Efficient greedy feature selection for unsupervised learning

Farahat, Ahmed K.; Ghodsi, Ali; Kamel, Mohamed S.

doi:10.1007/s10115-012-0538-1

Cited by 78 publications

(48 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In connection to the unsupervised feature selection problem, a variant of the greedy algorithm presented in this paper has previously been proposed for the unsupervised feature selection problem [27,28] where it has shown superior performance to other state-of-the-art methods for unsupervised feature selection. However, the algorithm proposed by Farahat et al [27,28] is centralized and it cannot be easily extended to handle big data that are massively distributed across different machines.…”

Section: Comparison With Related Workmentioning

confidence: 98%

“…However, the algorithm proposed by Farahat et al [27,28] is centralized and it cannot be easily extended to handle big data that are massively distributed across different machines.…”

Section: Comparison With Related Workmentioning

confidence: 98%

“…The minimization of this criterion is a combinatorial optimization problem whose optimal solution can be obtained in O n l mnl [6]. This section describes a deterministic greedy algorithm for optimizing this criterion, which extends the greedy method for unsupervised feature selection recently proposed by Farahat et al [27,28]. First, a recursive formula for the CSS criterion is presented, and then the greedy CSS algorithm is described in details.…”

Section: Greedy Column Subset Selectionmentioning

confidence: 98%

See 2 more Smart Citations

Greedy column subset selection for large-scale data sets

et al. 2014

Self Cite

View full text Add to dashboard Cite

In today's information systems, the availability of massive amounts of data necessitates the development of fast and accurate algorithms to summarize these data and represent them in a succinct format. One crucial problem in big data analytics is the selection of representative instances from large and massively distributed data, which is formally known as the Column Subset Selection problem. The solution to this problem enables data analysts to understand the insights of the data and explore its hidden structure. The selected instances can also be used for data preprocessing tasks such as learning a low-dimensional embedding of the data points or computing a low-rank approximation of the corresponding matrix. This paper presents a fast and accurate greedy algorithm for large-scale column subset selection. The algorithm minimizes an objective function, which measures the reconstruction error of the data matrix based on the subset of selected columns. The paper first presents a centralized greedy algorithm for column subset selection, which depends on a novel recursive formula for calculating the reconstruction error of the data matrix. The paper then presents a MapReduce algorithm, which selects a few representative columns from a matrix whose columns are massively distributed across several commodity machines. The algorithm first A preliminary version of this paper appeared as [26]. This work was completed while the second author was at the University of Waterloo.123 A. K. Farahat et al. learns a concise representation of all columns using random projection, and it then solves a generalized column subset selection problem at each machine in which a subset of columns are selected from the sub-matrix on that machine such that the reconstruction error of the concise representation is minimized. The paper demonstrates the effectiveness and efficiency of the proposed algorithm through an empirical evaluation on benchmark data sets.

show abstract

Section: Comparison With Related Workmentioning

confidence: 98%

“…However, the algorithm proposed by Farahat et al [27,28] is centralized and it cannot be easily extended to handle big data that are massively distributed across different machines.…”

Section: Comparison With Related Workmentioning

confidence: 98%

Section: Greedy Column Subset Selectionmentioning

confidence: 98%

See 1 more Smart Citation

Greedy column subset selection for large-scale data sets

et al. 2014

Self Cite

View full text Add to dashboard Cite

show abstract

“…The proposed framework will be executed in java dialect so it will be stage free. As there is no confinement on the extent of bug's data, an analyzer can include vast number of bugs in the framework [15]. This is one of the greatest preferences of the proposed framework.…”

Section: Automatic Approach For Data Reductionmentioning

confidence: 99%

A data analytics prototype for handling software bug triage procedures

2016

IJLTET

View full text Add to dashboard Cite

“…Dimensionality reduction techniques can be categorized mainly into feature extraction and feature selection (Farahat et al, 2013;Liu and Zheng, 2006;Zhang et al, 2014). The feature extraction methods usually transform the data from the original space into a new space with lower dimension.…”

Section: Introductionmentioning

confidence: 99%