Parallel Split-Join Networks for Shared-account Cross-domain Sequential Recommendations
Authors:
- Wenchao SunWSWenchao Sun
- Muyang MaMMMuyang Ma
- Pengjie RenPRPengjie Ren
- Yujie LinYLYujie Lin
- Zhumin ChenZCZhumin Chen
- Zhaochun RenZRZhaochun Ren
- Jun MaJMJun Ma
- Maarten de RijkeMRMaarten de Rijke
Preprint
Abstract
Sequential recommendation is a task in which one models and uses sequential information about user behavior for recommendation purposes. We study sequential recommendation in a particularly challenging context, in which multiple individual users share asingle account (i.e., they have a shared account) and in which user behavior is available in multiple domains (i.e., recommendations are cross-domain). These two characteristics bring new challenges on top of those of the traditional sequential recommendation task. First, we need to identify the behavior associated with different users and different user roles under the same account in order to recommend the right item to the right user role at the right time. Second, we need to identify behavior in one domain that might be helpful to improve recommendations in other domains. In this work, we study shared account cross-domain sequential recommendation and propose Parallel Split-Join Network (PSJNet), a parallel modeling network to address the two challenges above. We present two variants of PSJNet, PSJNet-I and PSJNet-II. PSJNet-I is a "split-by-join" framework that splits the mixed representations to get role-specific representations and joins them to obtain cross-domain representations at each timestamp simultaneously. PSJNet-II is a "split-and-join" framework that first splits role-specific representations at each timestamp, and then the representations from all timestamps and all roles are joined to obtain cross-domain representations. We use two datasets to assess the effectiveness of PSJNet. Our experimental results demonstrate that PSJNet outperforms state-of-the-art sequential recommendation baselines in terms of MRR and Recall.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Selective Knowledge Transfer for Cross-Domain Collaborative RecommendationIEEE Access, 2021
- Cross-Domain Recommendation via Deep Domain Adaptation2019
- Fast and Low Memory Cost Matrix Factorization: Algorithm, Analysis, and Case StudyIEEE Transactions on Knowledge and Data Engineering, 2018
- MV-RNN: A Multi-View Recurrent Neural Network for Sequential RecommendationIEEE Transactions on Knowledge and Data Engineering, 2018
- Neural information retrieval: at the end of the early yearsInformation Retrieval Journal, 2017
- Cross-system user modeling and personalization on the Social WebUser Modeling and User-Adapted Interaction, 2012
- Cross-Domain Learning from Multiple Sources: A Consensus Regularization PerspectiveIEEE Transactions on Knowledge and Data Engineering, 2009
- Matrix Factorization Techniques for Recommender SystemsComputer, 2009
- Mediation of user models for enhanced personalization in recommender systemsUser Modeling and User-Adapted Interaction, 2007
- Amazon.com recommendations: item-to-item collaborative filteringIEEE Internet Computing, 2003