Motif Enhanced Recommendation over Heterogeneous Information Network
This work addresses a limitation in HIN-based recommender systems by incorporating motifs for better similarity computation, representing an incremental improvement for recommendation tasks.
The paper tackles the problem of capturing higher-order relations among nodes of the same type in Heterogeneous Information Networks for recommender systems, proposing motif-enhanced meta-paths and achieving superior performance on Epinions and CiaoDVD datasets.
Heterogeneous Information Networks (HIN) has been widely used in recommender systems (RSs). In previous HIN-based RSs, meta-path is used to compute the similarity between users and items. However, existing meta-path based methods only consider first-order relations, ignoring higher-order relations among the nodes of \textit{same} type, captured by \textit{motifs}. In this paper, we propose to use motifs to capture higher-order relations among nodes of same type in a HIN and develop the motif-enhanced meta-path (MEMP) to combine motif-based higher-order relations with edge-based first-order relations. With MEMP-based similarities between users and items, we design a recommending model MoHINRec, and experimental results on two real-world datasets, Epinions and CiaoDVD, demonstrate its superiority over existing HIN-based RS methods.