A Novel XAI-Enhanced Quantum Adversarial Networks for Velocity Dispersion Modeling in MaNGA Galaxies

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Narkedimilli, Sathwik, Kumar, N V Saran, H, Aswath Babu, Vanahalli, Manjunath K, M, Manish, Jain, Vinija, Chadha, Aman
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917048192335872
author Narkedimilli, Sathwik
Kumar, N V Saran
H, Aswath Babu
Vanahalli, Manjunath K
M, Manish
Jain, Vinija
Chadha, Aman
author_facet Narkedimilli, Sathwik
Kumar, N V Saran
H, Aswath Babu
Vanahalli, Manjunath K
M, Manish
Jain, Vinija
Chadha, Aman
contents Current quantum machine learning approaches often face challenges balancing predictive accuracy, robustness, and interpretability. To address this, we propose a novel quantum adversarial framework that integrates a hybrid quantum neural network (QNN) with classical deep learning layers, guided by an evaluator model with LIME-based interpretability, and extended through quantum GAN and self-supervised variants. In the proposed model, an adversarial evaluator concurrently guides the QNN by computing feedback loss, thereby optimizing both prediction accuracy and model explainability. Empirical evaluations show that the Vanilla model achieves RMSE = 0.27, MSE = 0.071, MAE = 0.21, and R^2 = 0.59, delivering the most consistent performance across regression metrics compared to adversarial counterparts. These results demonstrate the potential of combining quantum-inspired methods with classical architectures to develop lightweight, high-performance, and interpretable predictive models, advancing the applicability of QML beyond current limitations.
format Preprint
id arxiv_https___arxiv_org_abs_2510_24598
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Novel XAI-Enhanced Quantum Adversarial Networks for Velocity Dispersion Modeling in MaNGA Galaxies
Narkedimilli, Sathwik
Kumar, N V Saran
H, Aswath Babu
Vanahalli, Manjunath K
M, Manish
Jain, Vinija
Chadha, Aman
Machine Learning
Cryptography and Security
Current quantum machine learning approaches often face challenges balancing predictive accuracy, robustness, and interpretability. To address this, we propose a novel quantum adversarial framework that integrates a hybrid quantum neural network (QNN) with classical deep learning layers, guided by an evaluator model with LIME-based interpretability, and extended through quantum GAN and self-supervised variants. In the proposed model, an adversarial evaluator concurrently guides the QNN by computing feedback loss, thereby optimizing both prediction accuracy and model explainability. Empirical evaluations show that the Vanilla model achieves RMSE = 0.27, MSE = 0.071, MAE = 0.21, and R^2 = 0.59, delivering the most consistent performance across regression metrics compared to adversarial counterparts. These results demonstrate the potential of combining quantum-inspired methods with classical architectures to develop lightweight, high-performance, and interpretable predictive models, advancing the applicability of QML beyond current limitations.
title A Novel XAI-Enhanced Quantum Adversarial Networks for Velocity Dispersion Modeling in MaNGA Galaxies
topic Machine Learning
Cryptography and Security
url https://arxiv.org/abs/2510.24598