Improved Differential Evolution based Feature Selection through Quantum, Chaos, and Lasso

TL;DR

This work tackles feature subset selection for high-dimensional data with an emphasis on interpretability. It introduces chaotic, quantum-inspired differential evolution (QBDE) enhanced by Lyapunov-exponent guided chaos, a threshold trick for quantum-to-binary encoding, and Lasso-assisted pruning, all implemented in an island-based Spark parallel framework. Two variants, CLQBDE-I (non-gate) and CLQBDE-II (gate), are evaluated against BDE and CQIEA across large medical datasets, using $AUC$ as the wrapper objective with LR/LLR classifiers. Results show that Lyapunov-guided chaotic initialization improves exploration and reduces cardinality while achieving higher $AUC$ on high-dimensional problems, offering scalable, interpretable feature selection with practical impact for medical analytics.

Abstract

Modern deep learning continues to achieve outstanding performance on an astounding variety of high-dimensional tasks. In practice, this is obtained by fitting deep neural models to all the input data with minimal feature engineering, thus sacrificing interpretability in many cases. However, in applications such as medicine, where interpretability is crucial, feature subset selection becomes an important problem. Metaheuristics such as Binary Differential Evolution are a popular approach to feature selection, and the research literature continues to introduce novel ideas, drawn from quantum computing and chaos theory, for instance, to improve them. In this paper, we demonstrate that introducing chaos-generated variables, generated from considerations of the Lyapunov time, in place of random variables in quantum-inspired metaheuristics significantly improves their performance on high-dimensional medical classification tasks and outperforms other approaches. We show that this chaos-induced improvement is a general phenomenon by demonstrating it for multiple varieties of underlying quantum-inspired metaheuristics. Performance is further enhanced through Lasso-assisted feature pruning. At the implementation level, we vastly speed up our algorithms through a scalable island-based computing cluster parallelization technique.

Figures (3)

• Figure 1: Generic framework of the proposed wrappers
• Figure 2: Generic schematic diagram of the island model based wrapper
• Figure 3: Histograms