Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386204625> ?p ?o ?g. }
Showing items 1 to 60 of
60
with 100 items per page.
- W4386204625 abstract "In recent years, heterogeneous graph neural networks (HGNNs) have achieved excellent performance. The efficient HGNNs consist of meta-graphs and aggregation operations. Since manually designing meta-graph is an expert-dependent and time-consuming process, the performance of HGNNs is limited. To address this challenge, the differentiable meta-graph search has been proposed to obtain promising meta-graph automatically. However, the previous differentiable meta-graph search constructs the supernet without learnable aggregation operations, which limits the semantics extracting ability of HGNNs with automatically designed meta-graph for downstream tasks. To solve this problem, we propose the Meta-graph Search with Learnable Supernet for Heterogeneous Graph Neural Networks (MSLS). Specifically, to obtain better performance HGNNs, MSLS constructs a supernet with learnable aggregation operations based on the meta-graphs. MSLS adopts decoupling training to train the learnable supernet and obtains the optimal meta-graph with learnable aggregation operations using a constrained evolution strategy. Extensive experiments show that our method (MSLS) achieves the best performance in different tasks." @default.
- W4386204625 created "2023-08-28" @default.
- W4386204625 creator A5003561523 @default.
- W4386204625 creator A5023594563 @default.
- W4386204625 creator A5038746457 @default.
- W4386204625 creator A5040496887 @default.
- W4386204625 creator A5079622474 @default.
- W4386204625 date "2023-07-10" @default.
- W4386204625 modified "2023-09-26" @default.
- W4386204625 title "MSLS: Meta-graph Search with Learnable Supernet for Heterogeneous Graph Neural Networks" @default.
- W4386204625 cites W2743104969 @default.
- W4386204625 cites W2911286998 @default.
- W4386204625 cites W2913312729 @default.
- W4386204625 cites W3004507689 @default.
- W4386204625 cites W3012871709 @default.
- W4386204625 cites W3130483513 @default.
- W4386204625 cites W3167197358 @default.
- W4386204625 cites W4210257598 @default.
- W4386204625 doi "https://doi.org/10.1145/3603719.3603727" @default.
- W4386204625 hasPublicationYear "2023" @default.
- W4386204625 type Work @default.
- W4386204625 citedByCount "0" @default.
- W4386204625 crossrefType "proceedings-article" @default.
- W4386204625 hasAuthorship W4386204625A5003561523 @default.
- W4386204625 hasAuthorship W4386204625A5023594563 @default.
- W4386204625 hasAuthorship W4386204625A5038746457 @default.
- W4386204625 hasAuthorship W4386204625A5040496887 @default.
- W4386204625 hasAuthorship W4386204625A5079622474 @default.
- W4386204625 hasConcept C132525143 @default.
- W4386204625 hasConcept C134306372 @default.
- W4386204625 hasConcept C154945302 @default.
- W4386204625 hasConcept C202615002 @default.
- W4386204625 hasConcept C33923547 @default.
- W4386204625 hasConcept C41008148 @default.
- W4386204625 hasConcept C50644808 @default.
- W4386204625 hasConcept C80444323 @default.
- W4386204625 hasConceptScore W4386204625C132525143 @default.
- W4386204625 hasConceptScore W4386204625C134306372 @default.
- W4386204625 hasConceptScore W4386204625C154945302 @default.
- W4386204625 hasConceptScore W4386204625C202615002 @default.
- W4386204625 hasConceptScore W4386204625C33923547 @default.
- W4386204625 hasConceptScore W4386204625C41008148 @default.
- W4386204625 hasConceptScore W4386204625C50644808 @default.
- W4386204625 hasConceptScore W4386204625C80444323 @default.
- W4386204625 hasLocation W43862046251 @default.
- W4386204625 hasOpenAccess W4386204625 @default.
- W4386204625 hasPrimaryLocation W43862046251 @default.
- W4386204625 hasRelatedWork W2386387936 @default.
- W4386204625 hasRelatedWork W2391817034 @default.
- W4386204625 hasRelatedWork W2805497261 @default.
- W4386204625 hasRelatedWork W2948568013 @default.
- W4386204625 hasRelatedWork W2953078254 @default.
- W4386204625 hasRelatedWork W3091248771 @default.
- W4386204625 hasRelatedWork W4234356815 @default.
- W4386204625 hasRelatedWork W4299882544 @default.
- W4386204625 hasRelatedWork W4324149105 @default.
- W4386204625 hasRelatedWork W1629725936 @default.
- W4386204625 isParatext "false" @default.
- W4386204625 isRetracted "false" @default.
- W4386204625 workType "article" @default.