Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288364260> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4288364260 abstract "We propose an inductive matrix completion model without using side information. By factorizing the (rating) matrix into the product of low-dimensional latent embeddings of rows (users) and columns (items), a majority of existing matrix completion methods are transductive, since the learned embeddings cannot generalize to unseen rows/columns or to new matrices. To make matrix completion inductive, most previous works use content (side information), such as user's age or movie's genre, to make predictions. However, high-quality content is not always available, and can be hard to extract. Under the extreme setting where not any side information is available other than the matrix to complete, can we still learn an inductive matrix completion model? In this paper, we propose an Inductive Graph-based Matrix Completion (IGMC) model to address this problem. IGMC trains a graph neural network (GNN) based purely on 1-hop subgraphs around (user, item) pairs generated from the rating matrix and maps these subgraphs to their corresponding ratings. It achieves highly competitive performance with state-of-the-art transductive baselines. In addition, IGMC is inductive -- it can generalize to users/items unseen during the training (given that their interactions exist), and can even transfer to new tasks. Our transfer learning experiments show that a model trained out of the MovieLens dataset can be directly used to predict Douban movie ratings with surprisingly good performance. Our work demonstrates that: 1) it is possible to train inductive matrix completion models without using side information while achieving similar or better performances than state-of-the-art transductive methods; 2) local graph patterns around a (user, item) pair are effective predictors of the rating this user gives to the item; and 3) Long-range dependencies might not be necessary for modeling recommender systems." @default.
- W4288364260 created "2022-07-29" @default.
- W4288364260 creator A5047318884 @default.
- W4288364260 creator A5071515223 @default.
- W4288364260 date "2019-04-26" @default.
- W4288364260 modified "2023-10-04" @default.
- W4288364260 title "Inductive Matrix Completion Based on Graph Neural Networks" @default.
- W4288364260 doi "https://doi.org/10.48550/arxiv.1904.12058" @default.
- W4288364260 hasPublicationYear "2019" @default.
- W4288364260 type Work @default.
- W4288364260 citedByCount "0" @default.
- W4288364260 crossrefType "posted-content" @default.
- W4288364260 hasAuthorship W4288364260A5047318884 @default.
- W4288364260 hasAuthorship W4288364260A5071515223 @default.
- W4288364260 hasBestOaLocation W42883642601 @default.
- W4288364260 hasConcept C106487976 @default.
- W4288364260 hasConcept C119857082 @default.
- W4288364260 hasConcept C121332964 @default.
- W4288364260 hasConcept C132525143 @default.
- W4288364260 hasConcept C135598885 @default.
- W4288364260 hasConcept C154945302 @default.
- W4288364260 hasConcept C159985019 @default.
- W4288364260 hasConcept C163716315 @default.
- W4288364260 hasConcept C192562407 @default.
- W4288364260 hasConcept C21569690 @default.
- W4288364260 hasConcept C2776156558 @default.
- W4288364260 hasConcept C2778459887 @default.
- W4288364260 hasConcept C41008148 @default.
- W4288364260 hasConcept C50644808 @default.
- W4288364260 hasConcept C557471498 @default.
- W4288364260 hasConcept C62520636 @default.
- W4288364260 hasConcept C77088390 @default.
- W4288364260 hasConcept C80444323 @default.
- W4288364260 hasConceptScore W4288364260C106487976 @default.
- W4288364260 hasConceptScore W4288364260C119857082 @default.
- W4288364260 hasConceptScore W4288364260C121332964 @default.
- W4288364260 hasConceptScore W4288364260C132525143 @default.
- W4288364260 hasConceptScore W4288364260C135598885 @default.
- W4288364260 hasConceptScore W4288364260C154945302 @default.
- W4288364260 hasConceptScore W4288364260C159985019 @default.
- W4288364260 hasConceptScore W4288364260C163716315 @default.
- W4288364260 hasConceptScore W4288364260C192562407 @default.
- W4288364260 hasConceptScore W4288364260C21569690 @default.
- W4288364260 hasConceptScore W4288364260C2776156558 @default.
- W4288364260 hasConceptScore W4288364260C2778459887 @default.
- W4288364260 hasConceptScore W4288364260C41008148 @default.
- W4288364260 hasConceptScore W4288364260C50644808 @default.
- W4288364260 hasConceptScore W4288364260C557471498 @default.
- W4288364260 hasConceptScore W4288364260C62520636 @default.
- W4288364260 hasConceptScore W4288364260C77088390 @default.
- W4288364260 hasConceptScore W4288364260C80444323 @default.
- W4288364260 hasLocation W42883642601 @default.
- W4288364260 hasOpenAccess W4288364260 @default.
- W4288364260 hasPrimaryLocation W42883642601 @default.
- W4288364260 hasRelatedWork W1479993970 @default.
- W4288364260 hasRelatedWork W19372541 @default.
- W4288364260 hasRelatedWork W2075040002 @default.
- W4288364260 hasRelatedWork W2369936857 @default.
- W4288364260 hasRelatedWork W2402445420 @default.
- W4288364260 hasRelatedWork W2750905689 @default.
- W4288364260 hasRelatedWork W4200211378 @default.
- W4288364260 hasRelatedWork W4206925842 @default.
- W4288364260 hasRelatedWork W4286521360 @default.
- W4288364260 hasRelatedWork W4297823578 @default.
- W4288364260 isParatext "false" @default.
- W4288364260 isRetracted "false" @default.
- W4288364260 workType "article" @default.