FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100278010> ?p ?o ?g. }

• W3100278010 abstract "Learning vector representations (aka. embeddings) of users and items lies at the core of modern recommender systems. Ranging from early matrix factorization to recently emerged deep learning based methods, existing efforts typically obtain a user's (or an item's) embedding by mapping from pre-existing features that describe the user (or the item), such as ID and attributes. We argue that an inherent drawback of such methods is that, the collaborative signal, which is latent in user-item interactions, is not encoded in the embedding process. As such, the resultant embeddings may not be sufficient to capture the collaborative filtering effect. In this work, we propose to integrate the user-item interactions -- more specifically the bipartite graph structure -- into the embedding process. We develop a new recommendation framework Neural Graph Collaborative Filtering (NGCF), which exploits the user-item graph structure by propagating embeddings on it. This leads to the expressive modeling of high-order connectivity in user-item graph, effectively injecting the collaborative signal into the embedding process in an explicit manner. We conduct extensive experiments on three public benchmarks, demonstrating significant improvements over several state-of-the-art models like HOP-Rec and Collaborative Memory Network. Further analysis verifies the importance of embedding propagation for learning better user and item representations, justifying the rationality and effectiveness of NGCF. Codes are available at https://github.com/xiangwang1223/neural_graph_collaborative_filtering." @default.
• W3100278010 created "2020-11-23" @default.
• W3100278010 creator A5036726873 @default.
• W3100278010 creator A5038668215 @default.
• W3100278010 creator A5048845021 @default.
• W3100278010 creator A5051925942 @default.
• W3100278010 creator A5089404640 @default.
• W3100278010 date "2019-07-18" @default.
• W3100278010 modified "2023-10-17" @default.
• W3100278010 title "Neural Graph Collaborative Filtering" @default.
• W3100278010 cites W1886704267 @default.
• W3100278010 cites W1994389483 @default.
• W3100278010 cites W2054141820 @default.
• W3100278010 cites W2108920354 @default.
• W3100278010 cites W2157881433 @default.
• W3100278010 cites W2253995343 @default.
• W3100278010 cites W2604433096 @default.
• W3100278010 cites W2605350416 @default.
• W3100278010 cites W2741249238 @default.
• W3100278010 cites W2765903581 @default.
• W3100278010 cites W2788730650 @default.
• W3100278010 cites W2788893025 @default.
• W3100278010 cites W2798868970 @default.
• W3100278010 cites W2798972759 @default.
• W3100278010 cites W2809583854 @default.
• W3100278010 cites W2894039884 @default.
• W3100278010 cites W2900229157 @default.
• W3100278010 cites W2911778742 @default.
• W3100278010 cites W2945623882 @default.
• W3100278010 cites W2954164237 @default.
• W3100278010 cites W2962805116 @default.
• W3100278010 cites W2962992837 @default.
• W3100278010 cites W2963249562 @default.
• W3100278010 cites W2963323306 @default.
• W3100278010 cites W2966349618 @default.
• W3100278010 cites W3099386565 @default.
• W3100278010 cites W3100591234 @default.
• W3100278010 cites W3100848837 @default.
• W3100278010 cites W4289257875 @default.
• W3100278010 cites W4297971002 @default.
• W3100278010 cites W4301312111 @default.
• W3100278010 doi "https://doi.org/10.1145/3331184.3331267" @default.
• W3100278010 hasPublicationYear "2019" @default.
• W3100278010 type Work @default.
• W3100278010 sameAs 3100278010 @default.
• W3100278010 citedByCount "1418" @default.
• W3100278010 countsByYear W31002780102019 @default.
• W3100278010 countsByYear W31002780102020 @default.
• W3100278010 countsByYear W31002780102021 @default.
• W3100278010 countsByYear W31002780102022 @default.
• W3100278010 countsByYear W31002780102023 @default.
• W3100278010 crossrefType "proceedings-article" @default.
• W3100278010 hasAuthorship W3100278010A5036726873 @default.
• W3100278010 hasAuthorship W3100278010A5038668215 @default.
• W3100278010 hasAuthorship W3100278010A5048845021 @default.
• W3100278010 hasAuthorship W3100278010A5051925942 @default.
• W3100278010 hasAuthorship W3100278010A5089404640 @default.
• W3100278010 hasBestOaLocation W31002780102 @default.
• W3100278010 hasConcept C107457646 @default.
• W3100278010 hasConcept C119857082 @default.
• W3100278010 hasConcept C132525143 @default.
• W3100278010 hasConcept C154945302 @default.
• W3100278010 hasConcept C165696696 @default.
• W3100278010 hasConcept C197657726 @default.
• W3100278010 hasConcept C21569690 @default.
• W3100278010 hasConcept C23123220 @default.
• W3100278010 hasConcept C38652104 @default.
• W3100278010 hasConcept C41008148 @default.
• W3100278010 hasConcept C41608201 @default.
• W3100278010 hasConcept C557471498 @default.
• W3100278010 hasConcept C75564084 @default.
• W3100278010 hasConcept C80444323 @default.
• W3100278010 hasConceptScore W3100278010C107457646 @default.
• W3100278010 hasConceptScore W3100278010C119857082 @default.
• W3100278010 hasConceptScore W3100278010C132525143 @default.
• W3100278010 hasConceptScore W3100278010C154945302 @default.
• W3100278010 hasConceptScore W3100278010C165696696 @default.
• W3100278010 hasConceptScore W3100278010C197657726 @default.
• W3100278010 hasConceptScore W3100278010C21569690 @default.
• W3100278010 hasConceptScore W3100278010C23123220 @default.
• W3100278010 hasConceptScore W3100278010C38652104 @default.
• W3100278010 hasConceptScore W3100278010C41008148 @default.
• W3100278010 hasConceptScore W3100278010C41608201 @default.
• W3100278010 hasConceptScore W3100278010C557471498 @default.
• W3100278010 hasConceptScore W3100278010C75564084 @default.
• W3100278010 hasConceptScore W3100278010C80444323 @default.
• W3100278010 hasLocation W31002780101 @default.
• W3100278010 hasLocation W31002780102 @default.
• W3100278010 hasLocation W31002780103 @default.
• W3100278010 hasOpenAccess W3100278010 @default.
• W3100278010 hasPrimaryLocation W31002780101 @default.
• W3100278010 hasRelatedWork W2348159088 @default.
• W3100278010 hasRelatedWork W2402445420 @default.
• W3100278010 hasRelatedWork W2944995967 @default.
• W3100278010 hasRelatedWork W3035116611 @default.
• W3100278010 hasRelatedWork W3094605108 @default.
• W3100278010 hasRelatedWork W3201252789 @default.
• W3100278010 hasRelatedWork W4281868159 @default.
• W3100278010 hasRelatedWork W4287763734 @default.
• W3100278010 hasRelatedWork W4288347691 @default.

• next