Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Debiasing Sequential Recommendation with Time-aware Inverse Propensity Scoring

Sirui Huang, Jing Long, Qian Li, Guandong Xu, Qing Li

TL;DR

Time aware Inverse Propensity Scoring (TIPS) is proposed, which effectively accounts for sequential dependencies and temporal dynamics, thereby capturing user preferences more accurately and consistently enhances recommendation performance as a plug-in for various sequential recommenders.

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.

Debiasing Sequential Recommendation with Time-aware Inverse Propensity Scoring

TL;DR

Time aware Inverse Propensity Scoring (TIPS) is proposed, which effectively accounts for sequential dependencies and temporal dynamics, thereby capturing user preferences more accurately and consistently enhances recommendation performance as a plug-in for various sequential recommenders.

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.
Paper Structure (33 sections, 23 equations, 4 figures, 3 tables)

This paper contains 33 sections, 23 equations, 4 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Preliminary
  3. Structural Causal Model for SR
  4. Inverse Propensity Scoring
  5. Propensity Score
  6. Using IPS to Address the Two Biases
  7. Problem Definition
  8. Methodology
  9. Dual Encoding Strategy
  10. Item Encoding
  11. Time Embeddings
  12. Counterfactual Samples Construction
  13. Exposure Influence Interaction ($\mathbf{E}\rightarrow \mathbf{C}$)
  14. Exposure Influence User Preference ($\mathbf{E}\rightarrow\mathbf{U}$)
  15. Traditional Sequential Models
  16. ...and 18 more sections

Figures (4)

  • Figure 1: (a) An example of a biased SR model that learns user preference solely from interactions. (b) Example of a system that considers exposure. Here, $\mathbf{C}_t$ denotes user interactions (e.g., clicks) at time $t$, $\mathbf{U}_t$ represents the user’s preference at time $t$, and $\mathbf{E}_t$ is the recommendation list containing all items exposed to the user at time $t$.
  • Figure 2: Structural Causal Model (SCM) of SR.
  • Figure 3: Overview of the Time-aware Inverse Propensity Scoring (TIPS) framework, designed as a plug-in for any SR model.
  • Figure 4: (a)(b) Results for different values of hyperparameters $\mu$ and $\gamma$, and (c)(d) distribution of the difference between the average propensity score of positive items and that of negative items, using HyperG (Ours) and traditional IPS (Base).