Block Model Guided Unsupervised Feature Selection

07/05/2020
by   Zilong Bai, et al.
4

Feature selection is a core area of data mining with a recent innovation of graph-driven unsupervised feature selection for linked data. In this setting we have a dataset 𝐘 consisting of n instances each with m features and a corresponding n node graph (whose adjacency matrix is 𝐀) with an edge indicating that the two instances are similar. Existing efforts for unsupervised feature selection on attributed networks have explored either directly regenerating the links by solving for f such that f(𝐲_i,𝐲_j) ≈𝐀_i,j or finding community structure in 𝐀 and using the features in 𝐘 to predict these communities. However, graph-driven unsupervised feature selection remains an understudied area with respect to exploring more complex guidance. Here we take the novel approach of first building a block model on the graph and then using the block model for feature selection. That is, we discover 𝐅𝐌𝐅^T ≈𝐀 and then find a subset of features 𝒮 that induces another graph to preserve both 𝐅 and 𝐌. We call our approach Block Model Guided Unsupervised Feature Selection (BMGUFS). Experimental results show that our method outperforms the state of the art on several real-world public datasets in finding high-quality features for clustering.

READ FULL TEXT
research
06/16/2021

Effective Streaming Evolutionary Feature Selection Using Dynamic Optimization

Feature selection is a key issue in machine learning and data mining. A ...
research
06/12/2018

Diverse Online Feature Selection

Online feature selection has been an active research area in recent year...
research
06/01/2017

Statistical Analysis and Parameter Selection for Mapper

In this article, we study the question of the statistical convergence of...
research
07/02/2021

Few-shot Learning for Unsupervised Feature Selection

We propose a few-shot learning method for unsupervised feature selection...
research
07/09/2020

Let the Data Choose its Features: Differentiable Unsupervised Feature Selection

Scientific observations often consist of a large number of variables (fe...
research
10/09/2020

Nonnegative Spectral Analysis with Adaptive Graph and L_2,0-Norm Regularization for Unsupervised Feature Selection

Feature selection is an important data preprocessing in data mining and ...
research
02/19/2023

Topological Feature Selection: A Graph-Based Filter Feature Selection Approach

In this paper, we introduce a novel unsupervised, graph-based filter fea...

Please sign up or login with your details

Forgot password? Click here to reset