Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367047312> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4367047312 abstract "Graph neural architecture search (NAS) has gained popularity in automatically designing powerful graph neural networks (GNNs) with relieving human efforts. However, existing graph NAS methods mainly work under the homophily assumption and overlook another important graph property, i.e., heterophily, which exists widely in various real-world applications. To date, automated heterophilic graph learning with NAS is still a research blank to be filled in. Due to the complexity and variety of heterophilic graphs, the critical challenge of heterophilic graph NAS mainly lies in developing the heterophily-specific search space and strategy. Therefore, in this paper, we propose a novel automated graph neural network on heterophilic graphs, namely Auto-HeG, to automatically build heterophilic GNN models with expressive learning abilities. Specifically, Auto-HeG incorporates heterophily into all stages of automatic heterophilic graph learning, including search space design, supernet training, and architecture selection. Through the diverse message-passing scheme with joint micro-level and macro-level designs, we first build a comprehensive heterophilic GNN search space, enabling Auto-HeG to integrate complex and various heterophily of graphs. With a progressive supernet training strategy, we dynamically shrink the initial search space according to layer-wise variation of heterophily, resulting in a compact and efficient supernet. Taking a heterophily-aware distance criterion as the guidance, we conduct heterophilic architecture selection in the leave-one-out pattern, so that specialized and expressive heterophilic GNN architectures can be derived. Extensive experiments illustrate the superiority of Auto-HeG in developing excellent heterophilic GNNs to human-designed models and graph NAS models." @default.
- W4367047312 created "2023-04-27" @default.
- W4367047312 creator A5003412012 @default.
- W4367047312 creator A5008056593 @default.
- W4367047312 creator A5017653751 @default.
- W4367047312 creator A5063035761 @default.
- W4367047312 creator A5075639297 @default.
- W4367047312 creator A5085319576 @default.
- W4367047312 date "2023-04-30" @default.
- W4367047312 modified "2023-09-25" @default.
- W4367047312 title "Auto-HeG: Automated Graph Neural Network on Heterophilic Graphs" @default.
- W4367047312 cites W2107559689 @default.
- W4367047312 cites W2148123869 @default.
- W4367047312 cites W2960010704 @default.
- W4367047312 cites W2962837431 @default.
- W4367047312 cites W2981748264 @default.
- W4367047312 cites W2990045899 @default.
- W4367047312 cites W3031047561 @default.
- W4367047312 cites W3034723893 @default.
- W4367047312 cites W3034764953 @default.
- W4367047312 cites W3080253043 @default.
- W4367047312 cites W3090999459 @default.
- W4367047312 cites W3100848837 @default.
- W4367047312 cites W3108099775 @default.
- W4367047312 cites W3128443161 @default.
- W4367047312 cites W3156351347 @default.
- W4367047312 cites W3167197358 @default.
- W4367047312 cites W3172402898 @default.
- W4367047312 cites W3174470190 @default.
- W4367047312 cites W4200632081 @default.
- W4367047312 cites W4210746245 @default.
- W4367047312 cites W4226437046 @default.
- W4367047312 cites W4382239867 @default.
- W4367047312 doi "https://doi.org/10.1145/3543507.3583498" @default.
- W4367047312 hasPublicationYear "2023" @default.
- W4367047312 type Work @default.
- W4367047312 citedByCount "1" @default.
- W4367047312 countsByYear W43670473122023 @default.
- W4367047312 crossrefType "proceedings-article" @default.
- W4367047312 hasAuthorship W4367047312A5003412012 @default.
- W4367047312 hasAuthorship W4367047312A5008056593 @default.
- W4367047312 hasAuthorship W4367047312A5017653751 @default.
- W4367047312 hasAuthorship W4367047312A5063035761 @default.
- W4367047312 hasAuthorship W4367047312A5075639297 @default.
- W4367047312 hasAuthorship W4367047312A5085319576 @default.
- W4367047312 hasBestOaLocation W43670473122 @default.
- W4367047312 hasConcept C114614502 @default.
- W4367047312 hasConcept C119857082 @default.
- W4367047312 hasConcept C132525143 @default.
- W4367047312 hasConcept C154945302 @default.
- W4367047312 hasConcept C2779812341 @default.
- W4367047312 hasConcept C33923547 @default.
- W4367047312 hasConcept C41008148 @default.
- W4367047312 hasConcept C80444323 @default.
- W4367047312 hasConceptScore W4367047312C114614502 @default.
- W4367047312 hasConceptScore W4367047312C119857082 @default.
- W4367047312 hasConceptScore W4367047312C132525143 @default.
- W4367047312 hasConceptScore W4367047312C154945302 @default.
- W4367047312 hasConceptScore W4367047312C2779812341 @default.
- W4367047312 hasConceptScore W4367047312C33923547 @default.
- W4367047312 hasConceptScore W4367047312C41008148 @default.
- W4367047312 hasConceptScore W4367047312C80444323 @default.
- W4367047312 hasLocation W43670473121 @default.
- W4367047312 hasLocation W43670473122 @default.
- W4367047312 hasOpenAccess W4367047312 @default.
- W4367047312 hasPrimaryLocation W43670473121 @default.
- W4367047312 hasRelatedWork W2961085424 @default.
- W4367047312 hasRelatedWork W4200632081 @default.
- W4367047312 hasRelatedWork W4226197742 @default.
- W4367047312 hasRelatedWork W4285821847 @default.
- W4367047312 hasRelatedWork W4286629047 @default.
- W4367047312 hasRelatedWork W4306321456 @default.
- W4367047312 hasRelatedWork W4306674287 @default.
- W4367047312 hasRelatedWork W4306920765 @default.
- W4367047312 hasRelatedWork W4310238751 @default.
- W4367047312 hasRelatedWork W4224009465 @default.
- W4367047312 isParatext "false" @default.
- W4367047312 isRetracted "false" @default.
- W4367047312 workType "article" @default.