Matches in SemOpenAlex for { <https://semopenalex.org/work/W4284665181> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4284665181 abstract "Graph-based recommender systems (GBRSs) have achieved promising performance by incorporating the user-item bipartite graph using the Graph Neural Network (GNN). Among GBRSs, the information from each user and item's multi-hop neighbours is effectively conveyed between nodes through neighbourhood aggregation and message passing. Although effective, existing neighbourhood information aggregation and passing functions are usually computationally expensive. Motivated by the emerging contrastive learning technique, we design a simple neighbourhood construction method in conjunction with the contrastive objective function to simulate the neighbourhood information processing of GNN. In addition, we propose a simple algorithm based on Multilayer Perceptron (MLP) for learning users and items' representations with extra non-linearity while lowering computational burden compared with multi-layers GNNs. Our extensive empirical experiments on three public datasets demonstrate that our proposed model, i.e. MLP-CGRec, can reduce the GPU memory consumption and training time by up to 24.0% and 33.1%, respectively, without significantly degenerating the recommendation accuracy in comparison with competitive baselines." @default.
- W4284665181 created "2022-07-08" @default.
- W4284665181 creator A5057643560 @default.
- W4284665181 creator A5079046603 @default.
- W4284665181 creator A5089330380 @default.
- W4284665181 date "2022-07-06" @default.
- W4284665181 modified "2023-10-03" @default.
- W4284665181 title "An MLP-based Algorithm for Efficient Contrastive Graph Recommendations" @default.
- W4284665181 cites W2157364932 @default.
- W4284665181 cites W2508625104 @default.
- W4284665181 cites W2605350416 @default.
- W4284665181 cites W2911407631 @default.
- W4284665181 cites W2945623882 @default.
- W4284665181 cites W2954808392 @default.
- W4284665181 cites W2998702515 @default.
- W4284665181 cites W3012705926 @default.
- W4284665181 cites W3025937945 @default.
- W4284665181 cites W3045200674 @default.
- W4284665181 cites W3081170586 @default.
- W4284665181 cites W3088777230 @default.
- W4284665181 cites W3098087397 @default.
- W4284665181 cites W3100278010 @default.
- W4284665181 cites W3101622805 @default.
- W4284665181 cites W3105817677 @default.
- W4284665181 cites W3153325943 @default.
- W4284665181 cites W3170682786 @default.
- W4284665181 cites W3171249018 @default.
- W4284665181 cites W3172854437 @default.
- W4284665181 cites W3206477365 @default.
- W4284665181 cites W3211009588 @default.
- W4284665181 cites W3211143493 @default.
- W4284665181 cites W4315977496 @default.
- W4284665181 doi "https://doi.org/10.1145/3477495.3531874" @default.
- W4284665181 hasPublicationYear "2022" @default.
- W4284665181 type Work @default.
- W4284665181 citedByCount "4" @default.
- W4284665181 countsByYear W42846651812023 @default.
- W4284665181 crossrefType "proceedings-article" @default.
- W4284665181 hasAuthorship W4284665181A5057643560 @default.
- W4284665181 hasAuthorship W4284665181A5079046603 @default.
- W4284665181 hasAuthorship W4284665181A5089330380 @default.
- W4284665181 hasBestOaLocation W42846651812 @default.
- W4284665181 hasConcept C11413529 @default.
- W4284665181 hasConcept C119857082 @default.
- W4284665181 hasConcept C124101348 @default.
- W4284665181 hasConcept C132525143 @default.
- W4284665181 hasConcept C134306372 @default.
- W4284665181 hasConcept C154945302 @default.
- W4284665181 hasConcept C161677786 @default.
- W4284665181 hasConcept C179717631 @default.
- W4284665181 hasConcept C197657726 @default.
- W4284665181 hasConcept C33923547 @default.
- W4284665181 hasConcept C41008148 @default.
- W4284665181 hasConcept C50644808 @default.
- W4284665181 hasConcept C557471498 @default.
- W4284665181 hasConcept C80444323 @default.
- W4284665181 hasConceptScore W4284665181C11413529 @default.
- W4284665181 hasConceptScore W4284665181C119857082 @default.
- W4284665181 hasConceptScore W4284665181C124101348 @default.
- W4284665181 hasConceptScore W4284665181C132525143 @default.
- W4284665181 hasConceptScore W4284665181C134306372 @default.
- W4284665181 hasConceptScore W4284665181C154945302 @default.
- W4284665181 hasConceptScore W4284665181C161677786 @default.
- W4284665181 hasConceptScore W4284665181C179717631 @default.
- W4284665181 hasConceptScore W4284665181C197657726 @default.
- W4284665181 hasConceptScore W4284665181C33923547 @default.
- W4284665181 hasConceptScore W4284665181C41008148 @default.
- W4284665181 hasConceptScore W4284665181C50644808 @default.
- W4284665181 hasConceptScore W4284665181C557471498 @default.
- W4284665181 hasConceptScore W4284665181C80444323 @default.
- W4284665181 hasLocation W42846651811 @default.
- W4284665181 hasLocation W42846651812 @default.
- W4284665181 hasOpenAccess W4284665181 @default.
- W4284665181 hasPrimaryLocation W42846651811 @default.
- W4284665181 hasRelatedWork W2787191226 @default.
- W4284665181 hasRelatedWork W3018959556 @default.
- W4284665181 hasRelatedWork W3201252789 @default.
- W4284665181 hasRelatedWork W3211546796 @default.
- W4284665181 hasRelatedWork W4231994957 @default.
- W4284665181 hasRelatedWork W4285741730 @default.
- W4284665181 hasRelatedWork W4294067781 @default.
- W4284665181 hasRelatedWork W4313152590 @default.
- W4284665181 hasRelatedWork W4320802194 @default.
- W4284665181 hasRelatedWork W4361795583 @default.
- W4284665181 isParatext "false" @default.
- W4284665181 isRetracted "false" @default.
- W4284665181 workType "article" @default.