Debiasing Sequential Recommendation with Time-aware Inverse Propensity Scoring
This work is significant for researchers and practitioners in sequential recommendation systems, as it offers an incremental improvement to existing methods by addressing biases related to item exposure and user interest.
The paper addresses selection and exposure biases in sequential recommendation systems by proposing Time-aware Inverse Propensity Scoring (TIPS). TIPS accounts for sequential dependencies and temporal dynamics, leading to consistent enhancements in recommendation performance when integrated as a plug-in for various sequential recommenders.
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.