Contrastive and generative graph convolutional networks for graph-based semi-supervised learning

S Wan, S Pan, J Yang, C Gong - … of the AAAI conference on artificial …, 2021 - ojs.aaai.org
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 …

Multi-modal curriculum learning for semi-supervised image classification

C Gong, D Tao, SJ Maybank, W Liu… - IEEE Transactions on …, 2016 - ieeexplore.ieee.org
Semi-supervised image classification aims to classify a large quantity of unlabeled images
by typically harnessing scarce labeled images. Existing semi-supervised methods often …

Contrastive graph poisson networks: Semi-supervised learning with extremely limited labels

S Wan, Y Zhan, L Liu, B Yu, S Pan… - Advances in Neural …, 2021 - proceedings.neurips.cc
Abstract Graph Neural Networks (GNNs) have achieved remarkable performance in the task
of semi-supervised node classification. However, most existing GNN models require …

Universal semi-supervised learning

Z Huang, C Xue, B Han, J Yang… - Advances in Neural …, 2021 - proceedings.neurips.cc
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) …

Semi-supervised nonnegative matrix factorization via constraint propagation

D Wang, X Gao, X Wang - IEEE transactions on cybernetics, 2015 - ieeexplore.ieee.org
As is well known, nonnegative matrix factorization (NMF) is a popular nonnegative
dimensionality reduction method which has been widely used in computer vision, document …

Tattoo inks for optical biosensing in interstitial fluid

MD Pazos, Y Hu, Y Elani, KL Browning… - Advanced …, 2021 - Wiley Online Library
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 …

Label propagation via teaching-to-learn and learning-to-teach

C Gong, D Tao, W Liu, L Liu… - IEEE transactions on …, 2016 - ieeexplore.ieee.org
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 …

Region-kernel-based support vector machines for hyperspectral image classification

J Peng, Y Zhou, CLP Chen - IEEE Transactions on Geoscience …, 2015 - ieeexplore.ieee.org
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 …

A regularization approach for instance-based superset label learning

C Gong, T Liu, Y Tang, J Yang… - IEEE transactions on …, 2017 - ieeexplore.ieee.org
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 …

Learning hierarchical spectral–spatial features for hyperspectral image classification

Y Zhou, Y Wei - IEEE transactions on cybernetics, 2015 - ieeexplore.ieee.org
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 …