MP2: A Momentum Contrast Approach for Recommendation with Pointwise and Pairwise Learning

TL;DR

This paper introduces MP2, a recommendation framework that combines pointwise and pairwise learning using a momentum contrast approach to mitigate annotation bias and improve recommendation accuracy.

Contribution

The paper proposes a novel momentum contrast framework (MP2) that integrates pointwise and pairwise learning with a three-tower network to address annotation bias in recommendation systems.

Findings

MP2 outperforms state-of-the-art algorithms on real-world datasets.

The momentum update stabilizes item representations, reducing annotation bias.

Combining pointwise and pairwise learning enhances recommendation quality.

Abstract

Binary pointwise labels (aka implicit feedback) are heavily leveraged by deep learning based recommendation algorithms nowadays. In this paper we discuss the limited expressiveness of these labels may fail to accommodate varying degrees of user preference, and thus lead to conflicts during model training, which we call annotation bias. To solve this issue, we find the soft-labeling property of pairwise labels could be utilized to alleviate the bias of pointwise labels. To this end, we propose a momentum contrast framework (MP2) that combines pointwise and pairwise learning for recommendation. MP2 has a three-tower network structure: one user network and two item networks. The two item networks are used for computing pointwise and pairwise loss respectively. To alleviate the influence of the annotation bias, we perform a momentum update to ensure a consistent item representation. Extensive experiments on real-world datasets demonstrate the superiority of our method against state-of-the-art recommendation algorithms.