EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Quotient Gradient System Adversarial Training: Eliminating Robust Overfitting With a Nonlinear Dynamical System Approach

Yixuan Jiang, Hsiao‐Dong Chiang

Artificial Intelligence for Engineering · 2025

DOI: 10.1049/aie2.12003 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Artificial Intelligence for Engineering, 2025. Verfasst von Yixuan Jiang und 1 weiteren Autor:innen. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Adversarial training is widely considered the most effective method for improving model robustness, yet the robust overfitting hinders its performance. In this paper, we investigate remedies for robust overfitting and argue that effective strategies typically fall into two categories: confidence calibration and flat minimum methods, both of which are commonly formulated as regularised adversarial training approaches. We show that these methods can be unified under a constrained optimisation framework, revealing that flat minimum approaches can be interpreted as adaptive confidence calibration. To solve this constrained optimisation problem, we propose a novel adversarial training framework based on a powerful nonlinear dynamical system technique called the quotient gradient system (QGS). Specifically, we introduce QGS adversarial training (QGSAT) framework and develop two numerical methods termed the QGS method assisted by confidence calibration and the QGS method assisted by a flat minimum . We theoretically prove that QGSAT enforces effective regularisation by ensuring convergence to the feasible region, and achieves optimal regularisation under convexity when the region is empty. Extensive numerical studies demonstrate that QGSAT mitigates robust overfitting and outperforms existing regularised adversarial training methods. The code is publicly available at: https://github.com/yj373/QGSAT .

Zitieren

APA

Jiang, Y., & Chiang, H. (2025). Quotient Gradient System Adversarial Training: Eliminating Robust Overfitting With a Nonlinear Dynamical System Approach. Artificial Intelligence for Engineering. https://doi.org/10.1049/aie2.12003

Vancouver

Jiang Y, Chiang H. Quotient Gradient System Adversarial Training: Eliminating Robust Overfitting With a Nonlinear Dynamical System Approach. Artificial Intelligence for Engineering. 2025. doi:10.1049/aie2.12003

BibTeX
@article{Jiang2025,
  author = {Jiang, Yixuan and Chiang, Hsiao‐Dong},
  title = {Quotient Gradient System Adversarial Training: Eliminating Robust Overfitting With a Nonlinear Dynamical System Approach},
  journal = {Artificial Intelligence for Engineering},
  year = {2025},
  doi = {10.1049/aie2.12003}
}
Kostenlos starten →