Learning Robust Recommenders through Cross-Model Agreement

TL;DR

This paper introduces DeCA, a cross-model agreement framework that enhances the robustness of recommender systems by effectively handling noisy implicit feedback, leading to improved recommendation accuracy.

Contribution

The paper proposes a novel denoising framework, DeCA, which leverages cross-model agreement to mitigate noise in implicit feedback for better recommendations.

Findings

DeCA outperforms standard training methods across four datasets.

Different models agree more on clean examples, less on noisy ones.

DeCA significantly improves recommendation performance over other denoising techniques.

Abstract

Learning from implicit feedback is one of the most common cases in the application of recommender systems. Generally speaking, interacted examples are considered as positive while negative examples are sampled from uninteracted ones. However, noisy examples are prevalent in real-world implicit feedback. A noisy positive example could be interacted but it actually leads to negative user preference. A noisy negative example which is uninteracted because of unawareness of the user could also denote potential positive user preference. Conventional training methods overlook these noisy examples, leading to sub-optimal recommendations. In this work, we propose a novel framework to learn robust recommenders from implicit feedback. Through an empirical study, we find that different models make relatively similar predictions on clean examples which denote the real user preference, while the predictions on noisy examples vary much more across different models. Motivated by this observation, we propose denoising with cross-model agreement(DeCA) which aims to minimize the KL-divergence between the real user preference distributions parameterized by two recommendation models while maximizing the likelihood of data observation. We employ the proposed DeCA on four state-of-the-art recommendation models and conduct experiments on four datasets. Experimental results demonstrate that DeCA significantly improves recommendation performance compared with normal training and other denoising methods. Codes will be open-sourced.