Generalization analysis of adversarial pairwise learning
Neural Networks · 2025
DOI: 10.1016/j.neunet.2024.106955 ↗Kurz gefasst
Fachartikel in der Zeitschrift Neural Networks, 2025. Verfasst von Wen Wen und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Informatics, Huazhong Agricultural University, Wuhan 430070, China. Hauptthemen laut MEDLINE: Neural Networks, Computer, Machine Learning, Generalization, Psychological. Die Arbeit nennt 60 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Adversarial pairwise learning has become the predominant method to enhance the discrimination ability of models against adversarial attacks, achieving tremendous success in various application fields. Despite excellent empirical performance, adversarial robustness and generalization of adversarial pairwise learning remain poorly understood from the theoretical perspective. This paper moves towards this by establishing the high-probability generalization bounds. Our bounds generally apply to various models and pairwise learning tasks. We give application examples involving explicit bounds of adversarial bipartite ranking and adversarial metric learning to illustrate how the theoretical results can be extended. Furthermore, we develop the optimistic generalization bound at order O(n-1) on the sample size n by leveraging local Rademacher complexity. Our analysis provides meaningful theoretical guidance for improving adversarial robustness through feature size and regularization. Experimental results validate theoretical findings.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Informatics, Huazhong Agricultural University, Wuhan 430070, China.
- College of Informatics, Huazhong Agricultural University, Wuhan 430070, China; Engineering Research Center of Intelligent Technology for Agriculture, Ministry of Education, Wuhan 430070, China. Electronic address: lihan…
- Horizon Robotics, Haidian District, BeiJing 100190, China.
- College of Informatics, Huazhong Agricultural University, Wuhan 430070, China; Engineering Research Center of Intelligent Technology for Agriculture, Ministry of Education, Wuhan 430070, China; Shenzhen Institute of Nut…
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Wen, W., Li, H., Wu, R., Wu, L., & Chen, H. (2025). Generalization analysis of adversarial pairwise learning. Neural Networks. https://doi.org/10.1016/j.neunet.2024.106955
Vancouver
Wen W, Li H, Wu R, Wu L, Chen H. Generalization analysis of adversarial pairwise learning. Neural Networks. 2025. doi:10.1016/j.neunet.2024.106955
BibTeX
@article{Wen2025,
author = {Wen, Wen and Li, Han and Wu, Rui and Wu, Lingjuan and Chen, Hong},
title = {Generalization analysis of adversarial pairwise learning},
journal = {Neural Networks},
year = {2025},
doi = {10.1016/j.neunet.2024.106955}
}
EUVIMED