Towards Faithful Local Explanations: Leveraging SVM to Interpret Black-Box Machine Learning Models

Xu, Jiaxiang; Zhang, Zhanhao; Wang, Junfei; Ouyang, Biao; Zhou, Benkuan; Zhao, Jianxiong; Ge, Hanfang; Xu, Bo

doi:10.3390/sym17060950

Open AccessArticle

Towards Faithful Local Explanations: Leveraging SVM to Interpret Black-Box Machine Learning Models

by

Jiaxiang Xu

¹,

Zhanhao Zhang

¹,

Junfei Wang

²,

Biao Ouyang

¹,

Benkuan Zhou

¹,

Jianxiong Zhao

¹,

Hanfang Ge

¹ and

Bo Xu

^1,*

¹

Hubei Key Laboratory of Internet of Intelligence, School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China

²

School of Economics, Huazhong University of Science and Technology, Wuhan 430074, China

^*

Author to whom correspondence should be addressed.

Symmetry 2025, 17(6), 950; https://doi.org/10.3390/sym17060950

Submission received: 8 May 2025 / Revised: 9 June 2025 / Accepted: 12 June 2025 / Published: 15 June 2025

(This article belongs to the Special Issue Symmetry/Asymmetry Studies in Data Mining & Machine Learning of Large Language Models)

Download

Browse Figures

Versions Notes

Abstract

Although machine learning (ML) models are widely used in many fields, their prediction processes are often hard to understand. This lack of transparency makes it harder for people to trust them, especially in high-stakes fields like healthcare and finance. Human-interpretable explanations for model predictions are crucial in these contexts. While existing local interpretation methods have been proposed, many suffer from low local fidelity, instability, and limited effectiveness when applied to highly nonlinear models. This paper presents SVM-X, a model-agnostic local explanation approach designed to address these challenges. By leveraging the inherent symmetry of the SVM hyperplane, SVM-X precisely captures the local decision boundaries of complex nonlinear models, providing more accurate and stable explanations. Experimental evaluations on the UCI Adult dataset, the Bank Marketing dataset, and the Amazon Product Review dataset demonstrate that SVM-X consistently outperforms state-of-the-art methods like LIME and LEMNA. Notably, SVM-X achieves up to a 27.2% improvement in accuracy. Our work introduces a reliable and interpretable framework for understanding machine learning predictions, offering a promising new direction for future research.

Keywords: explainable machine learning; black-box model; support vector machine; local fidelity; interpretation stability

Share and Cite

MDPI and ACS Style

Xu, J.; Zhang, Z.; Wang, J.; Ouyang, B.; Zhou, B.; Zhao, J.; Ge, H.; Xu, B. Towards Faithful Local Explanations: Leveraging SVM to Interpret Black-Box Machine Learning Models. Symmetry 2025, 17, 950. https://doi.org/10.3390/sym17060950

AMA Style

Xu J, Zhang Z, Wang J, Ouyang B, Zhou B, Zhao J, Ge H, Xu B. Towards Faithful Local Explanations: Leveraging SVM to Interpret Black-Box Machine Learning Models. Symmetry. 2025; 17(6):950. https://doi.org/10.3390/sym17060950

Chicago/Turabian Style

Xu, Jiaxiang, Zhanhao Zhang, Junfei Wang, Biao Ouyang, Benkuan Zhou, Jianxiong Zhao, Hanfang Ge, and Bo Xu. 2025. "Towards Faithful Local Explanations: Leveraging SVM to Interpret Black-Box Machine Learning Models" Symmetry 17, no. 6: 950. https://doi.org/10.3390/sym17060950

APA Style

Xu, J., Zhang, Z., Wang, J., Ouyang, B., Zhou, B., Zhao, J., Ge, H., & Xu, B. (2025). Towards Faithful Local Explanations: Leveraging SVM to Interpret Black-Box Machine Learning Models. Symmetry, 17(6), 950. https://doi.org/10.3390/sym17060950

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Towards Faithful Local Explanations: Leveraging SVM to Interpret Black-Box Machine Learning Models

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI