Unsupervised graph-based feature selection via subspace and pagerank centrality

Abstract

Feature selection has become an indispensable part of intelligent systems, especially with the proliferation of high dimensional data. It identifies the subset of discriminative features leading to better learning performances, i.e., higher learning accuracy, lower computational cost and significant model interpretability. This paper proposes a new efficient unsupervised feature selection method based on graph centrality and subspace learning called UGFS for 'Unsupervised Graph-based Feature Selection'. The method maps features on an affinity graph where the relationships (edges) between feature nodes are defined by means of data points subspace preference. Feature importance score is then computed on the entire graph using a centrality measure. For this purpose, we investigated the Google's PageRank method originally introduced to rank web-pages. The proposed feature selection method has been evaluated using classification and redundancy rates measured on the selected feature subsets. Comparisons with the well-known unsupervised feature selection methods, on gene/expression benchmark datasets, demonstrate the validity and the efficiency of the proposed method.

Cluster Density Properties Define a Graph for Effective Pattern Feature Selection

“…The drawbacks of the ECFS algorithm have motivated the development of the UGFS method [15], where features are graph nodes linked according to subspace preference clusters [6], i.e., features that correspond to significant cluster discrimination are linked. According to subspace learning [28], [41], the variance of the k-nearest neighbors of each data point indicate the most relevant features.…”

“…These latter are extracted and located on a graph, then the pageRank centrality measure is used to rank features mapped onto this graph. The UGFS performed significantly better than other methods, although three drawbacks have been noted: (i) the elements in a k-nearest neighbors set may belong to different clusters, and therefore, the search for cluster discriminating features may be unduly affected; (ii)considering all data points for feature combination may unduly change the results, especially if the data set contains outliers; and (iii) the correlation between features is not exploited as a means to disfavor the redundant features [15].…”

“…Feature selection methods can be divided into three categories according to their label information availability: (i) supervised methods, such as Relief [13]; (ii) semisupervised, such as Feature Selection Via Manifold Regularization (FS-Manifold) [14] and, (iii) unsupervised methods, such as Unsupervised Graph-based Feature Selection (UGFS) and Unsupervised Discriminative Feature Selection (UDFS) [15], [16]. Unsupervised methods have attracted wide attention due to the considerable cost and time required to acquire labelled data.…”

“…The main limitation of this algorithm is that it only accounts for feature redundancy in the graph design, using rather simple statistical considerations. In contrast to the ECFS, UGFS is an unsupervised graph-based method that represents the feature space by a graph that is designed through jointing data neighbourhood information and subspace learning [15].…”

Supervised machine learning for classification mining and ranking of illegal web contents = Aprendizaje automático supervisado para la clasificación, extracción de conocimiento y ordenación de contenidos web ilegales

“…Graph data structures have been used widely to represent a set of entities with their connections, including, but not limited to, social network analysis (Scott, 1988;Backstrom and Kleinberg, 2014;Ji et al, 2016), and data mining (Al-Nabki et al, 2017b). Henni et al (2018) used a graph-based approach to build an unsupervised feature selection method, whereas nodes correspond to features, and the graph edges captured the relationship between those features. Next, to assign an importance score for each feature, they addressed several graph centrality measures, and, in particular, PageRank algorithm.…”