Matching Distributions via Optimal Transport for Semi-Supervised Learning

Abstract

Semi-Supervised Learning (SSL) approaches have been an influential framework for the usage of unlabeled data when there is not a sufficient amount of labeled data available over the course of training. SSL methods based on Convolutional Neural Networks (CNNs) have recently provided successful results on standard benchmark tasks such as image classification. In this work, we consider the general setting of SSL problem where the labeled and unlabeled data come from the same underlying probability distribution. We propose a new approach that adopts an Optimal Transport (OT) technique serving as a metric of similarity between discrete empirical probability measures to provide pseudo-labels for the unlabeled data, which can then be used in conjunction with the initial labeled data to train the CNN model in an SSL manner. We have evaluated and compared our proposed method with state-of-the-art SSL algorithms on standard datasets to demonstrate the superiority and effectiveness of our SSL algorithm.

References in corpus (17)

• Adam: A Method for Stochastic Optimization
• Geometric deep learning: going beyond Euclidean data
• Wide Residual Networks
• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
• Temporal Ensembling for Semi-Supervised Learning
• Semi-Supervised Learning with Ladder Networks
• Fast Computation of Wasserstein Barycenters
• DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation
• Learning with Pseudo-Ensembles
• Learning with a Wasserstein Loss
• Sample Complexity of Sinkhorn divergences
• Multilevel Clustering via Wasserstein Means
• Principal Geodesic Analysis for Probability Measures under the Optimal Transport Metric
• Unsupervised Image-to-Image Translation Using Domain-Specific Variational Information Bound
• Borrowing strengh in hierarchical Bayes: Posterior concentration of the Dirichlet base measure
• Detection and Statistical Modeling of Birth-Death Anomaly
• A New Framework For Spatial Modeling And Synthesis of Genome Sequence