Traditionally, feature selection methods work directly on labeled examples. However, the availability of labeled examples cannot be taken for granted for many real world applications, such as medical diagnosis, forensic science, fraud detection, etc, where labeled examples are hard to find. This practical problem calls the need for “semi-supervised feature selection” to choose the optimal set o...

Most semi-supervised learning algorithms have been designed for binary classification, and are extended to multi-class classification by approaches such as one-against-the-rest. The main shortcoming of these approaches is that they are unable to exploit the fact that each example is only assigned to one class. Additional problems with extending semisupervised binary classifiers to multi-class p...

Automated detection and segmentation of pulmonary nodules on lung computed tomography (CT) scans can facilitate early lung cancer diagnosis. Existing supervised approaches for automated nodule segmentation on CT scans require voxel-based annotations for training, which are labor- and time-consuming to obtain. In this work, we propose a weakly-supervised method that generates accurate voxel-leve...

Semi-supervised classification has become an active topic recently and a number of algorithms, such as Self-training, have been proposed to improve the performance of supervised classification using unlabeled data. In this paper, we propose a semi-supervised learning framework which combines clustering and classification. Our motivation is that clustering analysis is a powerful knowledge-discov...

The self-supervised learning (SSL) paradigm is an essential exploration area, which tries to eliminate the need for expensive data labeling. Despite great success of SSL methods in computer vision and natural language processing, most them employ contrastive objectives that require negative samples, are hard define. This becomes even more challenging case graphs a bottleneck achieving robust re...

We propose a family of learning algorithms based on a new form of regularization that allows us to exploit the geometry of the marginal distribution. We focus on a semi-supervised framework that incorporates labeled and unlabeled data in a general-purpose learner. Some transductive graph learning algorithms and standard methods including Support Vector Machines and Regularized Least Squares can...

We propose a family of learning algorithms based on a new form of regularization that allows us to exploit the geometry of the marginal distribution. We focus on a semi-supervised framework that incorporates labeled and unlabeled data in a general-purpose learner. Some transductive graph learning algorithms and standard methods including Support Vector Machines and Regularized Least Squares can...