Shoestring: Graph-Based Semi-Supervised Learning with Severely Limited Labeled Data

TL;DR

Shoestring is a graph-based semi-supervised learning framework that effectively leverages very limited labeled data to improve classification performance across various domains, including image and text classification.

Contribution

The paper introduces Shoestring, a novel end-to-end framework that enhances semi-supervised learning with severely limited labels by semantic transfer and metric learning, achieving state-of-the-art results.

Findings

Achieves state-of-the-art node classification with few labels.

Significant improvements in few-shot image classification on miniImageNet and tieredImageNet.

Effective in leveraging limited labeled data for diverse classification tasks.

Abstract

Graph-based semi-supervised learning has been shown to be one of the most effective approaches for classification tasks from a wide range of domains, such as image classification and text classification, as they can exploit the connectivity patterns between labeled and unlabeled samples to improve learning performance. In this work, we advance this effective learning paradigm towards a scenario where labeled data are severely limited. More specifically, we address the problem of graph-based semi-supervised learning in the presence of severely limited labeled samples, and propose a new framework, called {\em Shoestring}, that improves the learning performance through semantic transfer from these very few labeled samples to large numbers of unlabeled samples. In particular, our framework learns a metric space in which classification can be performed by computing the similarity to centroid embedding of each class. {\em Shoestring} is trained in an end-to-end fashion to learn to leverage the semantic knowledge of limited labeled samples as well as their connectivity patterns with large numbers of unlabeled samples simultaneously. By combining {\em Shoestring} with graph convolutional networks, label propagation and their recent label-efficient variations (IGCN and GLP), we are able to achieve state-of-the-art node classification performance in the presence of very few labeled samples. In addition, we demonstrate the effectiveness of our framework on image classification tasks in the few-shot learning regime, with significant gains on miniImageNet ($2.57\%\sim3.59\%$) and tieredImageNet ($1.05\%\sim2.70\%$).