A Multi-granularity Knowledge-enhanced Sequential Recommendation
Yingying Xue, Kun Huang, Hui Peng, Aibo Song, Kun Zhao, Jibin Sun · 2023
Knowledge graph has been widely utilized to provide knowledge for the sequential recommendation. But their divergence produces new challenges to appropriately capture and represent items’ knowledge for recommendation. Additionally, the complex temporal features also increase the difficulty to model the user-item interaction sequences. The key issues remaining to be settled are how to mine adequate information from KG to capture items’ knowledge, and how to model the evolving user interests accurately. Facing the above problems, we propose a multi-task learning framework MLKT to learn the embedding of items and users’ dynamic preferences in both a knowledge-aware and time-aware way. Different from the previous works, we not only consider the timestamps of the interactions in the sequence, but also capture its evolution from multiple perspectives by designing a multi-scale temporal attention mechanism. Additionally, we represent each item’s features in different granularity by learning from neighbors and the category information in KG. Furthermore, to make the KG embeddings to be more suitable for the recommendation, a cross-component is designed to efficiently achieve the item information communication between KG and user-item interactions. Extensive experiments demonstrate the significant improvements of MLKT than the baseline methods on two recommendation tasks in three datasets.