Unsupervised feature selection for principal components analysis

By Christos Boutsidis, Michael W. Mahoney, Petros Drineas. 2008

136 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Nojun Kwak
2. Seonguk Park
3. Xuelong Li
4. Feiping Nie
5. Jiliang Tang
6. Dacheng Tao
7. Huan Liu
8. Deng Cai

In Molecular Biology

1. Nojun Kwak
2. Seonguk Park
3. Huan Liu
4. Jiliang Tang
5. Mohamed S. Kamel
6. Ahmed K. Farahat
7. A. Ghodsi
8. Xuelong Li

Citations in the corpus

• FEED: Feature-level Ensemble for Knowledge Distillation (2019, methodology): “Reconstruction errors were used as a criterion for feature selection or PCAs in (Boutsidis, Mahoney, and Drineas 2008; Farahat, Ghodsi, and Kamel 2011; Li, Tang, and Liu 2017; Masaeli et al. 2010), where they use linear models.”
• An improved approximation algorithm for the column subset selection problem (2008, background): “oncept of “PCA-correlated SNPs” (Single Nucleotide Polymorphisms) was introduced and applied to classify individuals from throughout the world without the need for any prior ancestry information. See [3] for a detailed evaluation of our main algorithm as an unsupervised feature selection strategy in”
• Reconstruction-based Unsupervised Feature Selection: An Embedded Approach (2017, background): “Recently, data reconstruction error [Boutsidis et al., 2008; Masaeli et al., 2010; Farahat et al., 2011] has emerged as another criterion for unsupervised feature selection.”
• Unsupervised feature selection for multi-cluster data (2010, methodology): “To overcome this problem, feature selection techniques [3, 4, 17, 21, 29, 30] are designed to reduce the dimensionality by finding a relevant feature subset.”
• Supervised, Unsupervised, and Semi-Supervised Feature Selection: A Review on Gene Selection (2016, methodology): “For example, Abeel et al. [57] and Tan et al. [58] implemented ensemble feature selection methods by using linear SVM-RFE as the selection mechanism.”
• Feature-Level Ensemble Knowledge Distillation for Aggregating Knowledge from Multiple Networks (2020, methodology): “Reconstruction errors were used as a criterion for feature selection or PCAs in [2, 5, 16, 17], where they use linear models.”
• Handbook of Big Data (2016, background): “In order to simply see some AN running, the reader may paste the following code into an R interpreter: source("http://stat.wharton.upenn.edu/~buja/association-navigator.R") p -200 mymatrix -matrix(rnorm(20000),ncol=p) colnames(mymatrix) - paste("V", 1:p, "_", c(rep("A",p/2),rep("B",p/2)), sep="")…”
• An Efficient Greedy Method for Unsupervised Feature Selection (2011, methodology): “Boutsidis et al. [6], [7] propose a feature selection method that randomly samples features based on probabilities calculated using the k-leading singular values of the data matrix.”
• Joint Embedding Learning and Sparse Regression: A Framework for Unsupervised Feature Selection (2014, background): “Besides, there are also some other related researches to extend PCA for feature selection, such as Principle Feature Analysis [31] and the works in [32], [33].”