Mining maximal quasi‐bicliques: Novel algorithm and applications in the stock market and protein networks

Sim, Kelvin; Li, Jinyan; Gopalkrishnan, Vivekanand; Liu, Guimei

doi:10.1002/sam.10051

Cited by 36 publications

(34 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The QBs defined by [1,31,46] are inclined to have skewed distribution of missing edges in their QBs, as the missing edges allowed in each vertex of their QBs are not restricted. QBs defined by [4,28,38,39] have this missing edges restrictions on each vertex of their quasi-biclique. Due to the high computation costs of mining QB subgraphs, only [28,38,39,46] mine the complete set of results, while [1,4,31] do not.…”

Section: Related Workmentioning

confidence: 98%

“…QBs defined by [4,28,38,39] have this missing edges restrictions on each vertex of their quasi-biclique. Due to the high computation costs of mining QB subgraphs, only [28,38,39,46] mine the complete set of results, while [1,4,31] do not. Sim et al [38] proposed clustering stocks with similar financial ratio values, but their clustering technique is limited only to a year, and they did not study the relation between financial ratios and price movements of stocks.…”

Section: Related Workmentioning

confidence: 98%

“…There are several works in mining quasi-biclique (QB) subgraphs from a single graph [1,4,28,31,38,39,46], and not from a set of bipartite graphs. The QBs defined by [1,31,46] are inclined to have skewed distribution of missing edges in their QBs, as the missing edges allowed in each vertex of their QBs are not restricted.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

A case study on financial ratios via cross-graph quasi-bicliques

Sim

Liu

Gopalkrishnan

et al. 2011

Information Sciences

Self Cite

View full text Add to dashboard Cite

a b s t r a c tStocks with similar financial ratio values across years have similar price movements. We investigate this hypothesis by clustering groups of stocks that exhibit homogeneous financial ratio values across years, and then study their price movements. We propose using cross-graph quasi-biclique (CGQB) subgraphs to cluster stocks, as they can define the three dimensional (3D) subspaces of financial ratios that the stocks are homogeneous in across the years, and they can also handle missing values that are rampant in the stock data. Furthermore, investors can easily analyze these 3D subspaces to explore the relations between the stocks and financial ratios. We develop a novel algorithm, CGQBminer, which mines the complete set of CGQB subgraphs from the stock data. Through experimental analysis, we show that the hypothesis is valid. Furthermore, we demonstrate that having an investment strategy which uses groups of stocks mined by CGQB subgraphs have higher returns than one that does not. We also conducted an extensive performance analysis on CGQBminer, and show that it is efficient across different 3D datasets and parameter settings.

show abstract

Section: Related Workmentioning

confidence: 98%

Section: Related Workmentioning

confidence: 98%

See 1 more Smart Citation

A case study on financial ratios via cross-graph quasi-bicliques

Sim

Liu

Gopalkrishnan

et al. 2011

Information Sciences

Self Cite

View full text Add to dashboard Cite

show abstract

“…In graph mining, a typical goal is to find all maximal quasibicliques satisfying a density condition. For example, Sim et al [12] give an algorithm to mine all maximal quasi-bicliques where each vertex is connected to all but ε ∈ N vertices in the other side (for other algorithms, see [8]). Such algorithms can be used to find the quasi-biclique that best represents the data (in terms of error), but only by exhaustively iterating over density values.…”

Section: Related Workmentioning

confidence: 99%

Detecting Bicliques in GF[q]

Ramon

Miettinen

Vreeken

2013

Advanced Information Systems Engineering

View full text Add to dashboard Cite

Abstract. We consider the problem of finding planted bicliques in random matrices over GF [q]. That is, our input matrix is a GF [q]-sum of an unknown biclique (rank-1 matrix) and a random matrix. We study different models for the random graphs and characterize the conditions when the planted biclique can be recovered. We also empirically show that a simple heuristic can reliably recover the planted bicliques when our theory predicts that they are recoverable. Existing methods can detect bicliques of O( √ N ), while it is NP-hard to find the largest such clique. Real graphs, however, are typically extremely sparse and seldom contain such large bicliques. Further, the noise can destroy parts of the planted biclique. We investigate the practical problem of how small a biclique can be and how much noise there can be such that we can still approximately correctly identify the biclique. Our derivations show that with high probability planted bicliques of size logarithmic in the network size can be detected in data following the Erdős-Rényi model and two bipartite variants of the Barabási-Albert model.

show abstract

“…Mining of quasi bi-cliques has been previously successfully applied in fields like the stock market and protein networks [28]. Our algorithm combines and extends approaches from [15] and [28] to yield a new method to compute the quasi-modules .…”

Section: Introductionmentioning

confidence: 99%

Finding quasi-modules of human and viral miRNAs: a case study of human cytomegalovirus (HCMV)

Veksler-Lublinsky

Shemer‐Avni

Meiri³

et al. 2012

BMC Bioinformatics

View full text Add to dashboard Cite

BackgroundMicroRNAs (miRNAs) are important regulators of gene expression encoded by a variety of organisms, including viruses. Although the function of most of the viral miRNAs is currently unknown, there is evidence that both viral and host miRNAs contribute to the interactions between viruses and their hosts. miRNAs constitute a complex combinatorial network, where one miRNA may target many genes and one gene may be targeted by multiple miRNAs. In particular, viral and host miRNAs may also have mutual target genes. Based on published evidence linking viral and host miRNAs there are three modes of mutual regulation: competing, cooperating, and compensating modes.ResultsIn this paper we explore the compensating mode of mutual regulation upon Human Cytomegalovirus (HCMV) infection, when host miRNAs are down regulated and viral miRNAs compensate by mimicking their function. To achieve this, we develop a new algorithm which finds groups, called quasi-modules, of viral and host miRNAs and their mutual target genes, and use a new host miRNA expression data for HCMV-infected and uninfected cells. For two of the reported quasi-modules, supporting evidence from biological and medical literature is provided.ConclusionsThe modules found by our method may advance the understanding of the role of miRNAs in host-viral interactions, and the genes in these modules may serve as candidates for further experimental validation.

show abstract

Mining maximal quasi‐bicliques: Novel algorithm and applications in the stock market and protein networks

Cited by 36 publications

References 29 publications

A case study on financial ratios via cross-graph quasi-bicliques

A case study on financial ratios via cross-graph quasi-bicliques

Detecting Bicliques in GF[q]

Finding quasi-modules of human and viral miRNAs: a case study of human cytomegalovirus (HCMV)

Contact Info

Product

Resources

About