Matches in SemOpenAlex for { <https://semopenalex.org/work/W3094876669> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W3094876669 abstract "Bipartite graphs have been used to represent data relationships in many data-mining applications such as in E-commerce recommendation systems. Since learning in graph space is more complicated than in Euclidian space, recent studies have extensively utilized neural nets to effectively and efficiently embed a graph's nodes into a multidimensional space. However, this embedding method has not yet been applied to large-scale bipartite graphs. Existing techniques either cannot be scaled to large-scale bipartite graphs that have limited labels or cannot exploit the unique structure of bipartite graphs, which have distinct node features in two domains. Thus, we propose Cascade Bipartite Graph Neural Networks, Cascade-BGNN, a novel node representation learning for bipartite graphs that is domain-consistent, self-supervised, and efficient. To efficiently aggregate information both across and within the two partitions of a bipartite graph, BGNN utilizes a customized Inter-domain Message Passing (IDMP) and Intra-domain Alignment (IDA), which is our adaptation of adversarial learning, for message aggregation across and within partitions, respectively. BGNN is trained in a self-supervised manner. Moreover, we formulate a multi-layer BGNN in a cascaded training manner to enable multi-hop relationship modeling while improving training efficiency. Extensive experiments on several datasets of varying scales verify the effectiveness and efficiency of BGNN over baselines. Our design is further affirmed through theoretical analysis for domain alignment. The scalability of BGNN is additionally verified through its demonstrated rapid training speed and low memory cost over a large-scale real-world bipartite graph." @default.
- W3094876669 created "2020-11-09" @default.
- W3094876669 creator A5003518978 @default.
- W3094876669 creator A5009408707 @default.
- W3094876669 creator A5012068017 @default.
- W3094876669 creator A5032642601 @default.
- W3094876669 creator A5068865316 @default.
- W3094876669 creator A5073860700 @default.
- W3094876669 creator A5082572337 @default.
- W3094876669 date "2019-06-27" @default.
- W3094876669 modified "2023-09-26" @default.
- W3094876669 title "Cascade-BGNN: Toward Efficient Self-supervised Representation Learning on Large-scale Bipartite Graphs" @default.
- W3094876669 cites W1710476689 @default.
- W3094876669 cites W2116341502 @default.
- W3094876669 cites W2153579005 @default.
- W3094876669 cites W2153959628 @default.
- W3094876669 cites W2159094788 @default.
- W3094876669 cites W2393319904 @default.
- W3094876669 cites W2519887557 @default.
- W3094876669 cites W2554952599 @default.
- W3094876669 cites W2624431344 @default.
- W3094876669 cites W2743104969 @default.
- W3094876669 cites W2786722833 @default.
- W3094876669 cites W2786915849 @default.
- W3094876669 cites W2808399177 @default.
- W3094876669 cites W2808409763 @default.
- W3094876669 cites W2809583854 @default.
- W3094876669 cites W2886970679 @default.
- W3094876669 cites W2890703109 @default.
- W3094876669 cites W2947209427 @default.
- W3094876669 cites W2962756421 @default.
- W3094876669 cites W2991425343 @default.
- W3094876669 cites W3104097132 @default.
- W3094876669 hasPublicationYear "2019" @default.
- W3094876669 type Work @default.
- W3094876669 sameAs 3094876669 @default.
- W3094876669 citedByCount "3" @default.
- W3094876669 countsByYear W30948766692021 @default.
- W3094876669 crossrefType "posted-content" @default.
- W3094876669 hasAuthorship W3094876669A5003518978 @default.
- W3094876669 hasAuthorship W3094876669A5009408707 @default.
- W3094876669 hasAuthorship W3094876669A5012068017 @default.
- W3094876669 hasAuthorship W3094876669A5032642601 @default.
- W3094876669 hasAuthorship W3094876669A5068865316 @default.
- W3094876669 hasAuthorship W3094876669A5073860700 @default.
- W3094876669 hasAuthorship W3094876669A5082572337 @default.
- W3094876669 hasConcept C119857082 @default.
- W3094876669 hasConcept C132525143 @default.
- W3094876669 hasConcept C154945302 @default.
- W3094876669 hasConcept C197657726 @default.
- W3094876669 hasConcept C41008148 @default.
- W3094876669 hasConcept C41608201 @default.
- W3094876669 hasConcept C48044578 @default.
- W3094876669 hasConcept C50644808 @default.
- W3094876669 hasConcept C59404180 @default.
- W3094876669 hasConcept C75564084 @default.
- W3094876669 hasConcept C77088390 @default.
- W3094876669 hasConcept C80444323 @default.
- W3094876669 hasConceptScore W3094876669C119857082 @default.
- W3094876669 hasConceptScore W3094876669C132525143 @default.
- W3094876669 hasConceptScore W3094876669C154945302 @default.
- W3094876669 hasConceptScore W3094876669C197657726 @default.
- W3094876669 hasConceptScore W3094876669C41008148 @default.
- W3094876669 hasConceptScore W3094876669C41608201 @default.
- W3094876669 hasConceptScore W3094876669C48044578 @default.
- W3094876669 hasConceptScore W3094876669C50644808 @default.
- W3094876669 hasConceptScore W3094876669C59404180 @default.
- W3094876669 hasConceptScore W3094876669C75564084 @default.
- W3094876669 hasConceptScore W3094876669C77088390 @default.
- W3094876669 hasConceptScore W3094876669C80444323 @default.
- W3094876669 hasLocation W30948766691 @default.
- W3094876669 hasOpenAccess W3094876669 @default.
- W3094876669 hasPrimaryLocation W30948766691 @default.
- W3094876669 hasRelatedWork W2765425003 @default.
- W3094876669 hasRelatedWork W2799012401 @default.
- W3094876669 hasRelatedWork W2899379687 @default.
- W3094876669 hasRelatedWork W2903885495 @default.
- W3094876669 hasRelatedWork W2911690298 @default.
- W3094876669 hasRelatedWork W2954183115 @default.
- W3094876669 hasRelatedWork W2975753138 @default.
- W3094876669 hasRelatedWork W2980682003 @default.
- W3094876669 hasRelatedWork W2998008360 @default.
- W3094876669 hasRelatedWork W3006402303 @default.
- W3094876669 hasRelatedWork W3082154031 @default.
- W3094876669 hasRelatedWork W3089266724 @default.
- W3094876669 hasRelatedWork W3104121894 @default.
- W3094876669 hasRelatedWork W3119582991 @default.
- W3094876669 hasRelatedWork W3126928293 @default.
- W3094876669 hasRelatedWork W3130041604 @default.
- W3094876669 hasRelatedWork W3130605614 @default.
- W3094876669 hasRelatedWork W3166679531 @default.
- W3094876669 hasRelatedWork W3193559596 @default.
- W3094876669 hasRelatedWork W3210073855 @default.
- W3094876669 isParatext "false" @default.
- W3094876669 isRetracted "false" @default.
- W3094876669 magId "3094876669" @default.
- W3094876669 workType "article" @default.