We provide a principle for semi-supervised learning based on optimizing the rate of communicating labels for unlabeled points with side information. The side information is expressed in terms of identities of sets of points or regions with the purpose of biasing the labels in each region to be the same. The resulting regularization objective is convex, has a unique solution, and the solution ca...

Semi-supervised learning methods address the problem of building classifiers when labeled data is scarce. Text classification is often augmented by rich set of labeled features representing a particular class. As tuple level labling is resource consuming, semi-supervised and weakly supervised learning methods are explored recently. Compared to labeling data instances (documents), feature labeli...

A foundational problem in semi-supervised learning is the construction of a graph underlying the data. We propose to use a method which optimally combines a number of differently constructed graphs. For each of these graphs we associate a basic graph kernel. We then compute an optimal combined kernel. This kernel solves an extended regularization problem which requires a joint minimization over...

The use of data-adapted kernels has been shown to lead to state-of-the-art results in machine learning tasks, especially in the context of semi-supervised and transductive learning. We introduce a general framework for analysis both of data sets and functions defined on them. Our approach is based on diffusion operators, adapted not only to the intrinsic geometry of the data, but also to the fu...

An ensemble is generated by training multiple component learners for a same task and then combining them for predictions. It is known that when lots of trained learners are available, it is better to ensemble some instead of all of them. The selection, however, is generally difficult and heuristics are often used. In this paper, we investigate the problem under the regularization framework, and...

Budgeted learning under constraints on both the amount of labeled information and the availability of features at test time pertains to a large number of real world problems. Ideas from multi-view learning, semisupervised learning, and even active learning have applicability, but a common framework whose assumptions fit these problem spaces is non-trivial to construct. We leverage ideas from th...

We study the convergence properties of an alternating proximal minimization algorithm for nonconvex structured functions of the type: L(x, y) = f(x)+Q(x, y)+g(y), where f : Rn → R∪{+∞} and g : Rm → R∪{+∞} are proper lower semicontinuous functions, and Q : Rn × Rm → R is a smooth C function which couples the variables x and y. The algorithm can be viewed as a proximal regularization of the usual...

Sentiment classification aims to automatically predict sentiment polarity (e.g., positive or negative) of user-generated sentiment data (e.g., reviews, blogs). To obtain sentiment classification with high accuracy, supervised techniques require a large amount of manually labeled data. The labeling work can be time-consuming and expensive, which makes unsupervised (or semisupervised) sentiment a...

Inferring latent attributes of online users has many applications in public health, politics, and marketing. Most existing approaches rely on supervised learning algorithms, which require manual data annotation and therefore are costly to develop and adapt over time. In this paper, we propose a lightly supervised approach based on label regularization to infer the age, ethnicity, and political ...

In classification, semi-supervised learning occurs when a large amount of unlabeled data is available with only a small number of labeled data. In such a situation, how to enhance predictability of classification through unlabeled data is the focus. In this article, we introduce a novel large margin semi-supervised learning methodology, using grouping information from unlabeled data, together w...