Overcoming the Myopia of Inductive Learning Algorithms with RELIEFF

By Igor Kononenko, E. Simec, Marko Robnik-Sikonja. Applied intelligence (Boston), 2004

770 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Information Systems

View Paper: https://www.semanticscholar.org/paper/8e9e7b8084082e599e16d65cc9539b415ee94738

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 Computational Theory and Mathematics

In Information Systems

Citations in the corpus

A machine learning framework for sport result prediction (2019, methodology): “Principal component analysis (PCA), sequential forward selection, ReliefF attribute evaluation, and correlation based feature subset selection were used [16,21,19,11,19].”
DÏoT: A Federated Self-learning Anomaly Detection System for IoT (2018, methodology): “Since kNN does not provide information about features most useful in classification, we used the ReliefF feature selection algorithm [21] to compute these scores.”
A Survey of Methods for Scaling Up Inductive Algorithms (1999, methodology): “The RELIEF-F algorithm (Kononenko, 1994) uses experiments with randomly drawn examples and a nearest-neighbor representation to identify (even highly interdependent) relevant features (Kononenko et al., 1997).”
A Consistent Estimator of the Expected Gradient Outerproduct (2014, methodology): “In addition to the baselines listed above, in classification experiments we considered another competitor: the popular feature relevance determination method called ReliefF [4, 5].”
A review of feature extraction and performance evaluation in epileptic seizure detection using EEG (2019, methodology): “Fast correlation based-filter proposed in [YL04], correlation-based selection (CFS) [Hal99], and ReliefF established in [KŠRŠ97], were utilized to select non-redundant features and the filtered features were classified by an artificial neural network (ANN).”
Relief-Based Feature Selection: Introduction and Review (2017, background): “However, experiments by (Kononenko et al., 1997) indicated no significant difference between results using diff or squared diff, thus the simplified description of the Relief algorithm has become standard.”
Machine Learning for Sequential Data: A Review (2002, methodology): “Several methods have been developed that identify such interactions including RELIEFF [ 14 ], Markov blankets [13], and feature racing [17].”
Theoretical and Empirical Analysis of ReliefF and RReliefF (2003, methodology): “ReliefF was successfully employed in classification (Kononenko & Šimec, 1995; Kononenko et al., 1997) and RReliefF in regression problems (Robnik Šikonja & Kononenko, 1996, 1997).”