Meghana Deodhar

Parallel Simultaneous Co-clustering and Learning with Map-Reduce

Many data mining applications involve predictive modeling of very large, complex datasets. Such applications present a need for innovative algorithms and associated implementations that are not only effective in terms of prediction accuracy, but can also be efficiently run on distributed computational systems to yield results in reasonable time. This paper focuses on predictive modeling of multirelational data such as dyadic data with associated covariates or “side-information”. We first give illustrative examples of applications that involve such data and then describe a general framework based on Simultaneous CO-clustering And Learning (SCOAL), which applies a divide-and-conquer approach to data analysis. We show that the main elements of the SCOAL algorithm can be effectively parallelized using the Map-Reduce framework. Experiments on Amazon’s EC2 demonstrate that the proposed parallelizations result in considerable improvements in run time when using a cluster of machines.

Consensus Clustering for Detection of Overlapping Clusters in Microarray Data

Most clustering algorithms are partitional in nature, assigning each data point to exactly one cluster. However, several real world datasets have inherently overlapping clusters in which a single data point can belong entirely to more than one cluster. This is often the case with gene microarray data since it is possible for a single gene to participate in more than one biological process. This paper deals with a novel application of consensus clustering for detecting overlapping clusters. Our approach takes advantage of the fact that results obtained by applying different clustering algorithms to the same dataset could be different and a consensus across these results could be used to detect overlapping clusters. Moreover we extend a popular model selection approach called X-means (Pelleg and Moore, 2000) to detect the inherent number of overlapping clusters in the data

Active Learning with Multiple Localized Regression Models

Oftentimes businesses face the challenge of requiring costly information to improve the accuracy of prediction tasks. One notable example is obtaining informative customer feedback (e.g., customer-product ratings via costly incentives) to improve the effectiveness of recommender systems. In this paper, we develop a novel active learning approach, which aims to intelligently select informative training instances to be labeled so as to maximally improve the prediction accuracy of a real-valued prediction model. We focus on large, heterogeneous, and dyadic data, and on localized modeling techniques, which have been shown to model such data particularly well, as compared to a single, “global” model. Importantly, dyadic data with covariates is pervasive in contemporary big data applications such as large-scale recommender systems and search advertising. A key benefit from incorporating dyadic information is their simple, meaningful representation of heterogeneous data, in contrast to alternative local modeling...