Quantum Phases Classification Using Quantum Machine Learning with SHAP-Driven Feature Selection
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915243366547456 |
|---|---|
| author | Franco, Giovanni S. Mahlow, Felipe Prado, Pedro M. Pexe, Guilherme E. L. Rattighieri, Lucas A. M. Fanchini, Felipe F. |
| author_facet | Franco, Giovanni S. Mahlow, Felipe Prado, Pedro M. Pexe, Guilherme E. L. Rattighieri, Lucas A. M. Fanchini, Felipe F. |
| contents | In this study, we present an innovative methodology to classify quantum phases within the ANNNI (Axial Next-Nearest Neighbor Ising) model by combining Quantum Machine Learning (QML) techniques with the Shapley Additive Explanations (SHAP) algorithm for feature selection and interpretability. Our investigation focuses on two prominent QML algorithms: Quantum Support Vector Machines (QSVM) and Variational Quantum Classifiers (VQC). By leveraging SHAP, we systematically identify the most relevant features within the dataset, ensuring that only the most informative variables are utilized for training and testing. The results reveal that both QSVM and VQC exhibit exceptional predictive accuracy when limited to 5 or 6 key features, thereby enhancing performance and reducing computational overhead. This approach not only demonstrates the effectiveness of feature selection in improving classification outcomes but also offers insights into the interpretability of quantum classification tasks. The proposed framework exemplifies the potential of interdisciplinary solutions for addressing challenges in the classification of quantum systems, contributing to advancements in both machine learning and quantum physics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_10673 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Quantum Phases Classification Using Quantum Machine Learning with SHAP-Driven Feature Selection Franco, Giovanni S. Mahlow, Felipe Prado, Pedro M. Pexe, Guilherme E. L. Rattighieri, Lucas A. M. Fanchini, Felipe F. Quantum Physics In this study, we present an innovative methodology to classify quantum phases within the ANNNI (Axial Next-Nearest Neighbor Ising) model by combining Quantum Machine Learning (QML) techniques with the Shapley Additive Explanations (SHAP) algorithm for feature selection and interpretability. Our investigation focuses on two prominent QML algorithms: Quantum Support Vector Machines (QSVM) and Variational Quantum Classifiers (VQC). By leveraging SHAP, we systematically identify the most relevant features within the dataset, ensuring that only the most informative variables are utilized for training and testing. The results reveal that both QSVM and VQC exhibit exceptional predictive accuracy when limited to 5 or 6 key features, thereby enhancing performance and reducing computational overhead. This approach not only demonstrates the effectiveness of feature selection in improving classification outcomes but also offers insights into the interpretability of quantum classification tasks. The proposed framework exemplifies the potential of interdisciplinary solutions for addressing challenges in the classification of quantum systems, contributing to advancements in both machine learning and quantum physics. |
| title | Quantum Phases Classification Using Quantum Machine Learning with SHAP-Driven Feature Selection |
| topic | Quantum Physics |
| url | https://arxiv.org/abs/2504.10673 |