While large-scale taxonomies--especially for web pages--have been in existence for some time, approaches to automatically classify documents into these taxonomies have met with limited success compared to the more general progress made in text classification. We argue that this stems from three causes: increasing sparsity of training data at deeper nodes in the taxonomy, error propagation where a mistake made high in the hierarchy cannot be recovered, and increasingly complex decision surfaces in higher nodes in the hierarchy. While prior research has focused on the first problem, we introduce methods that target the latter two problems--first by biasing the training distribution to reduce error propagation and second by propagating up "first-guess" expert information in a bottom-up manner before making a refined top down choice. Finally, we present an empirical study demonstrating that the suggested changes lead to 10--30% improvements in F1 scores versus an accepted competitive baseline, hierarchical SVMs.

In this paper, we address the problem of learning when some cases are fully labeled while other cases are only partially labeled, in the form of partial labels. Partial labels are represented as a set of possible labels for each training example, one of which is the correct label. We introduce a discriminative learning approach that incorporates partial label information into the conventional margin-based learning framework. The partial label learning problem is formulated as a convex quadratic optimization minimizing the L2-norm regularized empirical risk using hinge loss. We also present an efficient algorithm for classification in the presence of partial labels. Experiments with different data sets show that partial label information improves the performance of classification when there is traditional fully-labeled data, and also yields reasonable performance in the absence of any fully labeled data.

In this paper we address the problem of combining multiple clusterings without access to the underlying features of the data. This process is known in the literature as clustering ensembles, clustering aggregation, or consensus clustering. Consensus clustering yields a stable and robust final clustering that is in agreement with multiple clusterings. We find that an iterative EM-like method is remarkably effective for this problem. We present an iterative algorithm and its variations for finding clustering consensus. An extensive empirical study compares our proposed algorithms with eleven other consensus clustering methods on four data sets using three different clustering performance metrics. The experimental results show that the new ensemble clustering methods produce clusterings that are as good as, and often better than, these other methods.

In this paper, we survey the current state-of-art models for structured learning problems, including Hidden Markov Model (HMM), Conditional Random Fields (CRF), Averaged Perceptron (AP), Structured SVMs (SVMstruct), Max Margin Markov Networks (M3N), and an integration of search and learning algorithm (SEARN). With all due tuning efforts of various parameters of each model, on the data sets we have applied the models to, we found that SVMstruct enjoys better performance compared with the others. In addition, we also propose a new method which we call the Structured Learning Ensemble (SLE) to combine these structured learning models. Empirical results show that our SLE algorithm provides more accurate solutions compared with the best results of the individual models.

Clustering is ill-defined. Unlike supervised learning where labels lead to crisp performance criteria such as accuracy and squared error, clustering quality depends on how the clusters will be used. Devising clustering criteria that capture what users need is difficult. Most clustering algorithms search for optimal clusterings based on a pre-specified clustering criterion. Our approach differs. We search for many alternate clusterings of the data, and then allow users to select the clustering(s) that best fit their needs. Meta clustering first finds a variety of clusterings and then clusters this diverse set of clusterings so that users must only examine a small number of qualitatively different clusterings. We present methods for automatically generating a diverse set of alternate clusterings, as well as methods for grouping clusterings into meta clusters. We evaluate meta clustering on four test problems and two case studies. Surprisingly, clusterings that would be of most interest to users often are not very compact clusterings.