph construction in an end-to-end manner. We validate TPN on multiple benchmark datasets, on which it largely outperforms existing few-shot learning approaches and achieves the state-of-the-art results.