Positive region preserved random sampling: an efficient feature selection method for massive data

2025-07-01

AI Summary

To address the high computational cost and resource constraints in feature selection for large-scale data, this paper proposes an efficient feature reduction method based on sampling and rough set theory. The method integrates positive-region-preserving sampling, rough dependency computation, and discernibility matrix optimization to enhance scalability and efficiency. Its key contributions are threefold: (1) it quantifies the discriminative power of a feature subset via the proportion of discernible object pairs; (2) it enables *a priori* probabilistic estimation of a lower bound on the subset’s discriminative ability, facilitating controllable reduction; and (3) it achieves both theoretical guarantees and practical performance. Experiments on 11 datasets—including four large-scale ones—demonstrate that the method delivers near-optimal reductions within minutes on a standard PC. Empirically, the achieved discriminative ability consistently exceeds its theoretically estimated lower bound, confirming the approach’s efficiency, interpretability, and reliability.

Technology Category

• Machine Learning: Dimensionality Reduction/Feature Selection
• Search and Optimization: Sampling/Simulation-based Search
• Data Mining & Knowledge Management: Data Compression

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Security and Privacy: Large-scale security measurements

Abstract

Selecting relevant features is an important and necessary step for intelligent machines to maximize their chances of success. However, intelligent machines generally have no enough computing resources when faced with huge volume of data. This paper develops a new method based on sampling techniques and rough set theory to address the challenge of feature selection for massive data. To this end, this paper proposes using the ratio of discernible object pairs to all object pairs that should be distinguished to measure the discriminatory ability of a feature set. Based on this measure, a new feature selection method is proposed. This method constructs positive region preserved samples from massive data to find a feature subset with high discriminatory ability. Compared with other methods, the proposed method has two advantages. First, it is able to select a feature subset that can preserve the discriminatory ability of all the features of the target massive data set within an acceptable time on a personal computer. Second, the lower boundary of the probability of the object pairs that can be discerned using the feature subset selected in all object pairs that should be distinguished can be estimated before finding reducts. Furthermore, 11 data sets of different sizes were used to validate the proposed method. The results show that approximate reducts can be found in a very short period of time, and the discriminatory ability of the final reduct is larger than the estimated lower boundary. Experiments on four large-scale data sets also showed that an approximate reduct with high discriminatory ability can be obtained in reasonable time on a personal computer.

Problem

• Efficient feature selection for massive data sets
• Preserving discriminatory ability with limited computing resources
• Estimating lower boundary of feature subset discernibility probability

Innovation

• Positive region preserved random sampling technique
• Ratio-based discriminatory ability measurement
• Efficient feature selection for massive data