Contrastive and generative graph convolutional networks for graph-based semi-supervised learning
Abstract Graph-based Semi-Supervised Learning (SSL) aims to transfer the labels of a
handful of labeled data to the remaining massive unlabeled data via a graph. As one of the …
handful of labeled data to the remaining massive unlabeled data via a graph. As one of the …
Multi-modal curriculum learning for semi-supervised image classification
Semi-supervised image classification aims to classify a large quantity of unlabeled images
by typically harnessing scarce labeled images. Existing semi-supervised methods often …
by typically harnessing scarce labeled images. Existing semi-supervised methods often …
Contrastive graph poisson networks: Semi-supervised learning with extremely limited labels
Abstract Graph Neural Networks (GNNs) have achieved remarkable performance in the task
of semi-supervised node classification. However, most existing GNN models require …
of semi-supervised node classification. However, most existing GNN models require …
Universal semi-supervised learning
Abstract Universal Semi-Supervised Learning (UniSSL) aims to solve the open-set problem
where both the class distribution (ie, class set) and feature distribution (ie, feature domain) …
where both the class distribution (ie, class set) and feature distribution (ie, feature domain) …
Semi-supervised nonnegative matrix factorization via constraint propagation
As is well known, nonnegative matrix factorization (NMF) is a popular nonnegative
dimensionality reduction method which has been widely used in computer vision, document …
dimensionality reduction method which has been widely used in computer vision, document …
Tattoo inks for optical biosensing in interstitial fluid
The persistence of traditional tattoo inks presents an advantage for continuous and long‐
term health monitoring in point of care devices. The replacement of tattoo pigments with …
term health monitoring in point of care devices. The replacement of tattoo pigments with …
Label propagation via teaching-to-learn and learning-to-teach
How to propagate label information from labeled examples to unlabeled examples over a
graph has been intensively studied for a long time. Existing graph-based propagation …
graph has been intensively studied for a long time. Existing graph-based propagation …
Region-kernel-based support vector machines for hyperspectral image classification
This paper proposes a region kernel to measure the region-to-region distance similarity for
hyperspectral image (HSI) classification. The region kernel is designed to be a linear …
hyperspectral image (HSI) classification. The region kernel is designed to be a linear …
A regularization approach for instance-based superset label learning
Different from the traditional supervised learning in which each training example has only
one explicit label, superset label learning (SLL) refers to the problem that a training example …
one explicit label, superset label learning (SLL) refers to the problem that a training example …
Learning hierarchical spectral–spatial features for hyperspectral image classification
This paper proposes a spectral-spatial feature learning (SSFL) method to obtain robust
features of hyperspectral images (HSIs). It combines the spectral feature learning and spatial …
features of hyperspectral images (HSIs). It combines the spectral feature learning and spatial …