Adversarial Collaborative Filtering for Free

TL;DR

This paper introduces SharpCF, an adversarial collaborative filtering method that improves recommendation robustness and generalizability without additional computational cost by leveraging sharpness-aware minimization principles.

Contribution

SharpCF is a novel adversarial training approach for collaborative filtering that avoids min-max optimization, reducing computational overhead while enhancing model robustness.

Findings

SharpCF outperforms existing adversarial CF methods on real-world datasets.

It achieves superior recommendation accuracy with minimal additional computation.

Theoretical analysis links adversarial training to sharpness-aware minimization, explaining its effectiveness.

Abstract

Collaborative Filtering (CF) has been successfully used to help users discover the items of interest. Nevertheless, existing CF methods suffer from noisy data issue, which negatively impacts the quality of recommendation. To tackle this problem, many prior studies leverage adversarial learning to regularize the representations of users/items, which improves both generalizability and robustness. Those methods often learn adversarial perturbations and model parameters under min-max optimization framework. However, there still have two major drawbacks: 1) Existing methods lack theoretical guarantees of why adding perturbations improve the model generalizability and robustness; 2) Solving min-max optimization is time-consuming. In addition to updating the model parameters, each iteration requires additional computations to update the perturbations, making them not scalable for industry-scale datasets. In this paper, we present Sharpness-aware Collaborative Filtering (SharpCF), a simple yet effective method that conducts adversarial training without extra computational cost over the base optimizer. To achieve this goal, we first revisit the existing adversarial collaborative filtering and discuss its connection with recent Sharpness-aware Minimization. This analysis shows that adversarial training actually seeks model parameters that lie in neighborhoods around the optimal model parameters having uniformly low loss values, resulting in better generalizability. To reduce the computational overhead, SharpCF introduces a novel trajectory loss to measure the alignment between current weights and past weights. Experimental results on real-world datasets demonstrate that our SharpCF achieves superior performance with almost zero additional computational cost comparing to adversarial training.