A scalable framework for discovering coherent co-clusters in noisy data

Deodhar, Meghana; Gupta, Garima; Ghosh, Joydeep; Cho, Hyuk; Dhillon, Inderjit S.

doi:10.1145/1553374.1553405

Cited by 29 publications

(24 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the specific context of co-clustering of general data, there have been some prior works such as [37], [6]. However, these models either do not handle relevant object selection, do not exploit pairwise object similarities, and need the number of clusters to be specified a priori.…”

Section: Related Workmentioning

confidence: 99%

Stochastic Blockmodel with Cluster Overlap, Relevance Selection, and Similarity-Based Smoothing

Whang

Rai

Dhillon

2013

2013 IEEE 13th International Conference on Data Mining

View full text Add to dashboard Cite

Abstract-Stochastic blockmodels provide a rich, probabilistic framework for modeling relational data by expressing the objects being modeled in terms of a latent vector representation. This representation can be a latent indicator vector denoting the cluster membership (hard clustering), a vector of cluster membership probabilities (soft clustering), or more generally a real-valued vector (latent space representation). Recently, a new class of overlapping stochastic blockmodels has been proposed where the idea is to allow the objects to have hard memberships in multiple clusters (in form of a latent binary vector). This aspect captures the properties of many real-world networks in domains such as biology and social networks where objects can simultaneously have memberships in multiple clusters owing to the multiple roles they may have. In this paper, we improve upon this model in three key ways: (1) we extend the overlapping stochastic blockmodel to the bipartite graph case which enables us to simultaneously learn the overlapping clustering of two different sets of objects in the graph; the unipartite graph is just a special case of our model, (2) we allow objects (in either set) to not have membership in any cluster by using a relevant object selection mechanism, and (3) we make use of additionally available object features (or a kernel matrix of pairwise object similarities) to further improve the overlapping clustering performance. We do this by explicitly encouraging similar objects to have similar cluster membership vectors. Moreover, using nonparametric Bayesian prior distributions on the key model parameters, we side-step the model selection issues such as selecting the number of clusters a priori. Our model is quite general and can be applied for both overlapping clustering and link prediction tasks in unipartite and bipartite networks (directed/undirected), or for overlapping co-clustering of general binary-valued data. Experiments on synthetic and real-world datasets from biology and social networks demonstrate that our model outperforms several state-of-the-art methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Stochastic Blockmodel with Cluster Overlap, Relevance Selection, and Similarity-Based Smoothing

Whang

Rai

Dhillon

2013

2013 IEEE 13th International Conference on Data Mining

View full text Add to dashboard Cite

show abstract

“…We compared our message passing (EBMP) and greedy (EBG) algorithms with two other coherent biclustering algorithms, Chen&Church [6] (using the BicAT software from http://www.tik.ethz.ch/sop/bicat/) and ROCC [8], on four synthetic datasets. The first two of the four datasets each contain fifteen 10×10 data matrices, and the third and fourth datasets each contain fifteen 50×50 data matrices.…”

Section: Experiments With Synthetic Datamentioning

confidence: 99%

“…Sometimes these names refer to different variants of the biclustering problem: for example, the term "co-clustering" was used in [9] to describe the problem of finding biclusters that form a checkerboard pattern in the data matrix. Applications of biclustering include: finding groups of genes that display similar expression patterns under subsets of time points or conditions [6,13,25,24,21,7,8]; finding groups of users who share interest in certain subsets of movies [25,24]; finding clusters of documents that share subsets of words [9]; and finding correlations between groups of words and phrases in a natural language corpus to induce grammar rules [1,23].…”

Section: Introductionmentioning

confidence: 99%

“…Recent work has explored nonparametric Bayesian models for biclustering [19,15]. Deodhar et al [8] have recently introduced ROCC, a scalable and noise-tolerant biclustering algorithm that can discover an a priori unknown number of arbitrarily positioned, possibly overlapping, coherent biclusters.…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, they do not require that the number of biclusters be pre-specified. To the best of our knowledge, with the exception of the ROCC algorithm [8], few biclustering algorithms simultaneously offer all of these desirable features.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Exemplar-based Robust Coherent Biclustering

Ouyang

Han

et al. 2011

Proceedings of the 2011 SIAM International Conference on Data Mining

View full text Add to dashboard Cite

The biclustering, co-clustering, or subspace clustering problem involves simultaneously grouping the rows and columns of a data matrix to uncover biclusters or sub-matrices of the data matrix that optimize a desired objective function. In coherent biclustering, the objective function contains a coherence measure of the biclusters. We introduce a novel formulation of the coherent biclustering problem and use it to derive two algorithms. The first algorithm is based on loopy message passing; and the second relies on a greedy strategy yielding an algorithm that is significantly faster than the first. A distinguishing feature of these algorithms is that they identify an exemplar or a prototypical member of each bicluster. We note the interference from background elements in biclustering, and offer a means to circumvent such interference using additional regularization. Our experiments with synthetic as well as real-world datasets show that our algorithms are competitive with the current stateof-the-art algorithms for finding coherent biclusters.

show abstract

Co‐clustering numerical data under user‐defined constraints

Pensa

Boulicaut

Cordero

et al. 2009

Statistical Analysis

View full text Add to dashboard Cite

Abstract:In the generic setting of objects × attributes matrix data analysis, co-clustering appears as an interesting unsupervised data mining method. A co-clustering task provides a bi-partition made of co-clusters: each co-cluster is a group of objects associated to a group of attributes and these associations can support expert interpretations. Many constrained clustering algorithms have been proposed to exploit the domain knowledge and to improve partition relevancy in the mono-dimensional clustering case (e.g. using the must-link and cannot-link constraints on one of the two dimensions). Here, we consider constrained co-clustering not only for extended must-link and cannot-link constraints (i.e. both objects and attributes can be involved), but also for interval constraints that enforce properties of co-clusters when considering ordered domains. We describe an iterative co-clustering algorithm which exploits user-defined constraints while minimizing a given objective function. Thanks to a generic setting, we emphasize that different objective functions can be used. The added value of our approach is demonstrated on both synthetic and real data. Among others, several experiments illustrate the practical impact of this original co-clustering setting in the context of gene expression data analysis, and in an original application to a protein motif discovery problem.

show abstract

A scalable framework for discovering coherent co-clusters in noisy data

Cited by 29 publications

References 25 publications

Stochastic Blockmodel with Cluster Overlap, Relevance Selection, and Similarity-Based Smoothing

Stochastic Blockmodel with Cluster Overlap, Relevance Selection, and Similarity-Based Smoothing

Exemplar-based Robust Coherent Biclustering

Co‐clustering numerical data under user‐defined constraints

Contact Info

Product

Resources

About