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

by   Wanyu Lin, et al.

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 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. 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 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%∼3.59%) and tieredImageNet (1.05%∼2.70%).


page 1

page 2

page 3

page 4


Learning to Impute: A General Framework for Semi-supervised Learning

Recent semi-supervised learning methods have shown to achieve comparable...

Semisupervised Learning on Heterogeneous Graphs and its Applications to Facebook News Feed

Graph-based semi-supervised learning is a fundamental machine learning p...

L^γ-PageRank for Semi-Supervised Learning

PageRank for Semi-Supervised Learning has shown to leverage data structu...

Mathematical Foundations of Graph-Based Bayesian Semi-Supervised Learning

In recent decades, science and engineering have been revolutionized by a...

Sparse Activity and Sparse Connectivity in Supervised Learning

Sparseness is a useful regularizer for learning in a wide range of appli...

A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learning

In this paper, we proposed a general framework for data poisoning attack...

JADE: Joint Autoencoders for Dis-Entanglement

The problem of feature disentanglement has been explored in the literatu...

Please sign up or login with your details

Forgot password? Click here to reset