Bio:
Kristen is a fifth-year Ph.D. student at the University of Wisconsin - Madison, where she is advised by Professors David DeWitt and Raghu Ramakrishnan. She received a Bachelor's degree in Computer Science from Dartmouth College in 2002, and spent time as an intern at IBM Almaden Research Center in 2003 and 2005.

Short Bio:
Wolf-Tilo Balke currently is the associate research director of L3S Research Center of University of Hannover, Germany. Before that he was a research fellow at the University of California at Berkeley. His research is in the area of information systems and service provisioning, including middleware retrieval algorithms, preference-based session management, and ontology-based discovery and selection of services. Wolf-Tilo Balke is the recipient of two Emmy-Noether-Grants of the German Research Foundation (DFG) and the Scientific Award of the University Foundation Augsburg. He has received his B.A and MS degree in mathematics and a PhD in computer science from University of Augsburg, Germany

Bio: Dr. Tanya Berger-Wolf is an assistant professor at the Department of Computer Science at the University of Illinois at Chicago. Her research is in applications of algorithmic and data mining techniques to population biology, both human (epidemiology) and animal, from genetics to social interactions. Dr. Berger-Wolf has received her B.Sc. in Computer Science and Mathematics from Hebrew University (Jerusalem, Israel) in 1995 and her Ph.D. in Computer Science from University of Illinois at Urbana-Champaign in 2002. She has spent two years as a postdoctoral fellow at the University of New Mexico working in computational phylogenetics and a year at the Center for Discrete Mathematics and Theoretical Computer Science (DIMACS) doing research in computational epidemiology.

In this paper we explore linkage-based clustering, in which the similarity between two objects is measured based on the similarities between the objects linked with them. In comparison with a previous study (SimRank) that computes links recursively on all pairs of objects, we take advantage of the power law distribution of links, and develop a hierarchical structure called SimTree to represent similarities in multi-granularity manner. This method avoids the high cost of computing and storing pairwise similarities but still thoroughly explore relationships among objects. An efficient algorithm is proposed to compute similarities between objects by avoiding pairwise similarity computations through merging computations that go through the same branches in the SimTree. Experiments show the proposed approach achieves high efficiency, scalability, and accuracy in clustering multi-typed linked objects.

Abstract of FSE'05]: Automated localization of software bugs is one of the essential issues in debugging aids. Previous studies indicated that the evaluation history of program predicates may disclose important clues about underlying bugs. In this paper, we propose a new statistical model-based approach, called SOBER, which localizes software bugs without any prior knowledge of program semantics. Unlike existing statistical debugging approaches that select predicates correlated with program failures, SOBER models evaluation patterns of predicates in both correct and incorrect runs respectively and regards a predicate as bug-relevant if its evaluation pattern in incorrect runs differs significantly from that in correct ones. SOBER features a principled quantification of the pattern difference that measures the bug-relevance of program predicates. We systematically evaluated our approach under the same setting as previous studies. The result demonstrated the power of our approach in bug localization: SOBER can help programmers locate 68 out of 130 bugs in the Siemens suite when programmers are expected to examine no more than 10% of the code, whereas the best previously reported is 52 out of 130. Moreover, with the assistance of SOBER, we found two bugs in bc 1.06 (an arbitrary precision calculator on UNIX/Linux), one of which has never been reported before.

[Abstract of FSE'06]: Recent software systems usually feature an automated fail- ure reporting system, with which a huge number of failing traces are collected every day. In order to prioritize fault diagnosis, failing traces due to the same fault are expected to be grouped together. Previous methods, by hypothesiz- ing that similar failing traces imply the same fault, cluster failing traces based on the literal trace similarity, which we call trace proximity. However, since a fault can be trig- gered in many ways, failing traces due to the same fault can be quite different. Therefore, previous methods actu- ally group together traces exhibiting similar behaviors, like similar branch coverage, rather than traces due to the same fault. In this paper, we propose a new type of failure prox- imity, called R-Proximity, which regards two failing traces as similar if they suggest roughly the same fault location. The fault location each failing case suggests is automati- cally obtained with Sober, an existing statistical debugging tool. We show that with R-Proximity, failing traces due to the same fault can be grouped together. In addition, we find that R-Proximity is helpful for statistical debugging: It can help developers interpret and utilize the statistical debugging result. We illustrate the usage of R-Proximity with a case study on the grep program and some experiments on the Siemens suite, and the result clearly demonstrates the advantage of R-Proximity over trace proximity.

Contextual text mining is concerned with extracting topical themes from a text collection with context information (e.g., time and location) and comparing/analyzing the variations of themes over different contexts. Since the topics covered in a document are usually related to the context of the document, analyzing topical themes within context can potentially reveal many interesting theme patterns. Previous work has addressed a few specific forms of the contextual text mining problem. We propose a new general probabilistic model for contextual text mining that can cover several existing models as special cases. Specifically, we extend the probabilistic latent semantic analysis (PLSA) model by introducing context variables to model the context of a document. The proposed mixture model, called contextual probabilistic latent semantic analysis (CPLSA) model, can be applied to many interesting mining tasks, such as temporal text mining, spatiotemporal text mining, author-topic analysis, event impact analysis, and cross-collection comparative analysis. Empirical experiments show that the proposed mixture model can discover themes and their contextual variations effectively. In this talk, I will introduce the contextual text mining problem, the proposed probabilistic model, and show how it can be regularized to solve different specific mining problems such as spatiotemporal theme pattern mining from weblogs and event impact analysis.

Search Result Summarization and Disambiguation via Contextual Dimensions
Dynamically generated topic hierarchies are a popular method of summarizing the results obtained in response to a query in various search applications. However, topic hierarchies generated by statistical techniques tend to be somewhat unintuitive, rigid and inefficient for browsing and disambiguation. In this talk, we propose an alternative approach to query disambiguation and result summarization. The approach uses a fixed set of orthogonal contextual dimensions to summarize and disambiguate search results. A contextual dimension defines a specific type to a context which makes it incomparable to contexts of other types. For the generic search scenario, we propose to use three types of contextual dimensions, namely, concepts, features, and specializations. We use NLP techniques to extract the three types of contexts, and a data mining algorithm to select a subset of contexts that are as distinct (i.e., mutually exclusive) as possible. Our experimental results show that we can achieve a considerable reduction in the effort required for retrieving relevant documents via the proposed interface.

Efficient Named Entity Recognition using Inverse Index Operations
In this talk, we will present an efficient process for named entity annotation, an important IE problem, using inverse index operations. Named entity annotation involves attaching a label such as `name' or `organization' to a sequence of tokens in a document. The current rule-based and machine learning-based approaches for this task operate at the document level. We present a new and generic approach to entity annotation which uses the inverse index typically created for rapid key-word based searching of a document collection. We define a set of operations on the inverse index that allows us to create annotations defined by cascading regular expressions. The entity annotations for an entire document corpus can be created purely of the index with no need to access the original documents. Experiments on two publicly available data sets show very significant performance improvements over the document-based annotators.

Bio
Raghu Krishnapuram received his Ph.D. degree in electrical and computer engineering from Carnegie Mellon University, Pittsburgh, in 1987. From 1987 to 1997, he was on the faculty of the Department of Computer Engineering and Computer Science at the University of Missouri, Columbia. From 1997 to 2000, Dr. Krishnapuram was a Full Professor at the Department of Mathematical and Computer Sciences, Colorado School of Mines,Golden, Colorado. Since then, he has been at at IBM India Research Lab, New Delhi. Dr. Krishnapuram's research encompasses many aspects of Web mining, information retrieval, e-commerce, fuzzy set theory, neural networks, pattern recognition, computer vision, and image processing. He has published over 160 papers in journals and conferences in these areas. Dr. Krishnapuram is an IEEE Fellow, and a co-author (with J. Bezdek, J. Keller and N. Pal) of the book "Fuzzy Models and Algorithms for Pattern Recognition and Image Processing".

Graph cut optimization provides a plausible approach for the data clustering problem. In this paper, we present a unified framework for several graph-cut optimization problems arising from cluster analysis: the so-called 0-1 semidefinite programming (0-1 SDP). We show that the new model covers the classical K-means (kernel) clustering, constrained K-means clustering, normalized cut and ensemble clustering. Secondly, we consider the issue of how to solve the underlying 0-1 SDP problem. We consider two approximation methods based on singular value decomposition (SVD) of the coefficient matrix and the SVD of the coefficient matrix in a projected subspace, respectively and prove that both algorithms can provide a 2-approximation to the original clustering problem. The complexity of these approximation algorithms are discussed and preliminary numerical results based on the new algorithm are reported.

bio:
Dr. Peng received his PhD degree in 2001, from Delft University of Technology. Then he joined the department of computing and software, McMaster University as an assistant professor. He moved to the department of Industrial and Enterprise System Engineering at UIUC in the summer of 2006. Peng's research interest covers several topics in the field of mathematical programming including modeling and algorithm design. His recent research focuses on developing novel optimization models and algorithms in data mining and machine learning. He has published about 30 scientific research papers and a research monograph. He is currently in the editor-board of Optimization Letters

Motivation: Current approaches for biological network analysis focus mainly on the analysis of a single biological network, providing static descriptions of network features. With the rapid accumulation of biological networks generated under different conditions, there is an urgent need to analyze the dynamics of biological networks, i.e. how network features change with conditions. Such dynamic descriptions will provide deeper insights into cellular organization and pathway coordination.

Results: We developed a novel algorithm, NETBICLUSTER, to identify condition-specific network modules from a large number of biological networks. The NETBICLUSTER algorithm not only identifies network modules corresponding to particular biological processes, but also mines non-dense network sub-graph patterns and more importantly, provides network dynamics information such as condition-specific activation and pathway cross-talking. Applying NETBICLUSTER to 97 mouse gene co-expression networks derived from micro-array datasets, we discovered a large number of functionally homogeneous network modules and dataset conditions under which they are activated and deactivated.

To see more about Prof. Zhou, please visit her website at http://www.cmb.usc.edu/people/xjzhou/.

With the advent of RFID (Radio Frequency Identification) technology, manufacturers, distributors, and retailers will be able to track the movement of individual objects throughout the supply chain. The volume of data generated by a typical RFID application will be enormous as each item will generate a complete history of all the individual locations that it occupied at every point in time, possibly from a specific production line at a given factory, passing through multiple warehouses, and all the way to a particular checkout counter in a store. The movement trails of such RFID data form gigantic commodity flowgraph representing the locations and durations of the path stages traversed by each item. This commodity flow contains rich multi-dimensional information on the characteristics, trends, changes and outliers of commodity movements.

In this paper, we propose a method to construct a warehouse of commodity flows, called flowcube. As in standard OLAP, the model will be composed of cuboids that aggregate item flows at a given abstraction level. The flowcube differs from the traditional data cube in two major ways. First, the measure of each cell will not be a scalar aggregate but a commodity flowgraph that captures the major movement trends and significant deviations of the items aggregated in the cell. Second, each flowgraph itself can be viewed at multiple levels by changing the level of abstraction of path stages. In this paper, we motivate the importance of the model, and present an efficient method to compute it by (1) performing simultaneous aggregation of paths to all interesting abstraction levels, (2) pruning low support path segments along the item and path stage abstraction lattices, and (3) compressing the cube by removing rarely occurring cells, and cells whose commodity flows can be inferred from higher level cells.