Deep Factorization Model for Robust Recommendation

TL;DR

This paper introduces a deep factorization model with adversarial training to enhance the robustness of recommender systems against malicious user attacks, demonstrating effectiveness on real-world data.

Contribution

Proposes a novel deep factorization architecture incorporating adversarial training to improve recommendation robustness.

Findings

Effective against malicious user hacking in experiments

Outperforms traditional factorization models on real datasets

Demonstrates robustness improvements in recommender systems

Abstract

Recently, malevolent user hacking has become a huge problem for real-world companies. In order to learn predictive models for recommender systems, factorization techniques have been developed to deal with user-item ratings. In this paper, we suggest a broad architecture of a factorization model with adversarial training to get over these issues. The effectiveness of our systems is demonstrated by experimental findings on real-world datasets.