Generalized Fisher Score for Feature Selection
read the original abstract
Fisher score is one of the most widely used supervised feature selection methods. However, it selects each feature independently according to their scores under the Fisher criterion, which leads to a suboptimal subset of features. In this paper, we present a generalized Fisher score to jointly select features. It aims at finding an subset of features, which maximize the lower bound of traditional Fisher score. The resulting feature selection problem is a mixed integer programming, which can be reformulated as a quadratically constrained linear programming (QCLP). It is solved by cutting plane algorithm, in each iteration of which a multiple kernel learning problem is solved alternatively by multivariate ridge regression and projected gradient descent. Experiments on benchmark data sets indicate that the proposed method outperforms Fisher score as well as many other state-of-the-art feature selection methods.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
Power law scaling for classification accuracy in physical neural networks
HTC predicts PNN classification loss via a power law, with experimental and simulated data from distinct physical systems collapsing onto task-specific curves.
-
nCMD: Benign-Anchored Feature Selection for Imbalanced Network Intrusion Detection
nCMD is a benign-anchored feature selection method that matches or exceeds classical baselines in macro F1-score for imbalanced network intrusion detection on four benchmark datasets.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.