scholar.google.com › citations
Aug 7, 2021 · We propose a heterogeneous information network-based model to model the intensity of the user-item relationship and heterogeneity of different types of objects ...
Heterogeneous information network contains richer semantic information, considering multiple types of objects and relationships to more accurately determine ...
Aug 14, 2021 · First, we use heterogeneous information networks to model complex heterogeneous data, and obtain users and item node representations. Second, we ...
This paper proposes a new user heterogeneous information embedding method, called user heterogeneous information embedding (UHIE).
Missing: Metric | Show results with:Metric
In this study, we propose extensions for modeling online user activity trails that address two very important aspects of activities—time and noise.
We first present a user preference diffusion based feature generation method, and then define a recommendation func- tion with these features. We discuss the ...
Heterogeneous information of users is used in the network embedding. •. The embedded vectors contribute to better user behavior prediction performances.
Missing: Metric | Show results with:Metric
Heterogeneous information network contains richer semantic information, considering multiple types of objects and relationships to more accurately determine ...
Representation Learning on Heterogeneous Graph including Heterogeneous Graph Embedding, Heterogeneous Graph Neural Network and Applications.
Unified Embedding Model over Heterogeneous Information Network for. Personalized Recommendation. Zekai Wang1 , Hongzhi Liu1∗ , Yingpeng Du1 , Zhonghai Wu2,3 ...