Matches in SemOpenAlex for { <https://semopenalex.org/work/W4294152625> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4294152625 endingPage "1228" @default.
- W4294152625 startingPage "1228" @default.
- W4294152625 abstract "Currently, most Graph Structure Learning (GSL) methods, as a means of learning graph structure, improve the robustness of GNN merely from a local view by considering the local information related to each edge and indiscriminately applying the mechanism across edges, which may suffer from the local structure heterogeneity of the graph (i.e., the uneven distribution of inter-class connections over nodes). To overcome the drawbacks, we extract the graph structure as a learnable parameter and jointly learn the structure and common parameters of GNN from the global view. Excitingly, the common parameters contain the global information for nodes features mapping, which is also crucial for structure optimization (i.e., optimizing the structure relies on global mapping information). Mathematically, we apply a generic structure extractor to abstract the graph structure and transform GNNs in the form of learning structure and common parameters. Then, we model the learning process as a novel bi-level optimization, i.e., Generic Structure Extraction with Bi-level Optimization for Graph Structure Learning (GSEBO), which optimizes GNN parameters in the upper level to obtain the global mapping information and graph structure is optimized in the lower level with the global information learned from the upper level. We instantiate the proposed GSEBO on classical GNNs and compare it with the state-of-the-art GSL methods. Extensive experiments validate the effectiveness of the proposed GSEBO on four real-world datasets." @default.
- W4294152625 created "2022-09-02" @default.
- W4294152625 creator A5027852193 @default.
- W4294152625 creator A5061811574 @default.
- W4294152625 date "2022-09-01" @default.
- W4294152625 modified "2023-10-18" @default.
- W4294152625 title "Generic Structure Extraction with Bi-Level Optimization for Graph Structure Learning" @default.
- W4294152625 cites W2116341502 @default.
- W4294152625 cites W2148123869 @default.
- W4294152625 cites W2157085604 @default.
- W4294152625 cites W2948729509 @default.
- W4294152625 cites W2963017945 @default.
- W4294152625 cites W2963555845 @default.
- W4294152625 cites W2998496395 @default.
- W4294152625 cites W3005922524 @default.
- W4294152625 cites W3116239416 @default.
- W4294152625 cites W3126334507 @default.
- W4294152625 cites W3192421672 @default.
- W4294152625 doi "https://doi.org/10.3390/e24091228" @default.
- W4294152625 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36141114" @default.
- W4294152625 hasPublicationYear "2022" @default.
- W4294152625 type Work @default.
- W4294152625 citedByCount "0" @default.
- W4294152625 crossrefType "journal-article" @default.
- W4294152625 hasAuthorship W4294152625A5027852193 @default.
- W4294152625 hasAuthorship W4294152625A5061811574 @default.
- W4294152625 hasBestOaLocation W42941526251 @default.
- W4294152625 hasConcept C11413529 @default.
- W4294152625 hasConcept C121332964 @default.
- W4294152625 hasConcept C132525143 @default.
- W4294152625 hasConcept C154945302 @default.
- W4294152625 hasConcept C159467904 @default.
- W4294152625 hasConcept C164752517 @default.
- W4294152625 hasConcept C2986090443 @default.
- W4294152625 hasConcept C41008148 @default.
- W4294152625 hasConcept C80444323 @default.
- W4294152625 hasConceptScore W4294152625C11413529 @default.
- W4294152625 hasConceptScore W4294152625C121332964 @default.
- W4294152625 hasConceptScore W4294152625C132525143 @default.
- W4294152625 hasConceptScore W4294152625C154945302 @default.
- W4294152625 hasConceptScore W4294152625C159467904 @default.
- W4294152625 hasConceptScore W4294152625C164752517 @default.
- W4294152625 hasConceptScore W4294152625C2986090443 @default.
- W4294152625 hasConceptScore W4294152625C41008148 @default.
- W4294152625 hasConceptScore W4294152625C80444323 @default.
- W4294152625 hasIssue "9" @default.
- W4294152625 hasLocation W42941526251 @default.
- W4294152625 hasLocation W42941526252 @default.
- W4294152625 hasLocation W42941526253 @default.
- W4294152625 hasOpenAccess W4294152625 @default.
- W4294152625 hasPrimaryLocation W42941526251 @default.
- W4294152625 hasRelatedWork W2070514408 @default.
- W4294152625 hasRelatedWork W2078218923 @default.
- W4294152625 hasRelatedWork W2386767533 @default.
- W4294152625 hasRelatedWork W2386950660 @default.
- W4294152625 hasRelatedWork W2391817034 @default.
- W4294152625 hasRelatedWork W2952964201 @default.
- W4294152625 hasRelatedWork W3035116611 @default.
- W4294152625 hasRelatedWork W3048155040 @default.
- W4294152625 hasRelatedWork W3086197249 @default.
- W4294152625 hasRelatedWork W4367684998 @default.
- W4294152625 hasVolume "24" @default.
- W4294152625 isParatext "false" @default.
- W4294152625 isRetracted "false" @default.
- W4294152625 workType "article" @default.