Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383860413> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4383860413 abstract "Graph neural network (GNN) has gained increasing popularity in recent years owing to its capability and flexibility in modeling complex graph structure data. Among all graph learning methods, hypergraph learning is a technique for exploring the implicit higher-order correlations when training the embedding space of the graph. In this paper, we propose a hypergraph learning framework named LFH that is capable of dynamic hyperedge construction and attentive embedding update utilizing the heterogeneity attributes of the graph. Specifically, in our framework, the high-quality features are first generated by the pairwise fusion strategy that utilizes explicit graph structure information when generating initial node embedding. Afterwards, a hypergraph is constructed through the dynamic grouping of implicit hyperedges, followed by the type-specific hypergraph learning process. To evaluate the effectiveness of our proposed framework, we conduct comprehensive experiments on several popular datasets with eleven state-of-the-art models on both node classification and link prediction tasks, which fall into categories of homogeneous pairwise graph learning, heterogeneous pairwise graph learning, and hypergraph learning. The experiment results demonstrate a significant performance gain (average 12.5% in node classification and 13.3% in link prediction) compared with recent state-of-the-art methods." @default.
- W4383860413 created "2023-07-11" @default.
- W4383860413 creator A5019778525 @default.
- W4383860413 creator A5028462736 @default.
- W4383860413 creator A5034462519 @default.
- W4383860413 creator A5034923391 @default.
- W4383860413 creator A5072556657 @default.
- W4383860413 creator A5078711649 @default.
- W4383860413 creator A5080328538 @default.
- W4383860413 creator A5085410794 @default.
- W4383860413 date "2023-07-07" @default.
- W4383860413 modified "2023-09-23" @default.
- W4383860413 title "Learning from Heterogeneity: A Dynamic Learning Framework for Hypergraphs" @default.
- W4383860413 doi "https://doi.org/10.48550/arxiv.2307.03411" @default.
- W4383860413 hasPublicationYear "2023" @default.
- W4383860413 type Work @default.
- W4383860413 citedByCount "0" @default.
- W4383860413 crossrefType "posted-content" @default.
- W4383860413 hasAuthorship W4383860413A5019778525 @default.
- W4383860413 hasAuthorship W4383860413A5028462736 @default.
- W4383860413 hasAuthorship W4383860413A5034462519 @default.
- W4383860413 hasAuthorship W4383860413A5034923391 @default.
- W4383860413 hasAuthorship W4383860413A5072556657 @default.
- W4383860413 hasAuthorship W4383860413A5078711649 @default.
- W4383860413 hasAuthorship W4383860413A5080328538 @default.
- W4383860413 hasAuthorship W4383860413A5085410794 @default.
- W4383860413 hasBestOaLocation W43838604131 @default.
- W4383860413 hasConcept C118615104 @default.
- W4383860413 hasConcept C119857082 @default.
- W4383860413 hasConcept C127413603 @default.
- W4383860413 hasConcept C132525143 @default.
- W4383860413 hasConcept C154945302 @default.
- W4383860413 hasConcept C184898388 @default.
- W4383860413 hasConcept C2781221856 @default.
- W4383860413 hasConcept C33923547 @default.
- W4383860413 hasConcept C41008148 @default.
- W4383860413 hasConcept C41608201 @default.
- W4383860413 hasConcept C62611344 @default.
- W4383860413 hasConcept C66938386 @default.
- W4383860413 hasConcept C75564084 @default.
- W4383860413 hasConcept C80444323 @default.
- W4383860413 hasConceptScore W4383860413C118615104 @default.
- W4383860413 hasConceptScore W4383860413C119857082 @default.
- W4383860413 hasConceptScore W4383860413C127413603 @default.
- W4383860413 hasConceptScore W4383860413C132525143 @default.
- W4383860413 hasConceptScore W4383860413C154945302 @default.
- W4383860413 hasConceptScore W4383860413C184898388 @default.
- W4383860413 hasConceptScore W4383860413C2781221856 @default.
- W4383860413 hasConceptScore W4383860413C33923547 @default.
- W4383860413 hasConceptScore W4383860413C41008148 @default.
- W4383860413 hasConceptScore W4383860413C41608201 @default.
- W4383860413 hasConceptScore W4383860413C62611344 @default.
- W4383860413 hasConceptScore W4383860413C66938386 @default.
- W4383860413 hasConceptScore W4383860413C75564084 @default.
- W4383860413 hasConceptScore W4383860413C80444323 @default.
- W4383860413 hasLocation W43838604131 @default.
- W4383860413 hasOpenAccess W4383860413 @default.
- W4383860413 hasPrimaryLocation W43838604131 @default.
- W4383860413 hasRelatedWork W2892310698 @default.
- W4383860413 hasRelatedWork W2945365184 @default.
- W4383860413 hasRelatedWork W2971267355 @default.
- W4383860413 hasRelatedWork W2991563662 @default.
- W4383860413 hasRelatedWork W3035116611 @default.
- W4383860413 hasRelatedWork W3139353779 @default.
- W4383860413 hasRelatedWork W4285762435 @default.
- W4383860413 hasRelatedWork W4287763734 @default.
- W4383860413 hasRelatedWork W4323323198 @default.
- W4383860413 hasRelatedWork W4365794617 @default.
- W4383860413 isParatext "false" @default.
- W4383860413 isRetracted "false" @default.
- W4383860413 workType "article" @default.