Generalized Fisher Score for Feature Selection

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.

Cited by in corpus (11)

• Infinite Feature Selection: A Graph-based Feature Filtering Approach
• An overview of artificial intelligence techniques for diagnosis of Schizophrenia based on magnetic resonance imaging modalities: Methods, challenges, and future works
• Fast Genetic Algorithm for feature selection -- A qualitative approximation approach
• An Effective Feature Selection Method Based on Pair-Wise Feature Proximity for High Dimensional Low Sample Size Data
• Training on the test set? An analysis of Spampinato et al. [31]
• DLow: Diversifying Latent Flows for Diverse Human Motion Prediction
• Calibrated steganalysis of mp3stego in multi-encoder scenario
• An Embedded Feature Selection Framework for Control
• A Hybrid Feature Selection and Construction Method for Detection of Wind Turbine Generator Heating Faults
• Unsupervised Feature Selection via Multi-step Markov Transition Probability
• Important Molecular Descriptors Selection Using Self Tuned Reweighted Sampling Method for Prediction of Antituberculosis Activity