A review of feature selection methods on synthetic data

By Verónica Bolón-Canedo, Noelia Sánchez-Maroño, Amparo Alonso-Betanzos. Knowledge and Information Systems, 2013

836 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/7981a767bc0b57ad41187d31c8b62a3df89610df

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

Synthea: An approach, method, and software mechanism for generating synthetic patients and the synthetic electronic health care record (2017, methodology): “A well-documented but incorrect method is therefore preferable to any other method where the documentation itself is incomplete.(33) Nonetheless, multiple researchers have reported that the documentation of SDG methods is almost always incomplete, insufficient in detail, and replete with omissions.”
Recent advances and emerging challenges of feature selection in the context of big data (2015, methodology): “There is some evidence that good accuracy can be achieved by classifiers with embedded capacities even when the set of selected features is less than optimal [32].”
A comprehensive survey on recent metaheuristics for feature selection (2022, background): “algorithms to observe their performance on the task of selecting features [64].”
Feature selection for high-dimensional data (2016, background): “In addition to these works, we have performed our own review [6], in which we evaluated the performance of several state-of-the-art feature selection algorithms in an artificial controlled scenario, checking their efficiency in tackling problems such as redundancy between features, nonlinearity, noi”
Feature Selection: A literature Review (2014, methodology): “First, the Filter Approach exploits the general characteristics of training data with independent of the mining algorithm [6].”
Relief-Based Feature Selection: Introduction and Review (2017, methodology): “A large variety of feature selection methodologies have been proposed and research continues to support the claim that there is no universal “best” method for all tasks (Bolón-Canedo et al., 2013).”
A review of microarray datasets and applied feature selection methods (2014, background): “However, there were also attempts to tackle microarray data with multivariate methods, which are able to model feature dependencies, but at the cost of being slower and less scalable than univariate techniques [26].”
Synthetic Data for Deep Learning (2019, background): “This approach is widely used throughout the field, sometimes for entire meta-analyses [65], and we do not dwell on it here; our subject is synthetic data used to transfer to real data rather than direct comparisons between models on synthetic datasets.”
Complete Search for Feature Selection in Decision Trees (2019, background): “The wrapper model for feature selection has shown superior performance in many contexts (Doak, 1992; Bolón-Canedo et al., 2013).”
Machine Learning for Synthetic Data Generation: a Review (2023, background): “In most cases, synthetic data is required when real data is either unavailable or must be kept private for privacy or compliance risks [10, 13, 14].”