Disentangled Counterfactual Reasoning for Unbiased Sequential Recommendation

TL;DR

This paper introduces DCR, a novel causal modeling approach that disentangles popularity and interest to mitigate bias in sequential recommendation systems, leading to improved accuracy.

Contribution

It presents the first structural causal model for popularity bias correction in sequential recommendation, utilizing disentangled representations and counterfactual reasoning.

Findings

Significant performance improvements over existing methods.

Effective bias mitigation demonstrated through offline and online experiments.

Disentangled representations enhance model generalizability.

Abstract

Sequential recommender systems have achieved state-of-the-art recommendation performance by modeling the sequential dynamics of user activities. However, in most recommendation scenarios, the popular items comprise the major part of the previous user actions. Therefore, the learned models are biased towards the popular items irrespective of the user's real interests. In this paper, we propose a structural causal model-based method to address the popularity bias issue for sequential recommendation model learning. For more generalizable modeling, we disentangle the popularity and interest representations at both the item side and user context side. Based on the disentangled representation, we identify a more effective structural causal graph for general recommendation applications. Then, we design delicate sequential models to apply the aforementioned causal graph to the sequential recommendation scenario for unbiased prediction with counterfactual reasoning. Furthermore, we conduct extensive offline experiments and online A/B tests to verify the proposed \textbf{DCR} (Disentangled Counterfactual Reasoning) method's superior overall performance and understand the effectiveness of the various introduced components. Based on our knowledge, this is the first structural causal model specifically designed for the popularity bias correction of sequential recommendation models, which achieves significant performance gains over the existing methods.