Many of existing methods which exploit meta-path guided strategy have shown promising results. Extensive experiments are conducted on three real-world datasets and the results demonstrate that our proposed HicRec model outperforms the baselines. Abstract: Heterogeneous information network (HIN) embedding has gained considerable attention in recent years, which learns low-dimensional representation of nodes while preserving the semantic and structural correlations in HINs. The Software and Information Systems Department (SIS) is a pioneer in.
The composed user interests are obtained by their single interest from both intra- and inter-meta-paths for recommendation. and algorithms for network management in heterogeneous wireless systems. Then, users' interests in each item from each pair of related meta-paths are calculated by a combination of the user and item representations. Specifically, user and item representations are learned with a graph neural network on both the graph structure and features in each meta-path, and a parameter sharing mechanism is utilized here to ensure that the user and item representations are in the same latent space. The Pom is a tiny toy dog with an average height between 8 to 11 inches and an average weight between 4 to 7 pounds. In this paper, we provide a survey of heterogeneous information network analysis. In this article, we propose an HIN-based Interest Composition model for Recommendation (HicRec). Compared to widely studied homogeneous information network, the heterogeneous information network contains richer structure and semantic information, which provides plenty of opportunities as well as a lot of challenges for data mining. However, existing HIN-based recommendation models usually fuse the information from various meta-paths by simple weighted sum or concatenation, which limits performance improvement because it lacks the capability of interest compositions among meta-paths. Heterogeneous information networks (HINs) are widely applied to recommendation systems due to their capability of modeling various auxiliary information with meta-paths.
0 kommentar(er)
