Building robust deep recommender systems: Utilizing a weighted adversarial noise propagation framework with robust fine-tuning modules

Fulan Qian, Wenbin Chen, Hai Chen, Jinggang Liu, Shu Zhao, Yan-ping Zhang

Abstract: Highlights•We propose RAWP-FT to boost model robustness while maintaining generalization.•RAWP-FT uses weight perturbations and robust fine-tuning to improve model robustness.•RAWP-FT tested on MLP enhances model robustness under adversarial conditions.