Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366460384> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4366460384 abstract "Recent progress in Graph Neural Networks has resulted in wide adoption by many applications, including recommendation systems. The reason for Graph Neural Networks' superiority over other approaches is that many problems in recommendation systems can be naturally modeled as graphs, where nodes can be either users or items and edges represent preference relationships. In current Graph Neural Network approaches, nodes are represented with a static vector learned at training time. This static vector might only be suitable to capture some of the nuances of users or items they define. To overcome this limitation, we propose using a recently proposed model inspired by category theory: Sheaf Neural Networks. Sheaf Neural Networks, and its connected Laplacian, can address the previous problem by associating every node (and edge) with a vector space instead than a single vector. The vector space representation is richer and allows picking the proper representation at inference time. This approach can be generalized for different related tasks on graphs and achieves state-of-the-art performance in terms of F1-Score@N in collaborative filtering and Hits@20 in link prediction. For collaborative filtering, the approach is evaluated on the MovieLens 100K with a 5.1% improvement, on MovieLens 1M with a 5.4% improvement and on Book-Crossing with a 2.8% improvement, while for link prediction on the ogbl-ddi dataset with a 1.6% refinement with respect to the respective baselines." @default.
- W4366460384 created "2023-04-22" @default.
- W4366460384 creator A5010418278 @default.
- W4366460384 creator A5044165871 @default.
- W4366460384 creator A5056748708 @default.
- W4366460384 creator A5056068005 @default.
- W4366460384 date "2023-04-07" @default.
- W4366460384 modified "2023-09-26" @default.
- W4366460384 title "Sheaf Neural Networks for Graph-based Recommender Systems" @default.
- W4366460384 doi "https://doi.org/10.48550/arxiv.2304.09097" @default.
- W4366460384 hasPublicationYear "2023" @default.
- W4366460384 type Work @default.
- W4366460384 citedByCount "0" @default.
- W4366460384 crossrefType "posted-content" @default.
- W4366460384 hasAuthorship W4366460384A5010418278 @default.
- W4366460384 hasAuthorship W4366460384A5044165871 @default.
- W4366460384 hasAuthorship W4366460384A5056068005 @default.
- W4366460384 hasAuthorship W4366460384A5056748708 @default.
- W4366460384 hasBestOaLocation W43664603841 @default.
- W4366460384 hasConcept C115178988 @default.
- W4366460384 hasConcept C119857082 @default.
- W4366460384 hasConcept C132525143 @default.
- W4366460384 hasConcept C13336665 @default.
- W4366460384 hasConcept C154945302 @default.
- W4366460384 hasConcept C17744445 @default.
- W4366460384 hasConcept C199539241 @default.
- W4366460384 hasConcept C21569690 @default.
- W4366460384 hasConcept C2524010 @default.
- W4366460384 hasConcept C2776156558 @default.
- W4366460384 hasConcept C2776214188 @default.
- W4366460384 hasConcept C2776359362 @default.
- W4366460384 hasConcept C33923547 @default.
- W4366460384 hasConcept C41008148 @default.
- W4366460384 hasConcept C50644808 @default.
- W4366460384 hasConcept C557471498 @default.
- W4366460384 hasConcept C80444323 @default.
- W4366460384 hasConcept C94625758 @default.
- W4366460384 hasConceptScore W4366460384C115178988 @default.
- W4366460384 hasConceptScore W4366460384C119857082 @default.
- W4366460384 hasConceptScore W4366460384C132525143 @default.
- W4366460384 hasConceptScore W4366460384C13336665 @default.
- W4366460384 hasConceptScore W4366460384C154945302 @default.
- W4366460384 hasConceptScore W4366460384C17744445 @default.
- W4366460384 hasConceptScore W4366460384C199539241 @default.
- W4366460384 hasConceptScore W4366460384C21569690 @default.
- W4366460384 hasConceptScore W4366460384C2524010 @default.
- W4366460384 hasConceptScore W4366460384C2776156558 @default.
- W4366460384 hasConceptScore W4366460384C2776214188 @default.
- W4366460384 hasConceptScore W4366460384C2776359362 @default.
- W4366460384 hasConceptScore W4366460384C33923547 @default.
- W4366460384 hasConceptScore W4366460384C41008148 @default.
- W4366460384 hasConceptScore W4366460384C50644808 @default.
- W4366460384 hasConceptScore W4366460384C557471498 @default.
- W4366460384 hasConceptScore W4366460384C80444323 @default.
- W4366460384 hasConceptScore W4366460384C94625758 @default.
- W4366460384 hasLocation W43664603841 @default.
- W4366460384 hasOpenAccess W4366460384 @default.
- W4366460384 hasPrimaryLocation W43664603841 @default.
- W4366460384 hasRelatedWork W1479993970 @default.
- W4366460384 hasRelatedWork W19372541 @default.
- W4366460384 hasRelatedWork W2075040002 @default.
- W4366460384 hasRelatedWork W2369936857 @default.
- W4366460384 hasRelatedWork W2402445420 @default.
- W4366460384 hasRelatedWork W3154115324 @default.
- W4366460384 hasRelatedWork W4200211378 @default.
- W4366460384 hasRelatedWork W4206925842 @default.
- W4366460384 hasRelatedWork W4283711282 @default.
- W4366460384 hasRelatedWork W4297823578 @default.
- W4366460384 isParatext "false" @default.
- W4366460384 isRetracted "false" @default.
- W4366460384 workType "article" @default.