Link prediction is a key technique in many applications such as recommender systems, where potential links between users and items need to be predicted. A challenge in link predic...
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...
The `kernel approach' has attracted great attention with the development of support vector machine (SVM) and has been studied in a general way. It offers an alternative soluti...
Bias/variance analysis is a useful tool for investigating the performance of machine learning algorithms. Conventional analysis decomposes loss into errors due to aspects of the le...
Modeling the evolution of topics with time is of great value in automatic summarization and analysis of large document collections. In this work, we propose a new probabilistic gr...
Ramesh Nallapati, Susan Ditmore, John D. Lafferty,...