Unsupervised feature selection for multi-cluster data

By Deng Cai, Chiyuan Zhang, Xiaofei He. Knowledge Discovery and Data Mining, 2010

1,136 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/b526950bf959c886448f05ae9b2fb71895ae993b

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Molecular Biology

Citations in the corpus

A review of unsupervised feature selection methods (2019, methodology): “Finally, in the third step, after solving the regression problem, MCFS selects d features based on the highest absolute values of the coefficients obtained through the regression problem.”
Learning ordinal discriminative features for age estimation (2012, background): “[3] proposed a multi-cluster feature selection approach, which selected those features such that the multi-cluster structure of the data can be best preserved.”
Unsupervised Feature Selection with Structured Graph Optimization (2016, methodology): “It seems that embedded approaches, such as MCFS, UDFS, RSFS, RUFS, have better performance than LS.”
An Efficient Greedy Method for Unsupervised Feature Selection (2011, methodology): “Recently, Cai et al. [11] propose an algorithm called Multi-Cluster Feature Selection (MCFS) which selects a subset of features such that the multi-cluster structure of the data is preserved.”
Clustering-Guided Sparse Structural Learning for Unsupervised Feature Selection (2014, methodology): “Clustering is a commonly used learning algorithm [11], [12], [26].”
Feature Selection (2016, methodology): “MCFS consists of three steps.”
RolX: structural role extraction & mining in large graphs (2012, methodology): “Some methods for feature extraction explicitly preserve the multi-cluster structure in the data [4].”
Unsupervised Feature Selection Using Nonnegative Spectral Analysis (2012, methodology): “Finally, UDFS and NDFS achieve higher ACC and NMI by evaluating features jointly than others that select features one after another or using two-step strategies.”
Pattern Recognition (2018, positive): “As pointed out by Wu et al. [5] , spatial data augmentation including random cropping, random scale and random rotation does not improve performance.”
Feature Selection for Clustering: A Review (2018, methodology): “MCFS shows improvement over other methods such as LS according to [11].”
Robust Joint Graph Sparse Coding for Unsupervised Spectral Feature Selection (2017, methodology): “In contrast, both the MCFS and the MRSF separately conduct manifold learning and sparse regression to result in a suboptimum solution.”
A Unified Feature Selection Framework for Graph Embedding on High Dimensional Data (2015, methodology): “For SPCA, we chose the features with the highest absolute magnitudes of the weight matrix, similar to [32].”
We Can Hear You with Wi-Fi! (2014, methodology): “To avoid the well-known “dimensionality curse” [27], We apply a Multi-Cluster/Class Feature Selection (MCFS) scheme [18] to extract representative features from wavelet profiles to reduce the quantity of sub-waveforms.”
Reconstruction-based Unsupervised Feature Selection: An Embedded Approach (2017, methodology): “• In text data, i.e., RELATHE and BASEHOCK, and gene data, i.e., Lung and GLIOMA, REFS greatly improves the clustering performance in terms of both NMI and ACC.”
Robust Structured Subspace Learning for Data Representation (2015, background): “, Accuracy (ACC) and normalized mutual information (NMI) [18], [19].”