Recommender systems easily face the issue of user preference shifts. User representations will become out-of-date and lead to inappropriate recommendations if user preference has shifted over time. To solve the issue, existing work focuses on learning robust representations or predicting the shifting pattern. There lacks a comprehensive view to discover the underlying reasons for user preference shifts. To understand the preference shift, we abstract a causal graph to describe the generation procedure of user interaction sequences. Assuming user preference is stable within a short period, we abstract the interaction sequence as a set of chronological environments. From the causal graph, we find that the changes of some unobserved factors (e.g., becoming pregnant) cause preference shifts between environments. Besides, the fine-grained user preference over categories sparsely affects the interactions with different items. Inspired by the causal graph, our key considerations to handle preference shifts lie in modeling the interaction generation procedure by: 1) capturing the preference shifts across environments for accurate preference prediction, and 2) disentangling the sparse influence from user preference to interactions for accurate effect estimation of preference. To this end, we propose a Causal Disentangled Recommendation (CDR) framework, which captures preference shifts via a temporal variational autoencoder and learns the sparse influence from multiple environments. Specifically, an encoder is adopted to infer the unobserved factors from user interactions while a decoder is to model the interaction generation process. Besides, we introduce two learnable matrices to disentangle the sparse influence from user preference to interactions. Lastly, we devise a multi-objective loss to optimize CDR. Extensive experiments on three datasets show the superiority of CDR.

翻译：推荐系统易面临用户偏好迁移问题。若用户偏好随时间变化，其表征将过时并导致不当推荐。现有研究致力于学习鲁棒表征或预测迁移模式，但缺乏从全局视角探究偏好迁移的深层原因。为理解偏好迁移，我们抽象出因果图描述用户交互序列的生成过程。假设用户偏好在短期内稳定，我们将交互序列抽象为一组时序环境。从因果图中发现，某些未观测因素（如怀孕）的变化会导致环境间偏好迁移。此外，用户对类别的细粒度偏好在不同物品间的交互中具有稀疏影响。受因果图启发，我们处理偏好迁移的关键思路在于建模交互生成过程：1）捕获环境间偏好迁移以精准预测偏好，2）解耦用户偏好对交互的稀疏影响以准确估计偏好效应。为此，提出因果解耦推荐（CDR）框架，通过时序变分自编码器捕获偏好迁移，并学习多环境下的稀疏影响。具体而言，采用编码器从用户交互中推断未观测因素，解码器建模交互生成过程；同时引入两个可学习矩阵解耦用户偏好对交互的稀疏影响。最后设计多目标损失函数优化CDR。在三个数据集上的大量实验表明CDR具有优越性。