Taming Recommendation Bias with Causal Intervention on Evolving Personal Popularity

TL;DR

This paper introduces CausalEPP, a novel method that models evolving user preferences for popular items to effectively reduce popularity bias and enhance recommendation accuracy.

Contribution

It proposes a causal intervention framework that accounts for the dynamic nature of user preferences and item popularity over time, which is a novel approach.

Findings

CausalEPP outperforms baseline methods in reducing popularity bias.

It improves recommendation accuracy while addressing evolving user preferences.

The method effectively models the temporal dynamics of personal popularity.

Abstract

Popularity bias occurs when popular items are recommended far more frequently than they should be, negatively impacting both user experience and recommendation accuracy. Existing debiasing methods mitigate popularity bias often uniformly across all users and only partially consider the time evolution of users or items. However, users have different levels of preference for item popularity, and this preference is evolving over time. To address these issues, we propose a novel method called CausalEPP (Causal Intervention on Evolving Personal Popularity) for taming recommendation bias, which accounts for the evolving personal popularity of users. Specifically, we first introduce a metric called {Evolving Personal Popularity} to quantify each user's preference for popular items. Then, we design a causal graph that integrates evolving personal popularity into the conformity effect, and apply deconfounded training to mitigate the popularity bias of the causal graph. During inference, we consider the evolution consistency between users and items to achieve a better recommendation. Empirical studies demonstrate that CausalEPP outperforms baseline methods in reducing popularity bias while improving recommendation accuracy.