Debiasing Sequential Recommendation with Time-aware Inverse Propensity Scoring

TL;DR

This paper introduces TIPS, a novel time-aware inverse propensity scoring method that improves sequential recommendation accuracy by addressing exposure and selection biases through modeling temporal dynamics.

Contribution

The paper proposes TIPS, a dynamic IPS approach that captures sequential dependencies and temporal user behavior, advancing bias correction in sequential recommendation systems.

Findings

TIPS consistently improves recommendation performance across multiple models.

TIPS effectively distinguishes between unexposed and uninterested items.

Experimental results demonstrate the superiority of TIPS over static IPS methods.

Abstract

Sequential Recommendation (SR) predicts users next interactions by modeling the temporal order of their historical behaviors. Existing approaches, including traditional sequential models and generative recommenders, achieve strong performance but primarily rely on explicit interactions such as clicks or purchases while overlooking item exposures. This ignorance introduces selection bias, where exposed but unclicked items are misinterpreted as disinterest, and exposure bias, where unexposed items are treated as irrelevant. Effectively addressing these biases requires distinguishing between items that were "not exposed" and those that were "not of interest", which cannot be reliably inferred from correlations in historical data. Counterfactual reasoning provides a natural solution by estimating user preferences under hypothetical exposure, and Inverse Propensity Scoring (IPS) is a common tool for such estimation. However, conventional IPS methods are static and fail to capture the sequential dependencies and temporal dynamics of user behavior. To overcome these limitations, we propose Time aware Inverse Propensity Scoring (TIPS). Unlike traditional static IPS, TIPS effectively accounts for sequential dependencies and temporal dynamics, thereby capturing user preferences more accurately. Extensive experiments show that TIPS consistently enhances recommendation performance as a plug-in for various sequential recommenders. Our code will be publicly available upon acceptance.