Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319586592> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W4319586592 abstract "Graph convolution network (GCN) is widely used in recommendation. It has become the mainstream technology of collaborative filtering as its powerful graph representation learning ability. Since historical interactive data can be naturally modeled as a user-item bipartite graph, many excellent methods have been proposed for recommendation based on bipartite graphs. These methods have achieved impressive successes. However, most of these methods only utilize the intuitive topology information of bipartite graph and ignore semantic information. In this paper, we propose a new Dual Channel Hybrid Messaging-Passing Graph Convolutional Network(DCH-GCN) recommendation model. In our model, first the user-item bipartite graph and item-item co-occurrence graph is constructed based on historical interaction data. Then the explicit messaging passing channel is constructed for topology information by modeling user-item explicit interactions. In addition, the implicit message-passing channel is constructed for semantic information by modeling item-item implicit interactions. Finally the loss of the predictive user preference is co-trained and co-optimized. It is more interpretable that we add semantic information into the model in bipartite graph. We perform a comprehensive experiment on two public benchmark datasets to verify the effectiveness of our model. The experimental results show that our method can better learn user and item embedding by using dual channels, and achieve significant and consistent improvements over competitive baselines." @default.
- W4319586592 created "2023-02-09" @default.
- W4319586592 creator A5017273260 @default.
- W4319586592 creator A5041285376 @default.
- W4319586592 date "2022-10-13" @default.
- W4319586592 modified "2023-09-28" @default.
- W4319586592 title "Dual Channel Hybrid Messaging-Passing Graph Convolutional Network for Recommendation" @default.
- W4319586592 cites W2002834872 @default.
- W4319586592 cites W2054141820 @default.
- W4319586592 cites W2061212083 @default.
- W4319586592 cites W2145157418 @default.
- W4319586592 cites W2475334473 @default.
- W4319586592 cites W2605350416 @default.
- W4319586592 cites W2741249238 @default.
- W4319586592 cites W2788456731 @default.
- W4319586592 cites W2788893025 @default.
- W4319586592 cites W2894039884 @default.
- W4319586592 cites W2913904164 @default.
- W4319586592 cites W2914259457 @default.
- W4319586592 cites W2945623882 @default.
- W4319586592 cites W2998431760 @default.
- W4319586592 cites W3027226623 @default.
- W4319586592 cites W3035287707 @default.
- W4319586592 cites W3045200674 @default.
- W4319586592 cites W3100278010 @default.
- W4319586592 cites W3156861396 @default.
- W4319586592 cites W3187582009 @default.
- W4319586592 cites W3197001103 @default.
- W4319586592 cites W3211143493 @default.
- W4319586592 cites W4200310000 @default.
- W4319586592 cites W4289257875 @default.
- W4319586592 cites W4361854817 @default.
- W4319586592 doi "https://doi.org/10.1109/dsaa54385.2022.10032456" @default.
- W4319586592 hasPublicationYear "2022" @default.
- W4319586592 type Work @default.
- W4319586592 citedByCount "0" @default.
- W4319586592 crossrefType "proceedings-article" @default.
- W4319586592 hasAuthorship W4319586592A5017273260 @default.
- W4319586592 hasAuthorship W4319586592A5041285376 @default.
- W4319586592 hasConcept C124101348 @default.
- W4319586592 hasConcept C132525143 @default.
- W4319586592 hasConcept C197657726 @default.
- W4319586592 hasConcept C41008148 @default.
- W4319586592 hasConcept C80444323 @default.
- W4319586592 hasConceptScore W4319586592C124101348 @default.
- W4319586592 hasConceptScore W4319586592C132525143 @default.
- W4319586592 hasConceptScore W4319586592C197657726 @default.
- W4319586592 hasConceptScore W4319586592C41008148 @default.
- W4319586592 hasConceptScore W4319586592C80444323 @default.
- W4319586592 hasFunder F4320321001 @default.
- W4319586592 hasLocation W43195865921 @default.
- W4319586592 hasOpenAccess W4319586592 @default.
- W4319586592 hasPrimaryLocation W43195865921 @default.
- W4319586592 hasRelatedWork W2000133061 @default.
- W4319586592 hasRelatedWork W2348097614 @default.
- W4319586592 hasRelatedWork W2490229732 @default.
- W4319586592 hasRelatedWork W2998431760 @default.
- W4319586592 hasRelatedWork W3003997347 @default.
- W4319586592 hasRelatedWork W3080525460 @default.
- W4319586592 hasRelatedWork W4200211378 @default.
- W4319586592 hasRelatedWork W4253110361 @default.
- W4319586592 hasRelatedWork W4297823578 @default.
- W4319586592 hasRelatedWork W4327644045 @default.
- W4319586592 isParatext "false" @default.
- W4319586592 isRetracted "false" @default.
- W4319586592 workType "article" @default.