Nowadays, many recommender systems encompass various domains to cater to users' diverse needs, leading to user behaviors transitioning across different domains. In fact, user behaviors across different domains reveal changes in preference toward recommended items. For instance, a shift from negative feedback to positive feedback indicates improved user satisfaction. However, existing cross-domain sequential recommendation methods typically model user interests by focusing solely on information about domain transitions, often overlooking the valuable insights provided by users' feedback transitions. In this paper, we propose $\text{Transition}^2$, a novel method to model transitions across both domains and types of user feedback. Specifically, $\text{Transition}^2$ introduces a transition-aware graph encoder based on user history, assigning different weights to edges according to the feedback type. This enables the graph encoder to extract historical embeddings that capture the transition information between different domains and feedback types. Subsequently, we encode the user history using a cross-transition multi-head self-attention, incorporating various masks to distinguish different types of transitions. Finally, we integrate these modules to make predictions across different domains. Experimental results on two public datasets demonstrate the effectiveness of $\text{Transition}^2$.

翻译：如今，许多推荐系统涵盖多个领域以满足用户的多样化需求，导致用户行为在不同领域间转换。实际上，用户在不同领域的行为揭示了其对推荐项目偏好的变化。例如，从负面反馈到正面反馈的转变表明用户满意度的提升。然而，现有的跨领域序列推荐方法通常仅通过关注领域转换信息来建模用户兴趣，往往忽略了用户反馈转换所提供的宝贵洞见。本文提出 $\text{Transition}^2$，一种新颖的方法来同时对领域和用户反馈类型的转换进行建模。具体而言，$\text{Transition}^2$ 引入了一个基于用户历史的转换感知图编码器，根据反馈类型为边分配不同的权重。这使得图编码器能够提取捕获不同领域和反馈类型间转换信息的历史嵌入。随后，我们使用跨转换多头自注意力对用户历史进行编码，并结合多种掩码来区分不同类型的转换。最后，我们整合这些模块以进行跨领域预测。在两个公开数据集上的实验结果证明了 $\text{Transition}^2$ 的有效性。