English

KATRec: Knowledge Aware aTtentive Sequential Recommendations

Information Retrieval 2021-07-07 v3

Abstract

Sequential recommendation systems model dynamic preferences of users based on their historical interactions with platforms. Despite recent progress, modeling short-term and long-term behavior of users in such systems is nontrivial and challenging. To address this, we present a solution enhanced by a knowledge graph called KATRec (Knowledge Aware aTtentive sequential Recommendations). KATRec learns the short and long-term interests of users by modeling their sequence of interacted items and leveraging pre-existing side information through a knowledge graph attention network. Our novel knowledge graph-enhanced sequential recommender contains item multi-relations at the entity-level and users' dynamic sequences at the item-level. KATRec improves item representation learning by considering higher-order connections and incorporating them in user preference representation while recommending the next item. Experiments on three public datasets show that KATRec outperforms state-of-the-art recommendation models and demonstrates the importance of modeling both temporal and side information to achieve high-quality recommendations.

Keywords

Cite

@article{arxiv.2012.03323,
  title  = {KATRec: Knowledge Aware aTtentive Sequential Recommendations},
  author = {Mehrnaz Amjadi and Seyed Danial Mohseni Taheri and Theja Tulabandhula},
  journal= {arXiv preprint arXiv:2012.03323},
  year   = {2021}
}
R2 v1 2026-06-23T20:45:52.580Z