Matches in SemOpenAlex for { <https://semopenalex.org/work/W3208487946> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W3208487946 abstract "Recently, the graph neural network (GNN) has shown great power in matrix completion by formulating a rating matrix as a bipartite graph and then predicting the link between the corresponding user and item nodes. The majority of GNN-based matrix completion methods are based on Graph Autoencoder (GAE), which considers the one-hot index as input, maps a user (or item) index to a learnable embedding, applies a GNN to learn the node-specific representations based on these learnable embeddings and finally aggregates the representations of the target users and its corresponding item nodes to predict missing links. However, without node content (i.e., side information) for training, the user (or item) specific representation can not be learned in the inductive setting, that is, a model trained on one group of users (or items) cannot adapt to new users (or items). To this end, we propose an inductive matrix completion method using GAE (IMC-GAE), which utilizes the GAE to learn both the user-specific (or item-specific) representation for personalized recommendation and local graph patterns for inductive matrix completion. Specifically, we design two informative node features and employ a layer-wise node dropout scheme in GAE to learn local graph patterns which can be generalized to unseen data. The main contribution of our paper is the capability to efficiently learn local graph patterns in GAE, with good scalability and superior expressiveness compared to previous GNN-based matrix completion methods. Furthermore, extensive experiments demonstrate that our model achieves state-of-the-art performance on several matrix completion benchmarks." @default.
- W3208487946 created "2021-11-08" @default.
- W3208487946 creator A5023918894 @default.
- W3208487946 creator A5034407627 @default.
- W3208487946 creator A5038791483 @default.
- W3208487946 creator A5080460228 @default.
- W3208487946 creator A5081470345 @default.
- W3208487946 creator A5085997608 @default.
- W3208487946 creator A5087159582 @default.
- W3208487946 date "2021-10-26" @default.
- W3208487946 modified "2023-10-12" @default.
- W3208487946 title "Inductive Matrix Completion Using Graph Autoencoder" @default.
- W3208487946 cites W1720514416 @default.
- W3208487946 cites W2029119963 @default.
- W3208487946 cites W2099866409 @default.
- W3208487946 cites W2135598826 @default.
- W3208487946 cites W2144487656 @default.
- W3208487946 cites W2951369132 @default.
- W3208487946 cites W2999817249 @default.
- W3208487946 cites W3100278010 @default.
- W3208487946 cites W3100848837 @default.
- W3208487946 doi "https://doi.org/10.1145/3459637.3482266" @default.
- W3208487946 hasPublicationYear "2021" @default.
- W3208487946 type Work @default.
- W3208487946 sameAs 3208487946 @default.
- W3208487946 citedByCount "5" @default.
- W3208487946 countsByYear W32084879462022 @default.
- W3208487946 countsByYear W32084879462023 @default.
- W3208487946 crossrefType "proceedings-article" @default.
- W3208487946 hasAuthorship W3208487946A5023918894 @default.
- W3208487946 hasAuthorship W3208487946A5034407627 @default.
- W3208487946 hasAuthorship W3208487946A5038791483 @default.
- W3208487946 hasAuthorship W3208487946A5080460228 @default.
- W3208487946 hasAuthorship W3208487946A5081470345 @default.
- W3208487946 hasAuthorship W3208487946A5085997608 @default.
- W3208487946 hasAuthorship W3208487946A5087159582 @default.
- W3208487946 hasBestOaLocation W32084879462 @default.
- W3208487946 hasConcept C101738243 @default.
- W3208487946 hasConcept C121332964 @default.
- W3208487946 hasConcept C127413603 @default.
- W3208487946 hasConcept C132525143 @default.
- W3208487946 hasConcept C154945302 @default.
- W3208487946 hasConcept C163716315 @default.
- W3208487946 hasConcept C197657726 @default.
- W3208487946 hasConcept C2778459887 @default.
- W3208487946 hasConcept C2779172887 @default.
- W3208487946 hasConcept C41008148 @default.
- W3208487946 hasConcept C41608201 @default.
- W3208487946 hasConcept C48044578 @default.
- W3208487946 hasConcept C50644808 @default.
- W3208487946 hasConcept C62520636 @default.
- W3208487946 hasConcept C62611344 @default.
- W3208487946 hasConcept C66938386 @default.
- W3208487946 hasConcept C75564084 @default.
- W3208487946 hasConcept C77088390 @default.
- W3208487946 hasConcept C80444323 @default.
- W3208487946 hasConceptScore W3208487946C101738243 @default.
- W3208487946 hasConceptScore W3208487946C121332964 @default.
- W3208487946 hasConceptScore W3208487946C127413603 @default.
- W3208487946 hasConceptScore W3208487946C132525143 @default.
- W3208487946 hasConceptScore W3208487946C154945302 @default.
- W3208487946 hasConceptScore W3208487946C163716315 @default.
- W3208487946 hasConceptScore W3208487946C197657726 @default.
- W3208487946 hasConceptScore W3208487946C2778459887 @default.
- W3208487946 hasConceptScore W3208487946C2779172887 @default.
- W3208487946 hasConceptScore W3208487946C41008148 @default.
- W3208487946 hasConceptScore W3208487946C41608201 @default.
- W3208487946 hasConceptScore W3208487946C48044578 @default.
- W3208487946 hasConceptScore W3208487946C50644808 @default.
- W3208487946 hasConceptScore W3208487946C62520636 @default.
- W3208487946 hasConceptScore W3208487946C62611344 @default.
- W3208487946 hasConceptScore W3208487946C66938386 @default.
- W3208487946 hasConceptScore W3208487946C75564084 @default.
- W3208487946 hasConceptScore W3208487946C77088390 @default.
- W3208487946 hasConceptScore W3208487946C80444323 @default.
- W3208487946 hasLocation W32084879461 @default.
- W3208487946 hasLocation W32084879462 @default.
- W3208487946 hasOpenAccess W3208487946 @default.
- W3208487946 hasPrimaryLocation W32084879461 @default.
- W3208487946 hasRelatedWork W2940490924 @default.
- W3208487946 hasRelatedWork W3009791842 @default.
- W3208487946 hasRelatedWork W3019797369 @default.
- W3208487946 hasRelatedWork W3027226623 @default.
- W3208487946 hasRelatedWork W3109894107 @default.
- W3208487946 hasRelatedWork W3120206105 @default.
- W3208487946 hasRelatedWork W3134637941 @default.
- W3208487946 hasRelatedWork W3193865128 @default.
- W3208487946 hasRelatedWork W3204107002 @default.
- W3208487946 hasRelatedWork W3208487946 @default.
- W3208487946 isParatext "false" @default.
- W3208487946 isRetracted "false" @default.
- W3208487946 magId "3208487946" @default.
- W3208487946 workType "article" @default.