Mixed Information Flow for Cross-Domain Sequential Recommendations

<jats:p> Cross-domain sequential recommendation is the task of predict the next item that the user is most likely to interact with based on past sequential behavior from multiple domains. One of the key challenges in <jats:bold>cross-domain sequential recommendation</jats:bold> is to grasp and transfer the flow of information from multiple domains so as to promote recommendations in all domains. Previous studies have investigated the flow of <jats:italic>behavioral</jats:italic> information by exploring the connection between items from different domains. The flow of knowledge (i.e., the connection between knowledge from different domains) has so far been neglected. In this article, we propose a <jats:bold>mixed information flow network</jats:bold> for <jats:bold>cross-domain sequential recommendation</jats:bold> to consider both the flow of behavioral information and the flow of knowledge by incorporating a <jats:bold>behavior transfer unit</jats:bold> and a <jats:bold>knowledge transfer unit</jats:bold> . The proposed <jats:bold>mixed information flow network</jats:bold> is able to decide when cross-domain information should be used and, if so, which cross-domain information should be used to enrich the sequence representation according to users’ current preferences. Extensive experiments conducted on four e-commerce datasets demonstrate that the proposed <jats:bold>mixed information flow network</jats:bold> is able to improve recommendation performance in different domains by modeling mixed information flow. In this article, we focus on the application of <jats:bold>mixed information flow network</jats:bold> s to a scenario with two domains, but the method can easily be extended to multiple domains. </jats:p>